Authors: Mohamed Fawzi Abdelshafie Abuhussein, Ashraf Darwish, Aboul Ella Hassanien
Abstract: This dataset includes 6823 thermal images captured using a UNI-T UTi165A camera for face detection, recognition, and emotion analysis. It consists of 2485 facial recognition images depicting emotions (happy, sad, angry, natural, surprised), 2054 images for face recognition, and 2284 images for face detection. The dataset covers various conditions, color palettes, shooting angles, and zoom levels, with a temperature range of -10{\deg}C to 400{\deg}C and a resolution of 19,200 pixels. It serves as a valuable resource for advancing thermal imaging technology, aiding in algorithm development, and benchmarking for facial recognition across different palettes. Additionally, it contributes to facial motion recognition, fostering interdisciplinary collaboration in computer vision, psychology, and neuroscience. The dataset promotes transparency in thermal face detection and recognition research, with applications in security, healthcare, and human-computer interaction.
Authors: Vismay Modi, Nicholas Sharp, Or Perel, Shinjiro Sueda, David I. W. Levin
Abstract: The proliferation of 3D representations, from explicit meshes to implicit neural fields and more, motivates the need for simulators agnostic to representation. We present a data-, mesh-, and grid-free solution for elastic simulation for any object in any geometric representation undergoing large, nonlinear deformations. We note that every standard geometric representation can be reduced to an occupancy function queried at any point in space, and we define a simulator atop this common interface. For each object, we fit a small implicit neural network encoding spatially varying weights that act as a reduced deformation basis. These weights are trained to learn physically significant motions in the object via random perturbations. Our loss ensures we find a weight-space basis that best minimizes deformation energy by stochastically evaluating elastic energies through Monte Carlo sampling of the deformation volume. At runtime, we simulate in the reduced basis and sample the deformations back to the original domain. Our experiments demonstrate the versatility, accuracy, and speed of this approach on data including signed distance functions, point clouds, neural primitives, tomography scans, radiance fields, Gaussian splats, surface meshes, and volume meshes, as well as showing a variety of material energies, contact models, and time integration schemes.
Authors: Yunbei Zhang, Akshay Mehra, Jihun Hamm
Abstract: While Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training phase or modify model parameters at test time through entropy minimization. The former often overlooks unlabeled target data, while the latter doesn't fully address domain shifts. In this work, our approach, Optimal Transport-guided Test-Time Visual Prompting (OT-VP), handles these problems by leveraging prompt learning at test time to align the target and source domains without accessing the training process or altering pre-trained model parameters. This method involves learning a universal visual prompt for the target domain by optimizing the Optimal Transport distance. With just four prompt tokens learned, OT-VP achieves a $5.0\%$ and $1.5\%$ increase in averaged accuracy across single-source and multi-source settings on three benchmark datasets, which is $1.2\times$ and $1.5\times$ the improvement of the state-of-the-art method, respectively.
Authors: Damien Ferbach, Quentin Bertrand, Avishek Joey Bose, Gauthier Gidel
Abstract: The rapid progress in generative models has resulted in impressive leaps in generation quality, blurring the lines between synthetic and real data. Web-scale datasets are now prone to the inevitable contamination by synthetic data, directly impacting the training of future generated models. Already, some theoretical results on self-consuming generative models (a.k.a., iterative retraining) have emerged in the literature, showcasing that either model collapse or stability could be possible depending on the fraction of generated data used at each retraining step. However, in practice, synthetic data is often subject to human feedback and curated by users before being used and uploaded online. For instance, many interfaces of popular text-to-image generative models, such as Stable Diffusion or Midjourney, produce several variations of an image for a given query which can eventually be curated by the users. In this paper, we theoretically study the impact of data curation on iterated retraining of generative models and show that it can be seen as an \emph{implicit preference optimization mechanism}. However, unlike standard preference optimization, the generative model does not have access to the reward function or negative samples needed for pairwise comparisons. Moreover, our study doesn't require access to the density function, only to samples. We prove that, if the data is curated according to a reward model, then the expected reward of the iterative retraining procedure is maximized. We further provide theoretical results on the stability of the retraining loop when using a positive fraction of real data at each step. Finally, we conduct illustrative experiments on both synthetic datasets and on CIFAR10 showing that such a procedure amplifies biases of the reward model.
Authors: Steven Abreu, Tiffany D. Do, Karan Ahuja, Eric J. Gonzalez, Lee Payne, Daniel McDuff, Mar Gonzalez-Franco
Abstract: Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and evaluating these annotations. First, we used a prompt-engineered large language model (LLM) to generate context-aware action suggestions and identified over 18,000 action suggestions. While these synthetic action suggestions are valuable, the inherent limitations of LLMs necessitate human evaluation. To ensure high-quality and user-centered recommendations, we conducted a large-scale human annotation study that provides grounding in human preferences for all of PARSE-Ego4D. We analyze the inter-rater agreement and evaluate subjective preferences of participants. Based on our synthetic dataset and complete human annotations, we propose several new tasks for action suggestions based on ego-centric videos. We encourage novel solutions that improve latency and energy requirements. The annotations in PARSE-Ego4D will support researchers and developers who are working on building action recommendation systems for augmented and virtual reality systems.
Authors: Ashutosh, Rahul Jashvantbhai Pandya
Abstract: The expanse of information available over the internet makes it difficult to identify whether a specific work is a replica or a duplication of a protected work, especially if we talk about visual representations. Strategies are planned to identify the utilization of the copyrighted image in a report. Still, we want to resolve the issue of involving a copyrighted image in a video and a calculation that could recognize the degree of similarity of the copyrighted picture utilized in the video, even for the pieces of the video that are not featured a lot and in the end perform characterization errands on those edges. Machine learning (ML) and artificial intelligence (AI) are vital to address this problem. Numerous associations have been creating different calculations to screen the identification of copyrighted work. This work means concentrating on those calculations, recognizing designs inside the information, and fabricating a more reasonable model for copyrighted image classification and detection. We have used different algorithms like- Image Processing, Convolutional Neural Networks (CNN), Image hashing, etc. Keywords- Copyright, Artificial Intelligence(AI), Copyrighted Image, Convolutional Neural Network(CNN), Image processing, Degree of similarity, Image Hashing.
Authors: Guillaume Coiffier, Louis Bethune
Abstract: Neural implicit surfaces are a promising tool for geometry processing that represent a solid object as the zero level set of a neural network. Usually trained to approximate a signed distance function of the considered object, these methods exhibit great visual fidelity and quality near the surface, yet their properties tend to degrade with distance, making geometrical queries hard to perform without the help of complex range analysis techniques. Based on recent advancements in Lipschitz neural networks, we introduce a new method for approximating the signed distance function of a given object. As our neural function is made 1- Lipschitz by construction, it cannot overestimate the distance, which guarantees robustness even far from the surface. Moreover, the 1-Lipschitz constraint allows us to use a different loss function, called the hinge-Kantorovitch-Rubinstein loss, which pushes the gradient as close to unit-norm as possible, thus reducing computation costs in iterative queries. As this loss function only needs a rough estimate of occupancy to be optimized, this means that the true distance function need not to be known. We are therefore able to compute neural implicit representations of even bad quality geometry such as noisy point clouds or triangle soups. We demonstrate that our methods is able to approximate the distance function of any closed or open surfaces or curves in the plane or in space, while still allowing sphere tracing or closest point projections to be performed robustly.
Authors: Milena T. Bagdasarian, Paul Knoll, Florian Barthel, Wieland Morgenstern
Abstract: We present a work-in-progress survey on 3D Gaussian Splatting compression methods, focusing on their statistical performance across various benchmarks. This survey aims to facilitate comparability by summarizing key statistics of different compression approaches in a tabulated format. The datasets evaluated include TanksAndTemples, MipNeRF360, DeepBlending, and SyntheticNeRF. For each method, we report the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Learned Perceptual Image Patch Similarity (LPIPS), and the resultant size in megabytes (MB), as provided by the respective authors. This is an ongoing, open project, and we invite contributions from the research community as GitHub issues or pull requests. Please visit http://w-m.github.io/3dgs-compression-survey/ for more information and a sortable version of the table.
Authors: Mariko Yamaguchi, Masaru Tsuchida, Takahiro Matsumoto, Tetsuro Tokunaga, Takayoshi Mochizuki
Abstract: We have developed an innovative lighting system that changes specific target colors while keeping the lights appearing naturally white. By precisely controlling the spectral power distribution (SPD) of illumination and harnessing the unique phenomenon of metamerism, our system achieves unique color variations in ways you've never seen before. Our system calculates the optimal SPDs of illumination for given materials to intensively induce metamerism, and then synthesizes the illumination using various colors of LEDs. We successfully demonstrated the system's implementation at Paris Fashion Week 2024. As models step onto the stage, their dresses initiate a captivating transformation. Our system altering the colors of the dresses, showcasing an impressive transition from one stunning color to another.
Authors: Yang Han, Qin Guangjun, Liu Ziyuan, Hu Yongqing, Liu Guangnan, Dai Qinglong
Abstract: Convolutional Neural Network (CNN) struggle to capture the multi-dimensional structural information of complex high-dimensional data, which limits their feature learning capability. This paper proposes a feature fusion method based on Topological Data Analysis (TDA) and CNN, named TDA-CNN. This method combines numerical distribution features captured by CNN with topological structure features captured by TDA to improve the feature learning and representation ability of CNN. TDA-CNN divides feature extraction into a CNN channel and a TDA channel. CNN channel extracts numerical distribution features, and the TDA channel extracts topological structure features. The two types of features are fused to form a combined feature representation, with the importance weights of each feature adaptively learned through an attention mechanism. Experimental validation on datasets such as Intel Image, Gender Images, and Chinese Calligraphy Styles by Calligraphers demonstrates that TDA-CNN improves the performance of VGG16, DenseNet121, and GoogleNet networks by 17.5%, 7.11%, and 4.45%, respectively. TDA-CNN demonstrates improved feature clustering and the ability to recognize important features. This effectively enhances the model's decision-making ability.
Authors: Shengtai Ju, Amy R. Reibman
Abstract: In the real world, camera-based application systems can face many challenges, including environmental factors and distribution shift. In this paper, we investigate how pose and shadow impact a classifier's performance, using the specific application of handwashing action recognition. To accomplish this, we generate synthetic data with desired variations to introduce controlled distribution shift. Using our synthetic dataset, we define a classifier's breakdown points to be where the system's performance starts to degrade sharply, and we show these are heavily impacted by pose and shadow conditions. In particular, heavier and larger shadows create earlier breakdown points. Also, it is intriguing to observe model accuracy drop to almost zero with bigger changes in pose. Moreover, we propose a simple mitigation strategy for pose-induced breakdown points by utilizing additional training data from non-canonical poses. Results show that the optimal choices of additional training poses are those with moderate deviations from the canonical poses with 50-60 degrees of rotation.
Authors: Yang Wang, Haiyang Mei, Qirui Bao, Ziqi Wei, Mike Zheng Shou, Haizhou Li, Bo Dong, Xin Yang
Abstract: We introduce a novel multimodality synergistic knowledge distillation scheme tailored for efficient single-eye motion recognition tasks. This method allows a lightweight, unimodal student spiking neural network (SNN) to extract rich knowledge from an event-frame multimodal teacher network. The core strength of this approach is its ability to utilize the ample, coarser temporal cues found in conventional frames for effective emotion recognition. Consequently, our method adeptly interprets both temporal and spatial information from the conventional frame domain, eliminating the need for specialized sensing devices, e.g., event-based camera. The effectiveness of our approach is thoroughly demonstrated using both existing and our compiled single-eye emotion recognition datasets, achieving unparalleled performance in accuracy and efficiency over existing state-of-the-art methods.
Authors: Xixian Yong, Xiao Zhou
Abstract: Predicting socioeconomic indicators within urban regions is crucial for fostering inclusivity, resilience, and sustainability in cities and human settlements. While pioneering studies have attempted to leverage multi-modal data for socioeconomic prediction, jointly exploring their underlying semantics remains a significant challenge. To address the gap, this paper introduces a Multi-Semantic Contrastive Learning (MuseCL) framework for fine-grained urban region profiling and socioeconomic prediction. Within this framework, we initiate the process by constructing contrastive sample pairs for street view and remote sensing images, capitalizing on the similarities in human mobility and Point of Interest (POI) distribution to derive semantic features from the visual modality. Additionally, we extract semantic insights from POI texts embedded within these regions, employing a pre-trained text encoder. To merge the acquired visual and textual features, we devise an innovative cross-modality-based attentional fusion module, which leverages a contrastive mechanism for integration. Experimental results across multiple cities and indicators consistently highlight the superiority of MuseCL, demonstrating an average improvement of 10% in $R^2$ compared to various competitive baseline models. The code of this work is publicly available at https://github.com/XixianYong/MuseCL.
Authors: You-Wei Luo, Chuan-Xian Ren, Xiao-Lin Xu, Qingshan Liu
Abstract: To overcome the restriction of identical distribution assumption, invariant representation learning for unsupervised domain adaptation (UDA) has made significant advances in computer vision and pattern recognition communities. In UDA scenario, the training and test data belong to different domains while the task model is learned to be invariant. Recently, empirical connections between transferability and discriminability have received increasing attention, which is the key to understanding the invariant representations. However, theoretical study of these abilities and in-depth analysis of the learned feature structures are unexplored yet. In this work, we systematically analyze the essentials of transferability and discriminability from the geometric perspective. Our theoretical results provide insights into understanding the co-regularization relation and prove the possibility of learning these abilities. From methodology aspect, the abilities are formulated as geometric properties between domain/cluster subspaces (i.e., orthogonality and equivalence) and characterized as the relation between the norms/ranks of multiple matrices. Two optimization-friendly learning principles are derived, which also ensure some intuitive explanations. Moreover, a feasible range for the co-regularization parameters is deduced to balance the learning of geometric structures. Based on the theoretical results, a geometry-oriented model is proposed for enhancing the transferability and discriminability via nuclear norm optimization. Extensive experiment results validate the effectiveness of the proposed model in empirical applications, and verify that the geometric abilities can be sufficiently learned in the derived feasible range.
Authors: Doga Dikbayir, Abdel Alsnayyan, Vishnu Naresh Boddeti, Balasubramaniam Shanker, Hasan Metin Aktulga
Abstract: The inverse scattering problem is of critical importance in a number of fields, including medical imaging, sonar, sensing, non-destructive evaluation, and several others. The problem of interest can vary from detecting the shape to the constitutive properties of the obstacle. The challenge in both is that this problem is ill-posed, more so when there is limited information. That said, significant effort has been expended over the years in developing solutions to this problem. Here, we use a different approach, one that is founded on data. Specifically, we develop a deep learning framework for shape reconstruction using limited information with single incident wave, single frequency, and phase-less far-field data. This is done by (a) using a compact probabilistic shape latent space, learned by a 3D variational auto-encoder, and (b) a convolutional neural network trained to map the acoustic scattering information to this shape representation. The proposed framework is evaluated on a synthetic 3D particle dataset, as well as ShapeNet, a popular 3D shape recognition dataset. As demonstrated via a number of results, the proposed method is able to produce accurate reconstructions for large batches of complex scatterer shapes (such as airplanes and automobiles), despite the significant variation present within the data.
Authors: Jacob Nielsen, Peter Schneider-Kamp
Abstract: Recently proposed methods for 1-bit and 1.58-bit quantization aware training investigate the performance and behavior of these methods in the context of large language models, finding state-of-the-art performance for models with more than 3B parameters. In this work, we investigate 1.58-bit quantization for small language and vision models ranging from 100K to 48M parameters. We introduce a variant of BitNet b1.58, which allows to rely on the median rather than the mean in the quantization process. Through extensive experiments we investigate the performance of 1.58-bit models obtained through quantization aware training. We further investigate the robustness of 1.58-bit quantization-aware training to changes in the learning rate and regularization through weight decay, finding different patterns for small language and vision models than previously reported for large language models. Our results showcase that 1.58-bit quantization-aware training provides state-of-the-art performance for small language models when doubling hidden layer sizes and reaches or even surpasses state-of-the-art performance for small vision models of identical size. Ultimately, we demonstrate that 1.58-bit quantization-aware training is a viable and promising approach also for training smaller deep learning networks, facilitating deployment of such models in low-resource use-cases and encouraging future research.
Authors: Xi Chen (M-PSI), Julien Cumin (M-PSI), Fano Ramparany (M-PSI), Dominique Vaufreydaz (M-PSI)
Abstract: Human Activity Recognition (HAR) is one of the central problems in fields such as healthcare, elderly care, and security at home. However, traditional HAR approaches face challenges including data scarcity, difficulties in model generalization, and the complexity of recognizing activities in multi-person scenarios. This paper proposes a system framework called LAHAR, based on large language models. Utilizing prompt engineering techniques, LAHAR addresses HAR in multi-person scenarios by enabling subject separation and action-level descriptions of events occurring in the environment. We validated our approach on the ARAS dataset, and the results demonstrate that LAHAR achieves comparable accuracy to the state-of-the-art method at higher resolutions and maintains robustness in multi-person scenarios.
Authors: Zhipeng Ling, Qi Xin, Yiyu Lin, Guangze Su, Zuwei Shui
Abstract: YOLOv8 plays a crucial role in the realm of autonomous driving, owing to its high-speed target detection, precise identification and positioning, and versatile compatibility across multiple platforms. By processing video streams or images in real-time, YOLOv8 rapidly and accurately identifies obstacles such as vehicles and pedestrians on roadways, offering essential visual data for autonomous driving systems. Moreover, YOLOv8 supports various tasks including instance segmentation, image classification, and attitude estimation, thereby providing comprehensive visual perception for autonomous driving, ultimately enhancing driving safety and efficiency. Recognizing the significance of object detection in autonomous driving scenarios and the challenges faced by existing methods, this paper proposes a holistic approach to enhance the YOLOv8 model. The study introduces two pivotal modifications: the C2f_RFAConv module and the Triplet Attention mechanism. Firstly, the proposed modifications are elaborated upon in the methodological section. The C2f_RFAConv module replaces the original module to enhance feature extraction efficiency, while the Triplet Attention mechanism enhances feature focus. Subsequently, the experimental procedure delineates the training and evaluation process, encompassing training the original YOLOv8, integrating modified modules, and assessing performance improvements using metrics and PR curves. The results demonstrate the efficacy of the modifications, with the improved YOLOv8 model exhibiting significant performance enhancements, including increased MAP values and improvements in PR curves. Lastly, the analysis section elucidates the results and attributes the performance improvements to the introduced modules. C2f_RFAConv enhances feature extraction efficiency, while Triplet Attention improves feature focus for enhanced target detection.
Authors: Manan Tomar, Philippe Hansen-Estruch, Philip Bachman, Alex Lamb, John Langford, Matthew E. Taylor, Sergey Levine
Abstract: We introduce a new family of video prediction models designed to support downstream control tasks. We call these models Video Occupancy models (VOCs). VOCs operate in a compact latent space, thus avoiding the need to make predictions about individual pixels. Unlike prior latent-space world models, VOCs directly predict the discounted distribution of future states in a single step, thus avoiding the need for multistep roll-outs. We show that both properties are beneficial when building predictive models of video for use in downstream control. Code is available at \href{https://github.com/manantomar/video-occupancy-models}{\texttt{github.com/manantomar/video-occupancy-models}}.
Authors: Bayu Adhi Tama, Vandana Janeja, Sanjay Purushotham
Abstract: The increasing threat of sea level rise due to climate change necessitates a deeper understanding of ice sheet structures. This study addresses the need for accurate ice sheet data interpretation by introducing a suite of quantitative metrics designed to validate ice sheet annotation techniques. Focusing on both manual and automated methods, including ARESELP and its modified version, MARESELP, we assess their accuracy against expert annotations. Our methodology incorporates several computer vision metrics, traditionally underutilized in glaciological research, to evaluate the continuity and connectivity of ice layer annotations. The results demonstrate that while manual annotations provide invaluable expert insights, automated methods, particularly MARESELP, improve layer continuity and alignment with expert labels.
Authors: Patrick Takenaka, Johannes Maucher, Marco F. Huber
Abstract: We propose a novel architecture design for video prediction in order to utilize procedural domain knowledge directly as part of the computational graph of data-driven models. On the basis of new challenging scenarios we show that state-of-the-art video predictors struggle in complex dynamical settings, and highlight that the introduction of prior process knowledge makes their learning problem feasible. Our approach results in the learning of a symbolically addressable interface between data-driven aspects in the model and our dedicated procedural knowledge module, which we utilize in downstream control tasks.
Authors: Patrick Takenaka, Manuel Eberhardinger, Daniel Grie{\ss}haber, Johannes Maucher
Abstract: Knowing the printer model used to print a given document may provide a crucial lead towards identifying counterfeits or conversely verifying the validity of a real document. Inkjet printers produce probabilistic droplet patterns that appear to be distinct for each printer model and as such we investigate the utilization of droplet characteristics including frequency domain features extracted from printed document scans for the classification of the underlying printer model. We collect and publish a dataset of high resolution document scans and show that our extracted features are informative enough to enable a neural network to distinguish not only the printer manufacturer, but also individual printer models.
Authors: Nin Khodorivsko, Giacomo Spigler
Abstract: Depression and anxiety disorders are prevalent mental health challenges affecting a substantial segment of the global population. In this study, we explored the environmental correlates of these disorders by analyzing street-view images (SVI) of neighborhoods in the Netherlands. Our dataset comprises 9,879 Dutch SVIs sourced from Google Street View, paired with statistical depression and anxiety risk metrics from the Dutch Health Monitor. To tackle this challenge, we refined two existing neural network architectures, DeiT Base and ResNet50. Our goal was to predict neighborhood risk levels, categorized into four tiers from low to high risk, using the raw images. The results showed that DeiT Base and ResNet50 achieved accuracies of 43.43% and 43.63%, respectively. Notably, a significant portion of the errors were between adjacent risk categories, resulting in adjusted accuracies of 83.55% and 80.38%. We also implemented the SHapley Additive exPlanations (SHAP) method on both models and employed gradient rollout on DeiT. Interestingly, while SHAP underscored specific landscape attributes, the correlation between these features and distinct depression risk categories remained unclear. The gradient rollout findings were similarly non-definitive. However, through manual analysis, we identified certain landscape types that were consistently linked with specific risk categories. These findings suggest the potential of these techniques in monitoring the correlation between various landscapes and environmental risk factors for mental health issues. As a future direction, we recommend employing these methods to observe how risk scores from the Dutch Health Monitor shift across neighborhoods over time.
Authors: Ryo Tsujimoto, Hiroki Ouchi, Hidetaka Kamigaito, Taro Watanabe
Abstract: Explaining temporal changes between satellite images taken at different times is important for urban planning and environmental monitoring. However, manual dataset construction for the task is costly, so human-AI collaboration is promissing. Toward the direction, in this paper, we investigate the ability of Large-scale Vision-Language Models (LVLMs) to explain temporal changes between satellite images. While LVLMs are known to generate good image captions, they receive only a single image as input. To deal with a par of satellite images as input, we propose three prompting methods. Through human evaluation, we found the effectiveness of our step-by-step reasoning based prompting.
Authors: Javier Conde, Miguel Gonz\'alez, Gonzalo Mart\'inez, Fernando Moral, Elena Merino-G\'omez, Pedro Reviriego
Abstract: Generative Artificial Intelligence image models have achieved outstanding performance in text-to-image generation and other tasks, such as inpainting that completes images with missing fragments. The performance of inpainting can be accurately measured by taking an image, removing some fragments, performing the inpainting to restore them, and comparing the results with the original image. Interestingly, inpainting can also be applied recursively, starting from an image, removing some parts, applying inpainting to reconstruct the image, and then starting the inpainting process again on the reconstructed image, and so forth. This process of recursively applying inpainting can lead to an image that is similar or completely different from the original one, depending on the fragments that are removed and the ability of the model to reconstruct them. Intuitively, stability, understood as the capability to recover an image that is similar to the original one even after many recursive inpainting operations, is a desirable feature and can be used as an additional performance metric for inpainting. The concept of stability is also being studied in the context of recursive training of generative AI models with their own data. Recursive inpainting is an inference-only recursive process whose understanding may complement ongoing efforts to study the behavior of generative AI models under training recursion. In this paper, the impact of recursive inpainting is studied for one of the most widely used image models: Stable Diffusion. The results show that recursive inpainting can lead to image collapse, so ending with a nonmeaningful image, and that the outcome depends on several factors such as the type of image, the size of the inpainting masks, and the number of iterations.
Authors: Jia-Hau Bai, Chi-Ting Liu, Yu Wang, Fu-Chieh Chang, Pei-Yuan Wu
Abstract: This study uses CAPM (Convex Adversarial Polytope for Maxpool-based CNN) to improve the verified bound for general purpose maxpool-based convolutional neural networks (CNNs) under bounded norm adversarial perturbations. The maxpool function is decomposed as a series of ReLU functions to extend the convex relaxation technique to maxpool functions, by which the verified bound can be efficiently computed through a dual network. The experimental results demonstrate that this technique allows the state-of-the-art verification precision for maxpool-based CNNs and involves a much lower computational cost than current verification methods, such as DeepZ, DeepPoly and PRIMA. This method is also applicable to large-scale CNNs, which previous studies show to be often computationally prohibitively expensive. Under certain circumstances, CAPM is 40-times, 20-times or twice as fast and give a significantly higher verification bound (CAPM 98% vs. PRIMA 76%/DeepPoly 73%/DeepZ 8%) as compared to PRIMA/DeepPoly/DeepZ. Furthermore, we additionally present the time complexity of our algorithm as $O(W^2NK)$, where $W$ is the maximum width of the neural network, $N$ is the number of neurons, and $K$ is the size of the maxpool layer's kernel.
Authors: Xin Chen, Virgile Foussereau
Abstract: This study addresses gender bias in image generation models using Reinforcement Learning from Artificial Intelligence Feedback (RLAIF) with a novel Denoising Diffusion Policy Optimization (DDPO) pipeline. By employing a pretrained stable diffusion model and a highly accurate gender classification Transformer, the research introduces two reward functions: Rshift for shifting gender imbalances, and Rbalance for achieving and maintaining gender balance. Experiments demonstrate the effectiveness of this approach in mitigating bias without compromising image quality or requiring additional data or prompt modifications. While focusing on gender bias, this work establishes a foundation for addressing various forms of bias in AI systems, emphasizing the need for responsible AI development. Future research directions include extending the methodology to other bias types, enhancing the RLAIF pipeline's robustness, and exploring multi-prompt fine-tuning to further advance fairness and inclusivity in AI.
Authors: Zhiwei Wei, Nai Yang, Wenjia Xu, Su Ding
Abstract: In three-dimensional geographical scenes, adding labels with leader lines to point features can significantly improve their visibility. Leadered labels have a large degree of freedom in position con-figuration, but existing methods are mostly based on limited position candidate models, which not only fail to effectively utilize the map space but also make it difficult to consider the relative relationships between labels. Therefore, we conceptualize the dynamic configuration process of computing label positions as akin to solving a map displacement problem. We use a triangulated graph to delineate spatial relationships among labels and calculate the forces exerted on labels considering the constraints associated with point feature labels. Then we use the Beams Displacement Method to iteratively calculate new positions for the labels. Our experimental outcomes demonstrate that this method effectively mitigates label overlay issues while maintaining minimal average directional deviation between adjacent labels. Furthermore, this method is adaptable to various types of leader line labels. Meanwhile, we also discuss the block processing strategy to improve the efficiency of label configuration and analyze the impact of different proximity graphs.
Authors: Shuang Wang, Qingchuan Tao, Zhenming Tang
Abstract: This study presents ResVMUNetX, a novel image enhancement network for low-light conditions, addressing the limitations of existing deep learning methods in capturing long-range image information. Leveraging error regression and an efficient VMamba architecture, ResVMUNetX enhances brightness, recovers structural details, and removes noise through a two-step process involving direct pixel addition and a specialized Denoise CNN module. Demonstrating superior performance on the LOL dataset, ResVMUNetX significantly improves image clarity and quality with reduced computational demands, achieving real-time processing speeds of up to 70 frames per second. This confirms its effectiveness in enhancing low-light images and its potential for practical, real-time applications.
Authors: Rishi Kesav Mohan, Sanjay Sureshkumar, Vignesh Sivasubramaniam
Abstract: Image captioning is a technology that produces text-based descriptions for an image. Deep learning-based solutions built on top of feature recognition may very well serve the purpose. But as with any other machine learning solution, the user understanding in the process of caption generation is poor and the model does not provide any explanation for its predictions and hence the conventional methods are also referred to as Black-Box methods. Thus, an approach where the model's predictions are trusted by the user is needed to appreciate interoperability. Explainable AI is an approach where a conventional method is approached in a way that the model or the algorithm's predictions can be explainable and justifiable. Thus, this article tries to approach image captioning using Explainable AI such that the resulting captions generated by the model can be Explained and visualized. A newer architecture with a CNN decoder and hierarchical attention concept has been used to increase speed and accuracy of caption generation. Also, incorporating explainability to a model makes it more trustable when used in an application. The model is trained and evaluated using MSCOCO dataset and both quantitative and qualitative results are presented in this article.
Authors: Qiang Tong, Jinrui Wang, Wenshuang Yang, Songtao Wu, Wenqi Zhang, Chen Sun, Kuanhong Xu
Abstract: The utilization of AIoT technology has become a crucial trend in modern poultry management, offering the potential to optimize farming operations and reduce human workloads. This paper presents a real-time and compact edge-AI enabled detector designed to identify chickens and their healthy statuses using frames captured by a lightweight and intelligent camera equipped with an edge-AI enabled CMOS sensor. To ensure efficient deployment of the proposed compact detector within the memory-constrained edge-AI enabled CMOS sensor, we employ a FCOS-Lite detector leveraging MobileNet as the backbone. To mitigate the issue of reduced accuracy in compact edge-AI detectors without incurring additional inference costs, we propose a gradient weighting loss function as classification loss and introduce CIOU loss function as localization loss. Additionally, we propose a knowledge distillation scheme to transfer valuable information from a large teacher detector to the proposed FCOS-Lite detector, thereby enhancing its performance while preserving a compact model size. Experimental results demonstrate the proposed edge-AI enabled detector achieves commendable performance metrics, including a mean average precision (mAP) of 95.1$\%$ and an F1-score of 94.2$\%$, etc. Notably, the proposed detector can be efficiently deployed and operates at a speed exceeding 20 FPS on the edge-AI enabled CMOS sensor, achieved through int8 quantization. That meets practical demands for automated poultry health monitoring using lightweight intelligent cameras with low power consumption and minimal bandwidth costs.
Authors: Eunwoo Kim, Un Yang, Cheol Lae Roh, Stefano Ermon
Abstract: Conventional anomaly detection techniques based on reconstruction via denoising diffusion model are widely used due to their ability to identify anomaly locations and shapes with high performance. However, there is a limitation in determining appropriate noise parameters that can degrade anomalies while preserving normal characteristics. Also, due to the volatility of the diffusion model, normal regions can fluctuate considerably during reconstruction, resulting in false detection. In this paper, we propose a method to detect anomalies by analysis of reconstruction trend depending on the degree of degradation, effectively solving the both problems of existing methods. The proposed method is validated on an open dataset for industrial anomaly detection, improving the performance of existing methods on a number of evaluation criteria. With the ease of combination with existing anomaly detection methods, it provides a tradeoff between computational cost and performance, allowing it high application potential in manufacturing industry.
Authors: Qianchao Wang (Center of Mathematical Artificial Intelligence, Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China), Shijun Zhang (Department of Applied Mathematics, The Hong Kong Polytechnic University, Hong Kong, China), Dong Zeng (Department of Biomedical Engineering, Southern Medical University, Guangzhou, China), Zhaoheng Xie (Institute of Medical Technology, Peking University Health Science Center, Peking University, Beijing, China), Hengtao Guo (Independent Researcher, Seattle, WA, US), Feng-Lei Fan (Center of Mathematical Artificial Intelligence, Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China), Tieyong Zeng (Center of Mathematical Artificial Intelligence, Department of Mathematics, The Chinese University of Hong Kong, Hong Kong, China)
Abstract: In this paper, we propose a new super-expressive activation function called the Parametric Elementary Universal Activation Function (PEUAF). We demonstrate the effectiveness of PEUAF through systematic and comprehensive experiments on various industrial and image datasets, including CIFAR10, Tiny-ImageNet, and ImageNet. Moreover, we significantly generalize the family of super-expressive activation functions, whose existence has been demonstrated in several recent works by showing that any continuous function can be approximated to any desired accuracy by a fixed-size network with a specific super-expressive activation function. Specifically, our work addresses two major bottlenecks in impeding the development of super-expressive activation functions: the limited identification of super-expressive functions, which raises doubts about their broad applicability, and their often peculiar forms, which lead to skepticism regarding their scalability and practicality in real-world applications.
Authors: Haoye Dong, Aviral Chharia, Wenbo Gou, Francisco Vicente Carrasco, Fernando De la Torre
Abstract: 3D Hand reconstruction from a single RGB image is challenging due to the articulated motion, self-occlusion, and interaction with objects. Existing SOTA methods employ attention-based transformers to learn the 3D hand pose and shape, but they fail to achieve robust and accurate performance due to insufficient modeling of joint spatial relations. To address this problem, we propose a novel graph-guided Mamba framework, named Hamba, which bridges graph learning and state space modeling. Our core idea is to reformulate Mamba's scanning into graph-guided bidirectional scanning for 3D reconstruction using a few effective tokens. This enables us to learn the joint relations and spatial sequences for enhancing the reconstruction performance. Specifically, we design a novel Graph-guided State Space (GSS) block that learns the graph-structured relations and spatial sequences of joints and uses 88.5% fewer tokens than attention-based methods. Additionally, we integrate the state space features and the global features using a fusion module. By utilizing the GSS block and the fusion module, Hamba effectively leverages the graph-guided state space modeling features and jointly considers global and local features to improve performance. Extensive experiments on several benchmarks and in-the-wild tests demonstrate that Hamba significantly outperforms existing SOTAs, achieving the PA-MPVPE of 5.3mm and F@15mm of 0.992 on FreiHAND. Hamba is currently Rank 1 in two challenging competition leaderboards on 3D hand reconstruction. The code will be available upon acceptance. [Website](https://humansensinglab.github.io/Hamba/).
Authors: Anh Thai, Weiyao Wang, Hao Tang, Stefan Stojanov, Matt Feiszli, James M. Rehg
Abstract: 3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D datasets, which are expensive to collect. In this work, we propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels. By using features from pretrained foundation models and exploiting semantic and geometric correspondences, we are able to overcome the challenges of limited 3D annotations. Our approach leverages available 2D labels, enabling effective 3D object part segmentation. Our method 3-By-2 can accommodate various part taxonomies and granularities, demonstrating interesting part label transfer ability across different object categories. Project website: \url{https://ngailapdi.github.io/projects/3by2/}.
Authors: Zhexiao Xiong, Xin Xing, Scott Workman, Subash Khanal, Nathan Jacobs
Abstract: We introduce the task of mixed-view panorama synthesis, where the goal is to synthesize a novel panorama given a small set of input panoramas and a satellite image of the area. This contrasts with previous work which only uses input panoramas (same-view synthesis), or an input satellite image (cross-view synthesis). We argue that the mixed-view setting is the most natural to support panorama synthesis for arbitrary locations worldwide. A critical challenge is that the spatial coverage of panoramas is uneven, with few panoramas available in many regions of the world. We introduce an approach that utilizes diffusion-based modeling and an attention-based architecture for extracting information from all available input imagery. Experimental results demonstrate the effectiveness of our proposed method. In particular, our model can handle scenarios when the available panoramas are sparse or far from the location of the panorama we are attempting to synthesize.
Authors: Yiming Wang, Siyu Tang, Mengyu Chu
Abstract: We delve into the physics-informed neural reconstruction of smoke and obstacles through sparse-view RGB videos, tackling challenges arising from limited observation of complex dynamics. Existing physics-informed neural networks often emphasize short-term physics constraints, leaving the proper preservation of long-term conservation less explored. We introduce Neural Characteristic Trajectory Fields, a novel representation utilizing Eulerian neural fields to implicitly model Lagrangian fluid trajectories. This topology-free, auto-differentiable representation facilitates efficient flow map calculations between arbitrary frames as well as efficient velocity extraction via auto-differentiation. Consequently, it enables end-to-end supervision covering long-term conservation and short-term physics priors. Building on the representation, we propose physics-informed trajectory learning and integration into NeRF-based scene reconstruction. We enable advanced obstacle handling through self-supervised scene decomposition and seamless integrated boundary constraints. Our results showcase the ability to overcome challenges like occlusion uncertainty, density-color ambiguity, and static-dynamic entanglements. Code and sample tests are at \url{https://github.com/19reborn/PICT_smoke}.
Authors: Josh Myers-Dean, Jarek Reynolds, Brian Price, Yifei Fan, Danna Gurari
Abstract: Hierarchical segmentation entails creating segmentations at varying levels of granularity. We introduce the first hierarchical semantic segmentation dataset with subpart annotations for natural images, which we call SPIN (SubPartImageNet). We also introduce two novel evaluation metrics to evaluate how well algorithms capture spatial and semantic relationships across hierarchical levels. We benchmark modern models across three different tasks and analyze their strengths and weaknesses across objects, parts, and subparts. To facilitate community-wide progress, we publicly release our dataset at https://joshmyersdean.github.io/spin/index.html.
Authors: Saurav K. Shastri, Philip Schniter
Abstract: Accurately recovering images from phaseless measurements is a challenging and long-standing problem. In this work, we present "deepECpr," which combines expectation-consistent (EC) approximation with deep denoising networks to surpass state-of-the-art phase-retrieval methods in both speed and accuracy. In addition to applying EC in a non-traditional manner, deepECpr includes a novel stochastic damping scheme that is inspired by recent diffusion methods. Like existing phase-retrieval methods based on plug-and-play priors, regularization by denoising, or diffusion, deepECpr iterates a denoising stage with a measurement-exploitation stage. But unlike existing methods, deepECpr requires far fewer denoiser calls. We compare deepECpr to the state-of-the-art prDeep (Metzler et al., 2018), Deep-ITA (Wang et al., 2020), and Diffusion Posterior Sampling (Chung et al., 2023) methods for noisy phase-retrieval of color, natural, and unnatural grayscale images on oversampled-Fourier and coded-diffraction-pattern measurements and find improvements in both PSNR and SSIM with 5x fewer denoiser calls.
Authors: Tianyu Luan, Zhongpai Gao, Luyuan Xie, Abhishek Sharma, Hao Ding, Benjamin Planche, Meng Zheng, Ange Lou, Terrence Chen, Junsong Yuan, Ziyan Wu
Abstract: We introduce a novel bottom-up approach for human body mesh reconstruction, specifically designed to address the challenges posed by partial visibility and occlusion in input images. Traditional top-down methods, relying on whole-body parametric models like SMPL, falter when only a small part of the human is visible, as they require visibility of most of the human body for accurate mesh reconstruction. To overcome this limitation, our method employs a "Divide and Fuse (D&F)" strategy, reconstructing human body parts independently before fusing them, thereby ensuring robustness against occlusions. We design Human Part Parametric Models (HPPM) that independently reconstruct the mesh from a few shape and global-location parameters, without inter-part dependency. A specially designed fusion module then seamlessly integrates the reconstructed parts, even when only a few are visible. We harness a large volume of ground-truth SMPL data to train our parametric mesh models. To facilitate the training and evaluation of our method, we have established benchmark datasets featuring images of partially visible humans with HPPM annotations. Our experiments, conducted on these benchmark datasets, demonstrate the effectiveness of our D&F method, particularly in scenarios with substantial invisibility, where traditional approaches struggle to maintain reconstruction quality.
Authors: Shiqi Tan, Hamidreza Fazlali, Yixuan Xu, Yuan Ren, Bingbing Liu
Abstract: Range-View(RV)-based 3D point cloud segmentation is widely adopted due to its compact data form. However, RV-based methods fall short in providing robust segmentation for the occluded points and suffer from distortion of projected RGB images due to the sparse nature of 3D point clouds. To alleviate these problems, we propose a new LiDAR and Camera Range-view-based 3D point cloud semantic segmentation method (LaCRange). Specifically, a distortion-compensating knowledge distillation (DCKD) strategy is designed to remedy the adverse effect of RV projection of RGB images. Moreover, a context-based feature fusion module is introduced for robust and preservative sensor fusion. Finally, in order to address the limited resolution of RV and its insufficiency of 3D topology, a new point refinement scheme is devised for proper aggregation of features in 2D and augmentation of point features in 3D. We evaluated the proposed method on large-scale autonomous driving datasets \ie SemanticKITTI and nuScenes. In addition to being real-time, the proposed method achieves state-of-the-art results on nuScenes benchmark
Authors: Yake Wei, Siwei Li, Ruoxuan Feng, Di Hu
Abstract: To overcome the imbalanced multimodal learning problem, where models prefer the training of specific modalities, existing methods propose to control the training of uni-modal encoders from different perspectives, taking the inter-modal performance discrepancy as the basis. However, the intrinsic limitation of modality capacity is ignored. The scarcely informative modalities can be recognized as ``worse-learnt'' ones, which could force the model to memorize more noise, counterproductively affecting the multimodal model ability. Moreover, the current modality modulation methods narrowly concentrate on selected worse-learnt modalities, even suppressing the training of others. Hence, it is essential to consider the intrinsic limitation of modality capacity and take all modalities into account during balancing. To this end, we propose the Diagnosing \& Re-learning method. The learning state of each modality is firstly estimated based on the separability of its uni-modal representation space, and then used to softly re-initialize the corresponding uni-modal encoder. In this way, the over-emphasizing of scarcely informative modalities is avoided. In addition, encoders of worse-learnt modalities are enhanced, simultaneously avoiding the over-training of other modalities. Accordingly, multimodal learning is effectively balanced and enhanced. Experiments covering multiple types of modalities and multimodal frameworks demonstrate the superior performance of our simple-yet-effective method for balanced multimodal learning. The source code and dataset are available at \url{https://github.com/GeWu-Lab/Diagnosing_Relearning_ECCV2024}.
URLs: https://github.com/GeWu-Lab/Diagnosing_Relearning_ECCV2024
Authors: Dongmyeong Lee, Amanda Adkins, Joydeep Biswas
Abstract: In many applications, robots can benefit from object-level understanding of their environments, including the ability to distinguish object instances and re-identify previously seen instances. Object re-identification is challenging across different viewpoints and in scenes with significant appearance variation arising from weather or lighting changes. Most works on object re-identification focus on specific classes; approaches that address general object re-identification require foreground segmentation and have limited consideration of challenges such as occlusions, outdoor scenes, and illumination changes. To address this problem, we introduce CODa Re-ID: an in-the-wild object re-identification dataset containing 1,037,814 observations of 557 objects of 8 classes under diverse lighting conditions and viewpoints. Further, we propose CLOVER, a representation learning method for object observations that can distinguish between static object instances. Our results show that CLOVER achieves superior performance in static object re-identification under varying lighting conditions and viewpoint changes, and can generalize to unseen instances and classes.
Authors: Zhentao Huang, Minglun Gong
Abstract: In this paper, we introduce Textured-GS, an innovative method for rendering Gaussian splatting that incorporates spatially defined color and opacity variations using Spherical Harmonics (SH). This approach enables each Gaussian to exhibit a richer representation by accommodating varying colors and opacities across its surface, significantly enhancing rendering quality compared to traditional methods. To demonstrate the merits of our approach, we have adapted the Mini-Splatting architecture to integrate textured Gaussians without increasing the number of Gaussians. Our experiments across multiple real-world datasets show that Textured-GS consistently outperforms both the baseline Mini-Splatting and standard 3DGS in terms of visual fidelity. The results highlight the potential of Textured-GS to advance Gaussian-based rendering technologies, promising more efficient and high-quality scene reconstructions.
Authors: Xiaopei Wu, Yuenan Hou, Xiaoshui Huang, Binbin Lin, Tong He, Xinge Zhu, Yuexin Ma, Boxi Wu, Haifeng Liu, Deng Cai, Wanli Ouyang
Abstract: Training deep models for LiDAR semantic segmentation is challenging due to the inherent sparsity of point clouds. Utilizing temporal data is a natural remedy against the sparsity problem as it makes the input signal denser. However, previous multi-frame fusion algorithms fall short in utilizing sufficient temporal information due to the memory constraint, and they also ignore the informative temporal images. To fully exploit rich information hidden in long-term temporal point clouds and images, we present the Temporal Aggregation Network, termed TASeg. Specifically, we propose a Temporal LiDAR Aggregation and Distillation (TLAD) algorithm, which leverages historical priors to assign different aggregation steps for different classes. It can largely reduce memory and time overhead while achieving higher accuracy. Besides, TLAD trains a teacher injected with gt priors to distill the model, further boosting the performance. To make full use of temporal images, we design a Temporal Image Aggregation and Fusion (TIAF) module, which can greatly expand the camera FOV and enhance the present features. Temporal LiDAR points in the camera FOV are used as mediums to transform temporal image features to the present coordinate for temporal multi-modal fusion. Moreover, we develop a Static-Moving Switch Augmentation (SMSA) algorithm, which utilizes sufficient temporal information to enable objects to switch their motion states freely, thus greatly increasing static and moving training samples. Our TASeg ranks 1st on three challenging tracks, i.e., SemanticKITTI single-scan track, multi-scan track and nuScenes LiDAR segmentation track, strongly demonstrating the superiority of our method. Codes are available at https://github.com/LittlePey/TASeg.
Authors: Yixiao Yuan, Yingzhe Peng
Abstract: The Visual-Dialog Based Emotion Explanation Generation Challenge focuses on generating emotion explanations through visual-dialog interactions in art discussions. Our approach combines state-of-the-art multi-modal models, including Language Model (LM) and Large Vision Language Model (LVLM), to achieve superior performance. By leveraging these models, we outperform existing benchmarks, securing the top rank in the ICCV23 Visual-Dialog Based Emotion Explanation Generation Challenge, which is part of the 5th Workshop On Closing The Loop Between Vision And Language (CLCV) with significant scores in F1 and BLEU metrics. Our method demonstrates exceptional ability in generating accurate emotion explanations, advancing our understanding of emotional impacts in art.
Authors: Jinghao Zhang, Zizheng Yang, Qi Zhu, Feng Zhao
Abstract: Diffusion models have made remarkable progress in solving various inverse problems, attributing to the generative modeling capability of the data manifold. Posterior sampling from the conditional score function enable the precious data consistency certified by the measurement-based likelihood term. However, most prevailing approaches confined to the deterministic deterioration process of the measurement model, regardless of capricious unpredictable disturbance in real-world sceneries. To address this obstacle, we show that the measurement-based likelihood can be renovated with restoration-based likelihood via the opposite probabilistic graphic direction, licencing the patronage of various off-the-shelf restoration models and extending the strictly deterministic deterioration process to adaptable clustered processes with the supposed prototype, in what we call restorer guidance. Particularly, assembled with versatile prototypes optionally, we can resolve inverse problems with bunch of choices for assorted sample quality and realize the proficient deterioration control with assured realistic. We show that our work can be formally analogous to the transition from classifier guidance to classifier-free guidance in the field of inverse problem solver. Experiments on multifarious inverse problems demonstrate the effectiveness of our method, including image dehazing, rain streak removal, and motion deblurring.
Authors: Sixiao Zheng, Yanwei Fu
Abstract: Story visualization presents a challenging task in text-to-image generation, requiring not only the rendering of visual details from text prompt but also ensuring consistency across images. Recently, most approaches address inconsistency problem using an auto-regressive manner conditioned on previous image-sentence pairs. However, they overlook the fact that story context is dispersed across all sentences. The auto-regressive approach fails to encode information from susequent image-sentence pairs, thus unable to capture the entirety of the story context. To address this, we introduce TemporalStory, leveraging Spatial-Temporal attention to model complex spatial and temporal dependencies in images, enabling the generation of coherent images based on a given storyline. In order to better understand the storyline context, we introduce a text adapter capable of integrating information from other sentences into the embedding of the current sentence. Additionally, to utilize scene changes between story images as guidance for the model, we propose the StoryFlow Adapter to measure the degree of change between images. Through extensive experiments on two popular benchmarks, PororoSV and FlintstonesSV, our TemporalStory outperforms the previous state-of-the-art in both story visualization and story continuation tasks.
Authors: Kangyeol Kim, Wooseok Seo, Sehyun Nam, Bodam Kim, Suhyeon Jeong, Wonwoo Cho, Jaegul Choo, Youngjae Yu
Abstract: Personalized text-to-image (P-T2I) generation aims to create new, text-guided images featuring the personalized subject with a few reference images. However, balancing the trade-off relationship between prompt fidelity and identity preservation remains a critical challenge. To address the issue, we propose a novel P-T2I method called Layout-and-Retouch, consisting of two stages: 1) layout generation and 2) retouch. In the first stage, our step-blended inference utilizes the inherent sample diversity of vanilla T2I models to produce diversified layout images, while also enhancing prompt fidelity. In the second stage, multi-source attention swapping integrates the context image from the first stage with the reference image, leveraging the structure from the context image and extracting visual features from the reference image. This achieves high prompt fidelity while preserving identity characteristics. Through our extensive experiments, we demonstrate that our method generates a wide variety of images with diverse layouts while maintaining the unique identity features of the personalized objects, even with challenging text prompts. This versatility highlights the potential of our framework to handle complex conditions, significantly enhancing the diversity and applicability of personalized image synthesis.
Authors: Ruihuang Li, Zhengqiang Zhang, Chenhang He, Zhiyuan Ma, Vishal M. Patel, Lei Zhang
Abstract: Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or text supervision while neglecting the collective strength of all modalities. In this work, we propose a Dense Multimodal Alignment (DMA) framework to densely co-embed different modalities into a common space for maximizing their synergistic benefits. Instead of extracting coarse view- or region-level text prompts, we leverage large vision-language models to extract complete category information and scalable scene descriptions to build the text modality, and take image modality as the bridge to build dense point-pixel-text associations. Besides, in order to enhance the generalization ability of the 2D model for downstream 3D tasks without compromising the open-vocabulary capability, we employ a dual-path integration approach to combine frozen CLIP visual features and learnable mask features. Extensive experiments show that our DMA method produces highly competitive open-vocabulary segmentation performance on various indoor and outdoor tasks.
Authors: Lintai Wu, Xianjing Cheng, Junhui Hou, Yong Xu, Huanqiang Zeng
Abstract: In real-world scenarios, scanned point clouds are often incomplete due to occlusion issues. The task of self-supervised point cloud completion involves reconstructing missing regions of these incomplete objects without the supervision of complete ground truth. Current self-supervised methods either rely on multiple views of partial observations for supervision or overlook the intrinsic geometric similarity that can be identified and utilized from the given partial point clouds. In this paper, we propose MAL-SPC, a framework that effectively leverages both object-level and category-specific geometric similarities to complete missing structures. Our MAL-SPC does not require any 3D complete supervision and only necessitates a single partial point cloud for each object. Specifically, we first introduce a Pattern Retrieval Network to retrieve similar position and curvature patterns between the partial input and the predicted shape, then leverage these similarities to densify and refine the reconstructed results. Additionally, we render the reconstructed complete shape into multi-view depth maps and design an adversarial learning module to learn the geometry of the target shape from category-specific single-view depth images. To achieve anisotropic rendering, we design a density-aware radius estimation algorithm to improve the quality of the rendered images. Our MAL-SPC yields the best results compared to current state-of-the-art methods.We will make the source code publicly available at \url{https://github.com/ltwu6/malspc
Authors: Xiaopei Wu, Liang Peng, Liang Xie, Yuenan Hou, Binbin Lin, Xiaoshui Huang, Haifeng Liu, Deng Cai, Wanli Ouyang
Abstract: Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to generate pseudo labels for a student, and the quality of the pseudo labels is essential for the final performance. In this paper, we propose PatchTeacher, which focuses on partial scene 3D object detection to provide high-quality pseudo labels for the student. Specifically, we divide a complete scene into a series of patches and feed them to our PatchTeacher sequentially. PatchTeacher leverages the low memory consumption advantage of partial scene detection to process point clouds with a high-resolution voxelization, which can minimize the information loss of quantization and extract more fine-grained features. However, it is non-trivial to train a detector on fractions of the scene. Therefore, we introduce three key techniques, i.e., Patch Normalizer, Quadrant Align, and Fovea Selection, to improve the performance of PatchTeacher. Moreover, we devise PillarMix, a strong data augmentation strategy that mixes truncated pillars from different LiDAR scans to generate diverse training samples and thus help the model learn more general representation. Extensive experiments conducted on Waymo and ONCE datasets verify the effectiveness and superiority of our method and we achieve new state-of-the-art results, surpassing existing methods by a large margin. Codes are available at https://github.com/LittlePey/PTPM.
Authors: Pedro R. A. S. Bassi, Andrea Cavalli, Sergio Decherchi
Abstract: Bias and spurious correlations in data can cause shortcut learning, undermining out-of-distribution (OOD) generalization in deep neural networks. Most methods require unbiased data during training (and/or hyper-parameter tuning) to counteract shortcut learning. Here, we propose the use of explanation distillation to hinder shortcut learning. The technique does not assume any access to unbiased data, and it allows an arbitrarily sized student network to learn the reasons behind the decisions of an unbiased teacher, such as a vision-language model or a network processing debiased images. We found that it is possible to train a neural network with explanation (e.g by Layer Relevance Propagation, LRP) distillation only, and that the technique leads to high resistance to shortcut learning, surpassing group-invariant learning, explanation background minimization, and alternative distillation techniques. In the COLOURED MNIST dataset, LRP distillation achieved 98.2% OOD accuracy, while deep feature distillation and IRM achieved 92.1% and 60.2%, respectively. In COCO-on-Places, the undesirable generalization gap between in-distribution and OOD accuracy is only of 4.4% for LRP distillation, while the other two techniques present gaps of 15.1% and 52.1%, respectively.
Authors: Han Ling, Quansen Sun
Abstract: In this paper, we study the problem of estimating the 3D motion of dense pixels from continuous image pairs. Most previous methods are based on mature optical flow baselines and depth values, projecting the 2D motion on pixel planes into 3D space, and further optimizing the results by combining depth-motion-branch and other sub-modules. This stacked framework cannot leverage the complementarity between optical flow and other modules nor escape the dependence on accurate depth information. To address the above challenges, we propose a normalized scene flow framework, ScaleRAFT, based on cross-scale matching. Its core feature is directly matching objects between two frames in 3D scale space, i.e. matching features at the correct location and scale. Unlike previous methods, ScaleRAFT integrates optical flow and deep motion estimation into a unified architecture, allowing the optical flow pipeline and deep motion estimation to promote each other mutually. Moreover, ScaleRAFT estimates motion in the depth direction based on feature matching, breaking away from the dependence on accurate depth information. Experimentally, our method has achieved the best foreground performance so far in motion estimation tasks in driving scenarios, and has significantly improved various downstream 3D tasks.
Authors: Yujie Zhang, Qi Yang, Ziyu Shan, Yiling Xu
Abstract: Recent years have witnessed the success of the deep learning-based technique in research of no-reference point cloud quality assessment (NR-PCQA). For a more accurate quality prediction, many previous studies have attempted to capture global and local feature in a bottom-up manner, but ignored the interaction and promotion between them. To solve this problem, we propose a novel asynchronous feedback network (AFNet). Motivated by human visual perception mechanisms, AFNet employs a dual-branch structure to deal with global and local feature, simulating the left and right hemispheres of the human brain, and constructs a feedback module between them. Specifically, the input point clouds are first fed into a transformer-based global encoder to generate the attention maps that highlight these semantically rich regions, followed by being merged into the global feature. Then, we utilize the generated attention maps to perform dynamic convolution for different semantic regions and obtain the local feature. Finally, a coarse-to-fine strategy is adopted to merge the two features into the final quality score. We conduct comprehensive experiments on three datasets and achieve superior performance over the state-of-the-art approaches on all of these datasets. The code will be available at https://github.com/zhangyujie-1998/AFNet.
Authors: Wenjie Zhuo, Fan Ma, Hehe Fan, Yi Yang
Abstract: This paper presents Invariant Score Distillation (ISD), a novel method for high-fidelity text-to-3D generation. ISD aims to tackle the over-saturation and over-smoothing problems in Score Distillation Sampling (SDS). In this paper, SDS is decoupled into a weighted sum of two components: the reconstruction term and the classifier-free guidance term. We experimentally found that over-saturation stems from the large classifier-free guidance scale and over-smoothing comes from the reconstruction term. To overcome these problems, ISD utilizes an invariant score term derived from DDIM sampling to replace the reconstruction term in SDS. This operation allows the utilization of a medium classifier-free guidance scale and mitigates the reconstruction-related errors, thus preventing the over-smoothing and over-saturation of results. Extensive experiments demonstrate that our method greatly enhances SDS and produces realistic 3D objects through single-stage optimization.
Authors: Xiaoxu Xu, Yitian Yuan, Jinlong Li, Qiudan Zhang, Zequn Jie, Lin Ma, Hao Tang, Nicu Sebe, Xu Wang
Abstract: In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the aligned image and text spaces from the 2D vision-language model. Specifically, our method exploits the superior generalization ability of the 2D vision-language models and proposes the Embeddings Soft-Guidance Stage to utilize it to implicitly align 3D embeddings and text embeddings. Moreover, we introduce the Embeddings Specialization Stage to purify the feature representation with the help of a given scene-level label, specifying a better feature supervised by the corresponding text embedding. Thus, the 3D model is able to gain informative supervisions both from the image embedding and text embedding, leading to competitive segmentation performances. To the best of our knowledge, this is the first work to investigate 3D weakly supervised semantic segmentation by using the textual semantic information of text category labels. Moreover, with extensive quantitative and qualitative experiments, we present that our 3DSS-VLG is able not only to achieve the state-of-the-art performance on both S3DIS and ScanNet datasets, but also to maintain strong generalization capability.
Authors: Yiming Ren, Xiao Han, Yichen Yao, Xiaoxiao Long, Yujing Sun, Yuexin Ma
Abstract: LiDAR-based human motion capture has garnered significant interest in recent years for its practicability in large-scale and unconstrained environments. However, most methods rely on cleanly segmented human point clouds as input, the accuracy and smoothness of their motion results are compromised when faced with noisy data, rendering them unsuitable for practical applications. To address these limitations and enhance the robustness and precision of motion capture with noise interference, we introduce LiveHPS++, an innovative and effective solution based on a single LiDAR system. Benefiting from three meticulously designed modules, our method can learn dynamic and kinematic features from human movements, and further enable the precise capture of coherent human motions in open settings, making it highly applicable to real-world scenarios. Through extensive experiments, LiveHPS++ has proven to significantly surpass existing state-of-the-art methods across various datasets, establishing a new benchmark in the field.
Authors: Anqi Zhang, Guangyu Gao
Abstract: Class Incremental Semantic Segmentation~(CISS), within Incremental Learning for semantic segmentation, targets segmenting new categories while reducing the catastrophic forgetting on the old categories.Besides, background shifting, where the background category changes constantly in each step, is a special challenge for CISS. Current methods with a shared background classifier struggle to keep up with these changes, leading to decreased stability in background predictions and reduced accuracy of segmentation. For this special challenge, we designed a novel background adaptation mechanism, which explicitly models the background residual rather than the background itself in each step, and aggregates these residuals to represent the evolving background. Therefore, the background adaptation mechanism ensures the stability of previous background classifiers, while enabling the model to concentrate on the easy-learned residuals from the additional channel, which enhances background discernment for better prediction of novel categories. To precisely optimize the background adaptation mechanism, we propose Pseudo Background Binary Cross-Entropy loss and Background Adaptation losses, which amplify the adaptation effect. Group Knowledge Distillation and Background Feature Distillation strategies are designed to prevent forgetting old categories. Our approach, evaluated across various incremental scenarios on Pascal VOC 2012 and ADE20K datasets, outperforms prior exemplar-free state-of-the-art methods with mIoU of 3.0% in VOC 10-1 and 2.0% in ADE 100-5, notably enhancing the accuracy of new classes while mitigating catastrophic forgetting. Code is available in https://andyzaq.github.io/barmsite/.
Authors: Qianxiong Xu, Guosheng Lin, Chen Change Loy, Cheng Long, Ziyue Li, Rui Zhao
Abstract: Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features. However, due to the large receptive fields in deep layers of the backbone, the extracted query and support FG features are inevitably mingled with background (BG) features, impeding the FG-FG matching in cross attention. Hence, the query FG features are fused with less support FG features, i.e., the support information is not well utilized. This paper presents a novel plug-in termed ambiguity elimination network (AENet), which can be plugged into any existing cross attention-based FSS methods. The main idea is to mine discriminative query FG regions to rectify the ambiguous FG features, increasing the proportion of FG information, so as to suppress the negative impacts of the doped BG features. In this way, the FG-FG matching is naturally enhanced. We plug AENet into three baselines CyCTR, SCCAN and HDMNet for evaluation, and their scores are improved by large margins, e.g., the 1-shot performance of SCCAN can be improved by 3.0%+ on both PASCAL-5$^i$ and COCO-20$^i$. The code is available at https://github.com/Sam1224/AENet.
Authors: Han Li, Shaohui Li, Shuangrui Ding, Wenrui Dai, Maida Cao, Chenglin Li, Junni Zou, Hongkai Xiong
Abstract: Image compression for machine and human vision (ICMH) has gained increasing attention in recent years. Existing ICMH methods are limited by high training and storage overheads due to heavy design of task-specific networks. To address this issue, in this paper, we develop a novel lightweight adapter-based tuning framework for ICMH, named Adapt-ICMH, that better balances task performance and bitrates with reduced overheads. We propose a spatial-frequency modulation adapter (SFMA) that simultaneously eliminates non-semantic redundancy with a spatial modulation adapter, and enhances task-relevant frequency components and suppresses task-irrelevant frequency components with a frequency modulation adapter. The proposed adapter is plug-and-play and compatible with almost all existing learned image compression models without compromising the performance of pre-trained models. Experiments demonstrate that Adapt-ICMH consistently outperforms existing ICMH frameworks on various machine vision tasks with fewer fine-tuned parameters and reduced computational complexity. Code will be released at https://github.com/qingshi9974/ECCV2024-AdpatICMH .
Authors: Shaohong Wang, Lu Bin, Xinyu Xiao, Zhiyu Xiang, Hangguan Shan, Eryun Liu
Abstract: Multi-agent collaborative perception has emerged as a widely recognized technology in the field of autonomous driving in recent years. However, current collaborative perception predominantly relies on LiDAR point clouds, with significantly less attention given to methods using camera images. This severely impedes the development of budget-constrained collaborative systems and the exploitation of the advantages offered by the camera modality. This work proposes an instance-level fusion transformer for visual collaborative perception (IFTR), which enhances the detection performance of camera-only collaborative perception systems through the communication and sharing of visual features. To capture the visual information from multiple agents, we design an instance feature aggregation that interacts with the visual features of individual agents using predefined grid-shaped bird eye view (BEV) queries, generating more comprehensive and accurate BEV features. Additionally, we devise a cross-domain query adaptation as a heuristic to fuse 2D priors, implicitly encoding the candidate positions of targets. Furthermore, IFTR optimizes communication efficiency by sending instance-level features, achieving an optimal performance-bandwidth trade-off. We evaluate the proposed IFTR on a real dataset, DAIR-V2X, and two simulated datasets, OPV2V and V2XSet, achieving performance improvements of 57.96%, 9.23% and 12.99% in AP@70 metrics compared to the previous SOTAs, respectively. Extensive experiments demonstrate the superiority of IFTR and the effectiveness of its key components. The code is available at https://github.com/wangsh0111/IFTR.
Authors: Shaocheng Yan, Pengcheng Shi, Jiayuan Li
Abstract: Recent advances in point cloud registration mostly leverage geometric information. Although these methods have yielded promising results, they still struggle with problems of low overlap, thus limiting their practical usage. In this paper, we propose ML-SemReg, a plug-and-play point cloud registration framework that fully exploits semantic information. Our key insight is that mismatches can be categorized into two types, i.e., inter- and intra-class, after rendering semantic clues, and can be well addressed by utilizing multi-level semantic consistency. We first propose a Group Matching module to address inter-class mismatching, outputting multiple matching groups that inherently satisfy Local Semantic Consistency. For each group, a Mask Matching module based on Scene Semantic Consistency is then introduced to suppress intra-class mismatching. Benefit from those two modules, ML-SemReg generates correspondences with a high inlier ratio. Extensive experiments demonstrate excellent performance and robustness of ML-SemReg, e.g., in hard-cases of the KITTI dataset, the Registration Recall of MAC increases by almost 34 percentage points when our ML-SemReg is equipped. Code is available at \url{https://github.com/Laka-3DV/ML-SemReg}
Authors: Ling Zhao, Zhenyang Huang, Dongsheng Kuang, Chengli Peng, Jun Gan, Haifeng Li
Abstract: The existing change detection(CD) methods can be summarized as the visual-first change detection (ViFi-CD) paradigm, which first extracts change features from visual differences and then assigns them specific semantic information. However, CD is essentially dependent on change regions of interest (CRoIs), meaning that the CD results are directly determined by the semantics changes of interest, making its primary image factor semantic of interest rather than visual. The ViFi-CD paradigm can only assign specific semantics of interest to specific change features extracted from visual differences, leading to the inevitable omission of potential CRoIs and the inability to adapt to different CRoI CD tasks. In other words, changes in other CRoIs cannot be detected by the ViFi-CD method without retraining the model or significantly modifying the method. This paper introduces a new CD paradigm, the semantic-first CD (SeFi-CD) paradigm. The core idea of SeFi-CD is to first perceive the dynamic semantics of interest and then visually search for change features related to the semantics. Based on the SeFi-CD paradigm, we designed Anything You Want Change Detection (AUWCD). Experiments on public datasets demonstrate that the AUWCD outperforms the current state-of-the-art CD methods, achieving an average F1 score 5.01\% higher than that of these advanced supervised baselines on the SECOND dataset, with a maximum increase of 13.17\%. The proposed SeFi-CD offers a novel CD perspective and approach.
Authors: David Serrano-Lozano, Luis Herranz, Michael S. Brown, Javier Vazquez-Corral
Abstract: A popular method for enhancing images involves learning the style of a professional photo editor using pairs of training images comprised of the original input with the editor-enhanced version. When manipulating images, many editing tools offer a feature that allows the user to manipulate a limited selection of familiar colors. Editing by color name allows easy adjustment of elements like the "blue" of the sky or the "green" of trees. Inspired by this approach to color manipulation, we propose NamedCurves, a learning-based image enhancement technique that separates the image into a small set of named colors. Our method learns to globally adjust the image for each specific named color via tone curves and then combines the images using an attention-based fusion mechanism to mimic spatial editing. We demonstrate the effectiveness of our method against several competing methods on the well-known Adobe 5K dataset and the PPR10K dataset, showing notable improvements.
Authors: Noam Elata, Tomer Michaeli, Michael Elad
Abstract: Diffusion models dominate the field of image generation, however they have yet to make major breakthroughs in the field of image compression. Indeed, while pre-trained diffusion models have been successfully adapted to a wide variety of downstream tasks, existing work in diffusion-based image compression require task specific model training, which can be both cumbersome and limiting. This work addresses this gap by harnessing the image prior learned by existing pre-trained diffusion models for solving the task of lossy image compression. This enables the use of the wide variety of publicly-available models, and avoids the need for training or fine-tuning. Our method, PSC (Posterior Sampling-based Compression), utilizes zero-shot diffusion-based posterior samplers. It does so through a novel sequential process inspired by the active acquisition technique "Adasense" to accumulate informative measurements of the image. This strategy minimizes uncertainty in the reconstructed image and allows for construction of an image-adaptive transform coordinated between both the encoder and decoder. PSC offers a progressive compression scheme that is both practical and simple to implement. Despite minimal tuning, and a simple quantization and entropy coding, PSC achieves competitive results compared to established methods, paving the way for further exploration of pre-trained diffusion models and posterior samplers for image compression.
Authors: Haoyang Liu
Abstract: The project leverages advanced machine and deep learning techniques to address the challenge of emotion recognition by focusing on non-facial cues, specifically hands, body gestures, and gestures. Traditional emotion recognition systems mainly rely on facial expression analysis and often ignore the rich emotional information conveyed through body language. To bridge this gap, this method leverages the Aff-Wild2 and DFEW databases to train and evaluate a model capable of recognizing seven basic emotions (angry, disgust, fear, happiness, sadness, surprise, and neutral) and estimating valence and continuous scales wakeup descriptor. Leverage OpenPose for pose estimation to extract detailed body posture and posture features from images and videos. These features serve as input to state-of-the-art neural network architectures, including ResNet, and ANN for emotion classification, and fully connected layers for valence arousal regression analysis. This bifurcation strategy can solve classification and regression problems in the field of emotion recognition. The project aims to contribute to the field of affective computing by enhancing the ability of machines to interpret and respond to human emotions in a more comprehensive and nuanced way. By integrating multimodal data and cutting-edge computational models, I aspire to develop a system that not only enriches human-computer interaction but also has potential applications in areas as diverse as mental health support, educational technology, and autonomous vehicle systems.
Authors: Wei Shang, Dongwei Ren, Wanying Zhang, Yuming Fang, Wangmeng Zuo, Kede Ma
Abstract: Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding spatial detail reproduction, temporal consistency, and computational complexity. In this paper, we first describe a strong baseline for AVSR by putting together three variants of elementary building blocks: 1) a flow-guided recurrent unit that aggregates spatiotemporal information from previous frames, 2) a flow-refined cross-attention unit that selects spatiotemporal information from future frames, and 3) a hyper-upsampling unit that generates scaleaware and content-independent upsampling kernels. We then introduce ST-AVSR by equipping our baseline with a multi-scale structural and textural prior computed from the pre-trained VGG network. This prior has proven effective in discriminating structure and texture across different locations and scales, which is beneficial for AVSR. Comprehensive experiments show that ST-AVSR significantly improves super-resolution quality, generalization ability, and inference speed over the state-of-theart. The code is available at https://github.com/shangwei5/ST-AVSR.
Authors: Ziyue Huang, Yongchao Feng, Qingjie Liu, Yunhong Wang
Abstract: Detection pre-training methods for the DETR series detector have been extensively studied in natural scenes, e.g., DETReg. However, the detection pre-training remains unexplored in remote sensing scenes. In existing pre-training methods, alignment between object embeddings extracted from a pre-trained backbone and detector features is significant. However, due to differences in feature extraction methods, a pronounced feature discrepancy still exists and hinders the pre-training performance. The remote sensing images with complex environments and more densely distributed objects exacerbate the discrepancy. In this work, we propose a novel Mutually optimizing pre-training framework for remote sensing object Detection, dubbed as MutDet. In MutDet, we propose a systemic solution against this challenge. Firstly, we propose a mutual enhancement module, which fuses the object embeddings and detector features bidirectionally in the last encoder layer, enhancing their information interaction.Secondly, contrastive alignment loss is employed to guide this alignment process softly and simultaneously enhances detector features' discriminativity. Finally, we design an auxiliary siamese head to mitigate the task gap arising from the introduction of enhancement module. Comprehensive experiments on various settings show new state-of-the-art transfer performance. The improvement is particularly pronounced when data quantity is limited. When using 10% of the DIOR-R data, MutDet improves DetReg by 6.1% in AP50. Codes and models are available at: https://github.com/floatingstarZ/MutDet.
Authors: Hongsong Wang, Jie Gui
Abstract: Human action understanding is a fundamental and challenging task in computer vision. Although there exists tremendous research on this area, most works focus on action recognition, while action retrieval has received less attention. In this paper, we focus on the neglected but important task of image-based action retrieval which aims to find images that depict the same action as a query image. We establish benchmarks for this task and set up important baseline methods for fair comparison. We present an end-to-end model that learns rich action representations from three aspects: the anchored person, contextual regions, and the global image. A novel fusion transformer module is designed to model the relationships among different features and effectively fuses them into an action representation. Experiments on the Stanford-40 and PASCAL VOC 2012 Action datasets show that the proposed method significantly outperforms previous approaches for image-based action retrieval.
Authors: Jiacheng Li, Chang Chen, Fenglong Song, Youliang Yan, Zhiwei Xiong
Abstract: Image resampling is a basic technique that is widely employed in daily applications, such as camera photo editing. Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. Still, these methods are not the perfect substitute for interpolation, due to the drawbacks in efficiency and versatility. In this work, we propose a novel method of Learning Resampling Function (termed LeRF), which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption of interpolation. Specifically, LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the hyper-parameters that determine the shapes of these resampling functions with a neural network. Based on the formulation of LeRF, we develop a family of models, including both efficiency-orientated and performance-orientated ones. To achieve interpolation-level efficiency, we adopt look-up tables (LUTs) to accelerate the inference of the learned neural network. Furthermore, we design a directional ensemble strategy and edge-sensitive indexing patterns to better capture local structures. On the other hand, to obtain DNN-level performance, we propose an extension of LeRF to enable it in cooperation with pre-trained upsampling models for cascaded resampling. Extensive experiments show that the efficiency-orientated version of LeRF runs as fast as interpolation, generalizes well to arbitrary transformations, and outperforms interpolation significantly, e.g., up to 3dB PSNR gain over Bicubic for x2 upsampling on Manga109. Besides, the performance-orientated version of LeRF reaches comparable performance with existing DNNs at much higher efficiency, e.g., less than 25% running time on a desktop GPU.
Authors: Yibo Zhong, Yao Zhou
Abstract: Low-rank adaptation (LoRA), as one of the most well-known representative methods of parameter-efficient fine-tuning, freezes the backbone model and introduces parallel adapter modules to each layer of the model. These modules consist of two low-rank trainable matrices: a low-dimension projector (LP) and a high-dimension projector (HP) with their product approximating the change for updating the model weight. However, LoRA's paired LP and HP per layer limit learned weights to specific features, ignoring the varied information extracted by stacked layers in models like Transformers. By considering the differences between layers and establishing connections across them when learning the weights, we enhance the capture of relevant information for downstream tasks using this interconnected adaptation when fine-tuning. Meanwhile, preserving the unique characteristics of each layer and thus selectively mix the learning traits of various layers according to a specific ratio can also be crucial in certain tasks. In this paper, we propose Low-rank Interconnected adaptation across layers (Lily). Specifically, we retain layer-specific LPs (local LPs) for low-dimensional feature projection and unify all HPs into a model-wide global HP, thereby overcoming layer-specific constraints in LoRA. The global HP, layer-independent, supports multiple HP sub-modules, or inspired by Mixture of Experts (MoE), HP experts capturing learning traits across all layer depths. For the ratio to mix all the experts, we use a router inspired by MoE to selectively adapt the features of different layers, thus obtaining a unique expert distribution. We evaluated Lily on a wide range of downstream tasks and achieved state-of-the-art results, outperforming LoRA and a range of competitive methods. Code will be available at https://github.com/blameitonme1/lily.
Authors: Fa-Ting Hong, Dan Xu
Abstract: One-shot talking head video generation uses a source image and driving video to create a synthetic video where the source person's facial movements imitate those of the driving video. However, differences in scale between the source and driving images remain a challenge for face reenactment. Existing methods attempt to locate a frame in the driving video that aligns best with the source image, but imprecise alignment can result in suboptimal outcomes. To this end, we introduce a scale transformation module that can automatically adjust the scale of the driving image to fit that of the source image, by using the information of scale difference maintained in the detected keypoints of the source image and the driving frame. Furthermore, to keep perceiving the scale information of faces during the generation process, we incorporate the scale information learned from the scale transformation module into each layer of the generation process to produce a final result with an accurate scale. Our method can perform accurate motion transfer between the two images without any anchor frame, achieved through the contributions of the proposed online scale transformation facial reenactment network. Extensive experiments have demonstrated that our proposed method adjusts the scale of the driving face automatically according to the source face, and generates high-quality faces with an accurate scale in the cross-identity facial reenactment.
Authors: Mei Qiu, Lauren Ann Christopher, Lingxi Li, Stanley Chien, Yaobin Chen
Abstract: Vehicle re-identification (ReID) is a computer vision task that matches the same vehicle across different cameras or viewpoints in a surveillance system. This is crucial for Intelligent Transportation Systems (ITS), where the effectiveness is influenced by the regions from which vehicle images are cropped. This study explores whether optimal vehicle detection regions, guided by detection confidence scores, can enhance feature matching and ReID tasks. Using our framework with multiple Regions of Interest (ROIs) and lane-wise vehicle counts, we employed YOLOv8 for detection and DeepSORT for tracking across twelve Indiana Highway videos, including two pairs of videos from non-overlapping cameras. Tracked vehicle images were cropped from inside and outside the ROIs at five-frame intervals. Features were extracted using pre-trained models: ResNet50, ResNeXt50, Vision Transformer, and Swin-Transformer. Feature consistency was assessed through cosine similarity, information entropy, and clustering variance. Results showed that features from images cropped inside ROIs had higher mean cosine similarity values compared to those involving one image inside and one outside the ROIs. The most significant difference was observed during night conditions (0.7842 inside vs. 0.5 outside the ROI with Swin-Transformer) and in cross-camera scenarios (0.75 inside-inside vs. 0.52 inside-outside the ROI with Vision Transformer). Information entropy and clustering variance further supported that features in ROIs are more consistent. These findings suggest that strategically selected ROIs can enhance tracking performance and ReID accuracy in ITS.
Authors: Can Cui, Ruining Deng, Junlin Guo, Quan Liu, Tianyuan Yao, Haichun Yang, Yuankai Huo
Abstract: The Vision Foundation Model has recently gained attention in medical image analysis. Its zero-shot learning capabilities accelerate AI deployment and enhance the generalizability of clinical applications. However, segmenting pathological images presents a special focus on the flexibility of segmentation targets. For instance, a single click on a Whole Slide Image (WSI) could signify a cell, a functional unit, or layers, adding layers of complexity to the segmentation tasks. Current models primarily predict potential outcomes but lack the flexibility needed for physician input. In this paper, we explore the potential of enhancing segmentation model flexibility by introducing various task prompts through a Large Language Model (LLM) alongside traditional task tokens. Our contribution is in four-fold: (1) we construct a computational-efficient pipeline that uses finetuned language prompts to guide flexible multi-class segmentation; (2) We compare segmentation performance with fixed prompts against free-text; (3) We design a multi-task kidney pathology segmentation dataset and the corresponding various free-text prompts; and (4) We evaluate our approach on the kidney pathology dataset, assessing its capacity to new cases during inference.
Authors: Joel Sol, Jamil Fayyad, Shadi Alijani, Homayoun Najjaran
Abstract: Deformation detection is vital for enabling accurate assessment and prediction of structural changes in materials, ensuring timely and effective interventions to maintain safety and integrity. Automating deformation detection through computer vision is crucial for efficient monitoring, but it faces significant challenges in creating a comprehensive dataset of both deformed and non-deformed objects, which can be difficult to obtain in many scenarios. In this paper, we introduce a novel framework for generating controlled synthetic data that simulates deformed objects. This approach allows for the realistic modeling of object deformations under various conditions. Our framework integrates an intelligent adapter network that facilitates sim-to-real domain adaptation, enhancing classification results without requiring real data from deformed objects. We conduct experiments on domain adaptation and classification tasks and demonstrate that our framework improves sim-to-real classification results compared to simulation baseline.
Authors: Zhenyu Wang, Shahriar Nirjon
Abstract: Edge devices, with their widely varying capabilities, support a diverse range of edge AI models. This raises the question: how does an edge model differ from a high-accuracy (base) model for the same task? We introduce XDELTA, a novel explainable AI tool that explains differences between a high-accuracy base model and a computationally efficient but lower-accuracy edge model. To achieve this, we propose a learning-based approach to characterize the model difference, named the DELTA network, which complements the feature representation capability of the edge network in a compact form. To construct DELTA, we propose a sparsity optimization framework that extracts the essence of the base model to ensure compactness and sufficient feature representation capability of DELTA, and implement a negative correlation learning approach to ensure it complements the edge model. We conduct a comprehensive evaluation to test XDELTA's ability to explain model discrepancies, using over 1.2 million images and 24 models, and assessing real-world deployments with six participants. XDELTA excels in explaining differences between base and edge models (arbitrary pairs as well as compressed base models) through geometric and concept-level analysis, proving effective in real-world applications.
Authors: Vanshali Sharma
Abstract: Various trending image generative techniques, such as diffusion models, have enabled visually appealing outcomes with just text-based descriptions. Unlike general images, where assessing the quality and alignment with text descriptions is trivial, establishing such a relation in a clinical setting proves challenging. This work investigates various strategies to evaluate the clinical significance of synthetic polyp images of different pathologies. We further explore if a relation could be established between qualitative results and their clinical relevance.
Authors: Ayush V. Gowda (Florida Atlantic University), Juan D. Yepes (Florida Atlantic University), Daniel Raviv (Florida Atlantic University)
Abstract: This paper focuses on the educational journey of a computer engineering undergraduate student venturing into the domain of computer vision and robotics. It explores how optical flow and its applications can be used to detect moving objects when a camera undergoes translational motion, highlighting the challenges encountered and the strategies used to overcome them. Furthermore, the paper discusses not only the technical skills acquired by the student but also interpersonal skills as related to teamwork and diversity. In this paper, we detail the learning process, including the acquisition of technical and problem-solving skills, as well as out-of-the-box thinking.
Authors: Chengjie Jiang, Xiaowen Liu, Bowen Zheng, Lu Bai, Jing Li
Abstract: Infrared and visible image fusion has been developed from vision perception oriented fusion methods to strategies which both consider the vision perception and high-level vision task. However, the existing task-driven methods fail to address the domain gap between semantic and geometric representation. To overcome these issues, we propose a high-level vision task-driven infrared and visible image fusion network via semantic and geometric domain transformation, terms as HSFusion. Specifically, to minimize the gap between semantic and geometric representation, we design two separate domain transformation branches by CycleGAN framework, and each includes two processes: the forward segmentation process and the reverse reconstruction process. CycleGAN is capable of learning domain transformation patterns, and the reconstruction process of CycleGAN is conducted under the constraint of these patterns. Thus, our method can significantly facilitate the integration of semantic and geometric information and further reduces the domain gap. In fusion stage, we integrate the infrared and visible features that extracted from the reconstruction process of two seperate CycleGANs to obtain the fused result. These features, containing varying proportions of semantic and geometric information, can significantly enhance the high level vision tasks. Additionally, we generate masks based on segmentation results to guide the fusion task. These masks can provide semantic priors, and we design adaptive weights for two distinct areas in the masks to facilitate image fusion. Finally, we conducted comparative experiments between our method and eleven other state-of-the-art methods, demonstrating that our approach surpasses others in both visual appeal and semantic segmentation task.
Authors: Nazmul Karim, Abdullah Al Arafat, Umar Khalid, Zhishan Guo, Nazanin Rahnavard
Abstract: Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain types of triggers or poisoning mechanisms. State-of-the-art (SOTA) defenses employ too-sophisticated mechanisms that require either a computationally expensive adversarial search module for reverse-engineering the trigger distribution or an over-sensitive hyper-parameter selection module. Moreover, they offer sub-par performance in challenging scenarios, e.g., limited validation data and strong attacks. In this paper, we propose Neural mask Fine-Tuning (NFT) with an aim to optimally re-organize the neuron activities in a way that the effect of the backdoor is removed. Utilizing a simple data augmentation like MixUp, NFT relaxes the trigger synthesis process and eliminates the requirement of the adversarial search module. Our study further reveals that direct weight fine-tuning under limited validation data results in poor post-purification clean test accuracy, primarily due to overfitting issue. To overcome this, we propose to fine-tune neural masks instead of model weights. In addition, a mask regularizer has been devised to further mitigate the model drift during the purification process. The distinct characteristics of NFT render it highly efficient in both runtime and sample usage, as it can remove the backdoor even when a single sample is available from each class. We validate the effectiveness of NFT through extensive experiments covering the tasks of image classification, object detection, video action recognition, 3D point cloud, and natural language processing. We evaluate our method against 14 different attacks (LIRA, WaNet, etc.) on 11 benchmark data sets such as ImageNet, UCF101, Pascal VOC, ModelNet, OpenSubtitles2012, etc.
Authors: Zeyu Zhang, Akide Liu, Qi Chen, Feng Chen, Ian Reid, Richard Hartley, Bohan Zhuang, Hao Tang
Abstract: Text-to-motion generation holds potential for film, gaming, and robotics, yet current methods often prioritize short motion generation, making it challenging to produce long motion sequences effectively: (1) Current methods struggle to handle long motion sequences as a single input due to prohibitively high computational cost; (2) Breaking down the generation of long motion sequences into shorter segments can result in inconsistent transitions and requires interpolation or inpainting, which lacks entire sequence modeling. To solve these challenges, we propose InfiniMotion, a method that generates continuous motion sequences of arbitrary length within an autoregressive framework. We highlight its groundbreaking capability by generating a continuous 1-hour human motion with around 80,000 frames. Specifically, we introduce the Motion Memory Transformer with Bidirectional Mamba Memory, enhancing the transformer's memory to process long motion sequences effectively without overwhelming computational resources. Notably our method achieves over 30% improvement in FID and 6 times longer demonstration compared to previous state-of-the-art methods, showcasing significant advancements in long motion generation. See project webpage: https://steve-zeyu-zhang.github.io/InfiniMotion/
Authors: Jiyuan Zhang, Kang Chen, Shiyan Chen, Yajing Zheng, Tiejun Huang, Zhaofei Yu
Abstract: Novel View Synthesis plays a crucial role by generating new 2D renderings from multi-view images of 3D scenes. However, capturing high-speed scenes with conventional cameras often leads to motion blur, hindering the effectiveness of 3D reconstruction. To address this challenge, high-frame-rate dense 3D reconstruction emerges as a vital technique, enabling detailed and accurate modeling of real-world objects or scenes in various fields, including Virtual Reality or embodied AI. Spike cameras, a novel type of neuromorphic sensor, continuously record scenes with an ultra-high temporal resolution, showing potential for accurate 3D reconstruction. Despite their promise, existing approaches, such as applying Neural Radiance Fields (NeRF) to spike cameras, encounter challenges due to the time-consuming rendering process. To address this issue, we make the first attempt to introduce the 3D Gaussian Splatting (3DGS) into spike cameras in high-speed capture, providing 3DGS as dense and continuous clues of views, then constructing SpikeGS. Specifically, to train SpikeGS, we establish computational equations between the rendering process of 3DGS and the processes of instantaneous imaging and exposing-like imaging of the continuous spike stream. Besides, we build a very lightweight but effective mapping process from spikes to instant images to support training. Furthermore, we introduced a new spike-based 3D rendering dataset for validation. Extensive experiments have demonstrated our method possesses the high quality of novel view rendering, proving the tremendous potential of spike cameras in modeling 3D scenes.
Authors: Xuelong Dai, Bin Xiao
Abstract: Recent studies that incorporate geometric features and transformers into 3D point cloud feature learning have significantly improved the performance of 3D deep-learning models. However, their robustness against adversarial attacks has not been thoroughly explored. Existing attack methods primarily focus on white-box scenarios and struggle to transfer to recently proposed 3D deep-learning models. Even worse, these attacks introduce perturbations to 3D coordinates, generating unrealistic adversarial examples and resulting in poor performance against 3D adversarial defenses. In this paper, we generate high-quality adversarial point clouds using diffusion models. By using partial points as prior knowledge, we generate realistic adversarial examples through shape completion with adversarial guidance. The proposed adversarial shape completion allows for a more reliable generation of adversarial point clouds. To enhance attack transferability, we delve into the characteristics of 3D point clouds and employ model uncertainty for better inference of model classification through random down-sampling of point clouds. We adopt ensemble adversarial guidance for improved transferability across different network architectures. To maintain the generation quality, we limit our adversarial guidance solely to the critical points of the point clouds by calculating saliency scores. Extensive experiments demonstrate that our proposed attacks outperform state-of-the-art adversarial attack methods against both black-box models and defenses. Our black-box attack establishes a new baseline for evaluating the robustness of various 3D point cloud classification models.
Authors: Cheng Shi, Yuchen Zhu, Sibei Yang
Abstract: Recent advancements in large-scale foundational models have sparked widespread interest in training highly proficient large vision models. A common consensus revolves around the necessity of aggregating extensive, high-quality annotated data. However, given the inherent challenges in annotating dense tasks in computer vision, such as object detection and segmentation, a practical strategy is to combine and leverage all available data for training purposes. In this work, we propose Plain-Det, which offers flexibility to accommodate new datasets, robustness in performance across diverse datasets, training efficiency, and compatibility with various detection architectures. We utilize Def-DETR, with the assistance of Plain-Det, to achieve a mAP of 51.9 on COCO, matching the current state-of-the-art detectors. We conduct extensive experiments on 13 downstream datasets and Plain-Det demonstrates strong generalization capability. Code is release at https://github.com/ChengShiest/Plain-Det
Authors: Cheng Shi, Yulin Zhang, Bin Yang, Jiajin Tang, Yuexin Ma, Sibei Yang
Abstract: Unsupervised 3D instance segmentation aims to segment objects from a 3D point cloud without any annotations. Existing methods face the challenge of either too loose or too tight clustering, leading to under-segmentation or over-segmentation. To address this issue, we propose Part2Object, hierarchical clustering with object guidance. Part2Object employs multi-layer clustering from points to object parts and objects, allowing objects to manifest at any layer. Additionally, it extracts and utilizes 3D objectness priors from temporally consecutive 2D RGB frames to guide the clustering process. Moreover, we propose Hi-Mask3D to support hierarchical 3D object part and instance segmentation. By training Hi-Mask3D on the objects and object parts extracted from Part2Object, we achieve consistent and superior performance compared to state-of-the-art models in various settings, including unsupervised instance segmentation, data-efficient fine-tuning, and cross-dataset generalization. Code is release at https://github.com/ChengShiest/Part2Object
Authors: Yang Liu, Zhiyong Zhang
Abstract: The current methods of video-based 3D human pose estimation have achieved significant progress; however, they continue to confront the significant challenge of depth ambiguity. To address this limitation, this paper presents the spatio-temporal GraphFormer framework for 3D human pose estimation in video, which integrates body structure graph-based representations with spatio-temporal information. Specifically, we develop a spatio-temporal criss-cross graph (STG) attention mechanism. This approach is designed to learn the long-range dependencies in data across both time and space, integrating graph information directly into the respective attention layers. Furthermore, we introduce the dual-path modulated hop-wise regular GCN (MHR-GCN) module, which utilizes modulation to optimize parameter usage and employs spatio-temporal hop-wise skip connections to acquire higher-order information. Additionally, this module processes temporal and spatial dimensions independently to learn their respective features while avoiding mutual influence. Finally, we demonstrate that our method achieves state-of-the-art performance in 3D human pose estimation on the Human3.6M and MPI-INF-3DHP datasets.
Authors: Umar Khalid, Hasan Iqbal, Azib Farooq, Jing Hua, Chen Chen
Abstract: We introduce 3DEgo to address a novel problem of directly synthesizing photorealistic 3D scenes from monocular videos guided by textual prompts. Conventional methods construct a text-conditioned 3D scene through a three-stage process, involving pose estimation using Structure-from-Motion (SfM) libraries like COLMAP, initializing the 3D model with unedited images, and iteratively updating the dataset with edited images to achieve a 3D scene with text fidelity. Our framework streamlines the conventional multi-stage 3D editing process into a single-stage workflow by overcoming the reliance on COLMAP and eliminating the cost of model initialization. We apply a diffusion model to edit video frames prior to 3D scene creation by incorporating our designed noise blender module for enhancing multi-view editing consistency, a step that does not require additional training or fine-tuning of T2I diffusion models. 3DEgo utilizes 3D Gaussian Splatting to create 3D scenes from the multi-view consistent edited frames, capitalizing on the inherent temporal continuity and explicit point cloud data. 3DEgo demonstrates remarkable editing precision, speed, and adaptability across a variety of video sources, as validated by extensive evaluations on six datasets, including our own prepared GS25 dataset. Project Page: https://3dego.github.io/
URLs: https://3dego.github.io/
Authors: Sreeraj Ramachandran, Ajita Rattani
Abstract: Published research highlights the presence of demographic bias in automated facial attribute classification. The proposed bias mitigation techniques are mostly based on supervised learning, which requires a large amount of labeled training data for generalizability and scalability. However, labeled data is limited, requires laborious annotation, poses privacy risks, and can perpetuate human bias. In contrast, self-supervised learning (SSL) capitalizes on freely available unlabeled data, rendering trained models more scalable and generalizable. However, these label-free SSL models may also introduce biases by sampling false negative pairs, especially at low-data regimes 200K images) under low compute settings. Further, SSL-based models may suffer from performance degradation due to a lack of quality assurance of the unlabeled data sourced from the web. This paper proposes a fully self-supervised pipeline for demographically fair facial attribute classifiers. Leveraging completely unlabeled data pseudolabeled via pre-trained encoders, diverse data curation techniques, and meta-learning-based weighted contrastive learning, our method significantly outperforms existing SSL approaches proposed for downstream image classification tasks. Extensive evaluations on the FairFace and CelebA datasets demonstrate the efficacy of our pipeline in obtaining fair performance over existing baselines. Thus, setting a new benchmark for SSL in the fairness of facial attribute classification.
Authors: Tengfei Liu, Yongli Hu, Junbin Gao, Yanfeng Sun, Baocai Yin
Abstract: Long Document Classification (LDC) has gained significant attention recently. However, multi-modal data in long documents such as texts and images are not being effectively utilized. Prior studies in this area have attempted to integrate texts and images in document-related tasks, but they have only focused on short text sequences and images of pages. How to classify long documents with hierarchical structure texts and embedding images is a new problem and faces multi-modal representation difficulties. In this paper, we propose a novel approach called Hierarchical Multi-modal Transformer (HMT) for cross-modal long document classification. The HMT conducts multi-modal feature interaction and fusion between images and texts in a hierarchical manner. Our approach uses a multi-modal transformer and a dynamic multi-scale multi-modal transformer to model the complex relationships between image features, and the section and sentence features. Furthermore, we introduce a new interaction strategy called the dynamic mask transfer module to integrate these two transformers by propagating features between them. To validate our approach, we conduct cross-modal LDC experiments on two newly created and two publicly available multi-modal long document datasets, and the results show that the proposed HMT outperforms state-of-the-art single-modality and multi-modality methods.
Authors: Casper van Engelenburg, Fatemeh Mostafavi, Emanuel Kuhn, Yuntae Jeon, Michael Franzen, Matthias Standfest, Jan van Gemert, Seyran Khademi
Abstract: Diverse and realistic floor plan data are essential for the development of useful computer-aided methods in architectural design. Today's large-scale floor plan datasets predominantly feature simple floor plan layouts, typically representing single-apartment dwellings only. To compensate for the mismatch between current datasets and the real world, we develop \textbf{Modified Swiss Dwellings} (MSD) -- the first large-scale floor plan dataset that contains a significant share of layouts of multi-apartment dwellings. MSD features over 5.3K floor plans of medium- to large-scale building complexes, covering over 18.9K distinct apartments. We validate that existing approaches for floor plan generation, while effective in simpler scenarios, cannot yet seamlessly address the challenges posed by MSD. Our benchmark calls for new research in floor plan machine understanding. Code and data are open.
Authors: Yi Zhang, Wang Zeng, Sheng Jin, Chen Qian, Ping Luo, Wentao Liu
Abstract: Recent years have witnessed increasing research attention towards pedestrian detection by taking the advantages of different sensor modalities (e.g. RGB, IR, Depth, LiDAR and Event). However, designing a unified generalist model that can effectively process diverse sensor modalities remains a challenge. This paper introduces MMPedestron, a novel generalist model for multimodal perception. Unlike previous specialist models that only process one or a pair of specific modality inputs, MMPedestron is able to process multiple modal inputs and their dynamic combinations. The proposed approach comprises a unified encoder for modal representation and fusion and a general head for pedestrian detection. We introduce two extra learnable tokens, i.e. MAA and MAF, for adaptive multi-modal feature fusion. In addition, we construct the MMPD dataset, the first large-scale benchmark for multi-modal pedestrian detection. This benchmark incorporates existing public datasets and a newly collected dataset called EventPed, covering a wide range of sensor modalities including RGB, IR, Depth, LiDAR, and Event data. With multi-modal joint training, our model achieves state-of-the-art performance on a wide range of pedestrian detection benchmarks, surpassing leading models tailored for specific sensor modality. For example, it achieves 71.1 AP on COCO-Persons and 72.6 AP on LLVIP. Notably, our model achieves comparable performance to the InternImage-H model on CrowdHuman with 30x smaller parameters. Codes and data are available at https://github.com/BubblyYi/MMPedestron.
Authors: Xinjian Wu, Ruisong Zhang, Jie Qin, Shijie Ma, Cheng-Lin Liu
Abstract: Segmenting and recognizing diverse object parts is crucial in computer vision and robotics. Despite significant progress in object segmentation, part-level segmentation remains underexplored due to complex boundaries and scarce annotated data. To address this, we propose a novel Weakly-supervised Part Segmentation (WPS) setting and an approach called WPS-SAM, built on the large-scale pre-trained vision foundation model, Segment Anything Model (SAM). WPS-SAM is an end-to-end framework designed to extract prompt tokens directly from images and perform pixel-level segmentation of part regions. During its training phase, it only uses weakly supervised labels in the form of bounding boxes or points. Extensive experiments demonstrate that, through exploiting the rich knowledge embedded in pre-trained foundation models, WPS-SAM outperforms other segmentation models trained with pixel-level strong annotations. Specifically, WPS-SAM achieves 68.93% mIOU and 79.53% mACC on the PartImageNet dataset, surpassing state-of-the-art fully supervised methods by approximately 4% in terms of mIOU.
Authors: Zheng Jiang, Jinqing Zhang, Yanan Zhang, Qingjie Liu, Zhenghui Hu, Baohui Wang, Yunhong Wang
Abstract: Although multi-view 3D object detection based on the Bird's-Eye-View (BEV) paradigm has garnered widespread attention as an economical and deployment-friendly perception solution for autonomous driving, there is still a performance gap compared to LiDAR-based methods. In recent years, several cross-modal distillation methods have been proposed to transfer beneficial information from teacher models to student models, with the aim of enhancing performance. However, these methods face challenges due to discrepancies in feature distribution originating from different data modalities and network structures, making knowledge transfer exceptionally challenging. In this paper, we propose a Foreground Self-Distillation (FSD) scheme that effectively avoids the issue of distribution discrepancies, maintaining remarkable distillation effects without the need for pre-trained teacher models or cumbersome distillation strategies. Additionally, we design two Point Cloud Intensification (PCI) strategies to compensate for the sparsity of point clouds by frame combination and pseudo point assignment. Finally, we develop a Multi-Scale Foreground Enhancement (MSFE) module to extract and fuse multi-scale foreground features by predicted elliptical Gaussian heatmap, further improving the model's performance. We integrate all the above innovations into a unified framework named FSD-BEV. Extensive experiments on the nuScenes dataset exhibit that FSD-BEV achieves state-of-the-art performance, highlighting its effectiveness. The code and models are available at: https://github.com/CocoBoom/fsd-bev.
Authors: Youyi Zhan, Tuanfeng Y. Wang, Tianjia Shao, Kun Zhou
Abstract: The fast growth of E-Commerce creates a global market worth USD 821 billion for online fashion shopping. What unique about fashion presentation is that, the same design can usually be offered with different cloths textures. However, only real video capturing or manual per-frame editing can be used for virtual showcase on the same design with different textures, both of which are heavily labor intensive. In this paper, we present a pattern-based approach for UV and shading recovery from a captured real video so that the garment's texture can be replaced automatically. The core of our approach is a per-pixel UV regression module via blended-weight multilayer perceptrons (MLPs) driven by the detected discrete correspondences from the cloth pattern. We propose a novel loss on the Jacobian of the UV mapping to create pleasant seams around the folding areas and the boundary of occluded regions while avoiding UV distortion. We also adopts the temporal constraint to ensure consistency and accuracy in UV prediction across adjacent frames. We show that our approach is robust to a variety type of clothes, in the wild illuminations and with challenging motions. We show plausible texture replacement results in our experiment, in which the folding and overlapping of the garment can be greatly preserved. We also show clear qualitative and quantitative improvement compared to the baselines as well. With the one-click setup, we look forward to our approach contributing to the growth of fashion E-commerce.
Authors: Runzhao Yao, Shaoyi Du, Wenting Cui, Canhui Tang, Chengwu Yang
Abstract: Learning rotation-invariant distinctive features is a fundamental requirement for point cloud registration. Existing methods often use rotation-sensitive networks to extract features, while employing rotation augmentation to learn an approximate invariant mapping rudely. This makes networks fragile to rotations, overweight, and hinders the distinctiveness of features. To tackle these problems, we propose a novel position-aware rotation-equivariant network, for efficient, light-weighted, and robust registration. The network can provide a strong model inductive bias to learn rotation-equivariant/invariant features, thus addressing the aforementioned limitations. To further improve the distinctiveness of descriptors, we propose a position-aware convolution, which can better learn spatial information of local structures. Moreover, we also propose a feature-based hypothesis proposer. It leverages rotation-equivariant features that encode fine-grained structure orientations to generate reliable model hypotheses. Each correspondence can generate a hypothesis, thus it is more efficient than classic estimators that require multiple reliable correspondences. Accordingly, a contrastive rotation loss is presented to enhance the robustness of rotation-equivariant features against data degradation. Extensive experiments on indoor and outdoor datasets demonstrate that our method significantly outperforms the SOTA methods in terms of registration recall while being lightweight and keeping a fast speed. Moreover, experiments on rotated datasets demonstrate its robustness against rotation variations. Code is available at https://github.com/yaorz97/PARENet.
Authors: Lorenzo Vaquero, Yihong Xu, Xavier Alameda-Pineda, Victor M. Brea, Manuel Mucientes
Abstract: Multi-object tracking (MOT) endeavors to precisely estimate the positions and identities of multiple objects over time. The prevailing approach, tracking-by-detection (TbD), first detects objects and then links detections, resulting in a simple yet effective method. However, contemporary detectors may occasionally miss some objects in certain frames, causing trackers to cease tracking prematurely. To tackle this issue, we propose BUSCA, meaning `to search', a versatile framework compatible with any online TbD system, enhancing its ability to persistently track those objects missed by the detector, primarily due to occlusions. Remarkably, this is accomplished without modifying past tracking results or accessing future frames, i.e., in a fully online manner. BUSCA generates proposals based on neighboring tracks, motion, and learned tokens. Utilizing a decision Transformer that integrates multimodal visual and spatiotemporal information, it addresses the object-proposal association as a multi-choice question-answering task. BUSCA is trained independently of the underlying tracker, solely on synthetic data, without requiring fine-tuning. Through BUSCA, we showcase consistent performance enhancements across five different trackers and establish a new state-of-the-art baseline across three different benchmarks. Code available at: https://github.com/lorenzovaquero/BUSCA.
Authors: Li Li, Hubert P. H. Shum, Toby P. Breckon
Abstract: 3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets.
Authors: Sanmin Kim, Youngseok Kim, Sihwan Hwang, Hyeonjun Jeong, Dongsuk Kum
Abstract: Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However, existing cross-modal knowledge distillation methods tend to overlook the inherent imperfections of LiDAR, such as the ambiguity of measurements on distant or occluded objects, which should not be transferred to the image detector. To mitigate these imperfections in LiDAR teacher, we propose a novel method that leverages aleatoric uncertainty-free features from ground truth labels. In contrast to conventional label guidance approaches, we approximate the inverse function of the teacher's head to effectively embed label inputs into feature space. This approach provides additional accurate guidance alongside LiDAR teacher, thereby boosting the performance of the image detector. Additionally, we introduce feature partitioning, which effectively transfers knowledge from the teacher modality while preserving the distinctive features of the student, thereby maximizing the potential of both modalities. Experimental results demonstrate that our approach improves mAP and NDS by 5.1 points and 4.9 points compared to the baseline model, proving the effectiveness of our approach. The code is available at https://github.com/sanmin0312/LabelDistill
Authors: Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, Xiaochun Cao
Abstract: Transformer-based image restoration methods in adverse weather have achieved significant progress. Most of them use self-attention along the channel dimension or within spatially fixed-range blocks to reduce computational load. However, such a compromise results in limitations in capturing long-range spatial features. Inspired by the observation that the weather-induced degradation factors mainly cause similar occlusion and brightness, in this work, we propose an efficient Histogram Transformer (Histoformer) for restoring images affected by adverse weather. It is powered by a mechanism dubbed histogram self-attention, which sorts and segments spatial features into intensity-based bins. Self-attention is then applied across bins or within each bin to selectively focus on spatial features of dynamic range and process similar degraded pixels of the long range together. To boost histogram self-attention, we present a dynamic-range convolution enabling conventional convolution to conduct operation over similar pixels rather than neighbor pixels. We also observe that the common pixel-wise losses neglect linear association and correlation between output and ground-truth. Thus, we propose to leverage the Pearson correlation coefficient as a loss function to enforce the recovered pixels following the identical order as ground-truth. Extensive experiments demonstrate the efficacy and superiority of our proposed method. We have released the codes in Github.
Authors: Hao Fang, Jiawei Kong, Bin Chen, Tao Dai, Hao Wu, Shu-Tao Xia
Abstract: Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios. Recent studies have introduced \textit{single-target} generative attacks that train a generator for each target class to generate highly transferable perturbations, resulting in substantial computational overhead when handling multiple classes. \textit{Multi-target} attacks address this by training only one class-conditional generator for multiple classes. However, the generator simply uses class labels as conditions, failing to leverage the rich semantic information of the target class. To this end, we design a \textbf{C}LIP-guided \textbf{G}enerative \textbf{N}etwork with \textbf{C}ross-attention modules (CGNC) to enhance multi-target attacks by incorporating textual knowledge of CLIP into the generator. Extensive experiments demonstrate that CGNC yields significant improvements over previous multi-target generative attacks, e.g., a 21.46\% improvement in success rate from ResNet-152 to DenseNet-121. Moreover, we propose a masked fine-tuning mechanism to further strengthen our method in attacking a single class, which surpasses existing single-target methods.
Authors: Cheng-Yi Lee, Ching-Chia Kao, Cheng-Han Yeh, Chun-Shien Lu, Chia-Mu Yu, Chu-Song Chen
Abstract: Semi-supervised learning (SSL) has achieved remarkable performance with a small fraction of labeled data by leveraging vast amounts of unlabeled data from the Internet. However, this large pool of untrusted data is extremely vulnerable to data poisoning, leading to potential backdoor attacks. Current backdoor defenses are not yet effective against such a vulnerability in SSL. In this study, we propose a novel method, Unlabeled Data Purification (UPure), to disrupt the association between trigger patterns and target classes by introducing perturbations in the frequency domain. By leveraging the Rate- Distortion-Perception (RDP) trade-off, we further identify the frequency band, where the perturbations are added, and justify this selection. Notably, UPure purifies poisoned unlabeled data without the need of extra clean labeled data. Extensive experiments on four benchmark datasets and five SSL algorithms demonstrate that UPure effectively reduces the attack success rate from 99.78% to 0% while maintaining model accuracy
Authors: Jiaqi He, Zhihua Wang, Leon Wang, Tsein-I Liu, Yuming Fang, Qilin Sun, Kede Ma
Abstract: Contemporary color difference (CD) measures for photographic images typically operate by comparing co-located pixels, patches in a ``perceptually uniform'' color space, or features in a learned latent space. Consequently, these measures inadequately capture the human color perception of misaligned image pairs, which are prevalent in digital photography (e.g., the same scene captured by different smartphones). In this paper, we describe a perceptual CD measure based on the multiscale sliced Wasserstein distance, which facilitates efficient comparisons between non-local patches of similar color and structure. This aligns with the modern understanding of color perception, where color and structure are inextricably interdependent as a unitary process of perceptual organization. Meanwhile, our method is easy to implement and training-free. Experimental results indicate that our CD measure performs favorably in assessing CDs in photographic images, and consistently surpasses competing models in the presence of image misalignment. Additionally, we empirically verify that our measure functions as a metric in the mathematical sense, and show its promise as a loss function for image and video color transfer tasks. The code is available at https://github.com/real-hjq/MS-SWD.
Authors: Jing Li, Di Kang, Zhenyu He
Abstract: Deep learning-based multi-view facial capture methods have shown impressive accuracy while being several orders of magnitude faster than a traditional mesh registration pipeline. However, the existing systems (e.g. TEMPEH) are strictly restricted to inference on the data captured by the same camera array used to capture their training data. In this study, we aim to improve the generalization ability so that a trained model can be readily used for inference (i.e. capture new data) on a different camera array. To this end, we propose a more generalizable initialization module to extract the camera array-agnostic 3D feature, including a visual hull-based head localization and a visibility-aware 3D feature aggregation module enabled by the visual hull. In addition, we propose an ``update-by-disagreement'' learning strategy to better handle data noise (e.g. inaccurate registration, scan noise) by discarding potentially inaccurate supervision signals during training. The resultant generalizable and robust topologically consistent multi-view facial capture system (GRAPE) can be readily used to capture data on a different camera array, reducing great effort on data collection and processing. Experiments on the FaMoS and FaceScape datasets demonstrate the effectiveness of the proposed method.
Authors: Qianxin Qu, Yijin Xiong, Xin Wu, Hanyu Li, Shichun Guo
Abstract: Cooperative vehicle and infrastructure LiDAR systems hold great potential, yet their implementation faces numerous challenges. Calibration of LiDAR systems across heterogeneous vehicle and infrastructure endpoints is a critical step to ensure the accuracy and consistency of perception system data, necessitating calibration methods that are real-time and stable. To this end, this paper introduces a novel calibration method for cooperative vehicle and road infrastructure LiDAR systems, which exploits spatial association information between detection boxes. The method centers around a novel Overall IoU metric that reflects the correlation of targets between vehicle and infrastructure, enabling real-time monitoring of calibration results. We search for common matching boxes between vehicle and infrastructure nodes by constructing an affinity matrix. Subsequently, these matching boxes undergo extrinsic parameter computation and optimization. Comparative and ablation experiments on the DAIR-V2X dataset confirm the superiority of our method. To better reflect the differences in calibration results, we have categorized the calibration tasks on the DAIR-V2X dataset based on their level of difficulty, enriching the dataset's utility for future research. Our project is available at https://github.com/MassimoQu/v2i-calib .
Authors: Linh Trinh, Ali Anwar, Siegfried Mercelis
Abstract: Roads are an essential mode of transportation, and maintaining them is critical to economic growth and citizen well-being. With the continued advancement of AI, road surface inspection based on camera images has recently been extensively researched and can be performed automatically. However, because almost all of the deep learning methods for detecting road surface defects were optimized for a specific dataset, they are difficult to apply to a new, previously unseen dataset. Furthermore, there is a lack of research on training an efficient model using multiple data sources. In this paper, we propose a method for classifying road surface defects using camera images. In our method, we propose a scheme for dealing with the invariance of multiple data sources while training a model on multiple data sources. Furthermore, we present a domain generalization training algorithm for developing a generalized model that can work with new, completely unseen data sources without requiring model updates. We validate our method using an experiment with six data sources corresponding to six countries from the RDD2022 dataset. The results show that our method can efficiently classify road surface defects on previously unseen data.
Authors: Tuo Feng, Wenguan Wang, Ruijie Quan, Yi Yang
Abstract: Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect. Despite this, existing pre-training strategies on shape data offer limited potential for 3D scene understanding due to significant disparities in point quantities. To tackle these challenges, we propose Shape2Scene (S2S), a novel method that learns representations of large-scale 3D scenes from 3D shape data. We first design multiscale and high-resolution backbones for shape and scene level 3D tasks, i.e., MH-P (point-based) and MH-V (voxel-based). MH-P/V establishes direct paths to highresolution features that capture deep semantic information across multiple scales. This pivotal nature makes them suitable for a wide range of 3D downstream tasks that tightly rely on high-resolution features. We then employ a Shape-to-Scene strategy (S2SS) to amalgamate points from various shapes, creating a random pseudo scene (comprising multiple objects) for training data, mitigating disparities between shapes and scenes. Finally, a point-point contrastive loss (PPC) is applied for the pre-training of MH-P/V. In PPC, the inherent correspondence (i.e., point pairs) is naturally obtained in S2SS. Extensive experiments have demonstrated the transferability of 3D representations learned by MH-P/V across shape-level and scene-level 3D tasks. MH-P achieves notable performance on well-known point cloud datasets (93.8% OA on ScanObjectNN and 87.6% instance mIoU on ShapeNetPart). MH-V also achieves promising performance in 3D semantic segmentation and 3D object detection.
Authors: Yihao Liu, Junyu Chen, Lianrui Zuo, Aaron Carass, Jerry L. Prince
Abstract: Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over traditional algorithms as well as their better accuracy. Most existing deep learning-based methods require neural networks to encode location information in their feature maps and predict displacement or deformation fields though convolutional or fully connected layers from these high-dimensional feature maps. In this work, we present Vector Field Attention (VFA), a novel framework that enhances the efficiency of the existing network design by enabling direct retrieval of location correspondences. VFA uses neural networks to extract multi-resolution feature maps from the fixed and moving images and then retrieves pixel-level correspondences based on feature similarity. The retrieval is achieved with a novel attention module without the need of learnable parameters. VFA is trained end-to-end in either a supervised or unsupervised manner. We evaluated VFA for intra- and inter-modality registration and for unsupervised and semi-supervised registration using public datasets, and we also evaluated it on the Learn2Reg challenge. Experimental results demonstrate the superior performance of VFA compared to existing methods. The source code of VFA is publicly available at https://github.com/yihao6/vfa/.
Authors: Nermin Samet, C\'edric Rommel, David Picard, Eduardo Valle
Abstract: We introduce a novel approach for 3D whole-body pose estimation, addressing the challenge of scale- and deformability- variance across body parts brought by the challenge of extending the 17 major joints on the human body to fine-grained keypoints on the face and hands. In addition to addressing the challenge of exploiting motion in unevenly sampled data, we combine stable diffusion to a hierarchical part representation which predicts the relative locations of fine-grained keypoints within each part (e.g., face) with respect to the part's local reference frame. On the H3WB dataset, our method greatly outperforms the current state of the art, which fails to exploit the temporal information. We also show considerable improvements compared to other spatiotemporal 3D human-pose estimation approaches that fail to account for the body part specificities. Code is available at https://github.com/valeoai/PAFUSE.
Authors: Shuaibin Fan, Minglong Xue, Aoxiang Ning, Senming Zhong
Abstract: Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing model (DCM-dehaze) to address this issue. The proposed method consists of two collaborative branches: dehazing and contour constraints. Specifically, we design a dual depthwise separable convolutional module (DDSCM) to enhance the information expressiveness of deeper features and the correlation to shallow features. In addition, we construct a bidirectional contour function to optimize the edge features of the image to enhance the clarity and fidelity of the image details. Furthermore, we present feature enhancers via a residual dense architecture to eliminate redundant features of the dehazing process and further alleviate the domain deviation problem. Extensive experiments on benchmark datasets show that our method reaches the state-of-the-art. This project code will be available at \url{https://github.com/Fan-pixel/DCM-dehaze.
Authors: Ji-Jia Wu
Abstract: This paper introduces the Efficient Facial Landmark Detection (EFLD) model, specifically designed for edge devices confronted with the challenges related to power consumption and time latency. EFLD features a lightweight backbone and a flexible detection head, each significantly enhancing operational efficiency on resource-constrained devices. To improve the model's robustness, we propose a cross-format training strategy. This strategy leverages a wide variety of publicly accessible datasets to enhance the model's generalizability and robustness, without increasing inference costs. Our ablation study highlights the significant impact of each component on reducing computational demands, model size, and improving accuracy. EFLD demonstrates superior performance compared to competitors in the IEEE ICME 2024 Grand Challenges PAIR Competition, a contest focused on low-power, efficient, and accurate facial-landmark detection for embedded systems, showcasing its effectiveness in real-world facial landmark detection tasks.
Authors: Wei Suo, Lanqing Lai, Mengyang Sun, Hanwang Zhang, Peng Wang, Yanning Zhang
Abstract: As a fundamental and extensively studied task in computer vision, image segmentation aims to locate and identify different semantic concepts at the pixel level. Recently, inspired by In-Context Learning (ICL), several generalist segmentation frameworks have been proposed, providing a promising paradigm for segmenting specific objects. However, existing works mostly ignore the value of visual prompts or simply apply similarity sorting to select contextual examples. In this paper, we focus on rethinking and improving the example selection strategy. By comprehensive comparisons, we first demonstrate that ICL-based segmentation models are sensitive to different contexts. Furthermore, empirical evidence indicates that the diversity of contextual prompts plays a crucial role in guiding segmentation. Based on the above insights, we propose a new stepwise context search method. Different from previous works, we construct a small yet rich candidate pool and adaptively search the well-matched contexts. More importantly, this method effectively reduces the annotation cost by compacting the search space. Extensive experiments show that our method is an effective strategy for selecting examples and enhancing segmentation performance.
Authors: Muyao Niu, Tong Chen, Yifan Zhan, Zhuoxiao Li, Xiang Ji, Yinqiang Zheng
Abstract: Neural Radiance Fields (NeRFs) have become increasingly popular because of their impressive ability for novel view synthesis. However, their effectiveness is hindered by the Rolling Shutter (RS) effects commonly found in most camera systems. To solve this, we present RS-NeRF, a method designed to synthesize normal images from novel views using input with RS distortions. This involves a physical model that replicates the image formation process under RS conditions and jointly optimizes NeRF parameters and camera extrinsic for each image row. We further address the inherent shortcomings of the basic RS-NeRF model by delving into the RS characteristics and developing algorithms to enhance its functionality. First, we impose a smoothness regularization to better estimate trajectories and improve the synthesis quality, in line with the camera movement prior. We also identify and address a fundamental flaw in the vanilla RS model by introducing a multi-sampling algorithm. This new approach improves the model's performance by comprehensively exploiting the RGB data across different rows for each intermediate camera pose. Through rigorous experimentation, we demonstrate that RS-NeRF surpasses previous methods in both synthetic and real-world scenarios, proving its ability to correct RS-related distortions effectively. Codes and data available: https://github.com/MyNiuuu/RS-NeRF
Authors: Yinsheng He, Xingyu Li, Roger J. Zemp
Abstract: Segmenting tumors in histological images is vital for cancer diagnosis. While fully supervised models excel with pixel-level annotations, creating such annotations is labor-intensive and costly. Accurate histopathology image segmentation under weakly-supervised conditions with coarse-grained image labels is still a challenging problem. Although multiple instance learning (MIL) has shown promise in segmentation tasks, surprisingly, no previous pseudo-supervision methods have used MIL-based outputs as pseudo-masks for training. We suspect this stems from concerns over noises in MIL results affecting pseudo supervision quality. To explore the potential of leveraging MIL-based segmentation for pseudo supervision, we propose a novel distillation framework for histopathology image segmentation. This framework introduces a iterative fusion-knowledge distillation strategy, enabling the student model to learn directly from the teacher's comprehensive outcomes. Through dynamic role reversal between the fixed teacher and learnable student models and the incorporation of weighted cross-entropy loss for model optimization, our approach prevents performance deterioration and noise amplification during knowledge distillation. Experimental results on public histopathology datasets, Camelyon16 and Digestpath2019, demonstrate that our approach not only complements various MIL-based segmentation methods but also significantly enhances their performance. Additionally, our method achieves new SOTA in the field.
Authors: Geonho Son, Juhun Lee, Simon S. Woo
Abstract: The fabrication of visual misinformation on the web and social media has increased exponentially with the advent of foundational text-to-image diffusion models. Namely, Stable Diffusion inpainters allow the synthesis of maliciously inpainted images of personal and private figures, and copyrighted contents, also known as deepfakes. To combat such generations, a disruption framework, namely Photoguard, has been proposed, where it adds adversarial noise to the context image to disrupt their inpainting synthesis. While their framework suggested a diffusion-friendly approach, the disruption is not sufficiently strong and it requires a significant amount of GPU and time to immunize the context image. In our work, we re-examine both the minimal and favorable conditions for a successful inpainting disruption, proposing DDD, a "Digression guided Diffusion Disruption" framework. First, we identify the most adversarially vulnerable diffusion timestep range with respect to the hidden space. Within this scope of noised manifold, we pose the problem as a semantic digression optimization. We maximize the distance between the inpainting instance's hidden states and a semantic-aware hidden state centroid, calibrated both by Monte Carlo sampling of hidden states and a discretely projected optimization in the token space. Effectively, our approach achieves stronger disruption and a higher success rate than Photoguard while lowering the GPU memory requirement, and speeding the optimization up to three times faster.
Authors: Xinyuan Gao, Songlin Dong, Yuhang He, Qiang Wang, Yihong Gong
Abstract: The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale pre-trained models as the backbone and use key-query matching to generate trainable prompts to learn new knowledge. However, the domain gap between the pre-training dataset and the downstream datasets can easily lead to inaccuracies in key-query matching prompt selection when directly generating queries using the pre-trained model, which hampers learning new knowledge. Thus, in this paper, we propose a beyond prompt learning approach to the RFCL task, called Continual Adapter (C-ADA). It mainly comprises a parameter-extensible continual adapter layer (CAL) and a scaling and shifting (S&S) module in parallel with the pre-trained model. C-ADA flexibly extends specific weights in CAL to learn new knowledge for each task and freezes old weights to preserve prior knowledge, thereby avoiding matching errors and operational inefficiencies introduced by key-query matching. To reduce the gap, C-ADA employs an S&S module to transfer the feature space from pre-trained datasets to downstream datasets. Moreover, we propose an orthogonal loss to mitigate the interaction between old and new knowledge. Our approach achieves significantly improved performance and training speed, outperforming the current state-of-the-art (SOTA) method. Additionally, we conduct experiments on domain-incremental learning, surpassing the SOTA, and demonstrating the generality of our approach in different settings.
Authors: Qinyu Yang, Haoxin Chen, Yong Zhang, Menghan Xia, Xiaodong Cun, Zhixun Su, Ying Shan
Abstract: In order to improve the quality of synthesized videos, currently, one predominant method involves retraining an expert diffusion model and then implementing a noising-denoising process for refinement. Despite the significant training costs, maintaining consistency of content between the original and enhanced videos remains a major challenge. To tackle this challenge, we propose a novel formulation that considers both visual quality and consistency of content. Consistency of content is ensured by a proposed loss function that maintains the structure of the input, while visual quality is improved by utilizing the denoising process of pretrained diffusion models. To address the formulated optimization problem, we have developed a plug-and-play noise optimization strategy, referred to as Noise Calibration. By refining the initial random noise through a few iterations, the content of original video can be largely preserved, and the enhancement effect demonstrates a notable improvement. Extensive experiments have demonstrated the effectiveness of the proposed method.
Authors: Yuchen Yang, Kwonjoon Lee, Behzad Dariush, Yinzhi Cao, Shao-Yuan Lo
Abstract: Video Anomaly Detection (VAD) is crucial for applications such as security surveillance and autonomous driving. However, existing VAD methods provide little rationale behind detection, hindering public trust in real-world deployments. In this paper, we approach VAD with a reasoning framework. Although Large Language Models (LLMs) have shown revolutionary reasoning ability, we find that their direct use falls short of VAD. Specifically, the implicit knowledge pre-trained in LLMs focuses on general context and thus may not apply to every specific real-world VAD scenario, leading to inflexibility and inaccuracy. To address this, we propose AnomalyRuler, a novel rule-based reasoning framework for VAD with LLMs. AnomalyRuler comprises two main stages: induction and deduction. In the induction stage, the LLM is fed with few-shot normal reference samples and then summarizes these normal patterns to induce a set of rules for detecting anomalies. The deduction stage follows the induced rules to spot anomalous frames in test videos. Additionally, we design rule aggregation, perception smoothing, and robust reasoning strategies to further enhance AnomalyRuler's robustness. AnomalyRuler is the first reasoning approach for the one-class VAD task, which requires only few-normal-shot prompting without the need for full-shot training, thereby enabling fast adaption to various VAD scenarios. Comprehensive experiments across four VAD benchmarks demonstrate AnomalyRuler's state-of-the-art detection performance and reasoning ability.
Authors: Tianyi Zhang, Weiming Zhi, Kaining Huang, Joshua Mangelson, Corina Barbalata, Matthew Johnson-Roberson
Abstract: Water caustics are commonly observed in seafloor imaging data from shallow-water areas. Traditional methods that remove caustic patterns from images often rely on 2D filtering or pre-training on an annotated dataset, hindering the performance when generalizing to real-world seafloor data with 3D structures. In this paper, we present a novel method Recurrent Gaussian Splatting, which takes advantage of today's photorealistic 3D reconstruction technology, 3DGS, to separate caustics from seafloor imagery. With a sequence of images taken by an underwater robot, we build 3DGS recursively and decompose the caustic with low-pass filtering in each iteration. In the experiments, we analyze and compare with different methods, including joint optimization, 2D filtering, and deep learning approaches. The results show that our method can effectively separate the caustic from the seafloor, improving the visual appearance.
Authors: Jae Joong Lee, Bosheng Li, Sara Beery, Jonathan Huang, Songlin Fei, Raymond A. Yeh, Bedrich Benes
Abstract: We introduce Tree D-fusion, featuring the first collection of 600,000 environmentally aware, 3D simulation-ready tree models generated through Diffusion priors. Each reconstructed 3D tree model corresponds to an image from Google's Auto Arborist Dataset, comprising street view images and associated genus labels of trees across North America. Our method distills the scores of two tree-adapted diffusion models by utilizing text prompts to specify a tree genus, thus facilitating shape reconstruction. This process involves reconstructing a 3D tree envelope filled with point markers, which are subsequently utilized to estimate the tree's branching structure using the space colonization algorithm conditioned on a specified genus.
Authors: Bappaditya Dey, Vic De Ridder, Victor Blanco, Sandip Halder, Bartel Van Waeyenberge
Abstract: Precision in identifying nanometer-scale device-killer defects is crucial in both semiconductor research and development as well as in production processes. The effectiveness of existing ML-based approaches in this context is largely limited by the scarcity of data, as the production of real semiconductor wafer data for training these models involves high financial and time costs. Moreover, the existing simulation methods fall short of replicating images with identical noise characteristics, surface roughness and stochastic variations at advanced nodes. We propose a method for generating synthetic semiconductor SEM images using a diffusion model within a limited data regime. In contrast to images generated through conventional simulation methods, SEM images generated through our proposed DL method closely resemble real SEM images, replicating their noise characteristics and surface roughness adaptively. Our main contributions, which are validated on three different real semiconductor datasets, are: i) proposing a patch-based generative framework utilizing DDPM to create SEM images with intended defect classes, addressing challenges related to class-imbalance and data insufficiency, ii) demonstrating generated synthetic images closely resemble real SEM images acquired from the tool, preserving all imaging conditions and metrology characteristics without any metadata supervision, iii) demonstrating a defect detector trained on generated defect dataset, either independently or combined with a limited real dataset, can achieve similar or improved performance on real wafer SEM images during validation/testing compared to exclusive training on a real defect dataset, iv) demonstrating the ability of the proposed approach to transfer defect types, critical dimensions, and imaging conditions from one specified CD/Pitch and metrology specifications to another, thereby highlighting its versatility.
Authors: Yitian Zhang, Xu Ma, Yue Bai, Huan Wang, Yun Fu
Abstract: Vision foundation models are renowned for their generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is often inaccessible, e.g., CLIP, DINOv2, posing great challenges to developing derivatives that could advance research in this field. In this work, we offer a very simple and general solution, named Proteus, to distill foundation models into smaller equivalents on ImageNet-1K without access to the original training data. Specifically, we remove the designs from conventional knowledge distillation settings that result in dataset bias and present three levels of training objectives, i.e., token, patch, and feature, to maximize the efficacy of knowledge transfer. In this manner, Proteus is trained at ImageNet-level costs with surprising ability, facilitating the accessibility of training foundation models for the broader research community. Leveraging DINOv2-g/14 as the teacher, Proteus-L/14 matches the performance of the Oracle method DINOv2-L/14 (142M training data) across 15 benchmarks and outperforms other vision foundation models including CLIP-L/14 (400M), OpenCLIP-L/14 (400M/2B) and SynCLR-L/14 (600M).
Authors: Xiao Wang, Weizhe Kong, Jiandong Jin, Shiao Wang, Ruichong Gao, Qingchuan Ma, Chenglong Li, Jin Tang
Abstract: Current strong pedestrian attribute recognition models are developed based on Transformer networks, which are computationally heavy. Recently proposed models with linear complexity (e.g., Mamba) have garnered significant attention and have achieved a good balance between accuracy and computational cost across a variety of visual tasks. Relevant review articles also suggest that while these models can perform well on some pedestrian attribute recognition datasets, they are generally weaker than the corresponding Transformer models. To further tap into the potential of the novel Mamba architecture for PAR tasks, this paper designs and adapts Mamba into two typical PAR frameworks, i.e., the text-image fusion approach and pure vision Mamba multi-label recognition framework. It is found that interacting with attribute tags as additional input does not always lead to an improvement, specifically, Vim can be enhanced, but VMamba cannot. This paper further designs various hybrid Mamba-Transformer variants and conducts thorough experimental validations. These experimental results indicate that simply enhancing Mamba with a Transformer does not always lead to performance improvements but yields better results under certain settings. We hope this empirical study can further inspire research in Mamba for PAR, and even extend into the domain of multi-label recognition, through the design of these network structures and comprehensive experimentation. The source code of this work will be released at \url{https://github.com/Event-AHU/OpenPAR}
Authors: Pranshu Pandya, Agney S Talwarr, Vatsal Gupta, Tushar Kataria, Vivek Gupta, Dan Roth
Abstract: Cognitive textual and visual reasoning tasks, such as puzzles, series, and analogies, demand the ability to quickly reason, decipher, and evaluate patterns both textually and spatially. While LLMs and VLMs, through extensive training on large amounts of human-curated data, have attained a high level of pseudo-human intelligence in some common sense reasoning tasks, they still struggle with more complex reasoning tasks that require cognitive understanding. In this work, we introduce a new dataset, NTSEBench, designed to evaluate the cognitive multi-modal reasoning and problem-solving skills of large models. The dataset comprises 2,728 multiple-choice questions comprising of a total of 4,642 images across 26 categories sampled from the NTSE examination conducted nationwide in India, featuring both visual and textual general aptitude questions that do not rely on rote learning. We establish baselines on the dataset using state-of-the-art LLMs and VLMs. To facilitate a comparison between open source and propriety models, we propose four distinct modeling strategies to handle different modalities (text and images) in the dataset instances.
Authors: Francesco Di Sario, Riccardo Renzulli, Enzo Tartaglione, Marco Grangetto
Abstract: Since the introduction of NeRFs, considerable attention has been focused on improving their training and inference times, leading to the development of Fast-NeRFs models. Despite demonstrating impressive rendering speed and quality, the rapid convergence of such models poses challenges for further improving reconstruction quality. Common strategies to improve rendering quality involves augmenting model parameters or increasing the number of sampled points. However, these computationally intensive approaches encounter limitations in achieving significant quality enhancements. This study introduces a model-agnostic framework inspired by Sparsely-Gated Mixture of Experts to enhance rendering quality without escalating computational complexity. Our approach enables specialization in rendering different scene components by employing a mixture of experts with varying resolutions. We present a novel gate formulation designed to maximize expert capabilities and propose a resolution-based routing technique to effectively induce sparsity and decompose scenes. Our work significantly improves reconstruction quality while maintaining competitive performance.
Authors: Razaib Tariq, Shahroz Tariq, Simon S. Woo
Abstract: Deepfake detection is critical in mitigating the societal threats posed by manipulated videos. While various algorithms have been developed for this purpose, challenges arise when detectors operate externally, such as on smartphones, when users take a photo of deepfake images and upload on the Internet. One significant challenge in such scenarios is the presence of Moir\'e patterns, which degrade image quality and confound conventional classification algorithms, including deep neural networks (DNNs). The impact of Moir\'e patterns remains largely unexplored for deepfake detectors. In this study, we investigate how camera-captured deepfake videos from digital screens affect detector performance. We conducted experiments using two prominent datasets, CelebDF and FF++, comparing the performance of four state-of-the-art detectors on camera-captured deepfake videos with introduced Moir\'e patterns. Our findings reveal a significant decline in detector accuracy, with none achieving above 68% on average. This underscores the critical need to address Moir\'e pattern challenges in real-world deepfake detection scenarios.
Authors: Yuchen Yang, Xinyi Wang, Dong Li, Lu Tian, Ashish Sirasao, Xun Yang
Abstract: Full surround monodepth (FSM) methods can learn from multiple camera views simultaneously in a self-supervised manner to predict the scale-aware depth, which is more practical for real-world applications in contrast to scale-ambiguous depth from a standalone monocular camera. In this work, we focus on enhancing the scale-awareness of FSM methods for depth estimation. To this end, we propose to improve FSM from two perspectives: depth network structure optimization and training pipeline optimization. First, we construct a transformer-based depth network with neighbor-enhanced cross-view attention (NCA). The cross-attention modules can better aggregate the cross-view context in both global and neighboring views. Second, we formulate a transformer-based feature matching scheme with progressive training to improve the structure-from-motion (SfM) pipeline. That allows us to learn scale-awareness with sufficient matches and further facilitate network convergence by removing mismatches based on SfM loss. Experiments demonstrate that the resulting Scale-aware full surround monodepth (SA-FSM) method largely improves the scale-aware depth predictions without median-scaling at the test time, and performs favorably against the state-of-the-art FSM methods, e.g., surpassing SurroundDepth by 3.8% in terms of accuracy at delta<1.25 on the DDAD benchmark.
Authors: Seungri Yoon, Yunseong Cho, Tae In Ahn
Abstract: Monitoring and managing the growth and quality of fruits are very important tasks. To effectively train deep learning models like YOLO for real-time fruit detection, high-quality image datasets are essential. However, such datasets are often lacking in agriculture. Generative AI models can help create high-quality images. In this study, we used MidJourney and Firefly tools to generate images of melon greenhouses and post-harvest fruits through text-to-image, pre-harvest image-to-image, and post-harvest image-to-image methods. We evaluated these AIgenerated images using PSNR and SSIM metrics and tested the detection performance of the YOLOv9 model. We also assessed the net quality of real and generated fruits. Our results showed that generative AI could produce images very similar to real ones, especially for post-harvest fruits. The YOLOv9 model detected the generated images well, and the net quality was also measurable. This shows that generative AI can create realistic images useful for fruit detection and quality assessment, indicating its great potential in agriculture. This study highlights the potential of AI-generated images for data augmentation in melon fruit detection and quality assessment and envisions a positive future for generative AI applications in agriculture.
Authors: Zitong Lu, Yile Wang
Abstract: Deep convolutional neural networks (DCNNs) have demonstrated excellent performance in object recognition and have been found to share some similarities with brain visual processing. However, the substantial gap between DCNNs and human visual perception still exists. Functional magnetic resonance imaging (fMRI) as a widely used technique in cognitive neuroscience can record neural activation in the human visual cortex during the process of visual perception. Can we teach DCNNs human fMRI signals to achieve a more brain-like model? To answer this question, this study proposed ReAlnet-fMRI, a model based on the SOTA vision model CORnet but optimized using human fMRI data through a multi-layer encoding-based alignment framework. This framework has been shown to effectively enable the model to learn human brain representations. The fMRI-optimized ReAlnet-fMRI exhibited higher similarity to the human brain than both CORnet and the control model in within-and across-subject as well as within- and across-modality model-brain (fMRI and EEG) alignment evaluations. Additionally, we conducted an in-depth analyses to investigate how the internal representations of ReAlnet-fMRI differ from CORnet in encoding various object dimensions. These findings provide the possibility of enhancing the brain-likeness of visual models by integrating human neural data, helping to bridge the gap between computer vision and visual neuroscience.
Authors: Xianing Chen. Hanting Chen, Hailin Hu
Abstract: Frequency domain representation of time series feature offers a concise representation for handling real-world time series data with inherent complexity and dynamic nature. However, current frequency-based methods with complex operations still fall short of state-of-the-art time domain methods for general time series analysis. In this work, we present Omni-Dimensional Frequency Learner (ODFL) model based on a in depth analysis among all the three aspects of the spectrum feature: channel redundancy property among the frequency dimension, the sparse and un-salient frequency energy distribution among the frequency dimension, and the semantic diversity among the variable dimension. Technically, our method is composed of a semantic-adaptive global filter with attention to the un-salient frequency bands and partial operation among the channel dimension. Empirical results show that ODFL achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection, offering a promising foundation for time series analysis.
Authors: Chunshi Wang, Bin Zhao, Shuxue Ding
Abstract: Cone beam computed tomography (CBCT) is a common way of diagnosing dental related diseases. Accurate segmentation of 3D tooth is of importance for the treatment. Although deep learning based methods have achieved convincing results in medical image processing, they need a large of annotated data for network training, making it very time-consuming in data collection and annotation. Besides, domain shift widely existing in the distribution of data acquired by different devices impacts severely the model generalization. To resolve the problem, we propose a multi-stage framework for 3D tooth segmentation in dental CBCT, which achieves the third place in the "Semi-supervised Teeth Segmentation" 3D (STS-3D) challenge. The experiments on validation set compared with other semi-supervised segmentation methods further indicate the validity of our approach.
Authors: Yuzhou Liu, Lingjie Zhu, Xiaodong Ma, Hanqiao Ye, Xiang Gao, Xianwei Zheng, Shuhan Shen
Abstract: Reconstructing geometry and topology structures from raw unstructured data has always been an important research topic in indoor mapping research. In this paper, we aim to reconstruct the floorplan with a vectorized representation from point clouds. Despite significant advancements achieved in recent years, current methods still encounter several challenges, such as missing corners or edges, inaccuracies in corner positions or angles, self-intersecting or overlapping polygons, and potentially implausible topology. To tackle these challenges, we present PolyRoom, a room-aware Transformer that leverages uniform sampling representation, room-aware query initialization, and room-aware self-attention for floorplan reconstruction. Specifically, we adopt a uniform sampling floorplan representation to enable dense supervision during training and effective utilization of angle information. Additionally, we propose a room-aware query initialization scheme to prevent non-polygonal sequences and introduce room-aware self-attention to enhance memory efficiency and model performance. Experimental results on two widely used datasets demonstrate that PolyRoom surpasses current state-of-the-art methods both quantitatively and qualitatively. Our code is available at: https://github.com/3dv-casia/PolyRoom/.
Authors: Wenbo Jiang, Hongwei Li, Jiaming He, Rui Zhang, Guowen Xu, Tianwei Zhang, Rongxing Lu
Abstract: Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkable performance, the backdoor vulnerability of I2I networks has not been explored. To fill this research gap, we conduct a comprehensive investigation on the susceptibility of I2I networks to backdoor attacks. Specifically, we propose a novel backdoor attack technique, where the compromised I2I network behaves normally on clean input images, yet outputs a predefined image of the adversary for malicious input images containing the trigger. To achieve this I2I backdoor attack, we propose a targeted universal adversarial perturbation (UAP) generation algorithm for I2I networks, where the generated UAP is used as the backdoor trigger. Additionally, in the backdoor training process that contains the main task and the backdoor task, multi-task learning (MTL) with dynamic weighting methods is employed to accelerate convergence rates. In addition to attacking I2I tasks, we extend our I2I backdoor to attack downstream tasks, including image classification and object detection. Extensive experiments demonstrate the effectiveness of the I2I backdoor on state-of-the-art I2I network architectures, as well as the robustness against different mainstream backdoor defenses.
Authors: Yiwei Yang, Zheyuan Liu, Jun Jia, Zhongpai Gao, Yunhao Li, Wei Sun, Xiaohong Liu, Guangtao Zhai
Abstract: Traditional image steganography focuses on concealing one image within another, aiming to avoid steganalysis by unauthorized entities. Coverless image steganography (CIS) enhances imperceptibility by not using any cover image. Recent works have utilized text prompts as keys in CIS through diffusion models. However, this approach faces three challenges: invalidated when private prompt is guessed, crafting public prompts for semantic diversity, and the risk of prompt leakage during frequent transmission. To address these issues, we propose DiffStega, an innovative training-free diffusion-based CIS strategy for universal application. DiffStega uses a password-dependent reference image as an image prompt alongside the text, ensuring that only authorized parties can retrieve the hidden information. Furthermore, we develop Noise Flip technique to further secure the steganography against unauthorized decryption. To comprehensively assess our method across general CIS tasks, we create a dataset comprising various image steganography instances. Experiments indicate substantial improvements in our method over existing ones, particularly in aspects of versatility, password sensitivity, and recovery quality. Codes are available at \url{https://github.com/evtricks/DiffStega}.
Authors: Seonmi Park, Inhwan Bae, Seunghyun Shin, Hae-Gon Jeon
Abstract: This paper introduces a method for realistic kinetic typography that generates user-preferred animatable 'text content'. We draw on recent advances in guided video diffusion models to achieve visually-pleasing text appearances. To do this, we first construct a kinetic typography dataset, comprising about 600K videos. Our dataset is made from a variety of combinations in 584 templates designed by professional motion graphics designers and involves changing each letter's position, glyph, and size (i.e., flying, glitches, chromatic aberration, reflecting effects, etc.). Next, we propose a video diffusion model for kinetic typography. For this, there are three requirements: aesthetic appearances, motion effects, and readable letters. This paper identifies the requirements. For this, we present static and dynamic captions used as spatial and temporal guidance of a video diffusion model, respectively. The static caption describes the overall appearance of the video, such as colors, texture and glyph which represent a shape of each letter. The dynamic caption accounts for the movements of letters and backgrounds. We add one more guidance with zero convolution to determine which text content should be visible in the video. We apply the zero convolution to the text content, and impose it on the diffusion model. Lastly, our glyph loss, only minimizing a difference between the predicted word and its ground-truth, is proposed to make the prediction letters readable. Experiments show that our model generates kinetic typography videos with legible and artistic letter motions based on text prompts.
Authors: Yubin Hu, Xiaoyang Guo, Yang Xiao, Jingwei Huang, Yong-Jin Liu
Abstract: This paper presents NGP-RT, a novel approach for enhancing the rendering speed of Instant-NGP to achieve real-time novel view synthesis. As a classic NeRF-based method, Instant-NGP stores implicit features in multi-level grids or hash tables and applies a shallow MLP to convert the implicit features into explicit colors and densities. Although it achieves fast training speed, there is still a lot of room for improvement in its rendering speed due to the per-point MLP executions for implicit multi-level feature aggregation, especially for real-time applications. To address this challenge, our proposed NGP-RT explicitly stores colors and densities as hash features, and leverages a lightweight attention mechanism to disambiguate the hash collisions instead of using computationally intensive MLP. At the rendering stage, NGP-RT incorporates a pre-computed occupancy distance grid into the ray marching strategy to inform the distance to the nearest occupied voxel, thereby reducing the number of marching points and global memory access. Experimental results show that on the challenging Mip-NeRF360 dataset, NGP-RT achieves better rendering quality than previous NeRF-based methods, achieving 108 fps at 1080p resolution on a single Nvidia RTX 3090 GPU. Our approach is promising for NeRF-based real-time applications that require efficient and high-quality rendering.
Authors: Ziheng Chen, Yue Song, Xiao-Jun Wu, Gaowen Liu, Nicu Sebe
Abstract: Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations. GCP typically performs classification of the covariance matrices by applying matrix function normalization, such as matrix logarithm or power, followed by a Euclidean classifier. However, covariance matrices inherently lie in a Riemannian manifold, known as the Symmetric Positive Definite (SPD) manifold. The current literature does not provide a satisfactory explanation of why Euclidean classifiers can be applied directly to Riemannian features after the normalization of the matrix power. To mitigate this gap, this paper provides a comprehensive and unified understanding of the matrix logarithm and power from a Riemannian geometry perspective. The underlying mechanism of matrix functions in GCP is interpreted from two perspectives: one based on tangent classifiers (Euclidean classifiers on the tangent space) and the other based on Riemannian classifiers. Via theoretical analysis and empirical validation through extensive experiments on fine-grained and large-scale visual classification datasets, we conclude that the working mechanism of the matrix functions should be attributed to the Riemannian classifiers they implicitly respect.
Authors: Mufeng Yao, Jinlong Peng, Qingdong He, Bo Peng, Hao Chen, Mingmin Chi, Chao Liu, Jon Atli Benediktsson
Abstract: Multiple object tracking (MOT) from unmanned aerial vehicle (UAV) platforms requires efficient motion modeling. This is because UAV-MOT faces tracking difficulties caused by large and irregular motion, and insufficient training due to the motion long-tailed distribution of current UAV-MOT datasets. Previous UAV-MOT methods either extract motion and detection features redundantly or supervise motion model in a sparse scheme, which limited their tracking performance and speed. To this end, we propose a flowing-by-detection module to realize accurate motion modeling with a minimum cost. Focusing on the motion long-tailed problem that were ignored by previous works, the flow-guided margin loss is designed to enable more complete training of large moving objects. Experiments on two widely open-source datasets show that our proposed model can successfully track objects with large and irregular motion and outperform existing state-of-the-art methods in UAV-MOT tasks.
Authors: Pramod Rao, Gereon Fox, Abhimitra Meka, Mallikarjun B R, Fangneng Zhan, Tim Weyrich, Bernd Bickel, Hanspeter Pfister, Wojciech Matusik, Mohamed Elgharib, Christian Theobalt
Abstract: Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency, coupled with inaccuracies in physically realistic lighting and identity preservation. Furthermore, personalization from a single view is difficult to achieve and often requires multiview images during the testing phase or involves slow optimization processes. This paper introduces Lite2Relight, a novel technique that can predict 3D consistent head poses of portraits while performing physically plausible light editing at interactive speed. Our method uniquely extends the generative capabilities and efficient volumetric representation of EG3D, leveraging a lightstage dataset to implicitly disentangle face reflectance and perform relighting under target HDRI environment maps. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space, enhancing them with a strong face geometry and reflectance prior. Through extensive quantitative and qualitative evaluations, we show that our method outperforms the state-of-the-art methods in terms of efficacy, photorealism, and practical application. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions. Lite2Relight paves the way for large-scale adoption of photorealistic portrait editing in various domains, offering a robust, interactive solution to a previously constrained problem. Project page: https://vcai.mpi-inf.mpg.de/projects/Lite2Relight/
Authors: Peng Jin, Hao Li, Zesen Cheng, Kehan Li, Runyi Yu, Chang Liu, Xiangyang Ji, Li Yuan, Jie Chen
Abstract: Text-to-motion generation requires not only grounding local actions in language but also seamlessly blending these individual actions to synthesize diverse and realistic global motions. However, existing motion generation methods primarily focus on the direct synthesis of global motions while neglecting the importance of generating and controlling local actions. In this paper, we propose the local action-guided motion diffusion model, which facilitates global motion generation by utilizing local actions as fine-grained control signals. Specifically, we provide an automated method for reference local action sampling and leverage graph attention networks to assess the guiding weight of each local action in the overall motion synthesis. During the diffusion process for synthesizing global motion, we calculate the local-action gradient to provide conditional guidance. This local-to-global paradigm reduces the complexity associated with direct global motion generation and promotes motion diversity via sampling diverse actions as conditions. Extensive experiments on two human motion datasets, i.e., HumanML3D and KIT, demonstrate the effectiveness of our method. Furthermore, our method provides flexibility in seamlessly combining various local actions and continuous guiding weight adjustment, accommodating diverse user preferences, which may hold potential significance for the community. The project page is available at https://jpthu17.github.io/GuidedMotion-project/.
Authors: Rong Ma, Jie Chen, Xiangyang Xue, Jian Pu
Abstract: Deep supervised models possess significant capability to assimilate extensive training data, thereby presenting an opportunity to enhance model performance through training on multiple datasets. However, conflicts arising from different label spaces among datasets may adversely affect model performance. In this paper, we propose a novel approach to automatically construct a unified label space across multiple datasets using graph neural networks. This enables semantic segmentation models to be trained simultaneously on multiple datasets, resulting in performance improvements. Unlike existing methods, our approach facilitates seamless training without the need for additional manual reannotation or taxonomy reconciliation. This significantly enhances the efficiency and effectiveness of multi-dataset segmentation model training. The results demonstrate that our method significantly outperforms other multi-dataset training methods when trained on seven datasets simultaneously, and achieves state-of-the-art performance on the WildDash 2 benchmark.
Authors: J. J. Cabrera, V. Rom\'an, A. Gil, O. Reinoso, L. Pay\'a
Abstract: The objective of this paper is to address the localization problem using omnidirectional images captured by a catadioptric vision system mounted on the robot. For this purpose, we explore the potential of Siamese Neural Networks for modeling indoor environments using panoramic images as the unique source of information. Siamese Neural Networks are characterized by their ability to generate a similarity function between two input data, in this case, between two panoramic images. In this study, Siamese Neural Networks composed of two Convolutional Neural Networks (CNNs) are used. The output of each CNN is a descriptor which is used to characterize each image. The dissimilarity of the images is computed by measuring the distance between these descriptors. This fact makes Siamese Neural Networks particularly suitable to perform image retrieval tasks. First, we evaluate an initial task strongly related to localization that consists in detecting whether two images have been captured in the same or in different rooms. Next, we assess Siamese Neural Networks in the context of a global localization problem. The results outperform previous techniques for solving the localization task using the COLD-Freiburg dataset, in a variety of lighting conditions, specially when using images captured in cloudy and night conditions.
Authors: Nahyuk Lee, Juhong Min, Junha Lee, Seungwook Kim, Kanghee Lee, Jaesik Park, Minsu Cho
Abstract: Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and computation. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://nahyuklee.github.io/pmtr.
Authors: Sara Pohland, Claire Tomlin
Abstract: While deep neural network (DNN)-based perception models are useful for many applications, these models are black boxes and their outputs are not yet well understood. To confidently enable a real-world, decision-making system to utilize such a perception model without human intervention, we must enable the system to reason about the perception model's level of competency and respond appropriately when the model is incompetent. In order for the system to make an intelligent decision about the appropriate action when the model is incompetent, it would be useful for the system to understand why the model is incompetent. We explore five novel methods for identifying regions in the input image contributing to low model competency, which we refer to as image cropping, segment masking, pixel perturbation, competency gradients, and reconstruction loss. We assess the ability of these five methods to identify unfamiliar objects, recognize regions associated with unseen classes, and identify unexplored areas in an environment. We find that the competency gradients and reconstruction loss methods show great promise in identifying regions associated with low model competency, particularly when aspects of the image that are unfamiliar to the perception model are causing this reduction in competency. Both of these methods boast low computation times and high levels of accuracy in detecting image regions that are unfamiliar to the model, allowing them to provide potential utility in decision-making pipelines. The code for reproducing our methods and results is available on GitHub: https://github.com/sarapohland/explainable-competency.
URLs: https://github.com/sarapohland/explainable-competency.
Authors: Daichi Zhang, Zihao Xiao, Shikun Li, Fanzhao Lin, Jianmin Li, Shiming Ge
Abstract: Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and existing self-supervised detectors are strict on auxiliary tasks, such as requiring audio or multi-modalities, leading to limited generalization and robustness. In this paper, we examine whether we can address this issue by leveraging visual-only real face videos. To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervised manner, which is inspired by the observation that fake videos struggle to maintain the natural spatiotemporal consistency even under unknown forgery methods and different perturbations. Our NACO first extracts spatial features of each frame by CNNs then integrates them into Transformer to learn the long-range spatiotemporal representation, leveraging the advantages of CNNs and Transformer on local spatial receptive field and long-term memory respectively. Furthermore, a Spatial Predictive Module~(SPM) and a Temporal Contrastive Module~(TCM) are introduced to enhance the natural consistency representation learning. The SPM aims to predict random masked spatial features from spatiotemporal representation, and the TCM regularizes the latent distance of spatiotemporal representation by shuffling the natural order to disturb the consistency, which could both force our NACO more sensitive to the natural spatiotemporal consistency. After the representation learning stage, a MLP head is fine-tuned to perform the usual forgery video classification task. Extensive experiments show that our method outperforms other state-of-the-art competitors with impressive generalization and robustness.
Authors: Jaehoon Ahn, Sumin Cho, Harim Jung, Kibeom Hong, Seonghoon Ban, Moon-Ryul Jung
Abstract: We introduce ConTEXTure, a generative network designed to create a texture map/atlas for a given 3D mesh using images from multiple viewpoints. The process begins with generating a front-view image from a text prompt, such as 'Napoleon, front view', describing the 3D mesh. Additional images from different viewpoints are derived from this front-view image and camera poses relative to it. ConTEXTure builds upon the TEXTure network, which uses text prompts for six viewpoints (e.g., 'Napoleon, front view', 'Napoleon, left view', etc.). However, TEXTure often generates images for non-front viewpoints that do not accurately represent those viewpoints.To address this issue, we employ Zero123++, which generates multiple view-consistent images for the six specified viewpoints simultaneously, conditioned on the initial front-view image and the depth maps of the mesh for the six viewpoints. By utilizing these view-consistent images, ConTEXTure learns the texture atlas from all viewpoint images concurrently, unlike previous methods that do so sequentially. This approach ensures that the rendered images from various viewpoints, including back, side, bottom, and top, are free from viewpoint irregularities.
Authors: Davide Bianchi, Sonia Colombo Serra, Davide Evangelista, Pengpeng Luo, Elena Morotti, Giovanni Valbusa
Abstract: The adoption of contrast agents in medical imaging protocols is crucial for accurate and timely diagnosis. While highly effective and characterized by an excellent safety profile, the use of contrast agents has its limitation, including rare risk of allergic reactions, potential environmental impact and economic burdens on patients and healthcare systems. In this work, we address the contrast agent reduction (CAR) problem, which involves reducing the administered dosage of contrast agent while preserving the visual enhancement. The current literature on the CAR task is based on deep learning techniques within a fully image processing framework. These techniques digitally simulate high-dose images from images acquired with a low dose of contrast agent. We investigate the feasibility of a ``learned inverse problem'' (LIP) approach, as opposed to the end-to-end paradigm in the state-of-the-art literature. Specifically, we learn the image-to-image operator that maps high-dose images to their corresponding low-dose counterparts, and we frame the CAR task as an inverse problem. We then solve this problem through a regularized optimization reformulation. Regularization methods are well-established mathematical techniques that offer robustness and explainability. Our approach combines these rigorous techniques with cutting-edge deep learning tools. Numerical experiments performed on pre-clinical medical images confirm the effectiveness of this strategy, showing improved stability and accuracy in the simulated high-dose images.
Authors: Rong Quan, Yantao Lai, Mengyu Qiu, Dong Liang
Abstract: Scanpath prediction in 360{\deg} images can help realize rapid rendering and better user interaction in Virtual/Augmented Reality applications. However, existing scanpath prediction models for 360{\deg} images execute scanpath prediction on 2D equirectangular projection plane, which always result in big computation error owing to the 2D plane's distortion and coordinate discontinuity. In this work, we perform scanpath prediction for 360{\deg} images in 3D spherical coordinate system and proposed a novel 3D scanpath Transformer named Pathformer3D. Specifically, a 3D Transformer encoder is first used to extract 3D contextual feature representation for the 360{\deg} image. Then, the contextual feature representation and historical fixation information are input into a Transformer decoder to output current time step's fixation embedding, where the self-attention module is used to imitate the visual working memory mechanism of human visual system and directly model the time dependencies among the fixations. Finally, a 3D Gaussian distribution is learned from each fixation embedding, from which the fixation position can be sampled. Evaluation on four panoramic eye-tracking datasets demonstrates that Pathformer3D outperforms the current state-of-the-art methods. Code is available at https://github.com/lsztzp/Pathformer3D .
Authors: Leonard Siegert, Paul Fischer, Mattias P. Heinrich, Christian F. Baumgartner
Abstract: Deformable image registration is fundamental to many medical imaging applications. Registration is an inherently ambiguous task often admitting many viable solutions. While neural network-based registration techniques enable fast and accurate registration, the majority of existing approaches are not able to estimate uncertainty. Here, we present PULPo, a method for probabilistic deformable registration capable of uncertainty quantification. PULPo probabilistically models the distribution of deformation fields on different hierarchical levels combining them using Laplacian pyramids. This allows our method to model global as well as local aspects of the deformation field. We evaluate our method on two widely used neuroimaging datasets and find that it achieves high registration performance as well as substantially better calibrated uncertainty quantification compared to the current state-of-the-art.
Authors: Peihceng Wu, Runze Ma, Teoh Teik Toe
Abstract: This paper proposes a CNN classification network based on Bagging and stacking ensemble learning methods for breast cancer classification. The model was trained and tested on the public dataset of DDSM. The model is capable of fast and accurate classification of input images. According to our research results, for binary classification (presence or absence of breast cancer), the accuracy reached 98.84%, and for five-class classification, the accuracy reached 98.34%. The model also achieved a micro-average recall rate of 94.80% and an F1 score of 94.19%. In comparative experiments, we compared the effects of different values of bagging_ratio and n_models on the model, as well as several methods for ensemble bagging models. Furthermore, under the same parameter settings, our BSECNN outperformed VGG16 and ResNet-50 in terms of accuracy by 8.22% and 6.33% respectively.
Authors: Jingyi Deng, Chenhao Lin, Zhengyu Zhao, Shuai Liu, Qian Wang, Chao Shen
Abstract: Deep generative models have demonstrated impressive performance in various computer vision applications, including image synthesis, video generation, and medical analysis. Despite their significant advancements, these models may be used for malicious purposes, such as misinformation, deception, and copyright violation. In this paper, we provide a systematic and timely review of research efforts on defenses against AI-generated visual media, covering detection, disruption, and authentication. We review existing methods and summarize the mainstream defense-related tasks within a unified passive and proactive framework. Moreover, we survey the derivative tasks concerning the trustworthiness of defenses, such as their robustness and fairness. For each task, we formulate its general pipeline and propose a taxonomy based on methodological strategies that are uniformly applicable to the primary subtasks. Additionally, we summarize the commonly used evaluation datasets, criteria, and metrics. Finally, by analyzing the reviewed studies, we provide insights into current research challenges and suggest possible directions for future research.
Authors: Marco Pesavento, Marco Volino, Adrian Hilton
Abstract: We present a novel framework to reconstruct complete 3D human shapes from a given target image by leveraging monocular unconstrained images. The objective of this work is to reproduce high-quality details in regions of the reconstructed human body that are not visible in the input target. The proposed methodology addresses the limitations of existing approaches for reconstructing 3D human shapes from a single image, which cannot reproduce shape details in occluded body regions. The missing information of the monocular input can be recovered by using multiple views captured from multiple cameras. However, multi-view reconstruction methods necessitate accurately calibrated and registered images, which can be challenging to obtain in real-world scenarios. Given a target RGB image and a collection of multiple uncalibrated and unregistered images of the same individual, acquired using a single camera, we propose a novel framework to generate complete 3D human shapes. We introduce a novel module to generate 2D multi-view normal maps of the person registered with the target input image. The module consists of body part-based reference selection and body part-based registration. The generated 2D normal maps are then processed by a multi-view attention-based neural implicit model that estimates an implicit representation of the 3D shape, ensuring the reproduction of details in both observed and occluded regions. Extensive experiments demonstrate that the proposed approach estimates higher quality details in the non-visible regions of the 3D clothed human shapes compared to related methods, without using parametric models.
Authors: Giulia Panconi, Stefano Grasso, Sara Guarducci, Lorenzo Mucchi, Diego Minciacchi, Riccardo Bravi
Abstract: The current gold standard for the study of human movement is the marker-based motion capture system that offers high precision but constrained by costs and controlled environments. Markerless pose estimation systems emerge as ecological alternatives, allowing unobtrusive data acquisition in natural settings. This study compares the performance of two popular markerless systems, OpenPose (OP) and DeepLabCut (DLC), in assessing locomotion. Forty healthy subjects walked along a 5 meters walkway equipped with four force platforms and a camera. Gait parameters were obtained using OP BODY 25 Pre-Trained model (OPPT), DLC Model Zoo full human Pre-Trained model (DLCPT) and DLC Custom-Trained model (DLCCT), then compared with those acquired from the force platforms as reference system. Our results demonstrated that DLCCT outperformed DLCPT and OPPT, highlighting the importance of leveraging DeepLabCut transfer learning to enhance the pose estimation performance with a custom-trained neural networks. Moreover, DLCCT, with the implementation of the DLC refinement function, offers the most promising markerless pose estimation solution for evaluating locomotion. Therefore, our data provide insights into the DLC training and refinement processes required to achieve optimal performance. This study offers perspectives for clinicians and practitioners seeking accurate low-cost methods for movement assessment beyond laboratory settings.
Authors: Phillip Mueller, Jannik Wiese, Ioan Craciun, Lars Mikelsons
Abstract: Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge. This paper introduces InsertDiffusion, a novel, training-free diffusion architecture that efficiently embeds objects into images while preserving their structural and identity characteristics. Our approach utilizes off-the-shelf generative models and eliminates the need for fine-tuning, making it ideal for rapid and adaptable visualizations in product design and marketing. We demonstrate superior performance over existing methods in terms of image realism and alignment with input conditions. By decomposing the generation task into independent steps, InsertDiffusion offers a scalable solution that extends the capabilities of diffusion models for practical applications, achieving high-quality visualizations that maintain the authenticity of the original objects.
Authors: J. J. Cabrera, O. J. C\'espedes, S. Cebollada, O. Reinoso, L. Pay\'a
Abstract: This work presents an evaluation of CNN models and data augmentation to carry out the hierarchical localization of a mobile robot by using omnidireccional images. In this sense, an ablation study of different state-of-the-art CNN models used as backbone is presented and a variety of data augmentation visual effects are proposed for addressing the visual localization of the robot. The proposed method is based on the adaption and re-training of a CNN with a dual purpose: (1) to perform a rough localization step in which the model is used to predict the room from which an image was captured, and (2) to address the fine localization step, which consists in retrieving the most similar image of the visual map among those contained in the previously predicted room by means of a pairwise comparison between descriptors obtained from an intermediate layer of the CNN. In this sense, we evaluate the impact of different state-of-the-art CNN models such as ConvNeXt for addressing the proposed localization. Finally, a variety of data augmentation visual effects are separately employed for training the model and their impact is assessed. The performance of the resulting CNNs is evaluated under real operation conditions, including changes in the lighting conditions. Our code is publicly available on the project website https://github.com/juanjo-cabrera/IndoorLocalizationSingleCNN.git
URLs: https://github.com/juanjo-cabrera/IndoorLocalizationSingleCNN.git
Authors: Zijian He, Peixin Chen, Guangrun Wang, Guanbin Li, Philip H. S. Torr, Liang Lin
Abstract: Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex human movements and occlusions, limiting their effectiveness in video try-on applications. Moreover, video-based models require extensive, high-quality data and substantial computational resources. To tackle these issues, we reconceptualize video try-on as a process of generating videos conditioned on garment descriptions and human motion. Our solution, WildVidFit, employs image-based controlled diffusion models for a streamlined, one-stage approach. This model, conditioned on specific garments and individuals, is trained on still images rather than videos. It leverages diffusion guidance from pre-trained models including a video masked autoencoder for segment smoothness improvement and a self-supervised model for feature alignment of adjacent frame in the latent space. This integration markedly boosts the model's ability to maintain temporal coherence, enabling more effective video try-on within an image-based framework. Our experiments on the VITON-HD and DressCode datasets, along with tests on the VVT and TikTok datasets, demonstrate WildVidFit's capability to generate fluid and coherent videos. The project page website is at wildvidfit-project.github.io.
Authors: Lin Zhu, Yunlong Zheng, Yijun Zhang, Xiao Wang, Lizhi Wang, Hua Huang
Abstract: Event-based video reconstruction has garnered increasing attention due to its advantages, such as high dynamic range and rapid motion capture capabilities. However, current methods often prioritize the extraction of temporal information from continuous event flow, leading to an overemphasis on low-frequency texture features in the scene, resulting in over-smoothing and blurry artifacts. Addressing this challenge necessitates the integration of conditional information, encompassing temporal features, low-frequency texture, and high-frequency events, to guide the Denoising Diffusion Probabilistic Model (DDPM) in producing accurate and natural outputs. To tackle this issue, we introduce a novel approach, the Temporal Residual Guided Diffusion Framework, which effectively leverages both temporal and frequency-based event priors. Our framework incorporates three key conditioning modules: a pre-trained low-frequency intensity estimation module, a temporal recurrent encoder module, and an attention-based high-frequency prior enhancement module. In order to capture temporal scene variations from the events at the current moment, we employ a temporal-domain residual image as the target for the diffusion model. Through the combination of these three conditioning paths and the temporal residual framework, our framework excels in reconstructing high-quality videos from event flow, mitigating issues such as artifacts and over-smoothing commonly observed in previous approaches. Extensive experiments conducted on multiple benchmark datasets validate the superior performance of our framework compared to prior event-based reconstruction methods.
Authors: Hyungjin Chung, Jong Chul Ye
Abstract: Recent inverse problem solvers that leverage generative diffusion priors have garnered significant attention due to their exceptional quality. However, adaptation of the prior is necessary when there exists a discrepancy between the training and testing distributions. In this work, we propose deep diffusion image prior (DDIP), which generalizes the recent adaptation method of SCD by introducing a formal connection to the deep image prior. Under this framework, we propose an efficient adaptation method dubbed D3IP, specified for 3D measurements, which accelerates DDIP by orders of magnitude while achieving superior performance. D3IP enables seamless integration of 3D inverse solvers and thus leads to coherent 3D reconstruction. Moreover, we show that meta-learning techniques can also be applied to yield even better performance. We show that our method is capable of solving diverse 3D reconstructive tasks from the generative prior trained only with phantom images that are vastly different from the training set, opening up new opportunities of applying diffusion inverse solvers even when training with gold standard data is impossible. Code: https://github.com/HJ-harry/DDIP3D
Authors: Wangyu Wu, Tianhong Dai, Zhenhong Chen, Xiaowei Huang, Fei Ma, Jimin Xiao
Abstract: Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to its cost-effectiveness. The typical framework involves using image-level labels as training data to generate pixel-level pseudo-labels with refinements. Recently, methods based on Vision Transformers (ViT) have demonstrated superior capabilities in generating reliable pseudo-labels, particularly in recognizing complete object regions, compared to CNN methods. However, current ViT-based approaches have some limitations in the use of patch embeddings, being prone to being dominated by certain abnormal patches, as well as many multi-stage methods being time-consuming and lengthy in training, thus lacking efficiency. Therefore, in this paper, we introduce a novel ViT-based WSSS method named \textit{Adaptive Patch Contrast} (APC) that significantly enhances patch embedding learning for improved segmentation effectiveness. APC utilizes an Adaptive-K Pooling (AKP) layer to address the limitations of previous max pooling selection methods. Additionally, we propose a Patch Contrastive Learning (PCL) to enhance patch embeddings, thereby further improving the final results. Furthermore, we improve upon the existing multi-stage training framework without CAM by transforming it into an end-to-end single-stage training approach, thereby enhancing training efficiency. The experimental results show that our approach is effective and efficient, outperforming other state-of-the-art WSSS methods on the PASCAL VOC 2012 and MS COCO 2014 dataset within a shorter training duration.
Authors: Yu Wang, Xiangbo Su, Qiang Chen, Xinyu Zhang, Teng Xi, Kun Yao, Errui Ding, Gang Zhang, Jingdong Wang
Abstract: Open-vocabulary object detection focusing on detecting novel categories guided by natural language. In this report, we propose Open-Vocabulary Light-Weighted Detection Transformer (OVLW-DETR), a deployment friendly open-vocabulary detector with strong performance and low latency. Building upon OVLW-DETR, we provide an end-to-end training recipe that transferring knowledge from vision-language model (VLM) to object detector with simple alignment. We align detector with the text encoder from VLM by replacing the fixed classification layer weights in detector with the class-name embeddings extracted from the text encoder. Without additional fusing module, OVLW-DETR is flexible and deployment friendly, making it easier to implement and modulate. improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time open-vocabulary detectors on standard Zero-Shot LVIS benchmark. Source code and pre-trained models are available at [https://github.com/Atten4Vis/LW-DETR].
Authors: Kristine S{\o}rensen, Paula Diez, Jan Margeta, Yasmin El Youssef, Michael Pham, Jonas Jalili Pedersen, Tobias K\"uhl, Ole de Backer, Klaus Kofoed, Oscar Camara, Rasmus Paulsen
Abstract: The rhythmic pumping motion of the heart stands as a cornerstone in life, as it circulates blood to the entire human body through a series of carefully timed contractions of the individual chambers. Changes in the size, shape and movement of the chambers can be important markers for cardiac disease and modeling this in relation to clinical demography or disease is therefore of interest. Existing methods for spatio-temporal modeling of the human heart require shape correspondence over time or suffer from large memory requirements, making it difficult to use for complex anatomies. We introduce a novel conditional generative model, where the shape and movement is modeled implicitly in the form of a spatio-temporal neural distance field and conditioned on clinical demography. The model is based on an auto-decoder architecture and aims to disentangle the individual variations from that related to the clinical demography. It is tested on the left atrium (including the left atrial appendage), where it outperforms current state-of-the-art methods for anatomical sequence completion and generates synthetic sequences that realistically mimics the shape and motion of the real left atrium. In practice, this means we can infer functional measurements from a static image, generate synthetic populations with specified demography or disease and investigate how non-imaging clinical data effect the shape and motion of cardiac anatomies.
Authors: Youngsun Lim, Hyunjung Shim
Abstract: Text-to-image generation has shown remarkable progress with the emergence of diffusion models. However, these models often generate factually inconsistent images, failing to accurately reflect the factual information and common sense conveyed by the input text prompts. We refer to this issue as Image hallucination. Drawing from studies on hallucinations in language models, we classify this problem into three types and propose a methodology that uses factual images retrieved from external sources to generate realistic images. Depending on the nature of the hallucination, we employ off-the-shelf image editing tools, either InstructPix2Pix or IP-Adapter, to leverage factual information from the retrieved image. This approach enables the generation of images that accurately reflect the facts and common sense.
Authors: Honghao Xu, Juzhan Xu, Zeyu Huang, Pengfei Xu, Hui Huang, Ruizhen Hu
Abstract: In this paper, we introduce a novel method called FRI-Net for 2D floorplan reconstruction from 3D point cloud. Existing methods typically rely on corner regression or box regression, which lack consideration for the global shapes of rooms. To address these issues, we propose a novel approach using a room-wise implicit representation with structural regularization to characterize the shapes of rooms in floorplans. By incorporating geometric priors of room layouts in floorplans into our training strategy, the generated room polygons are more geometrically regular. We have conducted experiments on two challenging datasets, Structured3D and SceneCAD. Our method demonstrates improved performance compared to state-of-the-art methods, validating the effectiveness of our proposed representation for floorplan reconstruction.
Authors: Zhihao Chen, Yiyuan Ge, Qing Yue
Abstract: Cloth-changing person re-identification (CC-ReID) aims to retrieve specific pedestrians in a cloth-changing scenario. Its main challenge is to disentangle the clothing-related and clothing-unrelated features. Most existing approaches force the model to learn clothing-unrelated features by changing the color of the clothes. However, due to the lack of ground truth, these methods inevitably introduce noise, which destroys the discriminative features and leads to an uncontrollable disentanglement process. In this paper, we propose a new person re-identification network called features reconstruction disentanglement ReID (FRD-ReID), which can controllably decouple the clothing-unrelated and clothing-related features. Specifically, we first introduce the human parsing mask as the ground truth of the reconstruction process. At the same time, we propose the far away attention (FAA) mechanism and the person contour attention (PCA) mechanism for clothing-unrelated features and pedestrian contour features to improve the feature reconstruction efficiency. In the testing phase, we directly discard the clothing-related features for inference,which leads to a controllable disentanglement process. We conducted extensive experiments on the PRCC, LTCC, and Vc-Clothes datasets and demonstrated that our method outperforms existing state-of-the-art methods.
Authors: Shuaixian Wang, Haoran Xu, Yaokun Li, Jiwei Chen, Guang Tan
Abstract: We present a novel approach for synthesizing realistic novel views using Neural Radiance Fields (NeRF) with uncontrolled photos in the wild. While NeRF has shown impressive results in controlled settings, it struggles with transient objects commonly found in dynamic and time-varying scenes. Our framework called \textit{Inpainting Enhanced NeRF}, or \ours, enhances the conventional NeRF by drawing inspiration from the technique of image inpainting. Specifically, our approach extends the Multi-Layer Perceptrons (MLP) of NeRF, enabling it to simultaneously generate intrinsic properties (static color, density) and extrinsic transient masks. We introduce an inpainting module that leverages the transient masks to effectively exclude occlusions, resulting in improved volume rendering quality. Additionally, we propose a new training strategy with frequency regularization to address the sparsity issue of low-frequency transient components. We evaluate our approach on internet photo collections of landmarks, demonstrating its ability to generate high-quality novel views and achieve state-of-the-art performance.
Authors: Antoine Habis, Vannary Meas-Yedid, Elsa Angelini, Jean-Christophe Olivo-Marin
Abstract: This paper introduces a novel approach that combines unsupervised active contour models with deep learning for robust and adaptive image segmentation. Indeed, traditional active contours, provide a flexible framework for contour evolution and learning offers the capacity to learn intricate features and patterns directly from raw data. Our proposed methodology leverages the strengths of both paradigms, presenting a framework for both unsupervised and one-shot approaches for image segmentation. It is capable of capturing complex object boundaries without the need for extensive labeled training data. This is particularly required in histology, a field facing a significant shortage of annotations due to the challenging and time-consuming nature of the annotation process. We illustrate and compare our results to state of the art methods on a histology dataset and show significant improvements.
Authors: Yuhwan Jeong, Hoonhee Cho, Kuk-Jin Yoon
Abstract: Event cameras with high dynamic range ensure scene capture even in low-light conditions. However, night events exhibit patterns different from those captured during the day. This difference causes performance degradation when applying night events to a model trained solely on day events. This limitation persists due to a lack of annotated night events. To overcome the limitation, we aim to alleviate data imbalance by translating annotated day data into night events. However, generating events from different modalities challenges reproducing their unique properties. Accordingly, we propose an unpaired event-to-event day-to-night translation model that effectively learns to map from one domain to another using Diffusion GAN. The proposed translation model analyzes events in spatio-temporal dimension with wavelet decomposition and disentangled convolution layers. We also propose a new temporal contrastive learning with a novel shuffling and sampling strategy to regularize temporal continuity. To validate the efficacy of the proposed methodology, we redesign metrics for evaluating events translated in an unpaired setting, aligning them with the event modality for the first time. Our framework shows the successful day-to-night event translation while preserving the characteristics of events. In addition, through our translation method, we facilitate event-based modes to learn about night events by translating annotated day events into night events. Our approach effectively mitigates the performance degradation of applying real night events to downstream tasks. The code is available at https://github.com/jeongyh98/UDNET.
Authors: Tianxiang Hao, Xiaohan Ding, Juexiao Feng, Yuhong Yang, Hui Chen, Guiguang Ding
Abstract: In the past few years, large-scale pre-trained vision-language models like CLIP have achieved tremendous success in various fields. Naturally, how to transfer the rich knowledge in such huge pre-trained models to downstream tasks and datasets becomes a hot topic. During downstream adaptation, the most challenging problems are overfitting and catastrophic forgetting, which can cause the model to overly focus on the current data and lose more crucial domain-general knowledge. Existing works use classic regularization techniques to solve the problems. As solutions become increasingly complex, the ever-growing storage and inference costs are also a significant problem that urgently needs to be addressed. While in this paper, we start from an observation that proper random noise can suppress overfitting and catastrophic forgetting. Then we regard quantization error as a kind of noise, and explore quantization for regularizing vision-language model, which is quite efficiency and effective. Furthermore, to improve the model's generalization capability while maintaining its specialization capacity at minimal cost, we deeply analyze the characteristics of the weight distribution in prompts, conclude several principles for quantization module design and follow such principles to create several competitive baselines. The proposed method is significantly efficient due to its inherent lightweight nature, making it possible to adapt on extremely resource-limited devices. Our method can be fruitfully integrated into many existing approaches like MaPLe, enhancing accuracy while reducing storage overhead, making it more powerful yet versatile. Extensive experiments on 11 datasets shows great superiority of our method sufficiently. Code is available at https://github.com/beyondhtx/QPrompt.
Authors: Youyi Zhan, Tianjia Shao, He Wang, Yin Yang, Kun Zhou
Abstract: Creating relightable and animatable avatars from multi-view or monocular videos is a challenging task for digital human creation and virtual reality applications. Previous methods rely on neural radiance fields or ray tracing, resulting in slow training and rendering processes. By utilizing Gaussian Splatting, we propose a simple and efficient method to decouple body materials and lighting from sparse-view or monocular avatar videos, so that the avatar can be rendered simultaneously under novel viewpoints, poses, and lightings at interactive frame rates (6.9 fps). Specifically, we first obtain the canonical body mesh using a signed distance function and assign attributes to each mesh vertex. The Gaussians in the canonical space then interpolate from nearby body mesh vertices to obtain the attributes. We subsequently deform the Gaussians to the posed space using forward skinning, and combine the learnable environment light with the Gaussian attributes for shading computation. To achieve fast shadow modeling, we rasterize the posed body mesh from dense viewpoints to obtain the visibility. Our approach is not only simple but also fast enough to allow interactive rendering of avatar animation under environmental light changes. Experiments demonstrate that, compared to previous works, our method can render higher quality results at a faster speed on both synthetic and real datasets.
Authors: Phuc D. A. Nguyen, Anh Do, Minh Hoai
Abstract: This paper explores the application of computer vision technologies to the analysis of maps, an area with substantial historical, cultural, and political significance. Our focus is on developing and evaluating a method for automatically identifying maps that depict specific regions and feature landmarks with designated names, a task that involves complex challenges due to the diverse styles and methods used in map creation. We address three main subtasks: differentiating maps from non-maps, verifying the accuracy of the region depicted, and confirming the presence or absence of particular landmark names through advanced text recognition techniques. Our approach utilizes a Convolutional Neural Network and transfer learning to differentiate maps from non-maps, verify the accuracy of depicted regions, and confirm landmark names through advanced text recognition. We also introduce the VinMap dataset, containing annotated map images of Vietnam, to train and test our method. Experiments on this dataset demonstrate that our technique achieves F1-score of 85.51% for identifying maps excluding specific territorial landmarks. This result suggests practical utility and indicates areas for future improvement.
Authors: Youssef Zahran, Gertjan Burghouts, Yke Bauke Eisma
Abstract: Despite the significant advancements in computer vision models, their ability to generalize to novel object-attribute compositions remains limited. Existing methods for Compositional Zero-Shot Learning (CZSL) mainly focus on image classification. This paper aims to enhance CZSL in object detection without forgetting prior learned knowledge. We use Grounding DINO and incorporate Compositional Soft Prompting (CSP) into it and extend it with Compositional Anticipation. We achieve a 70.5% improvement over CSP on the harmonic mean (HM) between seen and unseen compositions on the CLEVR dataset. Furthermore, we introduce Contrastive Prompt Tuning to incrementally address model confusion between similar compositions. We demonstrate the effectiveness of this method and achieve an increase of 14.5% in HM across the pretrain, increment, and unseen sets. Collectively, these methods provide a framework for learning various compositions with limited data, as well as improving the performance of underperforming compositions when additional data becomes available.
Authors: Lucas Alvarenga, Victor Ferrari, Rafael Souza, Marcio Pereira, Guido Araujo
Abstract: Convolution is a compute-intensive operation placed at the heart of Convolution Neural Networks (CNNs). It has led to the development of many high-performance algorithms, such as Im2col-GEMM, Winograd, and Direct-Convolution. However, the comparison of different convolution algorithms is an error-prone task as it requires specific data layouts and system resources. Failure to address these requirements might lead to unwanted time penalties. Thus, considering all processing steps within convolution algorithms is essential to comprehensively evaluate and fairly compare their performance. Furthermore, most known convolution benchmarking adopts ad-hoc testing suites with limited coverage and handmade operations. This paper proposes ConvBench, a primitive-level benchmark for the evaluation and comparison of convolution algorithms. It assesses 9243 convolution operations derived from 1097 real-world deep learning models, resulting in performance and execution breakdown graphs for a detailed evaluation. ConvBench capability is evaluated across the Sliced Convolution (SConv) algorithm. The experiments showed results faster than Im2col-GEMM in 93.6% of the convolutions. However, the use of ConvBench allowed the delving into the remaining 6.4% underperforming convolutions, uncovering a critical slowdown of 79.5% on average of SConv's packing step. This analysis underscores a potential source of optimization for SConv, opening up new paths for convolution designers to improve their algorithms.
Authors: Dong-Hee Kim, Sungduk Cho, Hyeonwoo Cho, Chanmin Park, Jinyoung Kim, Won Hwa Kim
Abstract: In this work, we introduce Mask-JEPA, a self-supervised learning framework tailored for mask classification architectures (MCA), to overcome the traditional constraints associated with training segmentation models. Mask-JEPA combines a Joint Embedding Predictive Architecture with MCA to adeptly capture intricate semantics and precise object boundaries. Our approach addresses two critical challenges in self-supervised learning: 1) extracting comprehensive representations for universal image segmentation from a pixel decoder, and 2) effectively training the transformer decoder. The use of the transformer decoder as a predictor within the JEPA framework allows proficient training in universal image segmentation tasks. Through rigorous evaluations on datasets such as ADE20K, Cityscapes and COCO, Mask-JEPA demonstrates not only competitive results but also exceptional adaptability and robustness across various training scenarios. The architecture-agnostic nature of Mask-JEPA further underscores its versatility, allowing seamless adaptation to various mask classification family.
Authors: Sara Mandelli, Paolo Bestagini, Stefano Tubaro
Abstract: In recent years, methods for producing highly realistic synthetic images have significantly advanced, allowing the creation of high-quality images from text prompts that describe the desired content. Even more impressively, Stable Diffusion (SD) models now provide users with the option of creating synthetic images in an image-to-image translation fashion, modifying images in the latent space of advanced autoencoders. This striking evolution, however, brings an alarming consequence: it is possible to pass an image through SD autoencoders to reproduce a synthetic copy of the image with high realism and almost no visual artifacts. This process, known as SD image laundering, can transform real images into lookalike synthetic ones and risks complicating forensic analysis for content authenticity verification. Our paper investigates the forensic implications of image laundering, revealing a serious potential to obscure traces of real content, including sensitive and harmful materials that could be mistakenly classified as synthetic, thereby undermining the protection of individuals depicted. To address this issue, we propose a two-stage detection pipeline that effectively differentiates between pristine, laundered, and fully synthetic images (those generated from text prompts), showing robustness across various conditions. Finally, we highlight another alarming property of image laundering, which appears to mask the unique artifacts exploited by forensic detectors to solve the camera model identification task, strongly undermining their performance. Our experimental code is available at https://github.com/polimi-ispl/synthetic-image-detection.
URLs: https://github.com/polimi-ispl/synthetic-image-detection.
Authors: Rining Wu, Feixiang Zhou, Ziwei Yin, Jian K. Liu
Abstract: Our brains represent the ever-changing environment with neurons in a highly dynamic fashion. The temporal features of visual pixels in dynamic natural scenes are entrapped in the neuronal responses of the retina. It is crucial to establish the intrinsic temporal relationship between visual pixels and neuronal responses. Recent foundation vision models have paved an advanced way of understanding image pixels. Yet, neuronal coding in the brain largely lacks a deep understanding of its alignment with pixels. Most previous studies employ static images or artificial videos derived from static images for emulating more real and complicated stimuli. Despite these simple scenarios effectively help to separate key factors influencing visual coding, complex temporal relationships receive no consideration. To decompose the temporal features of visual coding in natural scenes, here we propose Vi-ST, a spatiotemporal convolutional neural network fed with a self-supervised Vision Transformer (ViT) prior, aimed at unraveling the temporal-based encoding patterns of retinal neuronal populations. The model demonstrates robust predictive performance in generalization tests. Furthermore, through detailed ablation experiments, we demonstrate the significance of each temporal module. Furthermore, we introduce a visual coding evaluation metric designed to integrate temporal considerations and compare the impact of different numbers of neuronal populations on complementary coding. In conclusion, our proposed Vi-ST demonstrates a novel modeling framework for neuronal coding of dynamic visual scenes in the brain, effectively aligning our brain representation of video with neuronal activity. The code is available at https://github.com/wurining/Vi-ST.
Authors: Zhihang Lin, Mingbao Lin, Meng Zhao, Rongrong Ji
Abstract: This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation. We propose AccDiffusion, an accurate method for patch-wise higher-resolution image generation without training. An in-depth analysis in this paper reveals an identical text prompt for different patches causes repeated object generation, while no prompt compromises the image details. Therefore, our AccDiffusion, for the first time, proposes to decouple the vanilla image-content-aware prompt into a set of patch-content-aware prompts, each of which serves as a more precise description of an image patch. Besides, AccDiffusion also introduces dilated sampling with window interaction for better global consistency in higher-resolution image generation. Experimental comparison with existing methods demonstrates that our AccDiffusion effectively addresses the issue of repeated object generation and leads to better performance in higher-resolution image generation. Our code is released at \url{https://github.com/lzhxmu/AccDiffusion}.
Authors: Zhe Liu, Jinghua Hou, Xiaoqing Ye, Tong Wang, Jingdong Wang, Xiang Bai
Abstract: Recently, detection transformers (DETRs) have gradually taken a dominant position in 2D detection thanks to their elegant framework. However, DETR-based detectors for 3D point clouds are still difficult to achieve satisfactory performance. We argue that the main challenges are twofold: 1) How to obtain the appropriate object queries is challenging due to the high sparsity and uneven distribution of point clouds; 2) How to implement an effective query interaction by exploiting the rich geometric structure of point clouds is not fully explored. To this end, we propose a simple and effective 3D DETR method (SEED) for detecting 3D objects from point clouds, which involves a dual query selection (DQS) module and a deformable grid attention (DGA) module. More concretely, to obtain appropriate queries, DQS first ensures a high recall to retain a large number of queries by the predicted confidence scores and then further picks out high-quality queries according to the estimated quality scores. DGA uniformly divides each reference box into grids as the reference points and then utilizes the predicted offsets to achieve a flexible receptive field, allowing the network to focus on relevant regions and capture more informative features. Extensive ablation studies on DQS and DGA demonstrate its effectiveness. Furthermore, our SEED achieves state-of-the-art detection performance on both the large-scale Waymo and nuScenes datasets, illustrating the superiority of our proposed method. The code is available at https://github.com/happinesslz/SEED
Authors: Jinghua Hou, Tong Wang, Xiaoqing Ye, Zhe Liu, Shi Gong, Xiao Tan, Errui Ding, Jingdong Wang, Xiang Bai
Abstract: Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection. Despite the success of some existing multi-view 3D detectors utilizing pixel-wise depth supervision, they overlook two significant phenomena: 1) the depth supervision obtained from LiDAR points is usually distributed on the surface of the object, which is not so friendly to existing DETR-based 3D detectors due to the lack of the depth of 3D object center; 2) for distant objects, fine-grained depth estimation of the whole object is more challenging. Therefore, we argue that the object-wise depth (or 3D center of the object) is essential for accurate detection. In this paper, we propose a new multi-view 3D object detector named OPEN, whose main idea is to effectively inject object-wise depth information into the network through our proposed object-wise position embedding. Specifically, we first employ an object-wise depth encoder, which takes the pixel-wise depth map as a prior, to accurately estimate the object-wise depth. Then, we utilize the proposed object-wise position embedding to encode the object-wise depth information into the transformer decoder, thereby producing 3D object-aware features for final detection. Extensive experiments verify the effectiveness of our proposed method. Furthermore, OPEN achieves a new state-of-the-art performance with 64.4% NDS and 56.7% mAP on the nuScenes test benchmark.
Authors: Rakesh John Amala Arokia Nathan, Sigrid Strand, Daniel Mehrwald, Dmitriy Shutin, Oliver Bimber
Abstract: Swarms of drones offer an increased sensing aperture, and having them mimic behaviors of natural swarms enhances sampling by adapting the aperture to local conditions. We demonstrate that such an approach makes detecting and tracking heavily occluded targets practically feasible. While object classification applied to conventional aerial images generalizes poorly the randomness of occlusion and is therefore inefficient even under lightly occluded conditions, anomaly detection applied to synthetic aperture integral images is robust for dense vegetation, such as forests, and is independent of pre-trained classes. Our autonomous swarm searches the environment for occurrences of the unknown or unexpected, tracking them while continuously adapting its sampling pattern to optimize for local viewing conditions. In our real-life field experiments with a swarm of six drones, we achieved an average positional accuracy of 0.39 m with an average precision of 93.2% and an average recall of 95.9%. Here, adapted particle swarm optimization considers detection confidences and predicted target appearance. We show that sensor noise can effectively be included in the synthetic aperture image integration process, removing the need for a computationally costly optimization of high-dimensional parameter spaces. Finally, we present a complete hard- and software framework that supports low-latency transmission (approx. 80 ms round-trip time) and fast processing (approx. 600 ms per formation step) of extensive (70-120 Mbit/s) video and telemetry data, and swarm control for swarms of up to ten drones.
Authors: Haonan Wang, Jie Liu, Jie Tang, Gangshan Wu, Bo Xu, Yanbing Chou, Yong Wang
Abstract: In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric quantities and computational overhead. Efficient human pose estimation remains a hurdle, especially for whole-body pose estimation with numerous keypoints. While most current methods for efficient human pose estimation primarily rely on CNNs, we propose the Group-based Token Pruning Transformer (GTPT) that fully harnesses the advantages of the Transformer. GTPT alleviates the computational burden by gradually introducing keypoints in a coarse-to-fine manner. It minimizes the computation overhead while ensuring high performance. Besides, GTPT groups keypoint tokens and prunes visual tokens to improve model performance while reducing redundancy. We propose the Multi-Head Group Attention (MHGA) between different groups to achieve global interaction with little computational overhead. We conducted experiments on COCO and COCO-WholeBody. Compared to other methods, the experimental results show that GTPT can achieve higher performance with less computation, especially in whole-body with numerous keypoints.
Authors: Antoine Legrand, Renaud Detry, Christophe De Vleeschouwer
Abstract: This work introduces a novel augmentation method that increases the diversity of a train set to improve the generalization abilities of a 6D pose estimation network. For this purpose, a Neural Radiance Field is trained from synthetic images and exploited to generate an augmented set. Our method enriches the initial set by enabling the synthesis of images with (i) unseen viewpoints, (ii) rich illumination conditions through appearance extrapolation, and (iii) randomized textures. We validate our augmentation method on the challenging use-case of spacecraft pose estimation and show that it significantly improves the pose estimation generalization capabilities. On the SPEED+ dataset, our method reduces the error on the pose by 50% on both target domains.
Authors: Friedhelm Hamann, Ziyun Wang, Ioannis Asmanis, Kenneth Chaney, Guillermo Gallego, Kostas Daniilidis
Abstract: Current optical flow and point-tracking methods rely heavily on synthetic datasets. Event cameras are novel vision sensors with advantages in challenging visual conditions, but state-of-the-art frame-based methods cannot be easily adapted to event data due to the limitations of current event simulators. We introduce a novel self-supervised loss combining the Contrast Maximization framework with a non-linear motion prior in the form of pixel-level trajectories and propose an efficient solution to solve the high-dimensional assignment problem between non-linear trajectories and events. Their effectiveness is demonstrated in two scenarios: In dense continuous-time motion estimation, our method improves the zero-shot performance of a synthetically trained model on the real-world dataset EVIMO2 by 29%. In optical flow estimation, our method elevates a simple UNet to achieve state-of-the-art performance among self-supervised methods on the DSEC optical flow benchmark. Our code is available at https://github.com/tub-rip/MotionPriorCMax.
Authors: Shubham Juneja, Povilas Daniu\v{s}is, Virginijus Marcinkevi\v{c}ius
Abstract: In this article, we focus on the pre-training of visual autonomous driving agents in the context of imitation learning. Current methods often rely on a classification-based pre-training, which we hypothesise to be holding back from extending capabilities of implicit image understanding. We propose pre-training the visual encoder of a driving agent using the self-distillation with no labels (DINO) method, which relies on a self-supervised learning paradigm.% and is trained on an unrelated task. Our experiments in CARLA environment in accordance with the Leaderboard benchmark reveal that the proposed pre-training is more efficient than classification-based pre-training, and is on par with the recently proposed pre-training based on visual place recognition (VPRPre).
Authors: Dingxin Zhang, Jianhui Yu, Tengfei Xue, Chaoyi Zhang, Dongnan Liu, Weidong Cai
Abstract: Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing robustness through various strategies, there still remains a gap in comprehensive analyzes from the standpoint of network architecture design. Unlike traditional methods that rely on generic techniques, our approach optimizes model robustness to noise corruption through network architecture design. Inspired by the token-mixing technique applied in 2D images, we propose Set-Mixer, a noise-robust aggregation module which facilitates communication among all points to extract geometric shape information and mitigating the influence of individual noise points. A sorting strategy is designed to enable our module to be invariant to point permutation, which also tackles the unordered structure of point cloud and introduces consistent relative spatial information. Experiments conducted on ModelNet40-C indicate that Set-Mixer significantly enhances the model performance on noisy point clouds, underscoring its potential to advance real-world applicability in 3D recognition and perception tasks.
Authors: Yuqi Jiang, Xudong Lu, Qian Jin, Qi Sun, Hanming Wu, Cheng Zhuo
Abstract: Intelligence is key to advancing integrated circuit (IC) fabrication. Recent breakthroughs in Large Multimodal Models (LMMs) have unlocked unparalleled abilities in understanding images and text, fostering intelligent fabrication. Leveraging the power of LMMs, we introduce FabGPT, a customized IC fabrication large multimodal model for wafer defect knowledge query. FabGPT manifests expertise in conducting defect detection in Scanning Electron Microscope (SEM) images, performing root cause analysis, and providing expert question-answering (Q&A) on fabrication processes. FabGPT matches enhanced multimodal features to automatically detect minute defects under complex wafer backgrounds and reduce the subjectivity of manual threshold settings. Besides, the proposed modulation module and interactive corpus training strategy embed wafer defect knowledge into the pre-trained model, effectively balancing Q&A queries related to defect knowledge and original knowledge and mitigating the modality bias issues. Experiments on in-house fab data (SEM-WaD) show that our FabGPT achieves significant performance improvement in wafer defect detection and knowledge querying.
Authors: Linhao Qu, Dingkang Yang, Dan Huang, Qinhao Guo, Rongkui Luo, Shaoting Zhang, Xiaosong Wang
Abstract: Current multi-instance learning algorithms for pathology image analysis often require a substantial number of Whole Slide Images for effective training but exhibit suboptimal performance in scenarios with limited learning data. In clinical settings, restricted access to pathology slides is inevitable due to patient privacy concerns and the prevalence of rare or emerging diseases. The emergence of the Few-shot Weakly Supervised WSI Classification accommodates the significant challenge of the limited slide data and sparse slide-level labels for diagnosis. Prompt learning based on the pre-trained models (\eg, CLIP) appears to be a promising scheme for this setting; however, current research in this area is limited, and existing algorithms often focus solely on patch-level prompts or confine themselves to language prompts. This paper proposes a multi-instance prompt learning framework enhanced with pathology knowledge, \ie, integrating visual and textual prior knowledge into prompts at both patch and slide levels. The training process employs a combination of static and learnable prompts, effectively guiding the activation of pre-trained models and further facilitating the diagnosis of key pathology patterns. Lightweight Messenger (self-attention) and Summary (attention-pooling) layers are introduced to model relationships between patches and slides within the same patient data. Additionally, alignment-wise contrastive losses ensure the feature-level alignment between visual and textual learnable prompts for both patches and slides. Our method demonstrates superior performance in three challenging clinical tasks, significantly outperforming comparative few-shot methods.
Authors: Hoonhee Cho, Jae-Young Kang, Kuk-Jin Yoon
Abstract: Event cameras are dynamic vision sensors inspired by the biological retina, characterized by their high dynamic range, high temporal resolution, and low power consumption. These features make them capable of perceiving 3D environments even in extreme conditions. Event data is continuous across the time dimension, which allows a detailed description of each pixel's movements. To fully utilize the temporally dense and continuous nature of event cameras, we propose a novel temporal event stereo, a framework that continuously uses information from previous time steps. This is accomplished through the simultaneous training of an event stereo matching network alongside stereoscopic flow, a new concept that captures all pixel movements from stereo cameras. Since obtaining ground truth for optical flow during training is challenging, we propose a method that uses only disparity maps to train the stereoscopic flow. The performance of event-based stereo matching is enhanced by temporally aggregating information using the flows. We have achieved state-of-the-art performance on the MVSEC and the DSEC datasets. The method is computationally efficient, as it stacks previous information in a cascading manner. The code is available at https://github.com/mickeykang16/TemporalEventStereo.
Authors: Kun-Yu Lin, Jiaming Zhou, Wei-Shi Zheng
Abstract: We study the domain adaptation task for action recognition, namely domain adaptive action recognition, which aims to effectively transfer action recognition power from a label-sufficient source domain to a label-free target domain. Since actions are performed by humans, it is crucial to exploit human cues in videos when recognizing actions across domains. However, existing methods are prone to losing human cues but prefer to exploit the correlation between non-human contexts and associated actions for recognition, and the contexts of interest agnostic to actions would reduce recognition performance in the target domain. To overcome this problem, we focus on uncovering human-centric action cues for domain adaptive action recognition, and our conception is to investigate two aspects of human-centric action cues, namely human cues and human-context interaction cues. Accordingly, our proposed Human-Centric Transformer (HCTransformer) develops a decoupled human-centric learning paradigm to explicitly concentrate on human-centric action cues in domain-variant video feature learning. Our HCTransformer first conducts human-aware temporal modeling by a human encoder, aiming to avoid a loss of human cues during domain-invariant video feature learning. Then, by a Transformer-like architecture, HCTransformer exploits domain-invariant and action-correlated contexts by a context encoder, and further models domain-invariant interaction between humans and action-correlated contexts. We conduct extensive experiments on three benchmarks, namely UCF-HMDB, Kinetics-NecDrone and EPIC-Kitchens-UDA, and the state-of-the-art performance demonstrates the effectiveness of our proposed HCTransformer.
Authors: Zheyuan Zhou, Le Wang, Naiyu Fang, Zili Wang, Lemiao Qiu, Shuyou Zhang
Abstract: 3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing. Embedding-based and reconstruction-based approaches are among the most popular and successful methods. However, there are two major challenges to the practical application of the current approaches: 1) the embedded models suffer the prohibitive computational and storage due to the memory bank structure; 2) the reconstructive models based on the MAE mechanism fail to detect anomalies in the unmasked regions. In this paper, we propose R3D-AD, reconstructing anomalous point clouds by diffusion model for precise 3D anomaly detection. Our approach capitalizes on the data distribution conversion of the diffusion process to entirely obscure the input's anomalous geometry. It step-wisely learns a strict point-level displacement behavior, which methodically corrects the aberrant points. To increase the generalization of the model, we further present a novel 3D anomaly simulation strategy named Patch-Gen to generate realistic and diverse defect shapes, which narrows the domain gap between training and testing. Our R3D-AD ensures a uniform spatial transformation, which allows straightforwardly generating anomaly results by distance comparison. Extensive experiments show that our R3D-AD outperforms previous state-of-the-art methods, achieving 73.4% Image-level AUROC on the Real3D-AD dataset and 74.9% Image-level AUROC on the Anomaly-ShapeNet dataset with an exceptional efficiency.
Authors: Keshav Bimbraw, Ye Wang, Jing Liu, Toshiaki Koike-Akino
Abstract: Large vision-language models (LVLMs), such as the Generative Pre-trained Transformer 4-omni (GPT-4o), are emerging multi-modal foundation models which have great potential as powerful artificial-intelligence (AI) assistance tools for a myriad of applications, including healthcare, industrial, and academic sectors. Although such foundation models perform well in a wide range of general tasks, their capability without fine-tuning is often limited in specialized tasks. However, full fine-tuning of large foundation models is challenging due to enormous computation/memory/dataset requirements. We show that GPT-4o can decode hand gestures from forearm ultrasound data even with no fine-tuning, and improves with few-shot, in-context learning.
Authors: Chunliang Li, Wencheng Han, Junbo Yin, Sanyuan Zhao, Jianbing Shen
Abstract: Concurrent processing of multiple autonomous driving 3D perception tasks within the same spatiotemporal scene poses a significant challenge, in particular due to the computational inefficiencies and feature competition between tasks when using traditional multi-task learning approaches. This paper addresses these issues by proposing a novel unified representation, RepVF, which harmonizes the representation of various perception tasks such as 3D object detection and 3D lane detection within a single framework. RepVF characterizes the structure of different targets in the scene through a vector field, enabling a single-head, multi-task learning model that significantly reduces computational redundancy and feature competition. Building upon RepVF, we introduce RFTR, a network designed to exploit the inherent connections between different tasks by utilizing a hierarchical structure of queries that implicitly model the relationships both between and within tasks. This approach eliminates the need for task-specific heads and parameters, fundamentally reducing the conflicts inherent in traditional multi-task learning paradigms. We validate our approach by combining labels from the OpenLane dataset with the Waymo Open dataset. Our work presents a significant advancement in the efficiency and effectiveness of multi-task perception in autonomous driving, offering a new perspective on handling multiple 3D perception tasks synchronously and in parallel. The code will be available at: https://github.com/jbji/RepVF
Authors: Sangeetha K, Balaji VS, Kamalesh P, Anirudh Ganapathy PS
Abstract: Hand gestures have evolved into a natural and intuitive means of engaging with technology. The objective of this research is to develop a robust system that can accurately recognize and classify hand gestures representing numbers. The proposed approach involves collecting a dataset of hand gesture images, preprocessing and enhancing the images, extracting relevant features, and training a machine learning model. The advancement of computer vision technology and object detection techniques, in conjunction with OpenCV's capability to analyze and comprehend hand gestures, presents a chance to transform the identification of numerical digits and its potential applications. The advancement of computer vision technology and object identification technologies, along with OpenCV's capacity to analyze and interpret hand gestures, has the potential to revolutionize human interaction, boosting people's access to information, education, and employment opportunities. Keywords: Computer Vision, Machine learning, Deep Learning, Neural Networks
Authors: Jae Myung Kim, Jessica Bader, Stephan Alaniz, Cordelia Schmid, Zeynep Akata
Abstract: While text-to-image diffusion models have been shown to achieve state-of-the-art results in image synthesis, they have yet to prove their effectiveness in downstream applications. Previous work has proposed to generate data for image classifier training given limited real data access. However, these methods struggle to generate in-distribution images or depict fine-grained features, thereby hindering the generalization of classification models trained on synthetic datasets. We propose DataDream, a framework for synthesizing classification datasets that more faithfully represents the real data distribution when guided by few-shot examples of the target classes. DataDream fine-tunes LoRA weights for the image generation model on the few real images before generating the training data using the adapted model. We then fine-tune LoRA weights for CLIP using the synthetic data to improve downstream image classification over previous approaches on a large variety of datasets. We demonstrate the efficacy of DataDream through extensive experiments, surpassing state-of-the-art classification accuracy with few-shot data across 7 out of 10 datasets, while being competitive on the other 3. Additionally, we provide insights into the impact of various factors, such as the number of real-shot and generated images as well as the fine-tuning compute on model performance. The code is available at https://github.com/ExplainableML/DataDream.
Authors: Xiao Li, Yining Liu, Na Dong, Sitian Qin, Xiaolin Hu
Abstract: Deep learning-based object recognition systems can be easily fooled by various adversarial perturbations. One reason for the weak robustness may be that they do not have part-based inductive bias like the human recognition process. Motivated by this, several part-based recognition models have been proposed to improve the adversarial robustness of recognition. However, due to the lack of part annotations, the effectiveness of these methods is only validated on small-scale nonstandard datasets. In this work, we propose PIN++, short for PartImageNet++, a dataset providing high-quality part segmentation annotations for all categories of ImageNet-1K (IN-1K). With these annotations, we build part-based methods directly on the standard IN-1K dataset for robust recognition. Different from previous two-stage part-based models, we propose a Multi-scale Part-supervised Model (MPM), to learn a robust representation with part annotations. Experiments show that MPM yielded better adversarial robustness on the large-scale IN-1K over strong baselines across various attack settings. Furthermore, MPM achieved improved robustness on common corruptions and several out-of-distribution datasets. The dataset, together with these results, enables and encourages researchers to explore the potential of part-based models in more real applications.
Authors: Shravan Nayak, Kanishk Jain, Rabiul Awal, Siva Reddy, Sjoerd van Steenkiste, Lisa Anne Hendricks, Karolina Sta\'nczak, Aishwarya Agrawal
Abstract: Foundation models and vision-language pre-training have notably advanced Vision Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their performance has been typically assessed on general scene understanding - recognizing objects, attributes, and actions - rather than cultural comprehension. This study introduces CulturalVQA, a visual question-answering benchmark aimed at assessing VLM's geo-diverse cultural understanding. We curate a collection of 2,378 image-question pairs with 1-5 answers per question representing cultures from 11 countries across 5 continents. The questions probe understanding of various facets of culture such as clothing, food, drinks, rituals, and traditions. Benchmarking VLMs on CulturalVQA, including GPT-4V and Gemini, reveals disparity in their level of cultural understanding across regions, with strong cultural understanding capabilities for North America while significantly lower performance for Africa. We observe disparity in their performance across cultural facets too, with clothing, rituals, and traditions seeing higher performances than food and drink. These disparities help us identify areas where VLMs lack cultural understanding and demonstrate the potential of CulturalVQA as a comprehensive evaluation set for gauging VLM progress in understanding diverse cultures.
Authors: Penglei Gao, Kai Yao, Tiandi Ye, Steven Wang, Yuan Yao, Xiaofeng Wang
Abstract: In this paper, we tackle the recently popular topic of generating 360-degree images given the conventional narrow field of view (NFoV) images that could be taken from a single camera or cellphone. This task aims to predict the reasonable and consistent surroundings from the NFoV images. Existing methods for feature extraction and fusion, often built with transformer-based architectures, incur substantial memory usage and computational expense. They also have limitations in maintaining visual continuity across the entire 360-degree images, which could cause inconsistent texture and style generation. To solve the aforementioned issues, we propose a novel text-guided out-painting framework equipped with a State-Space Model called Mamba to utilize its long-sequence modelling and spatial continuity. Furthermore, incorporating textual information is an effective strategy for guiding image generation, enriching the process with detailed context and increasing diversity. Efficiently extracting textual features and integrating them with image attributes presents a significant challenge for 360-degree image out-painting. To address this, we develop two modules, Visual-textual Consistency Refiner (VCR) and Global-local Mamba Adapter (GMA). VCR enhances contextual richness by fusing the modified text features with the image features, while GMA provides adaptive state-selective conditions by capturing the information flow from global to local representations. Our proposed method achieves state-of-the-art performance with extensive experiments on two broadly used 360-degree image datasets, including indoor and outdoor settings.
Authors: Soroush Mehraban, Mohammad Javad Rajabi, Babak Taati
Abstract: Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition. However, we show that, unlike contrastive learning approaches, they do not produce well-separated clusters. Additionally, these methods struggle with generalization in few-shot settings. To address these issues, we propose Self-supervised Tuning for 3D Action Recognition in Skeleton sequences (STARS). Specifically, STARS first uses a masked prediction stage using an encoder-decoder architecture. It then employs nearest-neighbor contrastive learning to partially tune the weights of the encoder, enhancing the formation of semantic clusters for different actions. By tuning the encoder for a few epochs, and without using hand-crafted data augmentations, STARS achieves state-of-the-art self-supervised results in various benchmarks, including NTU-60, NTU-120, and PKU-MMD. In addition, STARS exhibits significantly better results than masked prediction models in few-shot settings, where the model has not seen the actions throughout pretraining. Project page: https://soroushmehraban.github.io/stars/
Authors: Yuanhao Zhai, Kevin Lin, Linjie Li, Chung-Ching Lin, Jianfeng Wang, Zhengyuan Yang, David Doermann, Junsong Yuan, Zicheng Liu, Lijuan Wang
Abstract: Significant advances have been made in human-centric video generation, yet the joint video-depth generation problem remains underexplored. Most existing monocular depth estimation methods may not generalize well to synthesized images or videos, and multi-view-based methods have difficulty controlling the human appearance and motion. In this work, we present IDOL (unIfied Dual-mOdal Latent diffusion) for high-quality human-centric joint video-depth generation. Our IDOL consists of two novel designs. First, to enable dual-modal generation and maximize the information exchange between video and depth generation, we propose a unified dual-modal U-Net, a parameter-sharing framework for joint video and depth denoising, wherein a modality label guides the denoising target, and cross-modal attention enables the mutual information flow. Second, to ensure a precise video-depth spatial alignment, we propose a motion consistency loss that enforces consistency between the video and depth feature motion fields, leading to harmonized outputs. Additionally, a cross-attention map consistency loss is applied to align the cross-attention map of the video denoising with that of the depth denoising, further facilitating spatial alignment. Extensive experiments on the TikTok and NTU120 datasets show our superior performance, significantly surpassing existing methods in terms of video FVD and depth accuracy.
Authors: Yaoting Wang, Peiwen Sun, Yuanchao Li, Honggang Zhang, Di Hu
Abstract: The Audio-Visual Segmentation (AVS) task aims to segment sounding objects in the visual space using audio cues. However, in this work, it is recognized that previous AVS methods show a heavy reliance on detrimental segmentation preferences related to audible objects, rather than precise audio guidance. We argue that the primary reason is that audio lacks robust semantics compared to vision, especially in multi-source sounding scenes, resulting in weak audio guidance over the visual space. Motivated by the the fact that text modality is well explored and contains rich abstract semantics, we propose leveraging text cues from the visual scene to enhance audio guidance with the semantics inherent in text. Our approach begins by obtaining scene descriptions through an off-the-shelf image captioner and prompting a frozen large language model to deduce potential sounding objects as text cues. Subsequently, we introduce a novel semantics-driven audio modeling module with a dynamic mask to integrate audio features with text cues, leading to representative sounding object features. These features not only encompass audio cues but also possess vivid semantics, providing clearer guidance in the visual space. Experimental results on AVS benchmarks validate that our method exhibits enhanced sensitivity to audio when aided by text cues, achieving highly competitive performance on all three subsets. Project page: \href{https://github.com/GeWu-Lab/Sounding-Object-Segmentation-Preference}{https://github.com/GeWu-Lab/Sounding-Object-Segmentation-Preference}
URLs: https://github.com/GeWu-Lab/Sounding-Object-Segmentation-Preference, https://github.com/GeWu-Lab/Sounding-Object-Segmentation-Preference
Authors: Yaoting Wang, Peiwen Sun, Dongzhan Zhou, Guangyao Li, Honggang Zhang, Di Hu
Abstract: Traditional reference segmentation tasks have predominantly focused on silent visual scenes, neglecting the integral role of multimodal perception and interaction in human experiences. In this work, we introduce a novel task called Reference Audio-Visual Segmentation (Ref-AVS), which seeks to segment objects within the visual domain based on expressions containing multimodal cues. Such expressions are articulated in natural language forms but are enriched with multimodal cues, including audio and visual descriptions. To facilitate this research, we construct the first Ref-AVS benchmark, which provides pixel-level annotations for objects described in corresponding multimodal-cue expressions. To tackle the Ref-AVS task, we propose a new method that adequately utilizes multimodal cues to offer precise segmentation guidance. Finally, we conduct quantitative and qualitative experiments on three test subsets to compare our approach with existing methods from related tasks. The results demonstrate the effectiveness of our method, highlighting its capability to precisely segment objects using multimodal-cue expressions. Dataset is available at \href{https://gewu-lab.github.io/Ref-AVS}{https://gewu-lab.github.io/Ref-AVS}.
URLs: https://gewu-lab.github.io/Ref-AVS, https://gewu-lab.github.io/Ref-AVS
Authors: Nirat Saini, Navaneeth Bodla, Ashish Shrivastava, Avinash Ravichandran, Xiao Zhang, Abhinav Shrivastava, Bharat Singh
Abstract: We introduce InVi, an approach for inserting or replacing objects within videos (referred to as inpainting) using off-the-shelf, text-to-image latent diffusion models. InVi targets controlled manipulation of objects and blending them seamlessly into a background video unlike existing video editing methods that focus on comprehensive re-styling or entire scene alterations. To achieve this goal, we tackle two key challenges. Firstly, for high quality control and blending, we employ a two-step process involving inpainting and matching. This process begins with inserting the object into a single frame using a ControlNet-based inpainting diffusion model, and then generating subsequent frames conditioned on features from an inpainted frame as an anchor to minimize the domain gap between the background and the object. Secondly, to ensure temporal coherence, we replace the diffusion model's self-attention layers with extended-attention layers. The anchor frame features serve as the keys and values for these layers, enhancing consistency across frames. Our approach removes the need for video-specific fine-tuning, presenting an efficient and adaptable solution. Experimental results demonstrate that InVi achieves realistic object insertion with consistent blending and coherence across frames, outperforming existing methods.
Authors: Walter Simoncini, Spyros Gidaris, Andrei Bursuc, Yuki M. Asano
Abstract: This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of vision encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. These are projected to a lower dimension and then concatenated with the model's embedding. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio. Across backbones spanning various sizes and pretraining strategies, FUNGI features provide consistent performance improvements over the embeddings. We also show that using FUNGI features can benefit linear classification and image retrieval, and that they significantly improve the retrieval-based in-context scene understanding abilities of pretrained models, for example improving upon DINO by +17% for semantic segmentation - without any training.
Authors: Bocheng Zou, Mu Cai, Jianrui Zhang, Yong Jae Lee
Abstract: In the realm of vision models, the primary mode of representation is using pixels to rasterize the visual world. Yet this is not always the best or unique way to represent visual content, especially for designers and artists who depict the world using geometry primitives such as polygons. Vector graphics (VG), on the other hand, offer a textual representation of visual content, which can be more concise and powerful for content like cartoons or sketches. Recent studies have shown promising results on processing vector graphics with capable Large Language Models (LLMs). However, such works focus solely on qualitative results, understanding, or a specific type of vector graphics. We propose VGBench, a comprehensive benchmark for LLMs on handling vector graphics through diverse aspects, including (a) both visual understanding and generation, (b) evaluation of various vector graphics formats, (c) diverse question types, (d) wide range of prompting techniques, (e) under multiple LLMs. Evaluating on our collected 4279 understanding and 5845 generation samples, we find that LLMs show strong capability on both aspects while exhibiting less desirable performance on low-level formats (SVG). Both data and evaluation pipeline will be open-sourced at https://vgbench.github.io.
Authors: Abel C. H. Chen
Abstract: With the maturation of quantum computing technology, many cryptographic methods are gradually facing threats from quantum computing. Although the Grover algorithm can accelerate search speeds, current research indicates that the Advanced Encryption Standard (AES) method can still enhance security by increasing the length of the secret key. However, the AES method involves multiple modes in implementation, and not all modes are secure. Therefore, this study proposes a normalized Gini impurity (NGI) to verify the security of each mode, using encrypted images as a case study for empirical analysis. Furthermore, this study primarily compares the Electronic Codebook (ECB) mode, Cipher Block Chaining (CBC) mode, Counter (CTR) mode, Counter with CBC-Message Authentication Code (MAC) (CCM) mode, and Galois Counter Mode (GCM).
Authors: Emiel van Miltenburg
Abstract: This short position paper provides a manually curated list of non-English image captioning datasets (as of May 2024). Through this list, we can observe the dearth of datasets in different languages: only 23 different languages are represented. With the addition of the Crossmodal-3600 dataset (Thapliyal et al., 2022, 36 languages) this number increases somewhat, but still this number is tiny compared to the thousands of spoken languages that exist. This paper closes with some open questions for the field of Vision & Language.
Authors: Ling Zhang, Boxiang Yun, Xingran Xie, Qingli Li, Xinxing Li, Yan Wang
Abstract: Prediction of genetic biomarkers, e.g., microsatellite instability and BRAF in colorectal cancer is crucial for clinical decision making. In this paper, we propose a whole slide image (WSI) based genetic biomarker prediction method via prompting techniques. Our work aims at addressing the following challenges: (1) extracting foreground instances related to genetic biomarkers from gigapixel WSIs, and (2) the interaction among the fine-grained pathological components in WSIs.Specifically, we leverage large language models to generate medical prompts that serve as prior knowledge in extracting instances associated with genetic biomarkers. We adopt a coarse-to-fine approach to mine biomarker information within the tumor microenvironment. This involves extracting instances related to genetic biomarkers using coarse medical prior knowledge, grouping pathology instances into fine-grained pathological components and mining their interactions. Experimental results on two colorectal cancer datasets show the superiority of our method, achieving 91.49% in AUC for MSI classification. The analysis further shows the clinical interpretability of our method. Code is publicly available at https://github.com/DeepMed-Lab-ECNU/PromptBio.
Authors: Young Kyun Jang, Junmo Kang, Yong Jae Lee, Donghyun Kim
Abstract: While advancements in Vision Language Models (VLMs) have significantly improved the alignment of visual and textual data, these models primarily focus on aligning images with short descriptive captions. This focus limits their ability to handle complex text interactions, particularly with longer texts such as lengthy captions or documents, which have not been extensively explored yet. In this paper, we introduce Meet At The Embedding (MATE), a novel approach that combines the capabilities of VLMs with Large Language Models (LLMs) to overcome this challenge without the need for additional image-long text pairs. Specifically, we replace the text encoder of the VLM with a pretrained LLM-based encoder that excels in understanding long texts. To bridge the gap between VLM and LLM, MATE incorporates a projection module that is trained in a multi-stage manner. It starts by aligning the embeddings from the VLM text encoder with those from the LLM using extensive text pairs. This module is then employed to seamlessly align image embeddings closely with LLM embeddings. We propose two new cross-modal retrieval benchmarks to assess the task of connecting images with long texts (lengthy captions / documents). Extensive experimental results demonstrate that MATE effectively connects images with long texts, uncovering diverse semantic relationships.
Authors: Ali Ghadami, Alireza Taheri, Ali Meghdari
Abstract: Sign language is an essential means of communication for millions of people around the world and serves as their primary language. However, most communication tools are developed for spoken and written languages which can cause problems and difficulties for the deaf and hard of hearing community. By developing a sign language recognition system, we can bridge this communication gap and enable people who use sign language as their main form of expression to better communicate with people and their surroundings. This recognition system increases the quality of health services, improves public services, and creates equal opportunities for the deaf community. This research aims to recognize Iranian Sign Language words with the help of the latest deep learning tools such as transformers. The dataset used includes 101 Iranian Sign Language words frequently used in academic environments such as universities. The network used is a combination of early fusion and late fusion transformer encoder-based networks optimized with the help of genetic algorithm. The selected features to train this network include hands and lips key points, and the distance and angle between hands extracted from the sign videos. Also, in addition to the training model for the classes, the embedding vectors of words are used as multi-task learning to have smoother and more efficient training. This model was also tested on sentences generated from our word dataset using a windowing technique for sentence translation. Finally, the sign language training software that provides real-time feedback to users with the help of the developed model, which has 90.2% accuracy on test data, was introduced, and in a survey, the effectiveness and efficiency of this type of sign language learning software and the impact of feedback were investigated.
Authors: Malitha Gunawardhana, Anuradha Kulathilaka, Jichao Zhao
Abstract: Atrial fibrillation (AFib) is the prominent cardiac arrhythmia in the world. It affects mostly the elderly population, with potential consequences such as stroke and heart failure in the absence of necessary treatments as soon as possible. The importance of atrial scarring in the development and progression of AFib has gained recognition, positioning late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) as a crucial technique for the non-invasive evaluation of atrial scar tissue. This review delves into the recent progress in segmenting atrial scars using LGE-MRIs, emphasizing the importance of precise scar measurement in the treatment and management of AFib. Initially, it provides a detailed examination of AFib. Subsequently, it explores the application of deep learning in this domain. The review culminates in a discussion of the latest research advancements in atrial scar segmentation using deep learning methods. By offering a thorough analysis of current technologies and their impact on AFib management strategies, this review highlights the integral role of deep learning in enhancing atrial scar segmentation and its implications for future therapeutic approaches.
Authors: Santiago Fern\'andez, Emilio Mart\'inez, Gabriel Varela, Pablo Mus\'e, Federico Larroca
Abstract: In this work, we address the problem of eavesdropping on digital video displays by analyzing the electromagnetic waves that unintentionally emanate from the cables and connectors, particularly HDMI. This problem is known as TEMPEST. Compared to the analog case (VGA), the digital case is harder due to a 10-bit encoding that results in a much larger bandwidth and non-linear mapping between the observed signal and the pixel's intensity. As a result, eavesdropping systems designed for the analog case obtain unclear and difficult-to-read images when applied to digital video. The proposed solution is to recast the problem as an inverse problem and train a deep learning module to map the observed electromagnetic signal back to the displayed image. However, this approach still requires a detailed mathematical analysis of the signal, firstly to determine the frequency at which to tune but also to produce training samples without actually needing a real TEMPEST setup. This saves time and avoids the need to obtain these samples, especially if several configurations are being considered. Our focus is on improving the average Character Error Rate in text, and our system improves this rate by over 60 percentage points compared to previous available implementations. The proposed system is based on widely available Software Defined Radio and is fully open-source, seamlessly integrated into the popular GNU Radio framework. We also share the dataset we generated for training, which comprises both simulated and over 1000 real captures. Finally, we discuss some countermeasures to minimize the potential risk of being eavesdropped by systems designed based on similar principles.
Authors: Shentong Mo, Russ Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang
Abstract: The Internet of Things (IoT) network integrating billions of smart physical devices embedded with sensors, software, and communication technologies is a critical and rapidly expanding component of our modern world. The IoT ecosystem provides a rich source of real-world modalities such as motion, thermal, geolocation, imaging, depth, sensors, and audio to recognize the states of humans and physical objects. Machine learning presents a rich opportunity to automatically process IoT data at scale, enabling efficient inference for understanding human wellbeing, controlling physical devices, and interconnecting smart cities. To realize this potential, we introduce IoT-LM, an open-source large multisensory language model tailored for the IoT ecosystem. IoT-LM is enabled by two technical contributions: the first is MultiIoT, the most expansive unified IoT dataset to date, encompassing over 1.15 million samples from 12 modalities and 8 tasks prepared for multisensory pre-training and instruction-tuning. The second is a new multisensory multitask adapter layer to condition pre-trained large language models on multisensory IoT data. Not only does IoT-LM yield substantial improvements on 8 supervised IoT classification tasks, but it also demonstrates new interactive question-answering, reasoning, and dialog capabilities conditioned on IoT sensors. We release IoT-LM's data sources and new multisensory language modeling framework.
Authors: Md Rakibul Islam, Riad Hassan, Abdullah Nazib, Kien Nguyen, Clinton Fookes, Md Zahidul Islam
Abstract: Deep learning has achieved outstanding accuracy in medical image segmentation, particularly for objects like organs or tumors with smooth boundaries or large sizes. Whereas, it encounters significant difficulties with objects that have zigzag boundaries or are small in size, leading to a notable decrease in segmentation effectiveness. In this context, using a loss function that incorporates smoothness and volume information into a model's predictions offers a promising solution to these shortcomings. In this work, we introduce an Adaptive Focal Loss (A-FL) function designed to mitigate class imbalance by down-weighting the loss for easy examples that results in up-weighting the loss for hard examples and giving greater emphasis to challenging examples, such as small and irregularly shaped objects. The proposed A-FL involves dynamically adjusting a focusing parameter based on an object's surface smoothness, size information, and adjusting the class balancing parameter based on the ratio of targeted area to total area in an image. We evaluated the performance of the A-FL using ResNet50-encoded U-Net architecture on the Picai 2022 and BraTS 2018 datasets. On the Picai 2022 dataset, the A-FL achieved an Intersection over Union (IoU) of 0.696 and a Dice Similarity Coefficient (DSC) of 0.769, outperforming the regular Focal Loss (FL) by 5.5% and 5.4% respectively. It also surpassed the best baseline Dice-Focal by 2.0% and 1.2%. On the BraTS 2018 dataset, A-FL achieved an IoU of 0.883 and a DSC of 0.931. The comparative studies show that the proposed A-FL function surpasses conventional methods, including Dice Loss, Focal Loss, and their hybrid variants, in IoU, DSC, Sensitivity, and Specificity metrics. This work highlights A-FL's potential to improve deep learning models for segmenting clinically significant regions in medical images, leading to more precise and reliable diagnostic tools.
Authors: Kushan Choksi, Hongkai Chen, Karan Joshi, Sukrutha Jade, Shahriar Nirjon, Shan Lin
Abstract: Recent research has demonstrated the capability of physiological signals to infer both user emotional and attention responses. This presents an opportunity for leveraging widely available physiological sensors in smartwatches, to detect real-time emotional cues in users, such as stress and excitement. In this paper, we introduce SensEmo, a smartwatch-based system designed for affective learning. SensEmo utilizes multiple physiological sensor data, including heart rate and galvanic skin response, to recognize a student's motivation and concentration levels during class. This recognition is facilitated by a personalized emotion recognition model that predicts emotional states based on degrees of valence and arousal. With real-time emotion and attention feedback from students, we design a Markov decision process-based algorithm to enhance student learning effectiveness and experience by by offering suggestions to the teacher regarding teaching content and pacing. We evaluate SensEmo with 22 participants in real-world classroom environments. Evaluation results show that SensEmo recognizes student emotion with an average of 88.9% accuracy. More importantly, SensEmo assists students to achieve better online learning outcomes, e.g., an average of 40.0% higher grades in quizzes, over the traditional learning without student emotional feedback.
Authors: Xinyu Liu, Wuyang Li, Yixuan Yuan
Abstract: Semi-supervised medical image segmentation aims to leverage limited annotated data and rich unlabeled data to perform accurate segmentation. However, existing semi-supervised methods are highly dependent on the quality of self-generated pseudo labels, which are prone to incorrect supervision and confirmation bias. Meanwhile, they are insufficient in capturing the label distributions in latent space and suffer from limited generalization to unlabeled data. To address these issues, we propose a Latent Diffusion Label Rectification Model (DiffRect) for semi-supervised medical image segmentation. DiffRect first utilizes a Label Context Calibration Module (LCC) to calibrate the biased relationship between classes by learning the category-wise correlation in pseudo labels, then apply Latent Feature Rectification Module (LFR) on the latent space to formulate and align the pseudo label distributions of different levels via latent diffusion. It utilizes a denoising network to learn the coarse to fine and fine to precise consecutive distribution transportations. We evaluate DiffRect on three public datasets: ACDC, MS-CMRSEG 2019, and Decathlon Prostate. Experimental results demonstrate the effectiveness of DiffRect, e.g. it achieves 82.40\% Dice score on ACDC with only 1\% labeled scan available, outperforms the previous state-of-the-art by 4.60\% in Dice, and even rivals fully supervised performance. Code is released at \url{https://github.com/CUHK-AIM-Group/DiffRect}.
Authors: Peng Tang, Tobias Lasser
Abstract: Existing multi-modal approaches primarily focus on enhancing multi-label skin lesion classification performance through advanced fusion modules, often neglecting the associated rise in parameters. In clinical settings, both clinical and dermoscopy images are captured for diagnosis; however, dermoscopy images exhibit more crucial visual features for multi-label skin lesion classification. Motivated by this observation, we introduce a novel asymmetric multi-modal fusion method in this paper for efficient multi-label skin lesion classification. Our fusion method incorporates two innovative schemes. Firstly, we validate the effectiveness of our asymmetric fusion structure. It employs a light and simple network for clinical images and a heavier, more complex one for dermoscopy images, resulting in significant parameter savings compared to the symmetric fusion structure using two identical networks for both modalities. Secondly, in contrast to previous approaches using mutual attention modules for interaction between image modalities, we propose an asymmetric attention module. This module solely leverages clinical image information to enhance dermoscopy image features, considering clinical images as supplementary information in our pipeline. We conduct the extensive experiments on the seven-point checklist dataset. Results demonstrate the generality of our proposed method for both networks and Transformer structures, showcasing its superiority over existing methods We will make our code publicly available.
Authors: Lin Zhang, Wenbo Gao, Jie Yi, Yunyun Yang
Abstract: Multi-organ segmentation in medical image analysis is crucial for diagnosis and treatment planning. However, many factors complicate the task, including variability in different target categories and interference from complex backgrounds. In this paper, we utilize the knowledge of Deformable Convolution V3 (DCNv3) and multi-object segmentation to optimize our Spatially Adaptive Convolution Network (SACNet) in three aspects: feature extraction, model architecture, and loss constraint, simultaneously enhancing the perception of different segmentation targets. Firstly, we propose the Adaptive Receptive Field Module (ARFM), which combines DCNv3 with a series of customized block-level and architecture-level designs similar to transformers. This module can capture the unique features of different organs by adaptively adjusting the receptive field according to various targets. Secondly, we utilize ARFM as building blocks to construct the encoder-decoder of SACNet and partially share parameters between the encoder and decoder, making the network wider rather than deeper. This design achieves a shared lightweight decoder and a more parameter-efficient and effective framework. Lastly, we propose a novel continuity dynamic adjustment loss function, based on t-vMF dice loss and cross-entropy loss, to better balance easy and complex classes in segmentation. Experiments on 3D slice datasets from ACDC and Synapse demonstrate that SACNet delivers superior segmentation performance in multi-organ segmentation tasks compared to several existing methods.
Authors: Dimitris Papaioannou, Ioannis Christou, Nikos Anagnou, Aristotelis Chatziioannou
Abstract: Acute lymphoblastic leukemia (ALL) is a form of blood cancer that affects the white blood cells. ALL constitutes approximately 25% of pediatric cancers. Early diagnosis and treatment of ALL are crucial for improving patient outcomes. The task of identifying immature leukemic blasts from normal cells under the microscope can prove challenging, since the images of a healthy and cancerous cell appear similar morphologically. In this study, we propose a binary image classification model to assist in the diagnostic process of ALL. Our model takes as input microscopic images of blood samples and outputs a binary prediction of whether the sample is normal or cancerous. Our dataset consists of 10661 images out of 118 subjects. Deep learning techniques on convolutional neural network architectures were used to achieve accurate classification results. Our proposed method achieved 94.3% accuracy and could be used as an assisting tool for hematologists trying to predict the likelihood of a patient developing ALL.
Authors: Jianqiu Zhang
Abstract: Sora from Open AI has shown exceptional performance, yet it faces scrutiny over whether its technological prowess equates to an authentic comprehension of reality. Critics contend that it lacks a foundational grasp of the world, a deficiency V-JEPA from Meta aims to amend with its joint embedding approach. This debate is vital for steering the future direction of Artificial General Intelligence(AGI). We enrich this debate by developing a theory of productive imagination that generates a coherent world model based on Kantian philosophy. We identify three indispensable components of the coherent world model capable of genuine world understanding: representations of isolated objects, an a priori law of change across space and time, and Kantian categories. Our analysis reveals that Sora is limited because of its oversight of the a priori law of change and Kantian categories, flaws that are not rectifiable through scaling up the training. V-JEPA learns the context-dependent aspect of the a priori law of change. Yet it fails to fully comprehend Kantian categories and incorporate experience, leading us to conclude that neither system currently achieves a comprehensive world understanding. Nevertheless, each system has developed components essential to advancing an integrated AI productive imagination-understanding engine. Finally, we propose an innovative training framework for an AI productive imagination-understanding engine, centered around a joint embedding system designed to transform disordered perceptual input into a structured, coherent world model. Our philosophical analysis pinpoints critical challenges within contemporary video AI technologies and a pathway toward achieving an AI system capable of genuine world understanding, such that it can be applied for reasoning and planning in the future.
Authors: Henan Wang, Hanxin Zhu, Zhibo Chen
Abstract: Light field, as a new data representation format in multimedia, has the ability to capture both intensity and direction of light rays. However, the additional angular information also brings a large volume of data. Classical coding methods are not effective to describe the relationship between different views, leading to redundancy left. To address this problem, we propose a novel light field compression scheme based on implicit neural representation to reduce redundancies between views. We store the information of a light field image implicitly in an neural network and adopt model compression methods to further compress the implicit representation. Extensive experiments have demonstrated the effectiveness of our proposed method, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods.
Authors: Marawan Elbatel, Hualiang Wang, Jixiang Chen, Hao Wang, Xiaomeng Li
Abstract: Federated semi-supervised learning (FedSemi) refers to scenarios where there may be clients with fully labeled data, clients with partially labeled, and even fully unlabeled clients while preserving data privacy. However, challenges arise from client drift due to undefined heterogeneous class distributions and erroneous pseudo-labels. Existing FedSemi methods typically fail to aggregate models from unlabeled clients due to their inherent unreliability, thus overlooking unique information from their heterogeneous data distribution, leading to sub-optimal results. In this paper, we enable unlabeled client aggregation through SemiAnAgg, a novel Semi-supervised Anchor-Based federated Aggregation. SemiAnAgg learns unlabeled client contributions via an anchor model, effectively harnessing their informative value. Our key idea is that by feeding local client data to the same global model and the same consistently initialized anchor model (i.e., random model), we can measure the importance of each unlabeled client accordingly. Extensive experiments demonstrate that SemiAnAgg achieves new state-of-the-art results on four widely used FedSemi benchmarks, leading to substantial performance improvements: a 9% increase in accuracy on CIFAR-100 and a 7.6% improvement in recall on the medical dataset ISIC-18, compared with prior state-of-the-art. Code is available at: https://github.com/xmed-lab/SemiAnAgg.
Authors: Maziar Sabouri, Shadab Ahamed, Azin Asadzadeh, Atlas Haddadi Avval, Soroush Bagheri, Mohsen Arabi, Seyed Rasoul Zakavi, Emran Askari, Ali Rasouli, Atena Aghaee, Mohaddese Sehati, Fereshteh Yousefirizi, Carlos Uribe, Ghasem Hajianfar, Habib Zaidi, Arman Rahmim
Abstract: The objective of this study was to develop an automated pipeline that enhances thyroid disease classification using thyroid scintigraphy images, aiming to decrease assessment time and increase diagnostic accuracy. Anterior thyroid scintigraphy images from 2,643 patients were collected and categorized into diffuse goiter (DG), multinodal goiter (MNG), and thyroiditis (TH) based on clinical reports, and then segmented by an expert. A ResUNet model was trained to perform auto-segmentation. Radiomic features were extracted from both physician (scenario 1) and ResUNet segmentations (scenario 2), followed by omitting highly correlated features using Spearman's correlation, and feature selection using Recursive Feature Elimination (RFE) with XGBoost as the core. All models were trained under leave-one-center-out cross-validation (LOCOCV) scheme, where nine instances of algorithms were iteratively trained and validated on data from eight centers and tested on the ninth for both scenarios separately. Segmentation performance was assessed using the Dice similarity coefficient (DSC), while classification performance was assessed using metrics, such as precision, recall, F1-score, accuracy, area under the Receiver Operating Characteristic (ROC AUC), and area under the precision-recall curve (PRC AUC). ResUNet achieved DSC values of 0.84$\pm$0.03, 0.71$\pm$0.06, and 0.86$\pm$0.02 for MNG, TH, and DG, respectively. Classification in scenario 1 achieved an accuracy of 0.76$\pm$0.04 and a ROC AUC of 0.92$\pm$0.02 while in scenario 2, classification yielded an accuracy of 0.74$\pm$0.05 and a ROC AUC of 0.90$\pm$0.02. The automated pipeline demonstrated comparable performance to physician segmentations on several classification metrics across different classes, effectively reducing assessment time while maintaining high diagnostic accuracy. Code available at: https://github.com/ahxmeds/thyroidiomics.git.
Authors: Jian Ma, Wenguan Wang, Yi Yang, Feng Zheng
Abstract: Visual acoustic matching (VAM) is pivotal for enhancing the immersive experience, and the task of dereverberation is effective in improving audio intelligibility. Existing methods treat each task independently, overlooking the inherent reciprocity between them. Moreover, these methods depend on paired training data, which is challenging to acquire, impeding the utilization of extensive unpaired data. In this paper, we introduce MVSD, a mutual learning framework based on diffusion models. MVSD considers the two tasks symmetrically, exploiting the reciprocal relationship to facilitate learning from inverse tasks and overcome data scarcity. Furthermore, we employ the diffusion model as foundational conditional converters to circumvent the training instability and over-smoothing drawbacks of conventional GAN architectures. Specifically, MVSD employs two converters: one for VAM called reverberator and one for dereverberation called dereverberator. The dereverberator judges whether the reverberation audio generated by reverberator sounds like being in the conditional visual scenario, and vice versa. By forming a closed loop, these two converters can generate informative feedback signals to optimize the inverse tasks, even with easily acquired one-way unpaired data. Extensive experiments on two standard benchmarks, i.e., SoundSpaces-Speech and Acoustic AVSpeech, exhibit that our framework can improve the performance of the reverberator and dereverberator and better match specified visual scenarios.
Authors: Linxuan Han, Sa Xiao, Zimeng Li, Haidong Li, Xiuchao Zhao, Fumin Guo, Yeqing Han, Xin Zhou
Abstract: Multi-modality magnetic resonance imaging (MRI) can provide complementary information for computer-aided diagnosis. Traditional deep learning algorithms are suitable for identifying specific anatomical structures segmenting lesions and classifying diseases with magnetic resonance images. However, manual labels are limited due to high expense, which hinders further improvement of model accuracy. Self-supervised learning (SSL) can effectively learn feature representations from unlabeled data by pre-training and is demonstrated to be effective in natural image analysis. Most SSL methods ignore the similarity of multi-modality MRI, leading to model collapse. This limits the efficiency of pre-training, causing low accuracy in downstream segmentation and classification tasks. To solve this challenge, we establish and validate a multi-modality MRI masked autoencoder consisting of hybrid mask pattern (HMP) and pyramid barlow twin (PBT) module for SSL on multi-modality MRI analysis. The HMP concatenates three masking steps forcing the SSL to learn the semantic connections of multi-modality images by reconstructing the masking patches. We have proved that the proposed HMP can avoid model collapse. The PBT module exploits the pyramidal hierarchy of the network to construct barlow twin loss between masked and original views, aligning the semantic representations of image patches at different vision scales in latent space. Experiments on BraTS2023, PI-CAI, and lung gas MRI datasets further demonstrate the superiority of our framework over the state-of-the-art. The performance of the segmentation and classification is substantially enhanced, supporting the accurate detection of small lesion areas. The code is available at https://github.com/LinxuanHan/M2-MAE.
Authors: Hyungjun Yoon, Biniyam Aschalew Tolera, Taesik Gong, Kimin Lee, Sung-Ju Lee
Abstract: Large language models (LLMs) have demonstrated exceptional abilities across various domains. However, utilizing LLMs for ubiquitous sensing applications remains challenging as existing text-prompt methods show significant performance degradation when handling long sensor data sequences. We propose a visual prompting approach for sensor data using multimodal LLMs (MLLMs). We design a visual prompt that directs MLLMs to utilize visualized sensor data alongside the target sensory task descriptions. Additionally, we introduce a visualization generator that automates the creation of optimal visualizations tailored to a given sensory task, eliminating the need for prior task-specific knowledge. We evaluated our approach on nine sensory tasks involving four sensing modalities, achieving an average of 10% higher accuracy than text-based prompts and reducing token costs by 15.8x. Our findings highlight the effectiveness and cost-efficiency of visual prompts with MLLMs for various sensory tasks.
Authors: Santiago Pascual, Chunghsin Yeh, Ioannis Tsiamas, Joan Serr\`a
Abstract: Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural synchronization artifacts arise. Recent works have explored the progression of conditioning sound generators on still images and then video features, focusing on quality and semantic matching while ignoring synchronization, or by sacrificing some amount of quality to focus on improving synchronization only. In this work, we propose a V2A generative model, named MaskVAT, that interconnects a full-band high-quality general audio codec with a sequence-to-sequence masked generative model. This combination allows modeling both high audio quality, semantic matching, and temporal synchronicity at the same time. Our results show that, by combining a high-quality codec with the proper pre-trained audio-visual features and a sequence-to-sequence parallel structure, we are able to yield highly synchronized results on one hand, whilst being competitive with the state of the art of non-codec generative audio models. Sample videos and generated audios are available at https://maskvat.github.io .
Authors: Hang Li, Qiankun Dong, Xueshuo Xie, Xia Xu, Tao Li, Zhenwei Shi
Abstract: Multitemporal hyperspectral image unmixing (MTHU) holds significant importance in monitoring and analyzing the dynamic changes of surface. However, compared to single-temporal unmixing, the multitemporal approach demands comprehensive consideration of information across different phases, rendering it a greater challenge. To address this challenge, we propose the Multitemporal Hyperspectral Image Unmixing Transformer (MUFormer), an end-to-end unsupervised deep learning model. To effectively perform multitemporal hyperspectral image unmixing, we introduce two key modules: the Global Awareness Module (GAM) and the Change Enhancement Module (CEM). The Global Awareness Module computes self-attention across all phases, facilitating global weight allocation. On the other hand, the Change Enhancement Module dynamically learns local temporal changes by comparing endmember changes between adjacent phases. The synergy between these modules allows for capturing semantic information regarding endmember and abundance changes, thereby enhancing the effectiveness of multitemporal hyperspectral image unmixing. We conducted experiments on one real dataset and two synthetic datasets, demonstrating that our model significantly enhances the effect of multitemporal hyperspectral image unmixing.
Authors: Mark He Huang, Lin Geng Foo, Jun Liu
Abstract: Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the overall performance of the model. Despite recent advances in this field, balancing between the dual objectives of unlearning remains challenging. From a fresh perspective of generalization, we introduce a novel Learning-to-Unlearn (LTU) framework, which adopts a meta-learning approach to optimize the unlearning process to improve forgetting and remembering in a unified manner. LTU includes a meta-optimization scheme that facilitates models to effectively preserve generalizable knowledge with only a small subset of the remaining set, while thoroughly forgetting the specific data samples. We also introduce a Gradient Harmonization strategy to align the optimization trajectories for remembering and forgetting via mitigating gradient conflicts, thus ensuring efficient and effective model updates. Our approach demonstrates improved efficiency and efficacy for MU, offering a promising solution to the challenges of data rights and model reusability.
Authors: Yifei Yang, Wonjun Lee, Dongmian Zou, Gilad Lerman
Abstract: Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly applied for learning such representations from data, but they often fall short in preserving the geometric structures of the original feature spaces. In response to this challenge, our work applies the Gromov-Wasserstein (GW) distance as a novel regularization mechanism within hyperbolic neural networks. The GW distance quantifies how well the original data structure is maintained after embedding the data in a hyperbolic space. Specifically, we explicitly treat the layers of the hyperbolic neural networks as a transport map and calculate the GW distance accordingly. We validate that the GW distance computed based on a training set well approximates the GW distance of the underlying data distribution. Our approach demonstrates consistent enhancements over current state-of-the-art methods across various tasks, including few-shot image classification, as well as semi-supervised graph link prediction and node classification.
Authors: Shrajan Bhandary, Dejan Kuhn, Zahra Babaiee, Tobias Fechter, Simon K. B. Spohn, Constantinos Zamboglou, Anca-Ligia Grosu, Radu Grosu
Abstract: Accurate segmentation of prostate tumours from PET images presents a formidable challenge in medical image analysis. Despite considerable work and improvement in delineating organs from CT and MR modalities, the existing standards do not transfer well and produce quality results in PET related tasks. Particularly, contemporary methods fail to accurately consider the intensity-based scaling applied by the physicians during manual annotation of tumour contours. In this paper, we observe that the prostate-localised uptake threshold ranges are beneficial for suppressing outliers. Therefore, we utilize the intensity threshold values, to implement a new custom-feature-clipping normalisation technique. We evaluate multiple, established U-Net variants under different normalisation schemes, using the nnU-Net framework. All models were trained and tested on multiple datasets, obtained with two radioactive tracers: [68-Ga]Ga-PSMA-11 and [18-F]PSMA-1007. Our results show that the U-Net models achieve much better performance when the PET scans are preprocessed with our novel clipping technique.
Authors: Zeqing Wang, Fei Cheng, Kangye Ji, Bohu Huang
Abstract: Continual learning(CL) is a useful technique to acquire dynamic knowledge continually. Although powerful cloud platforms can fully exert the ability of CL,e.g., customized recommendation systems, similar personalized requirements for edge devices are almost disregarded. This phenomenon stems from the huge resource overhead involved in training neural networks and overcoming the forgetting problem of CL. This paper focuses on these scenarios and proposes a compact algorithm called LightCL. Different from other CL methods bringing huge resource consumption to acquire generalizability among all tasks for delaying forgetting, LightCL compress the resource consumption of already generalized components in neural networks and uses a few extra resources to improve memory in other parts. We first propose two new metrics of learning plasticity and memory stability to seek generalizability during CL. Based on the discovery that lower and middle layers have more generalizability and deeper layers are opposite, we $\textit{Maintain Generalizability}$ by freezing the lower and middle layers. Then, we $\textit{Memorize Feature Patterns}$ to stabilize the feature extracting patterns of previous tasks to improve generalizability in deeper layers. In the experimental comparison, LightCL outperforms other SOTA methods in delaying forgetting and reduces at most $\textbf{6.16$\times$}$ memory footprint, proving the excellent performance of LightCL in efficiency. We also evaluate the efficiency of our method on an edge device, the Jetson Nano, which further proves our method's practical effectiveness.
Authors: Vidhyapriya Ranganathan, Celshiya Udaiyar, Jaisree Jayanth, Meghaa P V, Srija B, Uthra S
Abstract: Brain tumor is a life-threatening problem and hampers the normal functioning of the human body. The average five-year relative survival rate for malignant brain tumors is 35.6 percent. For proper diagnosis and efficient treatment planning, it is necessary to detect the brain tumor in early stages. Due to advancement in medical imaging technology, the brain images are taken in different modalities. The ability to extract relevant characteristics from magnetic resonance imaging (MRI) scans is a crucial step for brain tumor classifiers. Several studies have proposed various strategies to extract relevant features from different modalities of MRI to predict the growth of abnormal tumors. Most techniques used conventional methods of image processing for feature extraction and machine learning for classification. More recently, the use of deep learning algorithms in medical imaging has resulted in significant improvements in the classification and diagnosis of brain tumors. Since tumors are located at different regions of the brain, localizing the tumor and classifying it to a particular category is a challenging task. The objective of this project is to develop a predictive system for brain tumor detection using machine learning(ensembling).
Authors: Zhening Liu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang
Abstract: With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches have primarily employed a unidirectional paradigm, where the compression of one view is dependent on the other, resulting in imbalanced compression. To address this issue, we introduce a symmetric bidirectional stereo image compression architecture, named BiSIC. Specifically, we propose a 3D convolution based codec backbone to capture local features and incorporate bidirectional attention blocks to exploit global features. Moreover, we design a novel cross-dimensional entropy model that integrates various conditioning factors, including the spatial context, channel context, and stereo dependency, to effectively estimate the distribution of latent representations for entropy coding. Extensive experiments demonstrate that our proposed BiSIC outperforms conventional image/video compression standards, as well as state-of-the-art learning-based methods, in terms of both PSNR and MS-SSIM.
Authors: Divya Thuremella, Lewis Ince, Lars Kunze
Abstract: To operate in open-ended environments where humans interact in complex, diverse ways, autonomous robots must learn to predict their behaviour, especially when that behavior is potentially dangerous to other agents or to the robot. However, reducing the risk of accidents requires prior knowledge of where potential collisions may occur and how. Therefore, we propose to gain this information by analyzing locations and speeds that commonly correspond to high-risk interactions within the dataset, and use it within training to generate better predictions in high risk situations. Through these location-based and speed-based re-weighting techniques, we achieve improved overall performance, as measured by most-likely FDE and KDE, as well as improved performance on high-speed vehicles, and vehicles within high-risk locations. 2023 IEEE International Conference on Robotics and Automation (ICRA)
Authors: Wentao Zhao, Qitian Wu, Chenxiao Yang, Junchi Yan
Abstract: Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. By synthesizing samples through the interpolation of features and labels, Mixup effectively addresses the issue of data scarcity. However, it has rarely been explored in graph learning tasks due to the irregularity and connectivity of graph data. Specifically, in node classification tasks, Mixup presents a challenge in creating connections for synthetic data. In this paper, we propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing. It effectively utilizes geometry information to interpolate features and labels with those from the nearby neighborhood, generating synthetic nodes and establishing connections for them. We conduct theoretical analysis to elucidate the rationale behind employing geometry information for node Mixup, emphasizing the significance of locality enhancement-a critical aspect of our method's design. Extensive experiments demonstrate that our lightweight Geometric Mixup achieves state-of-the-art results on a wide variety of standard datasets with limited labeled data. Furthermore, it significantly improves the generalization capability of underlying GNNs across various challenging out-of-distribution generalization tasks. Our code is available at https://github.com/WtaoZhao/geomix.
Authors: Nhat Le, Ciyue Shen, Chintan Shah, Blake Martin, Daniel Shenker, Harshith Padigela, Jennifer Hipp, Sean Grullon, John Abel, Harsha Vardhan Pokkalla, Dinkar Juyal
Abstract: Mechanistic interpretability has been explored in detail for large language models (LLMs). For the first time, we provide a preliminary investigation with similar interpretability methods for medical imaging. Specifically, we analyze the features from a ViT-Small encoder obtained from a pathology Foundation Model via application to two datasets: one dataset of pathology images, and one dataset of pathology images paired with spatial transcriptomics. We discover an interpretable representation of cell and tissue morphology, along with gene expression within the model embedding space. Our work paves the way for further exploration around interpretable feature dimensions and their utility for medical and clinical applications.
Authors: Toygar Tanyel, Nurper Denizoglu, Mustafa Ege Seker, Deniz Alis, Esma Cerekci, Ercan Karaarslan, Erkin Aribal, Ilkay Oksuz
Abstract: Breast cancer remains a leading cause of cancer-related deaths among women worldwide, with mammography screening as the most effective method for the early detection. Ensuring proper positioning in mammography is critical, as poor positioning can lead to diagnostic errors, increased patient stress, and higher costs due to recalls. Despite advancements in deep learning (DL) for breast cancer diagnostics, limited focus has been given to evaluating mammography positioning. This paper introduces a novel DL methodology to quantitatively assess mammogram positioning quality, specifically in mediolateral oblique (MLO) views using attention and coordinate convolution modules. Our method identifies key anatomical landmarks, such as the nipple and pectoralis muscle, and automatically draws a posterior nipple line (PNL), offering robust and inherently explainable alternative to well-known classification and regression-based approaches. We compare the performance of proposed methodology with various regression and classification-based models. The CoordAtt UNet model achieved the highest accuracy of 88.63% $\pm$ 2.84 and specificity of 90.25% $\pm$ 4.04, along with a noteworthy sensitivity of 86.04% $\pm$ 3.41. In landmark detection, the same model also recorded the lowest mean errors in key anatomical points and the smallest angular error of 2.42 degrees. Our results indicate that models incorporating attention mechanisms and CoordConv module increase the accuracy in classifying breast positioning quality and detecting anatomical landmarks. Furthermore, we make the labels and source codes available to the community to initiate an open research area for mammography, accessible at https://github.com/tanyelai/deep-breast-positioning.
Authors: Quang H. Nguyen, Nguyen Ngoc-Hieu, The-Anh Ta, Thanh Nguyen-Tang, Hoang Thanh-Tung, Khoa D. Doan
Abstract: Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks that can perform the attack without changing the labels of poisoned data. Early works on clean-label attacks added triggers to a random subset of the training set, ignoring the fact that samples contribute unequally to the attack's success. This results in high poisoning rates and low attack success rates. To alleviate the problem, several supervised learning-based sample selection strategies have been proposed. However, these methods assume access to the entire labeled training set and require training, which is expensive and may not always be practical. This work studies a new and more practical (but also more challenging) threat model where the attacker only provides data for the target class (e.g., in face recognition systems) and has no knowledge of the victim model or any other classes in the training set. We study different strategies for selectively poisoning a small set of training samples in the target class to boost the attack success rate in this setting. Our threat model poses a serious threat in training machine learning models with third-party datasets, since the attack can be performed effectively with limited information. Experiments on benchmark datasets illustrate the effectiveness of our strategies in improving clean-label backdoor attacks.
Authors: Yulin Ren, Xin Li, Bingchen Li, Xingrui Wang, Mengxi Guo, Shijie Zhao, Li Zhang, Zhibo Chen
Abstract: We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for different image codecs, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/.
Authors: Dennis Hein, Afshin Bozorgpour, Dorit Merhof, Ge Wang
Abstract: Physics-inspired generative models, in particular diffusion and Poisson flow models, enhance Bayesian methods and promise great utilities in medical imaging. This review examines the transformative role of such generative methods. First, a variety of physics-inspired generative models, including Denoising Diffusion Probabilistic Models (DDPM), Score-based Diffusion Models, and Poisson Flow Generative Models (PFGM and PFGM++), are revisited, with an emphasis on their accuracy, robustness as well as acceleration. Then, major applications of physics-inspired generative models in medical imaging are presented, comprising image reconstruction, image generation, and image analysis. Finally, future research directions are brainstormed, including unification of physics-inspired generative models, integration with vision-language models (VLMs),and potential novel applications of generative models. Since the development of generative methods has been rapid, this review will hopefully give peers and learners a timely snapshot of this new family of physics-driven generative models and help capitalize their enormous potential for medical imaging.
Authors: Keshav Bimbraw, Jing Liu, Ye Wang, Toshiaki Koike-Akino
Abstract: Biosignal-based hand gesture classification is an important component of effective human-machine interaction. For multimodal biosignal sensing, the modalities often face data loss due to missing channels in the data which can adversely affect the gesture classification performance. To make the classifiers robust to missing channels in the data, this paper proposes using Random Channel Ablation (RChA) during the training process. Ultrasound and force myography (FMG) data were acquired from the forearm for 12 hand gestures over 2 subjects. The resulting multimodal data had 16 total channels, 8 for each modality. The proposed method was applied to convolutional neural network architecture, and compared with baseline, imputation, and oracle methods. Using 5-fold cross-validation for the two subjects, on average, 12.2% and 24.5% improvement was observed for gesture classification with up to 4 and 8 missing channels respectively compared to the baseline. Notably, the proposed method is also robust to an increase in the number of missing channels compared to other methods. These results show the efficacy of using random channel ablation to improve classifier robustness for multimodal and multi-channel biosignal-based hand gesture classification.
Authors: Leonardo Crespi, Samuele Camnasio, Damiano Dei, Nicola Lambri, Pietro Mancosu, Marta Scorsetti, Daniele Loiacono
Abstract: In many clinical settings, the use of both Computed Tomography (CT) and Magnetic Resonance (MRI) is necessary to pursue a thorough understanding of the patient's anatomy and to plan a suitable therapeutical strategy; this is often the case in MRI-based radiotherapy, where CT is always necessary to prepare the dose delivery, as it provides the essential information about the radiation absorption properties of the tissues. Sometimes, MRI is preferred to contour the target volumes. However, this approach is often not the most efficient, as it is more expensive, time-consuming and, most importantly, stressful for the patients. To overcome this issue, in this work, we analyse the capabilities of different configurations of Deep Learning models to generate synthetic CT scans from MRI, leveraging the power of Generative Adversarial Networks (GANs) and, in particular, the CycleGAN architecture, capable of working in an unsupervised manner and without paired images, which were not available. Several CycleGAN models were trained unsupervised to generate CT scans from different MRI modalities with and without contrast agents. To overcome the problem of not having a ground truth, distribution-based metrics were used to assess the model's performance quantitatively, together with a qualitative evaluation where physicians were asked to differentiate between real and synthetic images to understand how realistic the generated images were. The results show how, depending on the input modalities, the models can have very different performances; however, models with the best quantitative results, according to the distribution-based metrics used, can generate very difficult images to distinguish from the real ones, even for physicians, demonstrating the approach's potential.
Authors: Pandiyaraju V, Shravan Venkatraman, Abeshek A, Aravintakshan S A, Pavan Kumar S, Kannan A
Abstract: Alzheimer's disease (AD) represents the primary form of neurodegeneration, impacting millions of individuals each year and causing progressive cognitive decline. Accurately diagnosing and classifying AD using neuroimaging data presents ongoing challenges in medicine, necessitating advanced interventions that will enhance treatment measures. In this research, we introduce a dual attention enhanced deep learning (DL) framework for classifying AD from neuroimaging data. Combined spatial and self-attention mechanisms play a vital role in emphasizing focus on neurofibrillary tangles and amyloid plaques from the MRI images, which are difficult to discern with regular imaging techniques. Results demonstrate that our model yielded remarkable performance in comparison to existing state of the art (SOTA) convolutional neural networks (CNNs), with an accuracy of 99.1%. Moreover, it recorded remarkable metrics, with an F1-Score of 99.31%, a precision of 99.24%, and a recall of 99.5%. These results highlight the promise of cutting edge DL methods in medical diagnostics, contributing to highly reliable and more efficient healthcare solutions.
Authors: Zhuoyuan Li, Jiacheng Li, Yao Li, Li Li, Dong Liu, Feng Wu
Abstract: In-loop filtering (ILF) is a key technology for removing the artifacts in image/video coding standards. Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards. However, the utilization of deep neural networks brings heavy time and computational complexity, and high demands of high-performance hardware, which is challenging to apply to the general uses of coding scene. To address this limitation, inspired by explorations in image restoration, we propose an efficient and practical in-loop filtering scheme by adopting the Look-up Table (LUT). We train the DNN of in-loop filtering within a fixed filtering reference range, and cache the output values of the DNN into a LUT via traversing all possible inputs. At testing time in the coding process, the filtered pixel is generated by locating input pixels (to-be-filtered pixel with reference pixels) and interpolating cached filtered pixel values. To further enable the large filtering reference range with the limited storage cost of LUT, we introduce the enhanced indexing mechanism in the filtering process, and clipping/finetuning mechanism in the training. The proposed method is implemented into the Versatile Video Coding (VVC) reference software, VTM-11.0. Experimental results show that the ultrafast, very fast, and fast mode of the proposed method achieves on average 0.13%/0.34%/0.51%, and 0.10%/0.27%/0.39% BD-rate reduction, under the all intra (AI) and random access (RA) configurations. Especially, our method has friendly time and computational complexity, only 101%/102%-104%/108% time increase with 0.13-0.93 kMACs/pixel, and only 164-1148 KB storage cost for a single model. Our solution may shed light on the journey of practical neural network-based coding tool evolution.
Authors: Hanqing Wang, Jiahe Chen, Wensi Huang, Qingwei Ben, Tai Wang, Boyu Mi, Tao Huang, Siheng Zhao, Yilun Chen, Sizhe Yang, Peizhou Cao, Wenye Yu, Zichao Ye, Jialun Li, Junfeng Long, Zirui Wang, Huiling Wang, Ying Zhao, Zhongying Tu, Yu Qiao, Dahua Lin, Jiangmiao Pang
Abstract: Recent works have been exploring the scaling laws in the field of Embodied AI. Given the prohibitive costs of collecting real-world data, we believe the Simulation-to-Real (Sim2Real) paradigm is a crucial step for scaling the learning of embodied models. This paper introduces project GRUtopia, the first simulated interactive 3D society designed for various robots. It features several advancements: (a) The scene dataset, GRScenes, includes 100k interactive, finely annotated scenes, which can be freely combined into city-scale environments. In contrast to previous works mainly focusing on home, GRScenes covers 89 diverse scene categories, bridging the gap of service-oriented environments where general robots would be initially deployed. (b) GRResidents, a Large Language Model (LLM) driven Non-Player Character (NPC) system that is responsible for social interaction, task generation, and task assignment, thus simulating social scenarios for embodied AI applications. (c) The benchmark, GRBench, supports various robots but focuses on legged robots as primary agents and poses moderately challenging tasks involving Object Loco-Navigation, Social Loco-Navigation, and Loco-Manipulation. We hope that this work can alleviate the scarcity of high-quality data in this field and provide a more comprehensive assessment of Embodied AI research. The project is available at https://github.com/OpenRobotLab/GRUtopia.
Authors: Jing Yang, Xiatian Zhu, Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos
Abstract: Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is largely overlooked. In this work, we propose a novel {\em \modelname{}} ({\bf\em \shortname{})} method dedicated for distilling representational knowledge semantically from a pretrained teacher to a target student. The key idea is that we leverage the teacher's classifier as a semantic critic for evaluating the representations of both teacher and student and distilling the semantic knowledge with high-order structured information over all feature dimensions. This is accomplished by introducing a notion of cross-network logit computed through passing student's representation into teacher's classifier. Further, considering the set of seen classes as a basis for the semantic space in a combinatorial perspective, we scale \shortname{} to unseen classes for enabling effective exploitation of largely available, arbitrary unlabeled training data. At the problem level, this establishes an interesting connection between knowledge distillation with open-set semi-supervised learning (SSL). Extensive experiments show that our \shortname{} outperforms significantly previous state-of-the-art knowledge distillation methods on both coarse object classification and fine face recognition tasks, as well as less studied yet practically crucial binary network distillation. Under more realistic open-set SSL settings we introduce, we reveal that knowledge distillation is generally more effective than existing Out-Of-Distribution (OOD) sample detection, and our proposed \shortname{} is superior over both previous distillation and SSL competitors. The source code is available at \url{https://github.com/jingyang2017/SRD\_ossl}.
Authors: Tianshui Chen, Tao Pu, Lingbo Liu, Yukai Shi, Zhijing Yang, Liang Lin
Abstract: Multi-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each image, may greatly reduce the cost of annotation and thus facilitate large-scale MLR. We find that strong semantic correlations exist within each image and across different images, and these correlations can help transfer the knowledge possessed by the known labels to retrieve the unknown labels and thus improve the performance of the MLR-PL task (see Figure 1). In this work, we propose a novel heterogeneous semantic transfer (HST) framework that consists of two complementary transfer modules that explore both within-image and cross-image semantic correlations to transfer the knowledge possessed by known labels to generate pseudo labels for the unknown labels. Specifically, an intra-image semantic transfer (IST) module learns an image-specific label co-occurrence matrix for each image and maps the known labels to complement the unknown labels based on these matrices. Additionally, a cross-image transfer (CST) module learns category-specific feature-prototype similarities and then helps complement the unknown labels that have high degrees of similarity with the corresponding prototypes. Finally, both the known and generated pseudo labels are used to train MLR models. Extensive experiments conducted on the Microsoft COCO, Visual Genome, and Pascal VOC 2007 datasets show that the proposed HST framework achieves superior performance to that of current state-of-the-art algorithms. Specifically, it obtains mean average precision (mAP) improvements of 1.4%, 3.3%, and 0.4% on the three datasets over the results of the best-performing previously developed algorithm.
Authors: Ranjana Roy Chowdhury, Deepti R. Bathula
Abstract: Prototypical network (PN) is a simple yet effective few shot learning strategy. It is a metric-based meta-learning technique where classification is performed by computing Euclidean distances to prototypical representations of each class. Conventional PN attributes equal importance to all samples and generates prototypes by simply averaging the support sample embeddings belonging to each class. In this work, we propose a novel version of PN that attributes weights to support samples corresponding to their influence on the support sample distribution. Influence weights of samples are calculated based on maximum mean discrepancy (MMD) between the mean embeddings of sample distributions including and excluding the sample. Further, the influence factor of a sample is measured using MMD based on the shift in the distribution in the absence of that sample.
Authors: Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Dana Dascalescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah
Abstract: We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models. To improve the fidelity of our student, we distill the low-resolution anomaly maps of the teachers by jointly applying standard and adversarial distillation, introducing an adversarial discriminator for each teacher to distinguish between target and generated anomaly maps. We conduct experiments on three benchmarks (Avenue, ShanghaiTech, UCSD Ped2), showing that our method is over 7 times faster than the fastest competing method, and between 28 and 62 times faster than object-centric models, while obtaining comparable results to recent methods. Our evaluation also indicates that our model achieves the best trade-off between speed and accuracy, due to its previously unheard-of speed of 1480 FPS. In addition, we carry out a comprehensive ablation study to justify our architectural design choices. Our code is freely available at: https://github.com/ristea/fast-aed.
Authors: Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu
Abstract: Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs -- the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in class-incremental learning and summarize these methods from several aspects. We also provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures. The source code is available at https://github.com/zhoudw-zdw/CIL_Survey/
Authors: Qi Zheng, Daqing Liu, Chaoyue Wang, Jing Zhang, Dadong Wang, Dacheng Tao
Abstract: Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes. Existing approaches have made enormous progress in navigation in new environments, such as beam search, pre-exploration, and dynamic or hierarchical history encoding. To balance generalization and efficiency, we resort to memorizing visited scenarios apart from the ongoing route while navigating. In this work, we introduce a mechanism of Episodic Scene memory (ESceme) for VLN that wakes an agent's memories of past visits when it enters the current scene. The episodic scene memory allows the agent to envision a bigger picture of the next prediction. This way, the agent learns to utilize dynamically updated information instead of merely adapting to the current observations. We provide a simple yet effective implementation of ESceme by enhancing the accessible views at each location and progressively completing the memory while navigating. We verify the superiority of ESceme on short-horizon (R2R), long-horizon (R4R), and vision-and-dialog (CVDN) VLN tasks. Our ESceme also wins first place on the CVDN leaderboard. Code is available: \url{https://github.com/qizhust/esceme}.
Authors: Yuguang Yao, Jiancheng Liu, Yifan Gong, Xiaoming Liu, Yanzhi Wang, Xue Lin, Sijia Liu
Abstract: Numerous adversarial attack methods have been developed to generate imperceptible image perturbations that can cause erroneous predictions of state-of-the-art machine learning (ML) models, in particular, deep neural networks (DNNs). Despite intense research on adversarial attacks, little effort was made to uncover 'arcana' carried in adversarial attacks. In this work, we ask whether it is possible to infer data-agnostic victim model (VM) information (i.e., characteristics of the ML model or DNN used to generate adversarial attacks) from data-specific adversarial instances. We call this 'model parsing of adversarial attacks' - a task to uncover 'arcana' in terms of the concealed VM information in attacks. We approach model parsing via supervised learning, which correctly assigns classes of VM's model attributes (in terms of architecture type, kernel size, activation function, and weight sparsity) to an attack instance generated from this VM. We collect a dataset of adversarial attacks across 7 attack types generated from 135 victim models (configured by 5 architecture types, 3 kernel size setups, 3 activation function types, and 3 weight sparsity ratios). We show that a simple, supervised model parsing network (MPN) is able to infer VM attributes from unseen adversarial attacks if their attack settings are consistent with the training setting (i.e., in-distribution generalization assessment). We also provide extensive experiments to justify the feasibility of VM parsing from adversarial attacks, and the influence of training and evaluation factors in the parsing performance (e.g., generalization challenge raised in out-of-distribution evaluation). We further demonstrate how the proposed MPN can be used to uncover the source VM attributes from transfer attacks, and shed light on a potential connection between model parsing and attack transferability.
Authors: Yifeng Ma, Suzhen Wang, Yu Ding, Lincheng Li, Bowen Ma, Tangjie Lv, Changjie Fan, Zhipeng Hu, Zhidong Deng, Xin Yu
Abstract: Audio-driven talking head generation has drawn growing attention. To produce talking head videos with desired facial expressions, previous methods rely on extra reference videos to provide expression information, which may be difficult to find and hence limits their usage. In this work, we propose TalkCLIP, a framework that can generate talking heads where the expressions are specified by natural language, hence allowing for specifying expressions more conveniently. To model the mapping from text to expressions, we first construct a text-video paired talking head dataset where each video has diverse text descriptions that depict both coarse-grained emotions and fine-grained facial movements. Leveraging the proposed dataset, we introduce a CLIP-based style encoder that projects natural language-based descriptions to the representations of expressions. TalkCLIP can even infer expressions for descriptions unseen during training. TalkCLIP can also use text to modulate expression intensity and edit expressions. Extensive experiments demonstrate that TalkCLIP achieves the advanced capability of generating photo-realistic talking heads with vivid facial expressions guided by text descriptions.
Authors: Zhenxiang Lin, Xidong Peng, Peishan Cong, Ge Zheng, Yujin Sun, Yuenan Hou, Xinge Zhu, Sibei Yang, Yuexin Ma
Abstract: We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images and 3D LiDAR point clouds. We present a novel method, dubbed WildRefer, for this task by fully utilizing the rich appearance information in images, the position and geometric clues in point cloud as well as the semantic knowledge of language descriptions. Besides, we propose two novel datasets, i.e., STRefer and LifeRefer, which focus on large-scale human-centric daily-life scenarios accompanied with abundant 3D object and natural language annotations. Our datasets are significant for the research of 3D visual grounding in the wild and has huge potential to boost the development of autonomous driving and service robots. Extensive experiments and ablation studies demonstrate that our method achieves state-of-the-art performance on the proposed benchmarks. The code is provided in https://github.com/4DVLab/WildRefer.
Authors: H M Dipu Kabir
Abstract: Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning to help researchers and organizations with limited computation power. We also present a methodology for selecting background images and discuss potential future improvements. We apply our approach to several datasets and achieve improved generalization with much lower computation. Through the class activation mappings (CAMs) of the trained models, we observed the tendency towards looking at a bigger picture with the proposed model training methodology. Applying the vision transformer with the proposed background class, we receive state-of-the-art (SOTA) performance on STL-10, Caltech-101, and CINIC-10 datasets. Example scripts are available in the 'CAM' folder of the following GitHub Repository: github.com/dipuk0506/UQ
Authors: Xiuwei Xu, Zhihao Sun, Ziwei Wang, Hongmin Liu, Jie Zhou, Jiwen Lu
Abstract: In this paper, we propose an efficient feature pruning strategy for 3D small object detection. Conventional 3D object detection methods struggle on small objects due to the weak geometric information from a small number of points. Although increasing the spatial resolution of feature representations can improve the detection performance on small objects, the additional computational overhead is unaffordable. With in-depth study, we observe the growth of computation mainly comes from the upsampling operation in the decoder of 3D detector. Motivated by this, we present a multi-level 3D detector named DSPDet3D which benefits from high spatial resolution to achieves high accuracy on small object detection, while reducing redundant computation by only focusing on small object areas. Specifically, we theoretically derive a dynamic spatial pruning (DSP) strategy to prune the redundant spatial representation of 3D scene in a cascade manner according to the distribution of objects. Then we design DSP module following this strategy and construct DSPDet3D with this efficient module. On ScanNet and TO-SCENE dataset, our method achieves leading performance on small object detection. Moreover, DSPDet3D trained with only ScanNet rooms can generalize well to scenes in larger scale. It takes less than 2s to directly process a whole building consisting of more than 4500k points while detecting out almost all objects, ranging from cups to beds, on a single RTX 3090 GPU. Project page: https://xuxw98.github.io/DSPDet3D/.
Authors: Changtao Miao, Qi Chu, Zhentao Tan, Zhenchao Jin, Tao Gong, Wanyi Zhuang, Yue Wu, Bin Liu, Honggang Hu, Nenghai Yu
Abstract: As deepfake content proliferates online, advancing face manipulation forensics has become crucial. To combat this emerging threat, previous methods mainly focus on studying how to distinguish authentic and manipulated face images. Although impressive, image-level classification lacks explainability and is limited to specific application scenarios, spurring recent research on pixel-level prediction for face manipulation forensics. However, existing forgery localization methods suffer from exploring frequency-based forgery traces in the localization network. In this paper, we observe that multi-frequency spectrum information is effective for identifying tampered regions. To this end, a novel Multi-Spectral Class Center Network (MSCCNet) is proposed for face manipulation detection and localization. Specifically, we design a Multi-Spectral Class Center (MSCC) module to learn more generalizable and multi-frequency features. Based on the features of different frequency bands, the MSCC module collects multi-spectral class centers and computes pixel-to-class relations. Applying multi-spectral class-level representations suppresses the semantic information of the visual concepts which is insensitive to manipulated regions of forgery images. Furthermore, we propose a Multi-level Features Aggregation (MFA) module to employ more low-level forgery artifacts and structural textures. Meanwhile, we conduct a comprehensive localization benchmark based on pixel-level FF++ and Dolos datasets. Experimental results quantitatively and qualitatively demonstrate the effectiveness and superiority of the proposed MSCCNet. We expect this work to inspire more studies on pixel-level face manipulation localization. The codes are available (https://github.com/miaoct/MSCCNet).
Authors: Xinhang Liu, Jiaben Chen, Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang
Abstract: Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifacts. We introduce Deceptive-NeRF/3DGS to enhance sparse-view reconstruction with only a limited set of input images, by leveraging a diffusion model pre-trained from multiview datasets. Different from using diffusion priors to regularize representation optimization, our method directly uses diffusion-generated images to train NeRF/3DGS as if they were real input views. Specifically, we propose a deceptive diffusion model turning noisy images rendered from few-view reconstructions into high-quality photorealistic pseudo-observations. To resolve consistency among pseudo-observations and real input views, we develop an uncertainty measure to guide the diffusion model's generation. Our system progressively incorporates diffusion-generated pseudo-observations into the training image sets, ultimately densifying the sparse input observations by 5 to 10 times. Extensive experiments across diverse and challenging datasets validate that our approach outperforms existing state-of-the-art methods and is capable of synthesizing novel views with super-resolution in the few-view setting.
Authors: Yi Shi, Jingbo Wang, Xuekun Jiang, Bingkun Lin, Bo Dai, Xue Bin Peng
Abstract: Real-time character control is an essential component for interactive experiences, with a broad range of applications, including physics simulations, video games, and virtual reality. The success of diffusion models for image synthesis has led to the use of these models for motion synthesis. However, the majority of these motion diffusion models are primarily designed for offline applications, where space-time models are used to synthesize an entire sequence of frames simultaneously with a pre-specified length. To enable real-time motion synthesis with diffusion model that allows time-varying controls, we propose A-MDM (Auto-regressive Motion Diffusion Model). Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on the previous frame. Despite its streamlined network architecture, which uses simple MLPs, our framework is capable of generating diverse, long-horizon, and high-fidelity motion sequences. Furthermore, we introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning. These techniques enable a pre-trained A-MDM to be efficiently adapted for a variety of new downstream tasks. We conduct a comprehensive suite of experiments to demonstrate the effectiveness of A-MDM, and compare its performance against state-of-the-art auto-regressive methods.
Authors: Jin-Young Kim, Soonwoo Kwon, Hyojun Go, Yunsung Lee, Seungtaek Choi, Hyun-Gyoon Kim
Abstract: Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing that of negative ones. Recently, it has been verified that the model learns better representation with diversely augmented positive pairs because they enable the model to be more view-invariant. However, only a few studies on CL have considered the difference between augmented views, and have not gone beyond the hand-crafted findings. In this paper, we first observe that the score-matching function can measure how much data has changed from the original through augmentation. With the observed property, every pair in CL can be weighted adaptively by the difference of score values, resulting in boosting the performance of the existing CL method. We show the generality of our method, referred to as ScoreCL, by consistently improving various CL methods, SimCLR, SimSiam, W-MSE, and VICReg, up to 3%p in k-NN evaluation on CIFAR-10, CIFAR-100, and ImageNet-100. Moreover, we have conducted exhaustive experiments and ablations, including results on diverse downstream tasks, comparison with possible baselines, and improvement when used with other proposed augmentation methods. We hope our exploration will inspire more research in exploiting the score matching for CL.
Authors: Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu, Robert Sheng, Soheil Kolouri
Abstract: Learning from set-structured data, such as point clouds, has gained significant attention from the machine learning community. Geometric deep learning provides a blueprint for designing effective set neural networks that preserve the permutation symmetry of set-structured data. Of our interest are permutation invariant networks, which are composed of a permutation equivariant backbone, permutation invariant global pooling, and regression/classification head. While existing literature has focused on improving equivariant backbones, the impact of the pooling layer is often overlooked. In this paper, we examine the interplay between permutation equivariant backbones and permutation invariant global pooling on three benchmark point cloud classification datasets. Our findings reveal that: 1) complex pooling methods, such as transport-based or attention-based poolings, can significantly boost the performance of simple backbones, but the benefits diminish for more complex backbones, 2) even complex backbones can benefit from pooling layers in low data scenarios, 3) surprisingly, the choice of pooling layers can have a more significant impact on the model's performance than adjusting the width and depth of the backbone, and 4) pairwise combination of pooling layers can significantly improve the performance of a fixed backbone. Our comprehensive study provides insights for practitioners to design better permutation invariant set neural networks. Our code is available at https://github.com/mint-vu/backbone_vs_pooling.
Authors: Yongzhu Miao, Shasha Li, Jintao Tang, Ting Wang
Abstract: Prompt tuning, like CoOp, has recently shown promising vision recognizing and transfer learning ability on various downstream tasks with the emergence of large pre-trained vision-language models like CLIP. However, we identify that existing uni-modal prompt tuning approaches may result in sub-optimal performance since this uni-modal design breaks the original alignment of textual and visual representations in the pre-trained model. Inspired by the nature of pre-trained vision-language models, we aim to achieve completeness in prompt tuning and propose a novel approach called Multi-modal Deep-symphysis Prompt Tuning, dubbed as MuDPT, which extends independent multi-modal prompt tuning by additionally learning a model-agnostic transformative network to allow deep hierarchical bi-directional prompt fusion. We evaluate the effectiveness of MuDPT on few-shot vision recognition and out-of-domain generalization tasks. Compared with the state-of-the-art methods, MuDPT achieves better recognition and generalization ability with an apparent margin thanks to synergistic alignment of textual and visual representations. Our code is available at: https://github.com/Mechrev0/MuDPT.
Authors: Siqi Wang, Bryan A. Plummer
Abstract: Learning with noisy labels (LNL) aims to train a high-performing model using a noisy dataset. We observe that noise for a given class often comes from a limited set of categories, yet many LNL methods overlook this. For example, an image mislabeled as a cheetah is more likely a leopard than a hippopotamus due to its visual similarity. Thus, we explore Learning with Noisy Labels with noise source Knowledge integration (LNL+K), which leverages knowledge about likely source(s) of label noise that is often provided in a dataset's meta-data. Integrating noise source knowledge boosts performance even in settings where LNL methods typically fail. For example, LNL+K methods are effective on datasets where noise represents the majority of samples, which breaks a critical premise of most methods developed for LNL. Our LNL+K methods can boost performance even when noise sources are estimated rather than extracted from meta-data. We provide several baseline LNL+K methods that integrate noise source knowledge into state-of-the-art LNL models that are evaluated across six diverse datasets and two types of noise, where we report gains of up to 23% compared to the unadapted methods. Critically, we show that LNL methods fail to generalize on some real-world datasets, even when adapted to integrate noise source knowledge, highlighting the importance of directly exploring LNL+K.
Authors: Luozhou Wang, Guibao Shen, Wenhang Ge, Guangyong Chen, Yijun Li, Ying-cong Chen
Abstract: Text-to-image diffusion models have advanced towards more controllable generation via supporting various additional conditions (e.g.,depth map, bounding box) beyond text. However, these models are learned based on the premise of perfect alignment between the text and extra conditions. If this alignment is not satisfied, the final output could be either dominated by one condition, or ambiguity may arise, failing to meet user expectations. To address this issue, we present a training free approach called Text-Anchored Score Composition (TASC) to further improve the controllability of existing models when provided with partially aligned conditions. The TASC firstly separates conditions based on pair relationships, computing the result individually for each pair. This ensures that each pair no longer has conflicting conditions. Then we propose an attention realignment operation to realign these independently calculated results via a cross-attention mechanism to avoid new conflicts when combining them back. Both qualitative and quantitative results demonstrate the effectiveness of our approach in handling unaligned conditions, which performs favorably against recent methods and more importantly adds flexibility to the controllable image generation process. Our code will be available at: https://github.com/EnVision-Research/Decompose-and-Realign.
URLs: https://github.com/EnVision-Research/Decompose-and-Realign.
Authors: Zhenyu Zhang, Wenhao Chai, Zhongyu Jiang, Tian Ye, Mingli Song, Jenq-Neng Hwang, Gaoang Wang
Abstract: Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years. Yet, prior to this, no such work has attempted to unify 2D and 3D pose representations in the shared feature space. In this paper, we propose \mpm, a unified 2D-3D human pose representation framework via masked pose modeling. We treat 2D and 3D poses as two different modalities like vision and language and build a single-stream transformer-based architecture. We apply two pretext tasks, which are masked 2D pose modeling, and masked 3D pose modeling to pre-train our network and use full-supervision to perform further fine-tuning. A high masking ratio of $71.8~\%$ in total with a spatio-temporal mask sampling strategy leads to better relation modeling both in spatial and temporal domains. \mpm~can handle multiple tasks including 3D human pose estimation, 3D pose estimation from occluded 2D pose, and 3D pose completion in a \textbf{single} framework. We conduct extensive experiments and ablation studies on several widely used human pose datasets and achieve state-of-the-art performance on MPI-INF-3DHP.
Authors: Giorgos Sfikas, George Retsinas
Abstract: We study matrix forms of quaternionic versions of the Fourier Transform and Convolution operations. Quaternions offer a powerful representation unit, however they are related to difficulties in their use that stem foremost from non-commutativity of quaternion multiplication, and due to that $\mu^2 = -1$ possesses infinite solutions in the quaternion domain. Handling of quaternionic matrices is consequently complicated in several aspects (definition of eigenstructure, determinant, etc.). Our research findings clarify the relation of the Quaternion Fourier Transform matrix to the standard (complex) Discrete Fourier Transform matrix, and the extend on which well-known complex-domain theorems extend to quaternions. We focus especially on the relation of Quaternion Fourier Transform matrices to Quaternion Circulant matrices (representing quaternionic convolution), and the eigenstructure of the latter. A proof-of-concept application that makes direct use of our theoretical results is presented, where we present a method to bound the Lipschitz constant of a Quaternionic Convolutional Neural Network.
Authors: Jishnu Jaykumar P, Kamalesh Palanisamy, Yu-Wei Chao, Xinya Du, Yu Xiang
Abstract: We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by unimodal prototypical networks for few-shot learning, we introduce Proto-CLIP which utilizes image prototypes and text prototypes for few-shot learning. Specifically, Proto-CLIP adapts the image and text encoder embeddings from CLIP in a joint fashion using few-shot examples. The embeddings from the two encoders are used to compute the respective prototypes of image classes for classification. During adaptation, we propose aligning the image and text prototypes of the corresponding classes. Such alignment is beneficial for few-shot classification due to the reinforced contributions from both types of prototypes. Proto-CLIP has both training-free and fine-tuned variants. We demonstrate the effectiveness of our method by conducting experiments on benchmark datasets for few-shot learning, as well as in the real world for robot perception. The project page is available at https://irvlutd.github.io/Proto-CLIP
Authors: Yumeng Li, Margret Keuper, Dan Zhang, Anna Khoreva
Abstract: Emerging large-scale text-to-image generative models, e.g., Stable Diffusion (SD), have exhibited overwhelming results with high fidelity. Despite the magnificent progress, current state-of-the-art models still struggle to generate images fully adhering to the input prompt. Prior work, Attend & Excite, has introduced the concept of Generative Semantic Nursing (GSN), aiming to optimize cross-attention during inference time to better incorporate the semantics. It demonstrates promising results in generating simple prompts, e.g., "a cat and a dog". However, its efficacy declines when dealing with more complex prompts, and it does not explicitly address the problem of improper attribute binding. To address the challenges posed by complex prompts or scenarios involving multiple entities and to achieve improved attribute binding, we propose Divide & Bind. We introduce two novel loss objectives for GSN: a novel attendance loss and a binding loss. Our approach stands out in its ability to faithfully synthesize desired objects with improved attribute alignment from complex prompts and exhibits superior performance across multiple evaluation benchmarks.
Authors: Amirhossein Aminimehr, Amirali Molaei, Erik Cambria
Abstract: Scene recognition based on deep-learning has made significant progress, but there are still limitations in its performance due to challenges posed by inter-class similarities and intra-class dissimilarities. Furthermore, prior research has primarily focused on improving classification accuracy, yet it has given less attention to achieving interpretable, precise scene classification. Therefore, we are motivated to propose EnTri, an ensemble scene recognition framework that employs ensemble learning using a hierarchy of visual features. EnTri represents features at three distinct levels of detail: pixel-level, semantic segmentation-level, and object class and frequency level. By incorporating distinct feature encoding schemes of differing complexity and leveraging ensemble strategies, our approach aims to improve classification accuracy while enhancing transparency and interpretability via visual and textual explanations. To achieve interpretability, we devised an extension algorithm that generates both visual and textual explanations highlighting various properties of a given scene that contribute to the final prediction of its category. This includes information about objects, statistics, spatial layout, and textural details. Through experiments on benchmark scene classification datasets, EnTri has demonstrated superiority in terms of recognition accuracy, achieving competitive performance compared to state-of-the-art approaches, with an accuracy of 87.69%, 75.56%, and 99.17% on the MIT67, SUN397, and UIUC8 datasets, respectively.
Authors: Omid Taheri, Yi Zhou, Dimitrios Tzionas, Yang Zhou, Duygu Ceylan, Soren Pirk, Michael J. Black
Abstract: Hands are dexterous and highly versatile manipulators that are central to how humans interact with objects and their environment. Consequently, modeling realistic hand-object interactions, including the subtle motion of individual fingers, is critical for applications in computer graphics, computer vision, and mixed reality. Prior work on capturing and modeling humans interacting with objects in 3D focuses on the body and object motion, often ignoring hand pose. In contrast, we introduce GRIP, a learning-based method that takes, as input, the 3D motion of the body and the object, and synthesizes realistic motion for both hands before, during, and after object interaction. As a preliminary step before synthesizing the hand motion, we first use a network, ANet, to denoise the arm motion. Then, we leverage the spatio-temporal relationship between the body and the object to extract two types of novel temporal interaction cues, and use them in a two-stage inference pipeline to generate the hand motion. In the first stage, we introduce a new approach to enforce motion temporal consistency in the latent space (LTC), and generate consistent interaction motions. In the second stage, GRIP generates refined hand poses to avoid hand-object penetrations. Given sequences of noisy body and object motion, GRIP upgrades them to include hand-object interaction. Quantitative experiments and perceptual studies demonstrate that GRIP outperforms baseline methods and generalizes to unseen objects and motions from different motion-capture datasets.
Authors: Ruijie Yao, Sheng Jin, Lumin Xu, Wang Zeng, Wentao Liu, Chen Qian, Ping Luo, Ji Wu
Abstract: Multi-Label Image Recognition (MLIR) is a challenging task that aims to predict multiple object labels in a single image while modeling the complex relationships between labels and image regions. Although convolutional neural networks and vision transformers have succeeded in processing images as regular grids of pixels or patches, these representations are sub-optimal for capturing irregular and discontinuous regions of interest. In this work, we present the first fully graph convolutional model, Group K-nearest neighbor based Graph convolutional Network (GKGNet), which models the connections between semantic label embeddings and image patches in a flexible and unified graph structure. To address the scale variance of different objects and to capture information from multiple perspectives, we propose the Group KGCN module for dynamic graph construction and message passing. Our experiments demonstrate that GKGNet achieves state-of-the-art performance with significantly lower computational costs on the challenging multi-label datasets, \ie MS-COCO and VOC2007 datasets. We will release the code and models to facilitate future research in this area.
Authors: Christopher Wewer, Eddy Ilg, Bernt Schiele, Jan Eric Lenssen
Abstract: Existing neural field representations for 3D object reconstruction either (1) utilize object-level representations, but suffer from low-quality details due to conditioning on a global latent code, or (2) are able to perfectly reconstruct the observations, but fail to utilize object-level prior knowledge to infer unobserved regions. We present SimNP, a method to learn category-level self-similarities, which combines the advantages of both worlds by connecting neural point radiance fields with a category-level self-similarity representation. Our contribution is two-fold. (1) We design the first neural point representation on a category level by utilizing the concept of coherent point clouds. The resulting neural point radiance fields store a high level of detail for locally supported object regions. (2) We learn how information is shared between neural points in an unconstrained and unsupervised fashion, which allows to derive unobserved regions of an object during the reconstruction process from given observations. We show that SimNP is able to outperform previous methods in reconstructing symmetric unseen object regions, surpassing methods that build upon category-level or pixel-aligned radiance fields, while providing semantic correspondences between instances
Authors: Naimul Haque, Iffat Labiba, Sadia Akter
Abstract: Automated image caption generation is essential for improving the accessibility and understanding of visual content. In this study, we introduce FaceGemma, a model that accurately describes facial attributes such as emotions, expressions, and features. Using FaceAttdb data, we generated descriptions for 2000 faces with the Llama 3 - 70B model and fine-tuned the PaliGemma model with these descriptions. Based on the attributes and captions supplied in FaceAttDB, we created a new description dataset where each description perfectly depicts the human-annotated attributes, including key features like attractiveness, full lips, big nose, blond hair, brown hair, bushy eyebrows, eyeglasses, male, smile, and youth. This detailed approach ensures that the generated descriptions are closely aligned with the nuanced visual details present in the images. Our FaceGemma model leverages an innovative approach to image captioning by using annotated attributes, human-annotated captions, and prompt engineering to produce high-quality facial descriptions. Our method significantly improved caption quality, achieving an average BLEU-1 score of 0.364 and a METEOR score of 0.355. These metrics demonstrate the effectiveness of incorporating facial attributes into image captioning, providing more accurate and descriptive captions for portrait images.
Authors: Han Lin, Abhay Zala, Jaemin Cho, Mohit Bansal
Abstract: Recent text-to-video (T2V) generation methods have seen significant advancements. However, the majority of these works focus on producing short video clips of a single event (i.e., single-scene videos). Meanwhile, recent large language models (LLMs) have demonstrated their capability in generating layouts and programs to control downstream visual modules. This prompts an important question: can we leverage the knowledge embedded in these LLMs for temporally consistent long video generation? In this paper, we propose VideoDirectorGPT, a novel framework for consistent multi-scene video generation that uses the knowledge of LLMs for video content planning and grounded video generation. Specifically, given a single text prompt, we first ask our video planner LLM (GPT-4) to expand it into a 'video plan', which includes the scene descriptions, the entities with their respective layouts, the background for each scene, and consistency groupings of the entities. Next, guided by this video plan, our video generator, named Layout2Vid, has explicit control over spatial layouts and can maintain temporal consistency of entities across multiple scenes, while being trained only with image-level annotations. Our experiments demonstrate that our proposed VideoDirectorGPT framework substantially improves layout and movement control in both single- and multi-scene video generation and can generate multi-scene videos with consistency, while achieving competitive performance with SOTAs in open-domain single-scene T2V generation. Detailed ablation studies, including dynamic adjustment of layout control strength with an LLM and video generation with user-provided images, confirm the effectiveness of each component of our framework and its future potential.
Authors: Baixin Xu, Jiangbei Hu, Fei Hou, Kwan-Yee Lin, Wayne Wu, Chen Qian, Ying He
Abstract: The advancements in neural rendering have increased the need for techniques that enable intuitive editing of 3D objects represented as neural implicit surfaces. This paper introduces a novel neural algorithm for parameterizing neural implicit surfaces to simple parametric domains like spheres and polycubes. Our method allows users to specify the number of cubes in the parametric domain, learning a configuration that closely resembles the target 3D object's geometry. It computes bi-directional deformation between the object and the domain using a forward mapping from the object's zero level set and an inverse deformation for backward mapping. We ensure nearly bijective mapping with a cycle loss and optimize deformation smoothness. The parameterization quality, assessed by angle and area distortions, is guaranteed using a Laplacian regularizer and an optimized learned parametric domain. Our framework integrates with existing neural rendering pipelines, using multi-view images of a single object or multiple objects of similar geometries to reconstruct 3D geometry and compute texture maps automatically, eliminating the need for any prior information. We demonstrate the method's effectiveness on images of human heads and man-made objects.
Authors: Gulcin Baykal, Melih Kandemir, Gozde Unal
Abstract: Codebook collapse is a common problem in training deep generative models with discrete representation spaces like Vector Quantized Variational Autoencoders (VQ-VAEs). We observe that the same problem arises for the alternatively designed discrete variational autoencoders (dVAEs) whose encoder directly learns a distribution over the codebook embeddings to represent the data. We hypothesize that using the softmax function to obtain a probability distribution causes the codebook collapse by assigning overconfident probabilities to the best matching codebook elements. In this paper, we propose a novel way to incorporate evidential deep learning (EDL) instead of softmax to combat the codebook collapse problem of dVAE. We evidentially monitor the significance of attaining the probability distribution over the codebook embeddings, in contrast to softmax usage. Our experiments using various datasets show that our model, called EdVAE, mitigates codebook collapse while improving the reconstruction performance, and enhances the codebook usage compared to dVAE and VQ-VAE based models. Our code can be found at https://github.com/ituvisionlab/EdVAE .
Authors: Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, Xinggang Wang
Abstract: Representing and rendering dynamic scenes has been an important but challenging task. Especially, to accurately model complex motions, high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency, we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. In 4D-GS, a novel explicit representation containing both 3D Gaussians and 4D neural voxels is proposed. A decomposed neural voxel encoding algorithm inspired by HexPlane is proposed to efficiently build Gaussian features from 4D neural voxels and then a lightweight MLP is applied to predict Gaussian deformations at novel timestamps. Our 4D-GS method achieves real-time rendering under high resolutions, 82 FPS at an 800$\times$800 resolution on an RTX 3090 GPU while maintaining comparable or better quality than previous state-of-the-art methods. More demos and code are available at https://guanjunwu.github.io/4dgs/.
Authors: Abhay Zala, Han Lin, Jaemin Cho, Mohit Bansal
Abstract: Text-to-image (T2I) generation has seen significant growth over the past few years. Despite this, there has been little work on generating diagrams with T2I models. A diagram is a symbolic/schematic representation that explains information using structurally rich and spatially complex visualizations (e.g., a dense combination of related objects, text labels, directional arrows/lines, etc.). Existing state-of-the-art T2I models often fail at diagram generation because they lack fine-grained object layout control when many objects are densely connected via complex relations such as arrows/lines, and also often fail to render comprehensible text labels. To address this gap, we present DiagrammerGPT, a novel two-stage text-to-diagram generation framework leveraging the layout guidance capabilities of LLMs to generate more accurate diagrams. In the first stage, we use LLMs to generate and iteratively refine 'diagram plans' (in a planner-auditor feedback loop). In the second stage, we use a diagram generator, DiagramGLIGEN, and a text label rendering module to generate diagrams (with clear text labels) following the diagram plans. To benchmark the text-to-diagram generation task, we introduce AI2D-Caption, a densely annotated diagram dataset built on top of the AI2D dataset. We show that our DiagrammerGPT framework produces more accurate diagrams, outperforming existing T2I models. We also provide comprehensive analysis, including open-domain diagram generation, multi-platform vector graphic diagram generation, human-in-the-loop editing, and multimodal planner/auditor LLMs.
Authors: Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, Huchuan Lu
Abstract: Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To this end, we propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and videos, \ie zooming in and out. Specifically, our approach employs the zooming strategy to learn discriminative mixed-scale semantics by the multi-head scale integration and rich granularity perception units, which are designed to fully explore imperceptible clues between candidate objects and background surroundings. The former's intrinsic multi-head aggregation provides more diverse visual patterns. The latter's routing mechanism can effectively propagate inter-frame differences in spatiotemporal scenarios and be adaptively deactivated and output all-zero results for static representations. They provide a solid foundation for realizing a unified architecture for static and dynamic COD. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization, uncertainty awareness loss, to encourage predictions with higher confidence in candidate regions. Our highly task-friendly framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks. Our code can be found at {https://github.com/lartpang/ZoomNeXt}.
Authors: Shijie Wang, Qi Zhao, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun
Abstract: What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to revisit text-based representations, such as general-purpose video captions, which are interpretable and can be directly consumed by large language models (LLMs). Intuitively, different video understanding tasks may require representations that are complementary and at different granularity. To this end, we propose versatile action models (Vamos), a learning framework powered by a large language model as the ``reasoner'', and can flexibly leverage visual embedding and free-form text descriptions as its input. To interpret the important text evidence for question answering, we generalize the concept bottleneck model to work with tokens and nonlinear models, which uses hard attention to select a small subset of tokens from the free-form text as inputs to the LLM reasoner. We evaluate Vamos on five complementary benchmarks, Ego4D, NeXT-QA, IntentQA, Spacewalk-18, and EgoSchema, on its capability to model temporal dynamics, encode visual history, and perform reasoning. Surprisingly, we observe that text-based representations consistently achieve competitive performance on all benchmarks, and that visual embeddings provide marginal or no performance improvement, demonstrating the effectiveness of text-based video representation in the LLM era. We also demonstrate that our token bottleneck model is able to select relevant evidence from free-form text, support test-time intervention, and achieves nearly 5 times inference speedup while keeping a competitive question answering performance. Code and models are publicly released at https://brown-palm.github.io/Vamos/
Authors: Xiuyuan Chen, Yuan Lin, Yuchen Zhang, Weiran Huang
Abstract: We propose a novel and challenging benchmark, AutoEval-Video, to comprehensively evaluate large vision-language models in open-ended video question answering. The comprehensiveness of AutoEval-Video is demonstrated in two aspects: 1) AutoEval-Video constructs open-ended video-questions across 9 skill dimensions, addressing capabilities of perception, comprehension, and generation. 2) AutoEval-Video contains newly collected videos that cover over 40 distinct themes. To efficiently evaluate responses to the open-ended questions, we employ an LLM-based evaluation approach, but instead of merely providing a reference answer, we annotate unique evaluation rules for every single instance (video-question pair). To maximize the robustness of these rules, we develop a novel adversarial annotation mechanism. By using instance-specific rules as prompt, GPT-4, as an automatic evaluator, can achieve a stable evaluation accuracy of around 97.0%, comparable to the 94.9% - 97.5% accuracy of a human evaluator. Furthermore, we assess the performance of eight large vision-language models on AutoEval-Video. Among them, GPT-4V(ision) significantly outperforms other models, achieving an accuracy of 32.2%. However, there is still substantial room for improvement compared to human accuracy of 72.8%. By conducting an extensive case study, we uncover several drawbacks of GPT-4V, such as limited temporal and dynamic comprehension, and overly general responses. Code is available at https://github.com/Xiuyuan-Chen/AutoEval-Video.
Authors: Haoyu Zhao, Tianyi Lu, Jiaxi Gu, Xing Zhang, Qingping Zheng, Zuxuan Wu, Hang Xu, Yu-Gang Jiang
Abstract: The diffusion model is widely leveraged for either video generation or video editing. As each field has its task-specific problems, it is difficult to merely develop a single diffusion for completing both tasks simultaneously. Video diffusion sorely relying on the text prompt can be adapted to unify the two tasks. However, it lacks a high capability of aligning heterogeneous modalities between text and image, leading to various misalignment problems. In this work, we are the first to propose a unified Multi-alignment Diffusion, dubbed as MagDiff, for both tasks of high-fidelity video generation and editing. The proposed MagDiff introduces three types of alignments, including subject-driven alignment, adaptive prompts alignment, and high-fidelity alignment. Particularly, the subject-driven alignment is put forward to trade off the image and text prompts, serving as a unified foundation generative model for both tasks. The adaptive prompts alignment is introduced to emphasize different strengths of homogeneous and heterogeneous alignments by assigning different values of weights to the image and the text prompts. The high-fidelity alignment is developed to further enhance the fidelity of both video generation and editing by taking the subject image as an additional model input. Experimental results on four benchmarks suggest that our method outperforms the previous method on each task.
Authors: Shashank Agnihotri, Julia Grabinski, Margret Keuper
Abstract: Pixel-wise predictions are required in a wide variety of tasks such as image restoration, image segmentation, or disparity estimation. Common models involve several stages of data resampling, in which the resolution of feature maps is first reduced to aggregate information and then increased to generate a high-resolution output. Previous works have shown that resampling operations are subject to artifacts such as aliasing. During downsampling, aliases have been shown to compromise the prediction stability of image classifiers. During upsampling, they have been leveraged to detect generated content. Yet, the effect of aliases during upsampling has not yet been discussed w.r.t. the stability and robustness of pixel-wise predictions. While falling under the same term (aliasing), the challenges for correct upsampling in neural networks differ significantly from those during downsampling: when downsampling, some high frequencies can not be correctly represented and have to be removed to avoid aliases. However, when upsampling for pixel-wise predictions, we actually require the model to restore such high frequencies that can not be encoded in lower resolutions. The application of findings from signal processing is therefore a necessary but not a sufficient condition to achieve the desirable output. In contrast, we find that the availability of large spatial context during upsampling allows to provide stable, high-quality pixel-wise predictions, even when fully learning all filter weights.
Authors: Andrey Voynov, Amir Hertz, Moab Arar, Shlomi Fruchter, Daniel Cohen-Or
Abstract: State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image capture. The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a text-to-image diffusion model with the particular lens geometry used in image rendering. Our method is based on a per-pixel coordinate conditioning method, enabling the control over the rendering geometry. Notably, we demonstrate the manipulation of curvature properties, achieving diverse visual effects, such as fish-eye, panoramic views, and spherical texturing using a single diffusion model.
Authors: Jiaman Li, Alexander Clegg, Roozbeh Mottaghi, Jiajun Wu, Xavier Puig, C. Karen Liu
Abstract: Synthesizing semantic-aware, long-horizon, human-object interaction is critical to simulate realistic human behaviors. In this work, we address the challenging problem of generating synchronized object motion and human motion guided by language descriptions in 3D scenes. We propose Controllable Human-Object Interaction Synthesis (CHOIS), an approach that generates object motion and human motion simultaneously using a conditional diffusion model given a language description, initial object and human states, and sparse object waypoints. Here, language descriptions inform style and intent, and waypoints, which can be effectively extracted from high-level planning, ground the motion in the scene. Naively applying a diffusion model fails to predict object motion aligned with the input waypoints; it also cannot ensure the realism of interactions that require precise hand-object and human-floor contact. To overcome these problems, we introduce an object geometry loss as additional supervision to improve the matching between generated object motion and input object waypoints; we also design guidance terms to enforce contact constraints during the sampling process of the trained diffusion model. We demonstrate that our learned interaction module can synthesize realistic human-object interactions, adhering to provided textual descriptions and sparse waypoint conditions. Additionally, our module seamlessly integrates with a path planning module, enabling the generation of long-term interactions in 3D environments.
Authors: Sijing Wu, Yunhao Li, Weitian Zhang, Jun Jia, Yucheng Zhu, Yichao Yan, Guangtao Zhai, Xiaokang Yang
Abstract: Singing, as a common facial movement second only to talking, can be regarded as a universal language across ethnicities and cultures, plays an important role in emotional communication, art, and entertainment. However, it is often overlooked in the field of audio-driven facial animation due to the lack of singing head datasets and the domain gap between singing and talking in rhythm and amplitude. To this end, we collect a high-quality large-scale singing head dataset, SingingHead, which consists of more than 27 hours of synchronized singing video, 3D facial motion, singing audio, and background music from 76 individuals and 8 types of music. Along with the SingingHead dataset, we benchmark existing audio-driven 3D facial animation methods and 2D talking head methods on the singing task. Furthermore, we argue that 3D and 2D facial animation tasks can be solved together, and propose a unified singing head animation framework named UniSinger to achieve both singing audio-driven 3D singing head animation and 2D singing portrait video synthesis, which achieves competitive results on both 3D and 2D benchmarks. Extensive experiments demonstrate the significance of the proposed singing-specific dataset in promoting the development of singing head animation tasks, as well as the promising performance of our unified facial animation framework.
Authors: Thuan Hoang Nguyen, Anh Tran
Abstract: Despite their ability to generate high-resolution and diverse images from text prompts, text-to-image diffusion models often suffer from slow iterative sampling processes. Model distillation is one of the most effective directions to accelerate these models. However, previous distillation methods fail to retain the generation quality while requiring a significant amount of images for training, either from real data or synthetically generated by the teacher model. In response to this limitation, we present a novel image-free distillation scheme named $\textbf{SwiftBrush}$. Drawing inspiration from text-to-3D synthesis, in which a 3D neural radiance field that aligns with the input prompt can be obtained from a 2D text-to-image diffusion prior via a specialized loss without the use of any 3D data ground-truth, our approach re-purposes that same loss for distilling a pretrained multi-step text-to-image model to a student network that can generate high-fidelity images with just a single inference step. In spite of its simplicity, our model stands as one of the first one-step text-to-image generators that can produce images of comparable quality to Stable Diffusion without reliance on any training image data. Remarkably, SwiftBrush achieves an FID score of $\textbf{16.67}$ and a CLIP score of $\textbf{0.29}$ on the COCO-30K benchmark, achieving competitive results or even substantially surpassing existing state-of-the-art distillation techniques.
Authors: Gustavo Perez, Daniel Sheldon, Grant Van Horn, Subhransu Maji
Abstract: Computer vision-based re-identification (Re-ID) systems are increasingly being deployed for estimating population size in large image collections. However, the estimated size can be significantly inaccurate when the task is challenging or when deployed on data from new distributions. We propose a human-in-the-loop approach for estimating population size driven by a pairwise similarity derived from an off-the-shelf Re-ID system. Our approach, based on nested importance sampling, selects pairs of images for human vetting driven by the pairwise similarity, and produces asymptotically unbiased population size estimates with associated confidence intervals. We perform experiments on various animal Re-ID datasets and demonstrate that our method outperforms strong baselines and active clustering approaches. In many cases, we are able to reduce the error rates of the estimated size from around 80% using CV alone to less than 20% by vetting a fraction (often less than 0.002%) of the total pairs. The cost of vetting reduces with the increase in accuracy and provides a practical approach for population size estimation within a desired tolerance when deploying Re-ID systems.
Authors: Sheng Jin, Shuhuai Li, Tong Li, Wentao Liu, Chen Qian, Ping Luo
Abstract: Human-centric perception (e.g. detection, segmentation, pose estimation, and attribute analysis) is a long-standing problem for computer vision. This paper introduces a unified and versatile framework (HQNet) for single-stage multi-person multi-task human-centric perception (HCP). Our approach centers on learning a unified human query representation, denoted as Human Query, which captures intricate instance-level features for individual persons and disentangles complex multi-person scenarios. Although different HCP tasks have been well-studied individually, single-stage multi-task learning of HCP tasks has not been fully exploited in the literature due to the absence of a comprehensive benchmark dataset. To address this gap, we propose COCO-UniHuman benchmark to enable model development and comprehensive evaluation. Experimental results demonstrate the proposed method's state-of-the-art performance among multi-task HCP models and its competitive performance compared to task-specific HCP models. Moreover, our experiments underscore Human Query's adaptability to new HCP tasks, thus demonstrating its robust generalization capability. Codes and data are available at https://github.com/lishuhuai527/COCO-UniHuman.
Authors: Tanveer Hannan, Md Mohaiminul Islam, Thomas Seidl, Gedas Bertasius
Abstract: Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply integrates clip retrieval and grounding into a single network capable of processing long videos into multiple granular levels, e.g., clips and frames. Its core component is a novel transformer encoder, RG-Encoder, that unifies the two stages through shared features and mutual optimization. The encoder incorporates a sparse attention mechanism and an attention loss to model both granularity jointly. Moreover, we introduce a contrastive clip sampling technique to mimic the long video paradigm closely during training. RGNet surpasses prior methods, showcasing state-of-the-art performance on long video temporal grounding (LVTG) datasets MAD and Ego4D.
Authors: Xueyan Zou, Linjie Li, Jianfeng Wang, Jianwei Yang, Mingyu Ding, Junyi Wei, Zhengyuan Yang, Feng Li, Hao Zhang, Shilong Liu, Arul Aravinthan, Yong Jae Lee, Lijuan Wang
Abstract: Foundation models possess strong capabilities in reasoning and memorizing across modalities. To further unleash the power of foundation models, we present FIND, a generalized interface for aligning foundation models' embeddings with unified image and dataset-level understanding spanning modality and granularity. As shown in the teaser figure, a lightweight transformer interface without tuning any foundation model weights is enough for segmentation, grounding, and retrieval in an interleaved manner. The proposed interface has the following favorable attributes: (1) Generalizable. It applies to various tasks spanning retrieval, segmentation, etc., under the same architecture and weights. (2) Interleavable. With the benefit of multi-task multi-modal training, the proposed interface creates an interleaved shared embedding space. (3) Extendable. The proposed interface is adaptive to new tasks, and new models. In light of the interleaved embedding space, we introduce FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleaved segmentation and retrieval. We are the first work aligning foundations models' embeddings for interleave understanding. Meanwhile, our approach achieves state-of-the-art performance on FIND-Bench and competitive performance on standard retrieval and segmentation settings.
Authors: Gu\'enol\'e Fiche, Simon Leglaive, Xavier Alameda-Pineda, Antonio Agudo, Francesc Moreno-Noguer
Abstract: Previous works on Human Pose and Shape Estimation (HPSE) from RGB images can be broadly categorized into two main groups: parametric and non-parametric approaches. Parametric techniques leverage a low-dimensional statistical body model for realistic results, whereas recent non-parametric methods achieve higher precision by directly regressing the 3D coordinates of the human body mesh. This work introduces a novel paradigm to address the HPSE problem, involving a low-dimensional discrete latent representation of the human mesh and framing HPSE as a classification task. Instead of predicting body model parameters or 3D vertex coordinates, we focus on predicting the proposed discrete latent representation, which can be decoded into a registered human mesh. This innovative paradigm offers two key advantages. Firstly, predicting a low-dimensional discrete representation confines our predictions to the space of anthropomorphic poses and shapes even when little training data is available. Secondly, by framing the problem as a classification task, we can harness the discriminative power inherent in neural networks. The proposed model, VQ-HPS, predicts the discrete latent representation of the mesh. The experimental results demonstrate that VQ-HPS outperforms the current state-of-the-art non-parametric approaches while yielding results as realistic as those produced by parametric methods when trained with little data. VQ-HPS also shows promising results when training on large-scale datasets, highlighting the significant potential of the classification approach for HPSE. See the project page at https://g-fiche.github.io/research-pages/vqhps/
Authors: Animesh Karnewar, Roman Shapovalov, Tom Monnier, Andrea Vedaldi, Niloy J. Mitra, David Novotny
Abstract: Encoding information from 2D views of an object into a 3D representation is crucial for generalized 3D feature extraction. Such features can then enable 3D reconstruction, 3D generation, and other applications. We propose GOEmbed (Gradient Origin Embeddings) that encodes input 2D images into any 3D representation, without requiring a pre-trained image feature extractor; unlike typical prior approaches in which input images are either encoded using 2D features extracted from large pre-trained models, or customized features are designed to handle different 3D representations; or worse, encoders may not yet be available for specialized 3D neural representations such as MLPs and hash-grids. We extensively evaluate our proposed GOEmbed under different experimental settings on the OmniObject3D benchmark. First, we evaluate how well the mechanism compares against prior encoding mechanisms on multiple 3D representations using an illustrative experiment called Plenoptic-Encoding. Second, the efficacy of the GOEmbed mechanism is further demonstrated by achieving a new SOTA FID of 22.12 on the OmniObject3D generation task using a combination of GOEmbed and DFM (Diffusion with Forward Models), which we call GOEmbedFusion. Finally, we evaluate how the GOEmbed mechanism bolsters sparse-view 3D reconstruction pipelines.
Authors: Zexiang Liu, Yangguang Li, Youtian Lin, Xin Yu, Sida Peng, Yan-Pei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, Wanli Ouyang
Abstract: Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects. Despite these developments, a prevalent limitation arises from the use of RGB data in diffusion or reconstruction models, which often results in models with inherent lighting and shadows effects that detract from their realism, thereby limiting their usability in applications that demand accurate relighting capabilities. To bridge this gap, we present UniDream, a text-to-3D generation framework by incorporating unified diffusion priors. Our approach consists of three main components: (1) a dual-phase training process to get albedo-normal aligned multi-view diffusion and reconstruction models, (2) a progressive generation procedure for geometry and albedo-textures based on Score Distillation Sample (SDS) using the trained reconstruction and diffusion models, and (3) an innovative application of SDS for finalizing PBR generation while keeping a fixed albedo based on Stable Diffusion model. Extensive evaluations demonstrate that UniDream surpasses existing methods in generating 3D objects with clearer albedo textures, smoother surfaces, enhanced realism, and superior relighting capabilities.
Authors: Jiafeng Mao, Xueting Wang, Kiyoharu Aizawa
Abstract: Text-to-image diffusion models allow users control over the content of generated images. Still, text-to-image generation occasionally leads to generation failure requiring users to generate dozens of images under the same text prompt before they obtain a satisfying result. We formulate the lottery ticket hypothesis in denoising: randomly initialized Gaussian noise images contain special pixel blocks (winning tickets) that naturally tend to be denoised into specific content independently. The generation failure in standard text-to-image synthesis is caused by the gap between optimal and actual spatial distribution of winning tickets in initial noisy images. To this end, we implement semantic-driven initial image construction creating initial noise from known winning tickets for each concept mentioned in the prompt. We conduct a series of experiments that verify the properties of winning tickets and demonstrate their generalizability across images and prompts. Our results show that aggregating winning tickets into the initial noise image effectively induce the model to generate the specified object at the corresponding location.
Authors: Dongchen Han, Tianzhu Ye, Yizeng Han, Zhuofan Xia, Siyuan Pan, Pengfei Wan, Shiji Song, Gao Huang
Abstract: The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel attention paradigm, Agent Attention, to strike a favorable balance between computational efficiency and representation power. Specifically, the Agent Attention, denoted as a quadruple $(Q, A, K, V)$, introduces an additional set of agent tokens $A$ into the conventional attention module. The agent tokens first act as the agent for the query tokens $Q$ to aggregate information from $K$ and $V$, and then broadcast the information back to $Q$. Given the number of agent tokens can be designed to be much smaller than the number of query tokens, the agent attention is significantly more efficient than the widely adopted Softmax attention, while preserving global context modelling capability. Interestingly, we show that the proposed agent attention is equivalent to a generalized form of linear attention. Therefore, agent attention seamlessly integrates the powerful Softmax attention and the highly efficient linear attention. Extensive experiments demonstrate the effectiveness of agent attention with various vision Transformers and across diverse vision tasks, including image classification, object detection, semantic segmentation and image generation. Notably, agent attention has shown remarkable performance in high-resolution scenarios, owning to its linear attention nature. For instance, when applied to Stable Diffusion, our agent attention accelerates generation and substantially enhances image generation quality without any additional training. Code is available at https://github.com/LeapLabTHU/Agent-Attention.
Authors: Zhiyuan You, Zheyuan Li, Jinjin Gu, Zhenfei Yin, Tianfan Xue, Chao Dong
Abstract: We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods. DepictQA allows for detailed, language-based, human-like evaluation of image quality by leveraging Multi-modal Large Language Models (MLLMs). Unlike conventional Image Quality Assessment (IQA) methods relying on scores, DepictQA interprets image content and distortions descriptively and comparatively, aligning closely with humans' reasoning process. To build the DepictQA model, we establish a hierarchical task framework, and collect a multi-modal IQA training dataset. To tackle the challenges of limited training data and multi-image processing, we propose to use multi-source training data and specialized image tags. These designs result in a better performance of DepictQA than score-based approaches on multiple benchmarks. Moreover, compared with general MLLMs, DepictQA can generate more accurate reasoning descriptive languages. We also demonstrate that our full-reference dataset can be extended to non-reference applications. These results showcase the research potential of multi-modal IQA methods. Codes and datasets are available in https://depictqa.github.io.
Authors: Umar Khalid, Hasan Iqbal, Nazmul Karim, Jing Hua, Chen Chen
Abstract: While neural fields have made significant strides in view synthesis and scene reconstruction, editing them poses a formidable challenge due to their implicit encoding of geometry and texture information from multi-view inputs. In this paper, we introduce \textsc{LatentEditor}, an innovative framework designed to empower users with the ability to perform precise and locally controlled editing of neural fields using text prompts. Leveraging denoising diffusion models, we successfully embed real-world scenes into the latent space, resulting in a faster and more adaptable NeRF backbone for editing compared to traditional methods. To enhance editing precision, we introduce a delta score to calculate the 2D mask in the latent space that serves as a guide for local modifications while preserving irrelevant regions. Our novel pixel-level scoring approach harnesses the power of InstructPix2Pix (IP2P) to discern the disparity between IP2P conditional and unconditional noise predictions in the latent space. The edited latents conditioned on the 2D masks are then iteratively updated in the training set to achieve 3D local editing. Our approach achieves faster editing speeds and superior output quality compared to existing 3D editing models, bridging the gap between textual instructions and high-quality 3D scene editing in latent space. We show the superiority of our approach on four benchmark 3D datasets, LLFF, IN2N, NeRFStudio and NeRF-Art. Project Page: https://latenteditor.github.io/
Authors: Pierluigi Zama Ramirez, Luca De Luigi, Daniele Sirocchi, Adriano Cardace, Riccardo Spezialetti, Francesco Ballerini, Samuele Salti, Luigi Di Stefano
Abstract: In recent years, Neural Fields (NFs) have emerged as an effective tool for encoding diverse continuous signals such as images, videos, audio, and 3D shapes. When applied to 3D data, NFs offer a solution to the fragmentation and limitations associated with prevalent discrete representations. However, given that NFs are essentially neural networks, it remains unclear whether and how they can be seamlessly integrated into deep learning pipelines for solving downstream tasks. This paper addresses this research problem and introduces nf2vec, a framework capable of generating a compact latent representation for an input NF in a single inference pass. We demonstrate that nf2vec effectively embeds 3D objects represented by the input NFs and showcase how the resulting embeddings can be employed in deep learning pipelines to successfully address various tasks, all while processing exclusively NFs. We test this framework on several NFs used to represent 3D surfaces, such as unsigned/signed distance and occupancy fields. Moreover, we demonstrate the effectiveness of our approach with more complex NFs that encompass both geometry and appearance of 3D objects such as neural radiance fields.
Authors: Nazmul Karim, Hasan Iqbal, Umar Khalid, Jing Hua, Chen Chen
Abstract: Text-to-Image (T2I) diffusion models have recently gained traction for their versatility and user-friendliness in 2D content generation and editing. However, training a diffusion model specifically for 3D scene editing is challenging due to the scarcity of large-scale datasets. Currently, editing 3D scenes necessitates either retraining the model to accommodate various 3D edits or developing specific methods tailored to each unique editing type. Moreover, state-of-the-art (SOTA) techniques require multiple synchronized edited images from the same scene to enable effective scene editing. Given the current limitations of T2I models, achieving consistent editing effects across multiple images remains difficult, leading to multi-view inconsistency in editing. This inconsistency undermines the performance of 3D scene editing when these images are utilized. In this study, we introduce a novel, training-free 3D scene editing technique called \textsc{Free-Editor}, which enables users to edit 3D scenes without the need for model retraining during the testing phase. Our method effectively addresses the issue of multi-view style inconsistency found in state-of-the-art (SOTA) methods through the implementation of a single-view editing scheme. Specifically, we demonstrate that editing a particular 3D scene can be achieved by modifying only a single view. To facilitate this, we present an Edit Transformer that ensures intra-view consistency and inter-view style transfer using self-view and cross-view attention mechanisms, respectively. By eliminating the need for model retraining and multi-view editing, our approach significantly reduces editing time and memory resource requirements, achieving runtimes approximately 20 times faster than SOTA methods. We have performed extensive experiments on various benchmark datasets, showcasing the diverse editing capabilities of our proposed technique.
Authors: Haiyang Guo, Fei Zhu, Wenzhuo Liu, Xu-Yao Zhang, Cheng-Lin Liu
Abstract: Existing federated learning methods have effectively dealt with decentralized learning in scenarios involving data privacy and non-IID data. However, in real-world situations, each client dynamically learns new classes, requiring the global model to classify all seen classes. To effectively mitigate catastrophic forgetting and data heterogeneity under low communication costs, we propose a simple and effective method named PILoRA. On the one hand, we adopt prototype learning to learn better feature representations and leverage the heuristic information between prototypes and class features to design a prototype re-weight module to solve the classifier bias caused by data heterogeneity without retraining the classifier. On the other hand, we view incremental learning as the process of learning distinct task vectors and encoding them within different LoRA parameters. Accordingly, we propose Incremental LoRA to mitigate catastrophic forgetting. Experimental results on standard datasets indicate that our method outperforms the state-of-the-art approaches significantly. More importantly, our method exhibits strong robustness and superiority in different settings and degrees of data heterogeneity. The code is available at \url{https://github.com/Ghy0501/PILoRA}.
Authors: Lukas Meyer, Floris Erich, Yusuke Yoshiyasu, Marc Stamminger, Noriaki Ando, Yukiyasu Domae
Abstract: We introduce Physically Enhanced Gaussian Splatting Simulation System (PEGASUS) for 6DOF object pose dataset generation, a versatile dataset generator based on 3D Gaussian Splatting. Environment and object representations can be easily obtained using commodity cameras to reconstruct with Gaussian Splatting. PEGASUS allows the composition of new scenes by merging the respective underlying Gaussian Splatting point cloud of an environment with one or multiple objects. Leveraging a physics engine enables the simulation of natural object placement within a scene through interaction between meshes extracted for the objects and the environment. Consequently, an extensive amount of new scenes - static or dynamic - can be created by combining different environments and objects. By rendering scenes from various perspectives, diverse data points such as RGB images, depth maps, semantic masks, and 6DoF object poses can be extracted. Our study demonstrates that training on data generated by PEGASUS enables pose estimation networks to successfully transfer from synthetic data to real-world data. Moreover, we introduce the Ramen dataset, comprising 30 Japanese cup noodle items. This dataset includes spherical scans that captures images from both object hemisphere and the Gaussian Splatting reconstruction, making them compatible with PEGASUS.
Authors: Seung Hyun Lee, Yinxiao Li, Junjie Ke, Innfarn Yoo, Han Zhang, Jiahui Yu, Qifei Wang, Fei Deng, Glenn Entis, Junfeng He, Gang Li, Sangpil Kim, Irfan Essa, Feng Yang
Abstract: Recent works have demonstrated that using reinforcement learning (RL) with multiple quality rewards can improve the quality of generated images in text-to-image (T2I) generation. However, manually adjusting reward weights poses challenges and may cause over-optimization in certain metrics. To solve this, we propose Parrot, which addresses the issue through multi-objective optimization and introduces an effective multi-reward optimization strategy to approximate Pareto optimal. Utilizing batch-wise Pareto optimal selection, Parrot automatically identifies the optimal trade-off among different rewards. We use the novel multi-reward optimization algorithm to jointly optimize the T2I model and a prompt expansion network, resulting in significant improvement of image quality and also allow to control the trade-off of different rewards using a reward related prompt during inference. Furthermore, we introduce original prompt-centered guidance at inference time, ensuring fidelity to user input after prompt expansion. Extensive experiments and a user study validate the superiority of Parrot over several baselines across various quality criteria, including aesthetics, human preference, text-image alignment, and image sentiment.
Authors: Kumara Kahatapitiya, Adil Karjauv, Davide Abati, Fatih Porikli, Yuki M. Asano, Amirhossein Habibian
Abstract: This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion alignment, such as optical flow, we propose a novel knowledge distillation schema coined as Delta Distillation. In our proposal, the student learns the variations in the teacher's intermediate features over time. We demonstrate that these temporal variations can be effectively distilled due to the temporal redundancies within video frames. During inference, both teacher and student cooperate for providing predictions: the former by providing initial representations extracted only on the key-frame, and the latter by iteratively estimating and applying deltas for the successive frames. Moreover, we consider various design choices to learn optimal student architectures including an end-to-end learnable architecture search. By extensive experiments on a wide range of architectures, including the most efficient ones, we demonstrate that delta distillation sets a new state of the art in terms of accuracy vs. efficiency trade-off for semantic segmentation and object detection in videos. Finally, we show that, as a by-product, delta distillation improves the temporal consistency of the teacher model.
Authors: Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev
Abstract: Recent studies have shown that Text-to-Image (T2I) model generations can reflect social stereotypes present in the real world. However, existing approaches for evaluating stereotypes have a noticeable lack of coverage of global identity groups and their associated stereotypes. To address this gap, we introduce the ViSAGe (Visual Stereotypes Around the Globe) dataset to enable the evaluation of known nationality-based stereotypes in T2I models, across 135 nationalities. We enrich an existing textual stereotype resource by distinguishing between stereotypical associations that are more likely to have visual depictions, such as `sombrero', from those that are less visually concrete, such as 'attractive'. We demonstrate ViSAGe's utility through a multi-faceted evaluation of T2I generations. First, we show that stereotypical attributes in ViSAGe are thrice as likely to be present in generated images of corresponding identities as compared to other attributes, and that the offensiveness of these depictions is especially higher for identities from Africa, South America, and South East Asia. Second, we assess the stereotypical pull of visual depictions of identity groups, which reveals how the 'default' representations of all identity groups in ViSAGe have a pull towards stereotypical depictions, and that this pull is even more prominent for identity groups from the Global South. CONTENT WARNING: Some examples contain offensive stereotypes.
Authors: Lintai Wu, Junhui Hou, Linqi Song, Yong Xu
Abstract: 3D shapes captured by scanning devices are often incomplete due to occlusion. 3D shape completion methods have been explored to tackle this limitation. However, most of these methods are only trained and tested on a subset of categories, resulting in poor generalization to unseen categories. In this paper, we introduce a novel weakly-supervised framework to reconstruct the complete shapes from unseen categories. We first propose an end-to-end prior-assisted shape learning network that leverages data from the seen categories to infer a coarse shape. Specifically, we construct a prior bank consisting of representative shapes from the seen categories. Then, we design a multi-scale pattern correlation module for learning the complete shape of the input by analyzing the correlation between local patterns within the input and the priors at various scales. In addition, we propose a self-supervised shape refinement model to further refine the coarse shape. Considering the shape variability of 3D objects across categories, we construct a category-specific prior bank to facilitate shape refinement. Then, we devise a voxel-based partial matching loss and leverage the partial scans to drive the refinement process. Extensive experimental results show that our approach is superior to state-of-the-art methods by a large margin.
Authors: Haibi Wang, Weifeng Ge
Abstract: With the breakthrough of multi-modal large language models, answering complex visual questions that demand advanced reasoning abilities and world knowledge has become a much more important testbed for developing AI models than ever. However, equipping AI models with robust cross-modality reasoning ability remains challenging since the cognition scheme of humans has not been understood systematically. In this paper, we believe that if we can collect visual clues in the given image as much as possible, we will recognize the image more accurately, understand the question better, recall relevant knowledge more easily, and finally reason out the answer. We discover these rich visual clues by mining question-answer pairs in images and sending them into multi-modal large language models as prompts. We call the proposed method Q&A Prompts. Specifically, we first use the image-answer pairs and the corresponding questions in the training set as inputs and outputs to train a visual question generation model. Then, we use an image tagging model to identify various instances and send packaged image-tag pairs into the visual question generation model to generate relevant questions with the extracted image tags as answers. Finally, we encode these generated question-answer pairs as prompts with a visual-aware prompting module and send them into pre-trained multi-modal large language models to reason out the final answers. Experimental results show that, compared with state-of-the-art methods, our Q&A Prompts achieves substantial improvements on the challenging visual question answering datasets requiring reasoning over diverse world knowledge, such as OK-VQA and A-OKVQA.
Authors: Guoxin Si, Shiliang Fu, Wei Yao
Abstract: As global warming intensifies, increased attention is being paid to monitoring fugitive methane emissions and detecting gas plumes from landfills. We have divided methane emission monitoring into three subtasks: methane concentration inversion, plume segmentation, and emission rate estimation. Traditional algorithms face certain limitations: methane concentration inversion typically employs the matched filter, which is sensitive to the global spectrum distribution and prone to significant noise. There is scant research on plume segmentation, with many studies depending on manual segmentation, which can be subjective. The estimation of methane emission rate frequently uses the IME algorithm, which necessitates meteorological measurement data. Utilizing the WENT landfill site in Hong Kong along with PRISMA hyperspectral satellite imagery, we introduce a novel deep learning-based framework for quantitative methane emission monitoring from remote sensing images that is grounded in physical simulation. We create simulated methane plumes using large eddy simulation (LES) and various concentration maps of fugitive emissions using the radiative transfer equation (RTE), while applying augmentation techniques to construct a simulated PRISMA dataset. We train a U-Net network for methane concentration inversion, a Mask R-CNN network for methane plume segmentation, and a ResNet-50 network for methane emission rate estimation. All three deep networks yield higher validation accuracy compared to traditional algorithms. Furthermore, we combine the first two subtasks and the last two subtasks to design multi-task learning models, MTL-01 and MTL-02, both of which outperform single-task models in terms of accuracy. Our research exemplifies the application of multi-task deep learning to quantitative methane monitoring and can be generalized to a wide array of methane monitoring tasks.
Authors: Baoxing Li, Yong Deng, Yehui Yang, Xu Zhao
Abstract: To reconstruct a 3D human surface from a single image, it is crucial to simultaneously consider human pose, shape, and clothing details. Recent approaches have combined parametric body models (such as SMPL), which capture body pose and shape priors, with neural implicit functions that flexibly learn clothing details. However, this combined representation introduces additional computation, e.g. signed distance calculation in 3D body feature extraction, leading to redundancy in the implicit query-and-infer process and failing to preserve the underlying body shape prior. To address these issues, we propose a novel IUVD-Feedback representation, consisting of an IUVD occupancy function and a feedback query algorithm. This representation replaces the time-consuming signed distance calculation with a simple linear transformation in the IUVD space, leveraging the SMPL UV maps. Additionally, it reduces redundant query points through a feedback mechanism, leading to more reasonable 3D body features and more effective query points, thereby preserving the parametric body prior. Moreover, the IUVD-Feedback representation can be embedded into any existing implicit human reconstruction pipeline without requiring modifications to the trained neural networks. Experiments on the THuman2.0 dataset demonstrate that the proposed IUVD-Feedback representation improves the robustness of results and achieves three times faster acceleration in the query-and-infer process. Furthermore, this representation holds potential for generative applications by leveraging its inherent semantic information from the parametric body model.
Authors: Long Ma, Jiajia Zhang, Hongping Deng, Ningyu Zhang, Qinglang Guo, Haiyang Yu, Yong Liao, Pengyuan Zhou
Abstract: The escalating quality of video generated by advanced video generation methods results in new security challenges, while there have been few relevant research efforts: 1) There is no open-source dataset for generated video detection, 2) No generated video detection method has been proposed so far. To this end, we propose an open-source dataset and a detection method for generated video for the first time. First, we propose a scalable dataset consisting of 964 prompts, covering various forgery targets, scenes, behaviors, and actions, as well as various generation models with different architectures and generation methods, including the most popular commercial models like OpenAI's Sora and Google's Veo. Second, we found via probing experiments that spatial artifact-based detectors lack generalizability. Hence, we propose a simple yet effective \textbf{de}tection model based on \textbf{f}rame \textbf{co}nsistency (\textbf{DeCoF}), which focuses on temporal artifacts by eliminating the impact of spatial artifacts during feature learning. Extensive experiments demonstrate the efficacy of DeCoF in detecting videos generated by unseen video generation models and confirm its powerful generalizability across several commercially proprietary models. Our code and dataset will be released at \url{https://github.com/wuwuwuyue/DeCoF}.
Authors: Xixu Hu, Runkai Zheng, Jindong Wang, Cheuk Hang Leung, Qi Wu, Xing Xie
Abstract: Vision Transformers (ViTs) are increasingly used in computer vision due to their high performance, but their vulnerability to adversarial attacks is a concern. Existing methods lack a solid theoretical basis, focusing mainly on empirical training adjustments. This study introduces SpecFormer, tailored to fortify ViTs against adversarial attacks, with theoretical underpinnings. We establish local Lipschitz bounds for the self-attention layer and propose the Maximum Singular Value Penalization (MSVP) to precisely manage these bounds By incorporating MSVP into ViTs' attention layers, we enhance the model's robustness without compromising training efficiency. SpecFormer, the resulting model, outperforms other state-of-the-art models in defending against adversarial attacks, as proven by experiments on CIFAR and ImageNet datasets. Code is released at https://github.com/microsoft/robustlearn.
Authors: Shufan Li, Harkanwar Singh, Aditya Grover
Abstract: In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs prohibitive compute and memory complexity that scales quadratically w.r.t. the sequence length. A recent architecture, Mamba, based on state space models has been shown to achieve comparable performance for modeling text sequences, while scaling linearly with the sequence length. In this work, we present Mamba-ND, a generalized design extending the Mamba architecture to arbitrary multi-dimensional data. Our design alternatively unravels the input data across different dimensions following row-major orderings. We provide a systematic comparison of Mamba-ND with several other alternatives, based on prior multi-dimensional extensions such as Bi-directional LSTMs and S4ND. Empirically, we show that Mamba-ND demonstrates performance competitive with the state-of-the-art on a variety of multi-dimensional benchmarks, including ImageNet-1K classification, HMDB-51 action recognition, and ERA5 weather forecasting.
Authors: Jihai Zhang, Xiang Lan, Xiaoye Qu, Yu Cheng, Mengling Feng, Bryan Hooi
Abstract: Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a phenomenon where the trained model captures only a limited portion of the information from the input data while overlooking other potentially valuable content. This issue often leads to indistinguishable representations for visually similar but semantically different inputs, adversely affecting downstream task performance, particularly those requiring rigorous semantic comprehension. To address this challenge, we propose a novel model-agnostic Multistage Contrastive Learning (MCL) framework. Unlike standard contrastive learning which inherently captures one single biased feature distribution, MCL progressively learns previously unlearned features through feature-aware negative sampling at each stage, where the negative samples of an anchor are exclusively selected from the cluster it was assigned to in preceding stages. Meanwhile, MCL preserves the previously well-learned features by cross-stage representation integration, integrating features across all stages to form final representations. Our comprehensive evaluation demonstrates MCL's effectiveness and superiority across both unimodal and multimodal contrastive learning, spanning a range of model architectures from ResNet to Vision Transformers (ViT). Remarkably, in tasks where the original CLIP model has shown limitations, MCL dramatically enhances performance, with improvements up to threefold on specific attributes in the recently proposed MMVP benchmark.
Authors: Yi Zhang, Yun Tang, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, Paul Jennings, Xingyu Zhao
Abstract: Text-to-Image (T2I) Diffusion Models (DMs) have shown impressive abilities in generating high-quality images based on simple text descriptions. However, as is common with many Deep Learning (DL) models, DMs are subject to a lack of robustness. While there are attempts to evaluate the robustness of T2I DMs as a binary or worst-case problem, they cannot answer how robust in general the model is whenever an adversarial example (AE) can be found. In this study, we first introduce a probabilistic notion of T2I DMs' robustness; and then establish an efficient framework, ProTIP, to evaluate it with statistical guarantees. The main challenges stem from: i) the high computational cost of the generation process; and ii) determining if a perturbed input is an AE involves comparing two output distributions, which is fundamentally harder compared to other DL tasks like classification where an AE is identified upon misprediction of labels. To tackle the challenges, we employ sequential analysis with efficacy and futility early stopping rules in the statistical testing for identifying AEs, and adaptive concentration inequalities to dynamically determine the "just-right" number of stochastic perturbations whenever the verification target is met. Empirical experiments validate the effectiveness and efficiency of ProTIP over common T2I DMs. Finally, we demonstrate an application of ProTIP to rank commonly used defence methods.
Authors: Pau de Jorge, Riccardo Volpi, Puneet K. Dokania, Philip H. S. Torr, Gregory Rogez
Abstract: When deploying a semantic segmentation model into the real world, it will inevitably encounter semantic classes that were not seen during training. To ensure a safe deployment of such systems, it is crucial to accurately evaluate and improve their anomaly segmentation capabilities. However, acquiring and labelling semantic segmentation data is expensive and unanticipated conditions are long-tail and potentially hazardous. Indeed, existing anomaly segmentation datasets capture a limited number of anomalies, lack realism or have strong domain shifts. In this paper, we propose the Placing Objects in Context (POC) pipeline to realistically add any object into any image via diffusion models. POC can be used to easily extend any dataset with an arbitrary number of objects. In our experiments, we present different anomaly segmentation datasets based on POC-generated data and show that POC can improve the performance of recent state-of-the-art anomaly fine-tuning methods across several standardized benchmarks. POC is also effective for learning new classes. For example, we utilize it to augment Cityscapes samples by incorporating a subset of Pascal classes and demonstrate that models trained on such data achieve comparable performance to the Pascal-trained baseline. This corroborates the low synth2real gap of models trained on POC-generated images. Code: https://github.com/naver/poc
Authors: Seong Hun Lee, Javier Civera, Patrick Vandewalle
Abstract: We propose a robust method for point cloud registration that can handle both unknown scales and extreme outlier ratios. Our method, dubbed PCR-99, uses a deterministic 3-point sampling approach with two novel mechanisms that significantly boost the speed: (1) an improved ordering of the samples based on pairwise scale consistency, prioritizing the point correspondences that are more likely to be inliers, and (2) an efficient outlier rejection scheme based on triplet scale consistency, prescreening bad samples and reducing the number of hypotheses to be tested. Our evaluation shows that, up to 98% outlier ratio, the proposed method achieves comparable performance to the state of the art. At 99% outlier ratio, however, it outperforms the state of the art for both known-scale and unknown-scale problems. Especially for the latter, we observe a clear superiority in terms of robustness and speed.
Authors: Zhewei Wu, Ruilong Yu, Qihe Liu, Shuying Cheng, Shilin Qiu, Shijie Zhou
Abstract: Adversarial attacks in visual object tracking have significantly degraded the performance of advanced trackers by introducing imperceptible perturbations into images. However, there is still a lack of research on designing adversarial defense methods for object tracking. To address these issues, we propose an effective auxiliary pre-processing defense network, AADN, which performs defensive transformations on the input images before feeding them into the tracker. Moreover, it can be seamlessly integrated with other visual trackers as a plug-and-play module without parameter adjustments. We train AADN using adversarial training, specifically employing Dua-Loss to generate adversarial samples that simultaneously attack the classification and regression branches of the tracker. Extensive experiments conducted on the OTB100, LaSOT, and VOT2018 benchmarks demonstrate that AADN maintains excellent defense robustness against adversarial attack methods in both adaptive and non-adaptive attack scenarios. Moreover, when transferring the defense network to heterogeneous trackers, it exhibits reliable transferability. Finally, AADN achieves a processing time of up to 5ms/frame, allowing seamless integration with existing high-speed trackers without introducing significant computational overhead.
Authors: Muyang Li, Tianle Cai, Jiaxin Cao, Qinsheng Zhang, Han Cai, Junjie Bai, Yangqing Jia, Ming-Yu Liu, Kai Li, Song Han
Abstract: Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting in a prohibitive latency for interactive applications. In this paper, we propose DistriFusion to tackle this problem by leveraging parallelism across multiple GPUs. Our method splits the model input into multiple patches and assigns each patch to a GPU. However, naively implementing such an algorithm breaks the interaction between patches and loses fidelity, while incorporating such an interaction will incur tremendous communication overhead. To overcome this dilemma, we observe the high similarity between the input from adjacent diffusion steps and propose displaced patch parallelism, which takes advantage of the sequential nature of the diffusion process by reusing the pre-computed feature maps from the previous timestep to provide context for the current step. Therefore, our method supports asynchronous communication, which can be pipelined by computation. Extensive experiments show that our method can be applied to recent Stable Diffusion XL with no quality degradation and achieve up to a 6.1$\times$ speedup on eight NVIDIA A100s compared to one. Our code is publicly available at https://github.com/mit-han-lab/distrifuser.
Authors: Yuxi Liu, Wenhan Yang, Huihui Bai, Yunchao Wei, Yao Zhao
Abstract: Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural transform that focuses on specific regions. In response, we introduce the class-agnostic segmentation masks (i.e. semantic masks without category labels) for extracting region-adaptive contextual information. Our proposed module, Region-Adaptive Transform, applies adaptive convolutions on different regions guided by the masks. Additionally, we introduce a plug-and-play module named Scale Affine Layer to incorporate rich contexts from various regions. While there have been prior image compression efforts that involve segmentation masks as additional intermediate inputs, our approach differs significantly from them. Our advantages lie in that, to avoid extra bitrate overhead, we treat these masks as privilege information, which is accessible during the model training stage but not required during the inference phase. To the best of our knowledge, we are the first to employ class-agnostic masks as privilege information and achieve superior performance in pixel-fidelity metrics, such as Peak Signal to Noise Ratio (PSNR). The experimental results demonstrate our improvement compared to previously well-performing methods, with about 8.2% bitrate saving compared to VTM-17.0. The source code is available at https://github.com/GityuxiLiu/SegPIC-for-Image-Compression.
URLs: https://github.com/GityuxiLiu/SegPIC-for-Image-Compression.
Authors: Yuli Wu, Julian Wittmann, Peter Walter, Johannes Stegmaier
Abstract: Implantable retinal prostheses offer a promising solution to restore partial vision by circumventing damaged photoreceptor cells in the retina and directly stimulating the remaining functional retinal cells. However, the information transmission between the camera and retinal cells is often limited by the low resolution of the electrode array and the lack of specificity for different ganglion cell types, resulting in suboptimal stimulations. In this work, we propose to utilize normalizing flow-based conditional invertible neural networks to optimize retinal implant stimulation in an unsupervised manner. The invertibility of these networks allows us to use them as a surrogate for the computational model of the visual system, while also encoding input camera signals into optimized electrical stimuli on the electrode array. Compared to other methods, such as trivial downsampling, linear models, and feed-forward convolutional neural networks, the flow-based invertible neural network and its conditional extension yield better visual reconstruction qualities w.r.t. various metrics using a physiologically validated simulation tool.
Authors: Ruinan Jin, Wenlong Deng, Minghui Chen, Xiaoxiao Li
Abstract: In the era of Foundation Models' (FMs) rising prominence in AI, our study addresses the challenge of biases in medical images while the model operates in black-box (e.g., using FM API), particularly spurious correlations between pixels and sensitive attributes. Traditional methods for bias mitigation face limitations due to the restricted access to web-hosted FMs and difficulties in addressing the underlying bias encoded within the FM API. We propose a D(ebiased) N(oise) E(diting) strategy, termed DNE, which generates DNE noise to mask such spurious correlation. DNE is capable of mitigating bias both within the FM API embedding and the images themselves. Furthermore, DNE is suitable for both white-box and black-box FM APIs, where we introduced G(reedy) (Z)eroth-O(rder) (GeZO) optimization for it when the gradient is inaccessible in black-box APIs. Our whole pipeline enables fairness-aware image editing that can be applied across various medical contexts without requiring direct model manipulation or significant computational resources. Our empirical results demonstrate the method's effectiveness in maintaining fairness and utility across different patient groups and diseases. In the era of AI-driven medicine, this work contributes to making healthcare diagnostics more equitable, showcasing a practical solution for bias mitigation in pre-trained image FMs. Our code is provided at https://github.com/ubc-tea/DNE-foundation-model-fairness.
URLs: https://github.com/ubc-tea/DNE-foundation-model-fairness.
Authors: Byung-Kwan Lee, Beomchan Park, Chae Won Kim, Yong Man Ro
Abstract: The rise of large language models (LLMs) and instruction tuning has led to the current trend of instruction-tuned large language and vision models (LLVMs). This trend involves either meticulously curating numerous instruction tuning datasets tailored to specific objectives or enlarging LLVMs to manage vast amounts of vision language (VL) data. However, current LLVMs have disregarded the detailed and comprehensive real-world scene understanding available from specialized computer vision (CV) models in visual perception tasks such as segmentation, detection, scene graph generation (SGG), and optical character recognition (OCR). Instead, the existing LLVMs rely mainly on the large capacity and emergent capabilities of their LLM backbones. Therefore, we present a new LLVM, Mixture of All Intelligence (MoAI), which leverages auxiliary visual information obtained from the outputs of external segmentation, detection, SGG, and OCR models. MoAI operates through two newly introduced modules: MoAI-Compressor and MoAI-Mixer. After verbalizing the outputs of the external CV models, the MoAI-Compressor aligns and condenses them to efficiently use relevant auxiliary visual information for VL tasks. MoAI-Mixer then blends three types of intelligence (1) visual features, (2) auxiliary features from the external CV models, and (3) language features by utilizing the concept of Mixture of Experts. Through this integration, MoAI significantly outperforms both open-source and closed-source LLVMs in numerous zero-shot VL tasks, particularly those related to real-world scene understanding such as object existence, positions, relations, and OCR without enlarging the model size or curating extra visual instruction tuning datasets.
Authors: Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu
Abstract: We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.
Authors: Tianyuan Yuan, Yucheng Mao, Jiawei Yang, Yicheng Liu, Yue Wang, Hang Zhao
Abstract: Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges persist under conditions like occlusion, extreme lighting, or in unfamiliar urban areas. Unlike these systems, humans do not solely depend on immediate observations to perceive the environment. In navigating new cities, humans gradually develop a preliminary mental map to supplement real-time perception during subsequent visits. Inspired by this human approach, we introduce a novel framework, PreSight, that leverages past traversals to construct static prior memories, enhancing online perception in later navigations. Our method involves optimizing a city-scale neural radiance field with data from previous journeys to generate neural priors. These priors, rich in semantic and geometric details, are derived without manual annotations and can seamlessly augment various state-of-the-art perception models, improving their efficacy with minimal additional computational cost. Experimental results on the nuScenes dataset demonstrate the framework's high compatibility with diverse online perception models. Specifically, it shows remarkable improvements in HD-map construction and occupancy prediction tasks, highlighting its potential as a new perception framework for autonomous driving systems. Our code will be released at https://github.com/yuantianyuan01/PreSight.
Authors: Aleksandr Matsun, Numan Saeed, Fadillah Adamsyah Maani, Mohammad Yaqub
Abstract: Medical data often exhibits distribution shifts, which cause test-time performance degradation for deep learning models trained using standard supervised learning pipelines. This challenge is addressed in the field of Domain Generalization (DG) with the sub-field of Single Domain Generalization (SDG) being specifically interesting due to the privacy- or logistics-related issues often associated with medical data. Existing disentanglement-based SDG methods heavily rely on structural information embedded in segmentation masks, however classification labels do not provide such dense information. This work introduces a novel SDG method aimed at medical image classification that leverages channel-wise contrastive disentanglement. It is further enhanced with reconstruction-based style regularization to ensure extraction of distinct style and structure feature representations. We evaluate our method on the complex task of multicenter histopathology image classification, comparing it against state-of-the-art (SOTA) SDG baselines. Results demonstrate that our method surpasses the SOTA by a margin of 1% in average accuracy while also showing more stable performance. This study highlights the importance and challenges of exploring SDG frameworks in the context of the classification task. The code is publicly available at https://github.com/BioMedIA-MBZUAI/ConDiSR
Authors: Wonjun Kang, Kevin Galim, Hyung Il Koo
Abstract: Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process to obtain a noisy representation of the original image, which is then denoised to achieve the desired edits. However, current methods for diffusion inversion often struggle to produce edits that are both faithful to the specified text prompt and closely resemble the source image. To overcome these limitations, we introduce a novel and adaptable diffusion inversion technique for real image editing, which is grounded in a theoretical analysis of the role of $\eta$ in the DDIM sampling equation for enhanced editability. By designing a universal diffusion inversion method with a time- and region-dependent $\eta$ function, we enable flexible control over the editing extent. Through a comprehensive series of quantitative and qualitative assessments, involving a comparison with a broad array of recent methods, we demonstrate the superiority of our approach. Our method not only sets a new benchmark in the field but also significantly outperforms existing strategies.
Authors: Yunhao Gou, Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung, James T. Kwok, Yu Zhang
Abstract: Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we observe that safety mechanisms of the pre-aligned LLMs in MLLMs can be easily bypassed with the introduction of image features. To construct robust MLLMs, we propose ECSO (Eyes Closed, Safety On), a novel training-free protecting approach that exploits the inherent safety awareness of MLLMs, and generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of pre-aligned LLMs in MLLMs. Experiments on five state-of-the-art (SoTA) MLLMs demonstrate that ECSO enhances model safety significantly (e.g.,, 37.6% improvement on the MM-SafetyBench (SD+OCR) and 71.3% on VLSafe with LLaVA-1.5-7B), while consistently maintaining utility results on common MLLM benchmarks. Furthermore, we show that ECSO can be used as a data engine to generate supervised-finetuning (SFT) data for MLLM alignment without extra human intervention.
Authors: Yogesh Kumar, Pekka Marttinen
Abstract: We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive multi-modal medical imaging analysis, notably data scarcity and the "modality gap" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is designed to be generally applicable to any variant of CLIP without requiring any modifications of the core architecture. Through detailed evaluations across several tasks, including zero-shot inference, linear probing, cross-modal retrieval, and Retrieval Augmented Generation (RAG) of radiology reports using a frozen Large Language Model, eCLIP showcases consistent improvements in embedding quality. The outcomes reveal enhanced alignment and uniformity, affirming eCLIP's capability to harness high-quality annotations for enriched multi-modal analysis in the medical imaging domain.
Authors: Mingxiao Li, Bo Wan, Marie-Francine Moens, Tinne Tuytelaars
Abstract: In recent years, diffusion models have made remarkable strides in text-to-video generation, sparking a quest for enhanced control over video outputs to more accurately reflect user intentions. Traditional efforts predominantly focus on employing either semantic cues, like images or depth maps, or motion-based conditions, like moving sketches or object bounding boxes. Semantic inputs offer a rich scene context but lack detailed motion specificity; conversely, motion inputs provide precise trajectory information but miss the broader semantic narrative. For the first time, we integrate both semantic and motion cues within a diffusion model for video generation, as demonstrated in Fig 1. To this end, we introduce the Scene and Motion Conditional Diffusion (SMCD), a novel methodology for managing multimodal inputs. It incorporates a recognized motion conditioning module and investigates various approaches to integrate scene conditions, promoting synergy between different modalities. For model training, we separate the conditions for the two modalities, introducing a two-stage training pipeline. Experimental results demonstrate that our design significantly enhances video quality, motion precision, and semantic coherence.
Authors: Jin-Young Kim, Hyojun Go, Soonwoo Kwon, Hyun-Gyoon Kim
Abstract: Diffusion-based generative models have emerged as powerful tools in the realm of generative modeling. Despite extensive research on denoising across various timesteps and noise levels, a conflict persists regarding the relative difficulties of the denoising tasks. While various studies argue that lower timesteps present more challenging tasks, others contend that higher timesteps are more difficult. To address this conflict, our study undertakes a comprehensive examination of task difficulties, focusing on convergence behavior and changes in relative entropy between consecutive probability distributions across timesteps. Our observational study reveals that denoising at earlier timesteps poses challenges characterized by slower convergence and higher relative entropy, indicating increased task difficulty at these lower timesteps. Building on these observations, we introduce an easy-to-hard learning scheme, drawing from curriculum learning, to enhance the training process of diffusion models. By organizing timesteps or noise levels into clusters and training models with ascending orders of difficulty, we facilitate an order-aware training regime, progressing from easier to harder denoising tasks, thereby deviating from the conventional approach of training diffusion models simultaneously across all timesteps. Our approach leads to improved performance and faster convergence by leveraging benefits of curriculum learning, while maintaining orthogonality with existing improvements in diffusion training techniques. We validate these advantages through comprehensive experiments in image generation tasks, including unconditional, class-conditional, and text-to-image generation.
Authors: Guohao Sun, Can Qin, Jiamian Wang, Zeyuan Chen, Ran Xu, Zhiqiang Tao
Abstract: Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which, however, is costly to obtain and has not thoroughly explored the rich contextual information contained in images. This paper first attempts to harness the overlooked context within visual instruction data, training the model to self-supervised "learning" how to ask high-quality questions. In this way, we introduce a novel framework named SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant. SQ-LLaVA exhibits proficiency in generating flexible and meaningful image-related questions while analyzing the visual clue and prior language knowledge, signifying an advanced level of generalized visual understanding. Moreover, fine-tuning SQ-LLaVA on higher-quality instruction data shows a performance improvement compared with traditional visual-instruction tuning methods. This improvement highlights the efficacy of self-questioning techniques in achieving a deeper and more nuanced comprehension of visual content across various contexts.
Authors: Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li
Abstract: We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos. In particular, the proposed multimodal agent VideoAgent: 1) constructs a structured memory to store both the generic temporal event descriptions and object-centric tracking states of the video; 2) given an input task query, it employs tools including video segment localization and object memory querying along with other visual foundation models to interactively solve the task, utilizing the zero-shot tool-use ability of LLMs. VideoAgent demonstrates impressive performances on several long-horizon video understanding benchmarks, an average increase of 6.6% on NExT-QA and 26.0% on EgoSchema over baselines, closing the gap between open-sourced models and private counterparts including Gemini 1.5 Pro.
Authors: Ruicheng Wang, Jianfeng Xiang, Jiaolong Yang, Xin Tong
Abstract: We propose a novel image editing technique that enables 3D manipulations on single images, such as object rotation and translation. Existing 3D-aware image editing approaches typically rely on synthetic multi-view datasets for training specialized models, thus constraining their effectiveness on open-domain images featuring significantly more varied layouts and styles. In contrast, our method directly leverages powerful image diffusion models trained on a broad spectrum of text-image pairs and thus retain their exceptional generalization abilities. This objective is realized through the development of an iterative novel view synthesis and geometry alignment algorithm. The algorithm harnesses diffusion models for dual purposes: they provide appearance prior by predicting novel views of the selected object using estimated depth maps, and they act as a geometry critic by correcting misalignments in 3D shapes across the sampled views. Our method can generate high-quality 3D-aware image edits with large viewpoint transformations and high appearance and shape consistency with the input image, pushing the boundaries of what is possible with single-image 3D-aware editing.
Authors: Hyeonho Jeong, Jinho Chang, Geon Yeong Park, Jong Chul Ye
Abstract: Text-driven diffusion-based video editing presents a unique challenge not encountered in image editing literature: establishing real-world motion. Unlike existing video editing approaches, here we focus on score distillation sampling to circumvent the standard reverse diffusion process and initiate optimization from videos that already exhibit natural motion. Our analysis reveals that while video score distillation can effectively introduce new content indicated by target text, it can also cause significant structure and motion deviation. To counteract this, we propose to match space-time self-similarities of the original video and the edited video during the score distillation. Thanks to the use of score distillation, our approach is model-agnostic, which can be applied for both cascaded and non-cascaded video diffusion frameworks. Through extensive comparisons with leading methods, our approach demonstrates its superiority in altering appearances while accurately preserving the original structure and motion.
Authors: Sensen Gao, Xiaojun Jia, Xuhong Ren, Ivor Tsang, Qing Guo
Abstract: Vision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs). Strengthening attacks and uncovering vulnerabilities, especially common issues in VLP models (e.g., high transferable AEs), can advance reliable and practical VLP models. A recent work (i.e., Set-level guidance attack) indicates that augmenting image-text pairs to increase AE diversity along the optimization path enhances the transferability of adversarial examples significantly. However, this approach predominantly emphasizes diversity around the online adversarial examples (i.e., AEs in the optimization period), leading to the risk of overfitting the victim model and affecting the transferability. In this study, we posit that the diversity of adversarial examples towards the clean input and online AEs are both pivotal for enhancing transferability across VLP models. Consequently, we propose using diversification along the intersection region of adversarial trajectory to expand the diversity of AEs. To fully leverage the interaction between modalities, we introduce text-guided adversarial example selection during optimization. Furthermore, to further mitigate the potential overfitting, we direct the adversarial text deviating from the last intersection region along the optimization path, rather than adversarial images as in existing methods. Extensive experiments affirm the effectiveness of our method in improving transferability across various VLP models and downstream vision-and-language tasks.
Authors: Haruya Ishikawa, Takumi Iida, Yoshinori Konishi, Yoshimitsu Aoki
Abstract: Generating annotations for bird's-eye-view (BEV) segmentation presents significant challenges due to the scenes' complexity and the high manual annotation cost. In this work, we address these challenges by leveraging the abundance of unlabeled data available. We propose the Perspective Cue Training (PCT) framework, a novel training framework that utilizes pseudo-labels generated from unlabeled perspective images using publicly available semantic segmentation models trained on large street-view datasets. PCT applies a perspective view task head to the image encoder shared with the BEV segmentation head, effectively utilizing the unlabeled data to be trained with the generated pseudo-labels. Since image encoders are present in nearly all camera-based BEV segmentation architectures, PCT is flexible and applicable to various existing BEV architectures. PCT can be applied to various settings where unlabeled data is available. In this paper, we applied PCT for semi-supervised learning (SSL) and unsupervised domain adaptation (UDA). Additionally, we introduce strong input perturbation through Camera Dropout (CamDrop) and feature perturbation via BEV Feature Dropout (BFD), which are crucial for enhancing SSL capabilities using our teacher-student framework. Our comprehensive approach is simple and flexible but yields significant improvements over various baselines for SSL and UDA, achieving competitive performances even against the current state-of-the-art.
Authors: Yihong Luo, Xiaolong Chen, Xinghua Qu, Jing Tang
Abstract: We introduce YOSO, a novel generative model designed for rapid, scalable, and high-fidelity one-step image synthesis. YOSO integrates the diffusion process with GANs to achieve the best of two worlds. Specifically, we smooth the distribution by the denoising generator itself, performing self-cooperative learning. We show that our method can serve as a one-step generation model training from scratch with competitive performance. Moreover, we show that our method can be extended to finetune pre-trained text-to-image diffusion for high-quality one-step text-to-image synthesis even with LoRA fine-tuning. In particular, we provide the first diffusion transformer that can generate images in one step trained on 512 resolution, with the capability of adapting to 1024 resolution without extra explicit training. Our code is provided at https://github.com/Luo-Yihong/YOSO
Authors: Gaurav Bhatt, James Ross, Leonid Sigal
Abstract: Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks. Despite notable progress in continual classification, systems designed for complex vision tasks such as detection or segmentation still struggle to attain satisfactory performance. In this work, we introduce a memory-based detection transformer architecture to adapt a pre-trained DETR-style detector to new tasks while preserving knowledge from previous tasks. We propose a novel localized query function for efficient information retrieval from memory units, aiming to minimize forgetting. Furthermore, we identify a fundamental challenge in continual detection referred to as background relegation. This arises when object categories from earlier tasks reappear in future tasks, potentially without labels, leading them to be implicitly treated as background. This is an inevitable issue in continual detection or segmentation. The introduced continual optimization technique effectively tackles this challenge. Finally, we assess the performance of our proposed system on continual detection benchmarks and demonstrate that our approach surpasses the performance of existing state-of-the-art resulting in 5-7% improvements on MS-COCO and PASCAL-VOC on the task of continual detection.
Authors: Dongbin Zhang, Chuming Wang, Weitao Wang, Peihao Li, Minghan Qin, Haoqian Wang
Abstract: Novel view synthesis from unconstrained in-the-wild images remains a meaningful but challenging task. The photometric variation and transient occluders in those unconstrained images make it difficult to reconstruct the original scene accurately. Previous approaches tackle the problem by introducing a global appearance feature in Neural Radiance Fields (NeRF). However, in the real world, the unique appearance of each tiny point in a scene is determined by its independent intrinsic material attributes and the varying environmental impacts it receives. Inspired by this fact, we propose Gaussian in the wild (GS-W), a method that uses 3D Gaussian points to reconstruct the scene and introduces separated intrinsic and dynamic appearance feature for each point, capturing the unchanged scene appearance along with dynamic variation like illumination and weather. Additionally, an adaptive sampling strategy is presented to allow each Gaussian point to focus on the local and detailed information more effectively. We also reduce the impact of transient occluders using a 2D visibility map. More experiments have demonstrated better reconstruction quality and details of GS-W compared to NeRF-based methods, with a faster rendering speed. Video results and code are available at https://eastbeanzhang.github.io/GS-W/.
Authors: Yuliang Guo, Abhinav Kumar, Cheng Zhao, Ruoyu Wang, Xinyu Huang, Liu Ren
Abstract: Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose. While gradient-based optimization in a NeRF framework updates the initial pose, this paper highlights that scale-depth ambiguity in monocular object reconstruction causes failures when the initial pose deviates moderately from the true pose. Consequently, existing methods often depend on a third-party 3D object to provide an initial object pose, leading to increased complexity and generalization issues. To address these challenges, we present SUP-NeRF, a Streamlined Unification of object Pose estimation and NeRF-based object reconstruction. SUP-NeRF decouples the object's dimension estimation and pose refinement to resolve the scale-depth ambiguity, and introduces a camera-invariant projected-box representation that generalizes cross different domains. While using a dedicated pose estimator that smoothly integrates into an object-centric NeRF, SUP-NeRF is free from external 3D detectors. SUP-NeRF achieves state-of-the-art results in both reconstruction and pose estimation tasks on the nuScenes dataset. Furthermore, SUP-NeRF exhibits exceptional cross-dataset generalization on the KITTI and Waymo datasets, surpassing prior methods with up to 50\% reduction in rotation and translation error.
Authors: Jiaxuan Lu, Fang Yan, Xiaofan Zhang, Yue Gao, Shaoting Zhang
Abstract: As natural image understanding moves towards the pretrain-finetune era, research in pathology imaging is concurrently evolving. Despite the predominant focus on pretraining pathological foundation models, how to adapt foundation models to downstream tasks is little explored. For downstream adaptation, we propose the existence of two domain gaps, i.e., the Foundation-Task Gap and the Task-Instance Gap. To mitigate these gaps, we introduce PathoTune, a framework designed to efficiently adapt pathological or even visual foundation models to pathology-specific tasks via multi-modal prompt tuning. The proposed framework leverages Task-specific Visual Prompts and Task-specific Textual Prompts to identify task-relevant features, along with Instance-specific Visual Prompts for encoding single pathological image features. Results across multiple datasets at both patch-level and WSI-level demonstrate its superior performance over single-modality prompt tuning approaches. Significantly, PathoTune facilitates the direct adaptation of natural visual foundation models to pathological tasks, drastically outperforming pathological foundation models with simple linear probing. The code is available at https://github.com/openmedlab/PathoDuet.
Authors: Yunlong Tang, Yuxuan Wan, Lei Qi, Xin Geng
Abstract: Source-Free Domain Generalization (SFDG) aims to develop a model that works for unseen target domains without relying on any source domain. Research in SFDG primarily bulids upon the existing knowledge of large-scale vision-language models and utilizes the pre-trained model's joint vision-language space to simulate style transfer across domains, thus eliminating the dependency on source domain images. However, how to efficiently simulate rich and diverse styles using text prompts, and how to extract domain-invariant information useful for classification from features that contain both semantic and style information after the encoder, are directions that merit improvement. In this paper, we introduce Dynamic PromptStyler (DPStyler), comprising Style Generation and Style Removal modules to address these issues. The Style Generation module refreshes all styles at every training epoch, while the Style Removal module eliminates variations in the encoder's output features caused by input styles. Moreover, since the Style Generation module, responsible for generating style word vectors using random sampling or style mixing, makes the model sensitive to input text prompts, we introduce a model ensemble method to mitigate this sensitivity. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods on benchmark datasets.
Authors: Ziyang Gong, Fuhao Li, Yupeng Deng, Deblina Bhattacharjee, Xianzheng Ma, Xiangwei Zhu, Zhenming Ji
Abstract: Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source domains to unlabeled target domains. When adapting to adverse scenes, existing UDA methods fail to perform well due to the lack of instructions, leading their models to overlook discrepancies within all adverse scenes. To tackle this, we propose CoDA which instructs models to distinguish, focus, and learn from these discrepancies at scene and image levels. Specifically, CoDA consists of a Chain-of-Domain (CoD) strategy and a Severity-Aware Visual Prompt Tuning (SAVPT) mechanism. CoD focuses on scene-level instructions to divide all adverse scenes into easy and hard scenes, guiding models to adapt from source to easy domains with easy scene images, and then to hard domains with hard scene images, thereby laying a solid foundation for whole adaptations. Building upon this foundation, we employ SAVPT to dive into more detailed image-level instructions to boost performance. SAVPT features a novel metric Severity that divides all adverse scene images into low-severity and high-severity images. Then Severity directs visual prompts and adapters, instructing models to concentrate on unified severity features instead of scene-specific features, without adding complexity to the model architecture. CoDA achieves SOTA performances on widely-used benchmarks under all adverse scenes. Notably, CoDA outperforms the existing ones by 4.6%, and 10.3% mIoU on the Foggy Driving, and Foggy Zurich benchmarks, respectively. Our code is available at https://github.com/Cuzyoung/CoDA
Authors: Astitva Srivastava, Pranav Manu, Amit Raj, Varun Jampani, Avinash Sharma
Abstract: In this paper, we tackle a new and challenging problem of text-driven generation of 3D garments with high-quality textures. We propose "WordRobe", a novel framework for the generation of unposed & textured 3D garment meshes from user-friendly text prompts. We achieve this by first learning a latent representation of 3D garments using a novel coarse-to-fine training strategy and a loss for latent disentanglement, promoting better latent interpolation. Subsequently, we align the garment latent space to the CLIP embedding space in a weakly supervised manner, enabling text-driven 3D garment generation and editing. For appearance modeling, we leverage the zero-shot generation capability of ControlNet to synthesize view-consistent texture maps in a single feed-forward inference step, thereby drastically decreasing the generation time as compared to existing methods. We demonstrate superior performance over current SOTAs for learning 3D garment latent space, garment interpolation, and text-driven texture synthesis, supported by quantitative evaluation and qualitative user study. The unposed 3D garment meshes generated using WordRobe can be directly fed to standard cloth simulation & animation pipelines without any post-processing.
Authors: Julian Jorge Andrade Guerreiro, Naoto Inoue, Kento Masui, Mayu Otani, Hideki Nakayama
Abstract: Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alternative to current diffusion-based layout generation models. Specifically, we propose LayoutFlow, an efficient flow-based model capable of generating high-quality layouts. Instead of progressively denoising the elements of a noisy layout, our method learns to gradually move, or flow, the elements of an initial sample until it reaches its final prediction. In addition, we employ a conditioning scheme that allows us to handle various generation tasks with varying degrees of conditioning with a single model. Empirically, LayoutFlow performs on par with state-of-the-art models while being significantly faster.
Authors: Sidi Yang, Binxiao Huang, Mingdeng Cao, Yatai Ji, Hanzhong Guo, Ngai Wong, Yujiu Yang
Abstract: The widespread use of high-definition screens in edge devices, such as end-user cameras, smartphones, and televisions, is spurring a significant demand for image enhancement. Existing enhancement models often optimize for high performance while falling short of reducing hardware inference time and power consumption, especially on edge devices with constrained computing and storage resources. To this end, we propose Image Color Enhancement Lookup Table (ICELUT) that adopts LUTs for extremely efficient edge inference, without any convolutional neural network (CNN). During training, we leverage pointwise (1x1) convolution to extract color information, alongside a split fully connected layer to incorporate global information. Both components are then seamlessly converted into LUTs for hardware-agnostic deployment. ICELUT achieves near-state-of-the-art performance and remarkably low power consumption. We observe that the pointwise network structure exhibits robust scalability, upkeeping the performance even with a heavily downsampled 32x32 input image. These enable ICELUT, the first-ever purely LUT-based image enhancer, to reach an unprecedented speed of 0.4ms on GPU and 7ms on CPU, at least one order faster than any CNN solution. Codes are available at https://github.com/Stephen0808/ICELUT.
Authors: Cheng Zhao, Su Sun, Ruoyu Wang, Yuliang Guo, Jun-Jun Wan, Zhou Huang, Xinyu Huang, Yingjie Victor Chen, Liu Ren
Abstract: Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but also overlooks the potential advantages of fusing LiDAR with camera data. In this paper, we design a novel tightly coupled LiDAR-Camera Gaussian Splatting (TCLC-GS) to fully leverage the combined strengths of both LiDAR and camera sensors, enabling rapid, high-quality 3D reconstruction and novel view RGB/depth synthesis. TCLC-GS designs a hybrid explicit (colorized 3D mesh) and implicit (hierarchical octree feature) 3D representation derived from LiDAR-camera data, to enrich the properties of 3D Gaussians for splatting. 3D Gaussian's properties are not only initialized in alignment with the 3D mesh which provides more completed 3D shape and color information, but are also endowed with broader contextual information through retrieved octree implicit features. During the Gaussian Splatting optimization process, the 3D mesh offers dense depth information as supervision, which enhances the training process by learning of a robust geometry. Comprehensive evaluations conducted on the Waymo Open Dataset and nuScenes Dataset validate our method's state-of-the-art (SOTA) performance. Utilizing a single NVIDIA RTX 3090 Ti, our method demonstrates fast training and achieves real-time RGB and depth rendering at 90 FPS in resolution of 1920x1280 (Waymo), and 120 FPS in resolution of 1600x900 (nuScenes) in urban scenarios.
Authors: Longwei Li, Huajian Huang, Sai-Kit Yeung, Hui Cheng
Abstract: Photorealistic reconstruction relying on 3D Gaussian Splatting has shown promising potential in various domains. However, the current 3D Gaussian Splatting system only supports radiance field reconstruction using undistorted perspective images. In this paper, we present OmniGS, a novel omnidirectional Gaussian splatting system, to take advantage of omnidirectional images for fast radiance field reconstruction. Specifically, we conduct a theoretical analysis of spherical camera model derivatives in 3D Gaussian Splatting. According to the derivatives, we then implement a new GPU-accelerated omnidirectional rasterizer that directly splats 3D Gaussians onto the equirectangular screen space for omnidirectional image rendering. We realize differentiable optimization of the omnidirectional radiance field without the requirement of cube-map rectification or tangent-plane approximation. Extensive experiments conducted in egocentric and roaming scenarios demonstrate that our method achieves state-of-the-art reconstruction quality and high rendering speed using omnidirectional images. The code will be publicly available.
Authors: Junkai Yan, Yipeng Gao, Qize Yang, Xihan Wei, Xuansong Xie, Ancong Wu, Wei-Shi Zheng
Abstract: Text-to-3D generation, which synthesizes 3D assets according to an overall text description, has significantly progressed. However, a challenge arises when the specific appearances need customizing at designated viewpoints but referring solely to the overall description for generating 3D objects. For instance, ambiguity easily occurs when producing a T-shirt with distinct patterns on its front and back using a single overall text guidance. In this work, we propose DreamView, a text-to-image approach enabling multi-view customization while maintaining overall consistency by adaptively injecting the view-specific and overall text guidance through a collaborative text guidance injection module, which can also be lifted to 3D generation via score distillation sampling. DreamView is trained with large-scale rendered multi-view images and their corresponding view-specific texts to learn to balance the separate content manipulation in each view and the global consistency of the overall object, resulting in a dual achievement of customization and consistency. Consequently, DreamView empowers artists to design 3D objects creatively, fostering the creation of more innovative and diverse 3D assets. Code and model will be released at https://github.com/iSEE-Laboratory/DreamView.
Authors: Jo\~ao Gabriel Vinholi, Marco Chini, Anis Amziane, Renato Machado, Danilo Silva, Patrick Matgen
Abstract: In the field of remote sensing, the challenge of comparing images captured by disparate sensors is a common obstacle. This requires image translation -- converting imagery from one sensor domain to another while preserving the original content. Denoising Diffusion Implicit Models (DDIM) are potential state-of-the-art solutions for such domain translation due to their proven superiority in multiple image-to-image translation tasks in classic computer vision. However, these models struggle with large-scale multi-patch imagery, often focusing solely on small patches and resulting in inconsistencies across the full image. To overcome these limitations, we propose a novel method that leverages DDIM for effective optical image translation over large areas. Our approach is tailored to super-resolve large-scale low spatial resolution images into high-resolution equivalents from disparate optical sensors, ensuring uniformity across hundreds of patches. Extensive experiments with a dataset of paired Sentinel-II and Planet Dove images show that our approach provides precise domain adaptation and artifact reduction. Our technique preserves the image content while also improving radiometric (color) accuracy and feature representations. The outcome is a high-resolution large-scale image with consistent patches, vital for applications such as heterogeneous change detection (HCD). We present a unique training and testing algorithm rooted in DDIMs, a thorough image quality assessment, and a comparative study against the standard classifier-free guided DDIM framework and five other leading methods. The efficacy of our approach is further demonstrated by substantial enhancements in HCD tasks performed in the urban settings of Beirut, Lebanon, and Austin, USA.
Authors: Zirui Wang, Wenjing Bian, Omkar Parkhi, Yuheng Ren, Victor Adrian Prisacariu
Abstract: We introduce a novel cross-reference image quality assessment method that effectively fills the gap in the image assessment landscape, complementing the array of established evaluation schemes -- ranging from full-reference metrics like SSIM, no-reference metrics such as NIQE, to general-reference metrics including FID, and Multi-modal-reference metrics, e.g., CLIPScore. Utilising a neural network with the cross-attention mechanism and a unique data collection pipeline from NVS optimisation, our method enables accurate image quality assessment without requiring ground truth references. By comparing a query image against multiple views of the same scene, our method addresses the limitations of existing metrics in novel view synthesis (NVS) and similar tasks where direct reference images are unavailable. Experimental results show that our method is closely correlated to the full-reference metric SSIM, while not requiring ground truth references.
Authors: Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin
Abstract: Recently, unsupervised salient object detection (USOD) has gained increasing attention due to its annotation-free nature. However, current methods mainly focus on specific tasks such as RGB and RGB-D, neglecting the potential for task migration. In this paper, we propose a unified USOD framework for generic USOD tasks. Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network. This mechanism starts with easy samples and progressively moves towards harder ones, to avoid initial interference caused by hard samples. Afterwards, the obtained saliency cues are utilized to train a saliency detector, and we employ a Self-rectify Pseudo-label Refinement (SPR) mechanism to improve the quality of pseudo-labels. Finally, an adapter-tuning method is devised to transfer the acquired saliency knowledge, leveraging shared knowledge to attain superior transferring performance on the target tasks. Extensive experiments on five representative SOD tasks confirm the effectiveness and feasibility of our proposed method. Code and supplement materials are available at https://github.com/I2-Multimedia-Lab/A2S-v3.
Authors: Philip M\"uller, Georgios Kaissis, Daniel Rueckert
Abstract: Report generation models offer fine-grained textual interpretations of medical images like chest X-rays, yet they often lack interactivity (i.e. the ability to steer the generation process through user queries) and localized interpretability (i.e. visually grounding their predictions), which we deem essential for future adoption in clinical practice. While there have been efforts to tackle these issues, they are either limited in their interactivity by not supporting textual queries or fail to also offer localized interpretability. Therefore, we propose a novel multitask architecture and training paradigm integrating textual prompts and bounding boxes for diverse aspects like anatomical regions and pathologies. We call this approach the Chest X-Ray Explainer (ChEX). Evaluations across a heterogeneous set of 9 chest X-ray tasks, including localized image interpretation and report generation, showcase its competitiveness with SOTA models while additional analysis demonstrates ChEX's interactive capabilities. Code: https://github.com/philip-mueller/chex
Authors: Sheng Jin, Ruijie Yao, Lumin Xu, Wentao Liu, Chen Qian, Ji Wu, Ping Luo
Abstract: Instance perception tasks (object detection, instance segmentation, pose estimation, counting) play a key role in industrial applications of visual models. As supervised learning methods suffer from high labeling cost, few-shot learning methods which effectively learn from a limited number of labeled examples are desired. Existing few-shot learning methods primarily focus on a restricted set of tasks, presumably due to the challenges involved in designing a generic model capable of representing diverse tasks in a unified manner. In this paper, we propose UniFS, a universal few-shot instance perception model that unifies a wide range of instance perception tasks by reformulating them into a dynamic point representation learning framework. Additionally, we propose Structure-Aware Point Learning (SAPL) to exploit the higher-order structural relationship among points to further enhance representation learning. Our approach makes minimal assumptions about the tasks, yet it achieves competitive results compared to highly specialized and well optimized specialist models. Codes will be released soon.
Authors: Prakash Chandra Chhipa, Meenakshi Subhash Chippa, Kanjar De, Rajkumar Saini, Marcus Liwicki, Mubarak Shah
Abstract: Perspective distortion (PD) causes unprecedented changes in shape, size, orientation, angles, and other spatial relationships of visual concepts in images. Precisely estimating camera intrinsic and extrinsic parameters is a challenging task that prevents synthesizing perspective distortion. Non-availability of dedicated training data poses a critical barrier to developing robust computer vision methods. Additionally, distortion correction methods make other computer vision tasks a multi-step approach and lack performance. In this work, we propose mitigating perspective distortion (MPD) by employing a fine-grained parameter control on a specific family of M\"obius transform to model real-world distortion without estimating camera intrinsic and extrinsic parameters and without the need for actual distorted data. Also, we present a dedicated perspectively distorted benchmark dataset, ImageNet-PD, to benchmark the robustness of deep learning models against this new dataset. The proposed method outperforms existing benchmarks, ImageNet-E and ImageNet-X. Additionally, it significantly improves performance on ImageNet-PD while consistently performing on standard data distribution. Notably, our method shows improved performance on three PD-affected real-world applications crowd counting, fisheye image recognition, and person re-identification and one PD-affected challenging CV task: object detection. The source code, dataset, and models are available on the project webpage at https://prakashchhipa.github.io/projects/mpd.
Authors: Xiaoyu Qiao, Weisheng Li, Bin Xiao, Yuping Huang, Lijian Yang
Abstract: Score matching with Langevin dynamics (SMLD) method has been successfully applied to accelerated MRI. However, the hyperparameters in the sampling process require subtle tuning, otherwise the results can be severely corrupted by hallucination artifacts, especially with out-of-distribution test data. To address the limitations, we proposed a novel workflow where naive SMLD samples serve as additional priors to guide model-driven network training. First, we adopted a pretrained score network to generate samples as preliminary guidance images (PGI), obviating the need for network retraining, parameter tuning and in-distribution test data. Although PGIs are corrupted by hallucination artifacts, we believe they can provide extra information through effective denoising steps to facilitate reconstruction. Therefore, we designed a denoising module (DM) in the second step to coarsely eliminate artifacts and noises from PGIs. The features are extracted from a score-based information extractor (SIE) and a cross-domain information extractor (CIE), which directly map to the noise patterns. Third, we designed a model-driven network guided by denoised PGIs (DGIs) to further recover fine details. DGIs are densely connected with intermediate reconstructions in each cascade to enrich the information and are periodically updated to provide more accurate guidance. Our experiments on different datasets reveal that despite the low average quality of PGIs, the proposed workflow can effectively extract valuable information to guide the network training, even with severely reduced training data and sampling steps. Our method outperforms other cutting-edge techniques by effectively mitigating hallucination artifacts, yielding robust and high-quality reconstruction results.
Authors: Anderson de Andrade, Ivan Baji\'c
Abstract: We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount of information available in it. We interpret this issue using the predictive $\mathcal{V}$-information framework. In learnable scalable coding, previous work increased the utilization of side-information for input reconstruction by also rewarding input reconstruction when learning this shared representation. We evaluate the impact of this idea in the context of input reconstruction more rigorously and extended it to other computer vision tasks. We perform experiments using representations trained for object detection on COCO 2017 and depth estimation on the Cityscapes dataset, and use them to assist in image reconstruction and semantic segmentation tasks. The results show considerable improvements in the rate-distortion performance of the assisted tasks. Moreover, using the proposed representations, the performance of the base tasks are also improved. Results suggest that the proposed method induces simpler representations that are more compatible with downstream processes.
Authors: Faegheh Sardari, Armin Mustafa, Philip J. B. Jackson, Adrian Hilton
Abstract: Weakly supervised audio-visual video parsing (AVVP) methods aim to detect audible-only, visible-only, and audible-visible events using only video-level labels. Existing approaches tackle this by leveraging unimodal and cross-modal contexts. However, we argue that while cross-modal learning is beneficial for detecting audible-visible events, in the weakly supervised scenario, it negatively impacts unaligned audible or visible events by introducing irrelevant modality information. In this paper, we propose CoLeaF, a novel learning framework that optimizes the integration of cross-modal context in the embedding space such that the network explicitly learns to combine cross-modal information for audible-visible events while filtering them out for unaligned events. Additionally, as videos often involve complex class relationships, modelling them improves performance. However, this introduces extra computational costs into the network. Our framework is designed to leverage cross-class relationships during training without incurring additional computations at inference. Furthermore, we propose new metrics to better evaluate a method's capabilities in performing AVVP. Our extensive experiments demonstrate that CoLeaF significantly improves the state-of-the-art results by an average of 1.9% and 2.4% F-score on the LLP and UnAV-100 datasets, respectively.
Authors: Weilian Zhou (Cynthia), Sei-Ichiro Kamata (Cynthia), Haipeng Wang (Cynthia), Man-Sing Wong (Cynthia), Huiying (Cynthia), Hou
Abstract: Hyperspectral image (HSI) classification is pivotal in the remote sensing (RS) field, particularly with the advancement of deep learning techniques. Sequential models, adapted from the natural language processing (NLP) field such as Recurrent Neural Networks (RNNs) and Transformers, have been tailored to this task, offering a unique viewpoint. However, several challenges persist 1) RNNs struggle with centric feature aggregation and are sensitive to interfering pixels, 2) Transformers require significant computational resources and often underperform with limited HSI training samples, and 3) Current scanning methods for converting images into sequence-data are simplistic and inefficient. In response, this study introduces the innovative Mamba-in-Mamba (MiM) architecture for HSI classification, the first attempt of deploying State Space Model (SSM) in this task. The MiM model includes 1) A novel centralized Mamba-Cross-Scan (MCS) mechanism for transforming images into sequence-data, 2) A Tokenized Mamba (T-Mamba) encoder that incorporates a Gaussian Decay Mask (GDM), a Semantic Token Learner (STL), and a Semantic Token Fuser (STF) for enhanced feature generation and concentration, and 3) A Weighted MCS Fusion (WMF) module coupled with a Multi-Scale Loss Design to improve decoding efficiency. Experimental results from three public HSI datasets with fixed and disjoint training-testing samples demonstrate that our method outperforms existing baselines and state-of-the-art approaches, highlighting its efficacy and potential in HSI applications.
Authors: Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu
Abstract: We present MVSGaussian, a new generalizable 3D Gaussian representation approach derived from Multi-View Stereo (MVS) that can efficiently reconstruct unseen scenes. Specifically, 1) we leverage MVS to encode geometry-aware Gaussian representations and decode them into Gaussian parameters. 2) To further enhance performance, we propose a hybrid Gaussian rendering that integrates an efficient volume rendering design for novel view synthesis. 3) To support fast fine-tuning for specific scenes, we introduce a multi-view geometric consistent aggregation strategy to effectively aggregate the point clouds generated by the generalizable model, serving as the initialization for per-scene optimization. Compared with previous generalizable NeRF-based methods, which typically require minutes of fine-tuning and seconds of rendering per image, MVSGaussian achieves real-time rendering with better synthesis quality for each scene. Compared with the vanilla 3D-GS, MVSGaussian achieves better view synthesis with less training computational cost. Extensive experiments on DTU, Real Forward-facing, NeRF Synthetic, and Tanks and Temples datasets validate that MVSGaussian attains state-of-the-art performance with convincing generalizability, real-time rendering speed, and fast per-scene optimization.
Authors: Mengyi Shan, Lu Dong, Yutao Han, Yuan Yao, Tao Liu, Ifeoma Nwogu, Guo-Jun Qi, Mitch Hill
Abstract: This work aims to generate natural and diverse group motions of multiple humans from textual descriptions. While single-person text-to-motion generation is extensively studied, it remains challenging to synthesize motions for more than one or two subjects from in-the-wild prompts, mainly due to the lack of available datasets. In this work, we curate human pose and motion datasets by estimating pose information from large-scale image and video datasets. Our models use a transformer-based diffusion framework that accommodates multiple datasets with any number of subjects or frames. Experiments explore both generation of multi-person static poses and generation of multi-person motion sequences. To our knowledge, our method is the first to generate multi-subject motion sequences with high diversity and fidelity from a large variety of textual prompts.
Authors: Markus J. Buehler
Abstract: We present Cephalo, a series of multimodal vision large language models (V-LLMs) designed for materials science applications, integrating visual and linguistic data for enhanced understanding. A key innovation of Cephalo is its advanced dataset generation method. Cephalo is trained on integrated image and text data from thousands of scientific papers and science-focused Wikipedia data demonstrates can interpret complex visual scenes, generate precise language descriptions, and answer queries about images effectively. The combination of a vision encoder with an autoregressive transformer supports multimodal natural language understanding, which can be coupled with other generative methods to create an image-to-text-to-3D pipeline. To develop more capable models from smaller ones, we report both mixture-of-expert methods and model merging. We examine the models in diverse use cases that incorporate biological materials, fracture and engineering analysis, protein biophysics, and bio-inspired design based on insect behavior. Generative applications include bio-inspired designs, including pollen-inspired architected materials, as well as the synthesis of bio-inspired material microstructures from a photograph of a solar eclipse. Additional model fine-tuning with a series of molecular dynamics results demonstrate Cephalo's enhanced capabilities to accurately predict statistical features of stress and atomic energy distributions, as well as crack dynamics and damage in materials.
Authors: Xuanchen Li, Yuhao Cheng, Xingyu Ren, Haozhe Jia, Di Xu, Wenhan Zhu, Yichao Yan
Abstract: 4D head capture aims to generate dynamic topological meshes and corresponding texture maps from videos, which is widely utilized in movies and games for its ability to simulate facial muscle movements and recover dynamic textures in pore-squeezing. The industry often adopts the method involving multi-view stereo and non-rigid alignment. However, this approach is prone to errors and heavily reliant on time-consuming manual processing by artists. To simplify this process, we propose Topo4D, a novel framework for automatic geometry and texture generation, which optimizes densely aligned 4D heads and 8K texture maps directly from calibrated multi-view time-series images. Specifically, we first represent the time-series faces as a set of dynamic 3D Gaussians with fixed topology in which the Gaussian centers are bound to the mesh vertices. Afterward, we perform alternative geometry and texture optimization frame-by-frame for high-quality geometry and texture learning while maintaining temporal topology stability. Finally, we can extract dynamic facial meshes in regular wiring arrangement and high-fidelity textures with pore-level details from the learned Gaussians. Extensive experiments show that our method achieves superior results than the current SOTA face reconstruction methods both in the quality of meshes and textures. Project page: https://xuanchenli.github.io/Topo4D/.
Authors: Bing Cao, Yinan Xia, Yi Ding, Changqing Zhang, Qinghua Hu
Abstract: Multimodal fusion is crucial in joint decision-making systems for rendering holistic judgments. Since multimodal data changes in open environments, dynamic fusion has emerged and achieved remarkable progress in numerous applications. However, most existing dynamic multimodal fusion methods lack theoretical guarantees and easily fall into suboptimal problems, yielding unreliability and instability. To address this issue, we propose a Predictive Dynamic Fusion (PDF) framework for multimodal learning. We proceed to reveal the multimodal fusion from a generalization perspective and theoretically derive the predictable Collaborative Belief (Co-Belief) with Mono- and Holo-Confidence, which provably reduces the upper bound of generalization error. Accordingly, we further propose a relative calibration strategy to calibrate the predicted Co-Belief for potential uncertainty. Extensive experiments on multiple benchmarks confirm our superiority. Our code is available at https://github.com/Yinan-Xia/PDF.
Authors: Ping Liu, Qiqi Tao, Joey Tianyi Zhou
Abstract: This survey addresses the critical challenge of deepfake detection amidst the rapid advancements in artificial intelligence. As AI-generated media, including video, audio and text, become more realistic, the risk of misuse to spread misinformation and commit identity fraud increases. Focused on face-centric deepfakes, this work traces the evolution from traditional single-modality methods to sophisticated multi-modal approaches that handle audio-visual and text-visual scenarios. We provide comprehensive taxonomies of detection techniques, discuss the evolution of generative methods from auto-encoders and GANs to diffusion models, and categorize these technologies by their unique attributes. To our knowledge, this is the first survey of its kind. We also explore the challenges of adapting detection methods to new generative models and enhancing the reliability and robustness of deepfake detectors, proposing directions for future research. This survey offers a detailed roadmap for researchers, supporting the development of technologies to counter the deceptive use of AI in media creation, particularly facial forgery. A curated list of all related papers can be found at \href{https://github.com/qiqitao77/Comprehensive-Advances-in-Deepfake-Detection-Spanning-Diverse-Modalities}{https://github.com/qiqitao77/Awesome-Comprehensive-Deepfake-Detection}.
URLs: https://github.com/qiqitao77/Comprehensive-Advances-in-Deepfake-Detection-Spanning-Diverse-Modalities, https://github.com/qiqitao77/Awesome-Comprehensive-Deepfake-Detection
Authors: Sandeep Singh Sengar, Abhishek Kumar, Owen Singh
Abstract: This study presents significant enhancements in human pose estimation using the MediaPipe framework. The research focuses on improving accuracy, computational efficiency, and real-time processing capabilities by comprehensively optimising the underlying algorithms. Novel modifications are introduced that substantially enhance pose estimation accuracy across challenging scenarios, such as dynamic movements and partial occlusions. The improved framework is benchmarked against traditional models, demonstrating considerable precision and computational speed gains. The advancements have wide-ranging applications in augmented reality, sports analytics, and healthcare, enabling more immersive experiences, refined performance analysis, and advanced patient monitoring. The study also explores the integration of these enhancements within mobile and embedded systems, addressing the need for computational efficiency and broader accessibility. The implications of this research set a new benchmark for real-time human pose estimation technologies and pave the way for future innovations in the field. The implementation code for the paper is available at https://github.com/avhixd/Human_pose_estimation.
Authors: Aniket Pal, Ajoy Mondal, C. V. Jawahar
Abstract: Question-answering handwritten documents is a challenging task with numerous real-world applications. This paper proposes a novel recognition-based approach that improves upon the previous state-of-the-art on the HW-SQuAD and BenthamQA datasets. Our model incorporates transformer-based document retrieval and ensemble methods at the model level, achieving an Exact Match score of 82.02% and 69% in HW-SQuAD and BenthamQA datasets, respectively, surpassing the previous best recognition-based approach by 10.89% and 3%. We also enhance the document retrieval component, boosting the top-5 retrieval accuracy from 90% to 95.30%. Our results demonstrate the significance of our proposed approach in advancing question answering on handwritten documents. The code and trained models will be publicly available to facilitate future research in this critical area of natural language.
Authors: Mohamed Sayed, Filippo Aleotti, Jamie Watson, Zawar Qureshi, Guillermo Garcia-Hernando, Gabriel Brostow, Sara Vicente, Michael Firman
Abstract: Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes use of previous frames in a multi view stereo framework, relying on matching textures in a local neighborhood. In contrast, our model leverages historical predictions by giving the latest 3D geometry data as an extra input to our network. This self-generated geometric hint can encode information from areas of the scene not covered by the keyframes and it is more regularized when compared to individual predicted depth maps for previous frames. We introduce a Hint MLP which combines cost volume features with a hint of the prior geometry, rendered as a depth map from the current camera location, together with a measure of the confidence in the prior geometry. We demonstrate that our method, which can run at interactive speeds, achieves state-of-the-art estimates of depth and 3D scene reconstruction in both offline and incremental evaluation scenarios.
Authors: Georgios Tziafas, Yucheng Xu, Zhibin Li, Hamidreza Kasaei
Abstract: Grounding natural language to the physical world is a ubiquitous topic with a wide range of applications in computer vision and robotics. Recently, 2D vision-language models such as CLIP have been widely popularized, due to their impressive capabilities for open-vocabulary grounding in 2D images. Recent works aim to elevate 2D CLIP features to 3D via feature distillation, but either learn neural fields that are scene-specific and hence lack generalization, or focus on indoor room scan data that require access to multiple camera views, which is not practical in robot manipulation scenarios. Additionally, related methods typically fuse features at pixel-level and assume that all camera views are equally informative. In this work, we show that this approach leads to sub-optimal 3D features, both in terms of grounding accuracy, as well as segmentation crispness. To alleviate this, we propose a multi-view feature fusion strategy that employs object-centric priors to eliminate uninformative views based on semantic information, and fuse features at object-level via instance segmentation masks. To distill our object-centric 3D features, we generate a large-scale synthetic multi-view dataset of cluttered tabletop scenes, spawning 15k scenes from over 3300 unique object instances, which we make publicly available. We show that our method reconstructs 3D CLIP features with improved grounding capacity and spatial consistency, while doing so from single-view RGB-D, thus departing from the assumption of multiple camera views at test time. Finally, we show that our approach can generalize to novel tabletop domains and be re-purposed for 3D instance segmentation without fine-tuning, and demonstrate its utility for language-guided robotic grasping in clutter
Authors: Avraham Raviv, Yizhak Y. Elboher, Michelle Aluf-Medina, Yael Leibovich Weiss, Omer Cohen, Roy Assa, Guy Katz, Hillel Kugler
Abstract: Deep Neural Networks (DNNs) are ubiquitous in real-world applications, yet they remain vulnerable to errors and adversarial attacks. This work tackles the challenge of applying formal verification to ensure the safety of computer vision models, extending verification beyond image classification to object detection. We propose a general formulation for certifying the robustness of object detection models using formal verification and outline implementation strategies compatible with state-of-the-art verification tools. Our approach enables the application of these tools, originally designed for verifying classification models, to object detection. We define various attacks for object detection, illustrating the diverse ways adversarial inputs can compromise neural network outputs. Our experiments, conducted on several common datasets and networks, reveal potential errors in object detection models, highlighting system vulnerabilities and emphasizing the need for expanding formal verification to these new domains. This work paves the way for further research in integrating formal verification across a broader range of computer vision applications.
Authors: Zihao Huang, Shoukang Hu, Guangcong Wang, Tianqi Liu, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu
Abstract: Existing human datasets for avatar creation are typically limited to laboratory environments, wherein high-quality annotations (e.g., SMPL estimation from 3D scans or multi-view images) can be ideally provided. However, their annotating requirements are impractical for real-world images or videos, posing challenges toward real-world applications on current avatar creation methods. To this end, we propose the WildAvatar dataset, a web-scale in-the-wild human avatar creation dataset extracted from YouTube, with $10,000+$ different human subjects and scenes. WildAvatar is at least $10\times$ richer than previous datasets for 3D human avatar creation. We evaluate several state-of-the-art avatar creation methods on our dataset, highlighting the unexplored challenges in real-world applications on avatar creation. We also demonstrate the potential for generalizability of avatar creation methods, when provided with data at scale. We publicly release our data source links and annotations, to push forward 3D human avatar creation and other related fields for real-world applications.
Authors: Baijiong Lin, Weisen Jiang, Pengguang Chen, Yu Zhang, Shu Liu, Ying-Cong Chen
Abstract: Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios. Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense prediction. In this paper, we propose MTMamba, a novel Mamba-based architecture for multi-task scene understanding. It contains two types of core blocks: self-task Mamba (STM) block and cross-task Mamba (CTM) block. STM handles long-range dependency by leveraging Mamba, while CTM explicitly models task interactions to facilitate information exchange across tasks. Experiments on NYUDv2 and PASCAL-Context datasets demonstrate the superior performance of MTMamba over Transformer-based and CNN-based methods. Notably, on the PASCAL-Context dataset, MTMamba achieves improvements of +2.08, +5.01, and +4.90 over the previous best methods in the tasks of semantic segmentation, human parsing, and object boundary detection, respectively. The code is available at https://github.com/EnVision-Research/MTMamba.
Authors: Junsung Park, Kyungmin Kim, Hyunjung Shim
Abstract: Existing LiDAR semantic segmentation methods often struggle with performance declines in adverse weather conditions. Previous research has addressed this issue by simulating adverse weather or employing universal data augmentation during training. However, these methods lack a detailed analysis and understanding of how adverse weather negatively affects LiDAR semantic segmentation performance. Motivated by this issue, we identified key factors of adverse weather and conducted a toy experiment to pinpoint the main causes of performance degradation: (1) Geometric perturbation due to refraction caused by fog or droplets in the air and (2) Point drop due to energy absorption and occlusions. Based on these findings, we propose new strategic data augmentation techniques. First, we introduced a Selective Jittering (SJ) that jitters points in the random range of depth (or angle) to mimic geometric perturbation. Additionally, we developed a Learnable Point Drop (LPD) to learn vulnerable erase patterns with Deep Q-Learning Network to approximate the point drop phenomenon from adverse weather conditions. Without precise weather simulation, these techniques strengthen the LiDAR semantic segmentation model by exposing it to vulnerable conditions identified by our data-centric analysis. Experimental results confirmed the suitability of the proposed data augmentation methods for enhancing robustness against adverse weather conditions. Our method attains a remarkable 39.5 mIoU on the SemanticKITTI-to-SemanticSTF benchmark, surpassing the previous state-of-the-art by over 5.4%p, tripling the improvement over the baseline compared to previous methods achieved.
Authors: Yi Zhang, Ke Yu, Siqi Wu, Zhihai He
Abstract: In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream tasks in a few-shot setting. We recognize that visual concepts, such as textures, shapes, and colors are naturally transferable across domains and play a crucial role in generalization tasks. Motivated by this interesting finding, we learn a conceptual codebook consisting of visual concepts as keys and conceptual prompts as values, which serves as a link between the image encoder's outputs and the text encoder's inputs. Specifically, for a given image, we leverage the codebook to identify the most relevant conceptual prompts associated with the class embeddings to perform the classification. Additionally, we incorporate a handcrafted concept cache as a regularization to alleviate the overfitting issues in low-shot scenarios. We observe that this conceptual codebook learning method is able to achieve enhanced alignment between visual and linguistic modalities. Extensive experimental results demonstrate that our CoCoLe method remarkably outperforms the existing state-of-the-art methods across various evaluation settings, including base-to-new generalization, cross-dataset evaluation, and domain generalization tasks. Detailed ablation studies further confirm the efficacy of each component in CoCoLe.
Authors: Sungwon Hwang, Min-Jung Kim, Taewoong Kang, Jayeon Kang, Jaegul Choo
Abstract: Neural rendering-based urban scene reconstruction methods commonly rely on images collected from driving vehicles with cameras facing and moving forward. Although these methods can successfully synthesize from views similar to training camera trajectory, directing the novel view outside the training camera distribution does not guarantee on-par performance. In this paper, we tackle the Extrapolated View Synthesis (EVS) problem by evaluating the reconstructions on views such as looking left, right or downwards with respect to training camera distributions. To improve rendering quality for EVS, we initialize our model by constructing dense LiDAR map, and propose to leverage prior scene knowledge such as surface normal estimator and large-scale diffusion model. Qualitative and quantitative comparisons demonstrate the effectiveness of our methods on EVS. To the best of our knowledge, we are the first to address the EVS problem in urban scene reconstruction. Link to our project page: https://vegs3d.github.io/.
Authors: Saandeep Aathreya, Shaun Canavan
Abstract: Identifying Out-of-distribution (OOD) data is becoming increasingly critical as the real-world applications of deep learning methods expand. Post-hoc methods modify softmax scores fine-tuned on outlier data or leverage intermediate feature layers to identify distinctive patterns between In-Distribution (ID) and OOD samples. Other methods focus on employing diverse OOD samples to learn discrepancies between ID and OOD. These techniques, however, are typically dependent on the quality of the outlier samples assumed. Density-based methods explicitly model class-conditioned distributions but this requires long training time or retraining the classifier. To tackle these issues, we introduce \textit{FlowCon}, a new density-based OOD detection technique. Our main innovation lies in efficiently combining the properties of normalizing flow with supervised contrastive learning, ensuring robust representation learning with tractable density estimation. Empirical evaluation shows the enhanced performance of our method across common vision datasets such as CIFAR-10 and CIFAR-100 pretrained on ResNet18 and WideResNet classifiers. We also perform quantitative analysis using likelihood plots and qualitative visualization using UMAP embeddings and demonstrate the robustness of the proposed method under various OOD contexts. Code will be open-sourced post decision.
Authors: Gunbir Singh Baveja, Aaryavir Verma
Abstract: The stock market has become an increasingly popular investment option among new generations, with individuals exploring more complex assets. This rise in retail investors' participation necessitates a deeper understanding of the driving factors behind this trend and the role of financial literacy in enhancing investment decisions. This study aims to investigate how financial literacy influences financial decision-making and stock market participation. By identifying key barriers and motivators, the findings can provide valuable insights for individuals and policymakers to promote informed investing practices. Our research is qualitative in nature, utilizing data collected from social media platforms to analyze real-time investor behavior and attitudes. This approach allows us to capture the nuanced ways in which financial literacy impacts investment choices and participation in the stock market. The findings indicate that financial literacy plays a critical role in stock market participation and financial decision-making. Key barriers to participation include low financial literacy, while increased financial knowledge enhances investment confidence and decision-making. Additionally, behavioral finance factors and susceptibility to financial scams are significantly influenced by levels of financial literacy. These results underscore the importance of targeted financial education programs to improve financial literacy and empower individuals to participate effectively in the stock market.
Authors: Zongqian Zhan, Yifei Yu, Rui Xia, Wentian Gan, Hong Xie, Giulio Perda, Luca Morelli, Fabio Remondino, Xin Wang
Abstract: In the last twenty years, Structure from Motion (SfM) has been a constant research hotspot in the fields of photogrammetry, computer vision, robotics etc., whereas real-time performance is just a recent topic of growing interest. This work builds upon the original on-the-fly SfM (Zhan et al., 2024) and presents an updated version with three new advancements to get better 3D from what you capture: (i) real-time image matching is further boosted by employing the Hierarchical Navigable Small World (HNSW) graphs, thus more true positive overlapping image candidates are faster identified; (ii) a self-adaptive weighting strategy is proposed for robust hierarchical local bundle adjustment to improve the SfM results; (iii) multiple agents are included for supporting collaborative SfM and seamlessly merge multiple 3D reconstructions into a complete 3D scene when commonly registered images appear. Various comprehensive experiments demonstrate that the proposed SfM method (named on-the-fly SfMv2) can generate more complete and robust 3D reconstructions in a high time-efficient way. Code is available at http://yifeiyu225.github.io/on-the-flySfMv2.github.io/.
URLs: http://yifeiyu225.github.io/on-the-flySfMv2.github.io/.
Authors: Thuc Nguyen-Quang, Minh-Triet Tran
Abstract: Multi-object tracking (MOT) in computer vision remains a significant challenge, requiring precise localization and continuous tracking of multiple objects in video sequences. The emergence of data sets that emphasize robust reidentification, such as DanceTrack, has highlighted the need for effective solutions. While memory-based approaches have shown promise, they often suffer from high computational complexity and memory usage due to storing feature at every single frame. In this paper, we propose a novel memory-based approach that selectively stores critical features based on object motion and overlapping awareness, aiming to enhance efficiency while minimizing redundancy. As a result, our method not only store longer temporal information with limited number of stored features in the memory, but also diversify states of a particular object to enhance the association performance. Our approach significantly improves over MOTRv2 in the DanceTrack test set, demonstrating a gain of 2.0% AssA score and 2.1% in IDF1 score.
Authors: Jisu Shin, Junmyeong Lee, Seongmin Lee, Min-Gyu Park, Ju-Mi Kang, Ju Hong Yoon, Hae-Gon Jeon
Abstract: We present a novel framework for reconstructing animatable human avatars from multiple images, termed CanonicalFusion. Our central concept involves integrating individual reconstruction results into the canonical space. To be specific, we first predict Linear Blend Skinning (LBS) weight maps and depth maps using a shared-encoder-dual-decoder network, enabling direct canonicalization of the 3D mesh from the predicted depth maps. Here, instead of predicting high-dimensional skinning weights, we infer compressed skinning weights, i.e., 3-dimensional vector, with the aid of pre-trained MLP networks. We also introduce a forward skinning-based differentiable rendering scheme to merge the reconstructed results from multiple images. This scheme refines the initial mesh by reposing the canonical mesh via the forward skinning and by minimizing photometric and geometric errors between the rendered and the predicted results. Our optimization scheme considers the position and color of vertices as well as the joint angles for each image, thereby mitigating the negative effects of pose errors. We conduct extensive experiments to demonstrate the effectiveness of our method and compare our CanonicalFusion with state-of-the-art methods. Our source codes are available at https://github.com/jsshin98/CanonicalFusion.
Authors: Qi Wang, Zhou Xu, Yuming Lin, Jingtao Ye, Hongsheng Li, Guangming Zhu, Syed Afaq Ali Shah, Mohammed Bennamoun, Liang Zhang
Abstract: Neuromorphic sensors, specifically event cameras, revolutionize visual data acquisition by capturing pixel intensity changes with exceptional dynamic range, minimal latency, and energy efficiency, setting them apart from conventional frame-based cameras. The distinctive capabilities of event cameras have ignited significant interest in the domain of event-based action recognition, recognizing their vast potential for advancement. However, the development in this field is currently slowed by the lack of comprehensive, large-scale datasets, which are critical for developing robust recognition frameworks. To bridge this gap, we introduces DailyDVS-200, a meticulously curated benchmark dataset tailored for the event-based action recognition community. DailyDVS-200 is extensive, covering 200 action categories across real-world scenarios, recorded by 47 participants, and comprises more than 22,000 event sequences. This dataset is designed to reflect a broad spectrum of action types, scene complexities, and data acquisition diversity. Each sequence in the dataset is annotated with 14 attributes, ensuring a detailed characterization of the recorded actions. Moreover, DailyDVS-200 is structured to facilitate a wide range of research paths, offering a solid foundation for both validating existing approaches and inspiring novel methodologies. By setting a new benchmark in the field, we challenge the current limitations of neuromorphic data processing and invite a surge of new approaches in event-based action recognition techniques, which paves the way for future explorations in neuromorphic computing and beyond. The dataset and source code are available at https://github.com/QiWang233/DailyDVS-200.
Authors: Zixu Cheng, Yujiang Pu, Shaogang Gong, Parisa Kordjamshidi, Yu Kong
Abstract: Temporal grounding, also known as video moment retrieval, aims at locating video segments corresponding to a given query sentence. The compositional nature of natural language enables the localization beyond predefined events, posing a certain challenge to the compositional generalizability of existing methods. Recent studies establish the correspondence between videos and queries through a decompose-reconstruct manner to achieve compositional generalization. However, they only consider dominant primitives and build negative queries through random sampling and recombination, resulting in semantically implausible negatives that hinder the models from learning rational compositions. In addition, recent DETR-based methods still underperform in compositional temporal grounding, showing irrational saliency responses when given negative queries that have subtle differences from positive queries. To address these limitations, we first propose a large language model-driven method for negative query construction, utilizing GPT-3.5-Turbo to generate semantically plausible hard negative queries. Subsequently, we introduce a coarse-to-fine saliency ranking strategy, which encourages the model to learn the multi-granularity semantic relationships between videos and hierarchical negative queries to boost compositional generalization. Extensive experiments on two challenging benchmarks validate the effectiveness and generalizability of our proposed method. Our code is available at https://github.com/zxccade/SHINE.
Authors: Zhonghang Liu, Panzhong Lu, Guoyang Xie, Zhichao Lu, Wen-Yan Lin
Abstract: In the realm of unsupervised image outlier detection, assigning outlier scores holds greater significance than its subsequent task: thresholding for predicting labels. This is because determining the optimal threshold on non-separable outlier score functions is an ill-posed problem. However, the lack of predicted labels not only hiders some real applications of current outlier detectors but also causes these methods not to be enhanced by leveraging the dataset's self-supervision. To advance existing scoring methods, we propose a multiple thresholding (Multi-T) module. It generates two thresholds that isolate inliers and outliers from the unlabelled target dataset, whereas outliers are employed to obtain better feature representation while inliers provide an uncontaminated manifold. Extensive experiments verify that Multi-T can significantly improve proposed outlier scoring methods. Moreover, Multi-T contributes to a naive distance-based method being state-of-the-art.
Authors: Shahaf E. Finder, Roy Amoyal, Eran Treister, Oren Freifeld
Abstract: In recent years, there have been attempts to increase the kernel size of Convolutional Neural Nets (CNNs) to mimic the global receptive field of Vision Transformers' (ViTs) self-attention blocks. That approach, however, quickly hit an upper bound and saturated way before achieving a global receptive field. In this work, we demonstrate that by leveraging the Wavelet Transform (WT), it is, in fact, possible to obtain very large receptive fields without suffering from over-parameterization, e.g., for a $k \times k$ receptive field, the number of trainable parameters in the proposed method grows only logarithmically with $k$. The proposed layer, named WTConv, can be used as a drop-in replacement in existing architectures, results in an effective multi-frequency response, and scales gracefully with the size of the receptive field. We demonstrate the effectiveness of the WTConv layer within ConvNeXt and MobileNetV2 architectures for image classification, as well as backbones for downstream tasks, and show it yields additional properties such as robustness to image corruption and an increased response to shapes over textures. Our code is available at https://github.com/BGU-CS-VIL/WTConv.
Authors: Taolin Zhang, Jiawang Bai, Zhihe Lu, Dongze Lian, Genping Wang, Xinchao Wang, Shu-Tao Xia
Abstract: Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new structures into the pre-trained model, entire intermediate features of that model are changed and thus need to be stored to be involved in back-propagation, resulting in memory-heavy training. We solve this problem from a novel disentangled perspective, i.e., dividing PETL into two aspects: task-specific learning and pre-trained knowledge utilization. Specifically, we synthesize the task-specific query with a learnable and lightweight module, which is independent of the pre-trained model. The synthesized query equipped with task-specific knowledge serves to extract the useful features for downstream tasks from the intermediate representations of the pre-trained model in a query-only manner. Built upon these features, a customized classification head is proposed to make the prediction for the input sample. lightweight architecture and avoids the use of heavy intermediate features for running gradient descent, it demonstrates limited memory usage in training. Extensive experiments manifest that our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
Authors: Peifu Liu, Tingfa Xu, Jie Wang, Huan Chen, Huiyan Bai, Jianan Li
Abstract: Hyperspectral image classification, a task that assigns pre-defined classes to each pixel in a hyperspectral image of remote sensing scenes, often faces challenges due to the neglect of correlations between spectrally similar pixels. This oversight can lead to inaccurate edge definitions and difficulties in managing minor spectral variations in contiguous areas. To address these issues, we introduce the novel Dual-stage Spectral Supertoken Classifier (DSTC), inspired by superpixel concepts. DSTC employs spectrum-derivative-based pixel clustering to group pixels with similar spectral characteristics into spectral supertokens. By projecting the classification of these tokens onto the image space, we achieve pixel-level results that maintain regional classification consistency and precise boundary. Moreover, recognizing the diversity within tokens, we propose a class-proportion-based soft label. This label adaptively assigns weights to different categories based on their prevalence, effectively managing data distribution imbalances and enhancing classification performance. Comprehensive experiments on WHU-OHS, IP, KSC, and UP datasets corroborate the robust classification capabilities of DSTC and the effectiveness of its individual components. Code will be publicly available at https://github.com/laprf/DSTC.
Authors: Seonghoon Yu, Paul Hongsuck Seo, Jeany Son
Abstract: We propose a new framework that automatically generates high-quality segmentation masks with their referring expressions as pseudo supervisions for referring image segmentation (RIS). These pseudo supervisions allow the training of any supervised RIS methods without the cost of manual labeling. To achieve this, we incorporate existing segmentation and image captioning foundation models, leveraging their broad generalization capabilities. However, the naive incorporation of these models may generate non-distinctive expressions that do not distinctively refer to the target masks. To address this challenge, we propose two-fold strategies that generate distinctive captions: 1) 'distinctive caption sampling', a new decoding method for the captioning model, to generate multiple expression candidates with detailed words focusing on the target. 2) 'distinctiveness-based text filtering' to further validate the candidates and filter out those with a low level of distinctiveness. These two strategies ensure that the generated text supervisions can distinguish the target from other objects, making them appropriate for the RIS annotations. Our method significantly outperforms both weakly and zero-shot SoTA methods on the RIS benchmark datasets. It also surpasses fully supervised methods in unseen domains, proving its capability to tackle the open-world challenge within RIS. Furthermore, integrating our method with human annotations yields further improvements, highlighting its potential in semi-supervised learning applications.
Authors: Kun Wu, Zhiguo Jiang, Kunming Tang, Jun Shi, Fengying Xie, Wei Wang, Haibo Wu, Yushan Zheng
Abstract: Large-scale pre-training models have promoted the development of histopathology image analysis. However, existing self-supervised methods for histopathology images focus on learning patch features, while there is still a lack of available pre-training models for WSI-level feature learning. In this paper, we propose a novel self-supervised learning framework for pan-cancer WSI-level representation pre-training with the designed position-aware masked autoencoder (PAMA). Meanwhile, we propose the position-aware cross-attention (PACA) module with a kernel reorientation (KRO) strategy and an anchor dropout (AD) mechanism. The KRO strategy can capture the complete semantic structure and eliminate ambiguity in WSIs, and the AD contributes to enhancing the robustness and generalization of the model. We evaluated our method on 6 large-scale datasets from multiple organs for pan-cancer classification tasks. The results have demonstrated the effectiveness of PAMA in generalized and discriminative WSI representation learning and pan-cancer WSI pre-training. The proposed method was also compared with 7 WSI analysis methods. The experimental results have indicated that our proposed PAMA is superior to the state-of-the-art methods.The code and checkpoints are available at https://github.com/WkEEn/PAMA.
Authors: Xiaoyong Lu, Songlin Du
Abstract: Current feature matching methods prioritize improving modeling capabilities to better align outputs with ground-truth matches, which are the theoretical upper bound on matching results, metaphorically depicted as the "ceiling". However, these enhancements fail to address the underlying issues that directly hinder ground-truth matches, including the scarcity of matchable points in small scale images, matching conflicts in dense methods, and the keypoint-repeatability reliance in sparse methods. We propose a novel feature matching method named RCM, which Raises the Ceiling of Matching from three aspects. 1) RCM introduces a dynamic view switching mechanism to address the scarcity of matchable points in source images by strategically switching image pairs. 2) RCM proposes a conflict-free coarse matching module, addressing matching conflicts in the target image through a many-to-one matching strategy. 3) By integrating the semi-sparse paradigm and the coarse-to-fine architecture, RCM preserves the benefits of both high efficiency and global search, mitigating the reliance on keypoint repeatability. As a result, RCM enables more matchable points in the source image to be matched in an exhaustive and conflict-free manner in the target image, leading to a substantial 260% increase in ground-truth matches. Comprehensive experiments show that RCM exhibits remarkable performance and efficiency in comparison to state-of-the-art methods.
Authors: Jianan Wei, Tianfei Zhou, Yi Yang, Wenguan Wang
Abstract: This work addresses a new challenge of understanding human nonverbal interaction in social contexts. Nonverbal signals pervade virtually every communicative act. Our gestures, facial expressions, postures, gaze, even physical appearance all convey messages, without anything being said. Despite their critical role in social life, nonverbal signals receive very limited attention as compared to the linguistic counterparts, and existing solutions typically examine nonverbal cues in isolation. Our study marks the first systematic effort to enhance the interpretation of multifaceted nonverbal signals. First, we contribute a novel large-scale dataset, called NVI, which is meticulously annotated to include bounding boxes for humans and corresponding social groups, along with 22 atomic-level nonverbal behaviors under five broad interaction types. Second, we establish a new task NVI-DET for nonverbal interaction detection, which is formalized as identifying triplets in the form
Authors: Jinlong Li, Zequn Jie, Elisa Ricci, Lin Ma, Nicu Sebe
Abstract: Efficient finetuning of vision-language models (VLMs) like CLIP for specific downstream tasks is gaining significant attention. Previous works primarily focus on prompt learning to adapt the CLIP into a variety of downstream tasks, however, suffering from task overfitting when finetuned on a small data set. In this paper, we introduce an orthogonal finetuning method for efficiently updating pretrained weights which enhances robustness and generalization, while a cross-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed \textbf{\textit{OrthCR}}. Specifically, trainable orthogonal matrices are injected seamlessly into the transformer architecture and enforced with orthogonality constraint using Cayley parameterization, benefiting from the norm-preserving property and thus leading to stable and faster convergence. To alleviate deviation from orthogonal constraint during training, a cross-regularization strategy is further employed with initial pretrained weights within a bypass manner. In addition, to enrich the sample diversity for downstream tasks, we first explore Cutout data augmentation to boost the efficient finetuning and comprehend how our approach improves the specific downstream performance and maintains the generalizability in the perspective of Orthogonality Learning. Beyond existing prompt learning techniques, we conduct extensive experiments to demonstrate that our method explicitly steers pretrained weight space to represent the task-specific knowledge and presents competitive generalizability under base-to-base/base-to-new, cross-dataset transfer and domain generalization evaluations.
Authors: Youssef Sultan, Jiangqin Ma, Yu-Ying Liao
Abstract: In this paper, we show different fine-tuning methods for Stable Diffusion XL; this includes inference steps, and caption customization for each image to align with generating images in the style of a commercial 2D icon training set. We also show how important it is to properly define what "high-quality" really is especially for a commercial-use environment. As generative AI models continue to gain widespread acceptance and usage, there emerge many different ways to optimize and evaluate them for various applications. Specifically text-to-image models, such as Stable Diffusion XL and DALL-E 3 require distinct evaluation practices to effectively generate high-quality icons according to a specific style. Although some images that are generated based on a certain style may have a lower FID score (better), we show how this is not absolute in and of itself even for rasterized icons. While FID scores reflect the similarity of generated images to the overall training set, CLIP scores measure the alignment between generated images and their textual descriptions. We show how FID scores miss significant aspects, such as the minority of pixel differences that matter most in an icon, while CLIP scores result in misjudging the quality of icons. The CLIP model's understanding of "similarity" is shaped by its own training data; which does not account for feature variation in our style of choice. Our findings highlight the need for specialized evaluation metrics and fine-tuning approaches when generating high-quality commercial icons, potentially leading to more effective and tailored applications of text-to-image models in professional design contexts.
Authors: Sebastian Bordt, Uddeshya Upadhyay, Zeynep Akata, Ulrike von Luxburg
Abstract: When do gradient-based explanation algorithms provide perceptually-aligned explanations? We propose a criterion: the feature attributions need to be aligned with the tangent space of the data manifold. To provide evidence for this hypothesis, we introduce a framework based on variational autoencoders that allows to estimate and generate image manifolds. Through experiments across a range of different datasets -- MNIST, EMNIST, CIFAR10, X-ray pneumonia and Diabetic Retinopathy detection -- we demonstrate that the more a feature attribution is aligned with the tangent space of the data, the more perceptually-aligned it tends to be. We then show that the attributions provided by popular post-hoc methods such as Integrated Gradients and SmoothGrad are more strongly aligned with the data manifold than the raw gradient. Adversarial training also improves the alignment of model gradients with the data manifold. As a consequence, we suggest that explanation algorithms should actively strive to align their explanations with the data manifold. This is an extended version of a CVPR Workshop paper. Code is available at https://github.com/tml-tuebingen/explanations-manifold.
URLs: https://github.com/tml-tuebingen/explanations-manifold.
Authors: Dhananjay Joshi, Bhupesh Kumar Singh, Kapil Kumar Nagwanshi, Nitin S. Choubey
Abstract: In today's world of health care, brain tumor detection has become common. However, the manual brain tumor classification approach is time-consuming. So Deep Convolutional Neural Network (DCNN) is used by many researchers in the medical field for making accurate diagnoses and aiding in the patient's treatment. The traditional techniques have problems such as overfitting and the inability to extract necessary features. To overcome these problems, we developed the Topological Data Analysis based Improved Persistent Homology (TDA-IPH) and Convolutional Transfer learning and Visual Recurrent learning with Elephant Herding Optimization hyper-parameter tuning (CTVR-EHO) models for brain tumor segmentation and classification. Initially, the Topological Data Analysis based Improved Persistent Homology is designed to segment the brain tumor image. Then, from the segmented image, features are extracted using TL via the AlexNet model and Bidirectional Visual Long Short-Term Memory (Bi-VLSTM). Next, elephant Herding Optimization (EHO) is used to tune the hyperparameters of both networks to get an optimal result. Finally, extracted features are concatenated and classified using the softmax activation layer. The simulation result of this proposed CTVR-EHO and TDA-IPH method is analyzed based on precision, accuracy, recall, loss, and F score metrics. When compared to other existing brain tumor segmentation and classification models, the proposed CTVR-EHO and TDA-IPH approaches show high accuracy (99.8%), high recall (99.23%), high precision (99.67%), and high F score (99.59%).
Authors: Chenghao Wu, Hamila Mailee, Zahra Montazeri, Tobias Ritschel
Abstract: Differentiable rasterization changes the standard formulation of primitive rasterization -- by enabling gradient flow from a pixel to its underlying triangles -- using distribution functions in different stages of rendering, creating a "soft" version of the original rasterizer. However, choosing the optimal softening function that ensures the best performance and convergence to a desired goal requires trial and error. Previous work has analyzed and compared several combinations of softening. In this work, we take it a step further and, instead of making a combinatorial choice of softening operations, parameterize the continuous space of common softening operations. We study meta-learning tunable softness functions over a set of inverse rendering tasks (2D and 3D shape, pose and occlusion) so it generalizes to new and unseen differentiable rendering tasks with optimal softness.
Authors: Mehdi Cherti, Romain Beaumont, Ross Wightman, Mitchell Wortsman, Gabriel Ilharco, Cade Gordon, Christoph Schuhmann, Ludwig Schmidt, Jenia Jitsev
Abstract: Scaling up neural networks has led to remarkable performance across a wide range of tasks. Moreover, performance often follows reliable scaling laws as a function of training set size, model size, and compute, which offers valuable guidance as large-scale experiments are becoming increasingly expensive. However, previous work on scaling laws has primarily used private data \& models or focused on uni-modal language or vision learning. To address these limitations, we investigate scaling laws for contrastive language-image pre-training (CLIP) with the public LAION dataset and the open-source OpenCLIP repository. Our large-scale experiments involve models trained on up to two billion image-text pairs and identify power law scaling for multiple downstream tasks including zero-shot classification, retrieval, linear probing, and end-to-end fine-tuning. We find that the training distribution plays a key role in scaling laws as the OpenAI and OpenCLIP models exhibit different scaling behavior despite identical model architectures and similar training recipes. We open-source our evaluation workflow and all models, including the largest public CLIP models, to ensure reproducibility and make scaling laws research more accessible. Source code and instructions to reproduce this study will be available at https://github.com/LAION-AI/scaling-laws-openclip
Authors: Seungwoo Son, Jegwang Ryu, Namhoon Lee, Jaeho Lee
Abstract: Knowledge distillation is an effective method for training lightweight vision models. However, acquiring teacher supervision for training samples is often costly, especially from large-scale models like vision transformers (ViTs). In this paper, we develop a simple framework to reduce the supervision cost of ViT distillation: masking out a fraction of input tokens given to the teacher. By masking input tokens, one can skip the computations associated with the masked tokens without requiring any change to teacher parameters or architecture. We find that masking patches with the lowest student attention scores is highly effective, saving up to 50% of teacher FLOPs without any drop in student accuracy, while other masking criterion leads to suboptimal efficiency gains. Through in-depth analyses, we reveal that the student-guided masking provides a good curriculum to the student, making teacher supervision easier to follow during the early stage and challenging in the later stage.
Authors: Emanuel Sanchez Aimar, Nathaniel Helgesen, Yonghao Xu, Marco Kuhlmann, Michael Felsberg
Abstract: Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. This problem is often aggravated by discrepancies between labeled and unlabeled class distributions, leading to biased pseudo-labels, neglect of rare classes, and poorly calibrated probabilities. To address these issues, we introduce Flexible Distribution Alignment (FlexDA), a novel adaptive logit-adjusted loss framework designed to dynamically estimate and align predictions with the actual distribution of unlabeled data and achieve a balanced classifier by the end of training. FlexDA is further enhanced by a distillation-based consistency loss, promoting fair data usage across classes and effectively leveraging underconfident samples. This method, encapsulated in ADELLO (Align and Distill Everything All at Once), proves robust against label shift, significantly improves model calibration in LTSSL contexts, and surpasses previous state-of-of-art approaches across multiple benchmarks, including CIFAR100-LT, STL10-LT, and ImageNet127, addressing class imbalance challenges in semi-supervised learning. Our code is available at https://github.com/emasa/ADELLO-LTSSL.
Authors: Xuelong Dai, Kaisheng Liang, Bin Xiao
Abstract: Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms. However, previous attack methods often directly inject Projected Gradient Descent (PGD) gradients into the sampling of generative models, which are not theoretically provable and thus generate unrealistic examples by incorporating adversarial objectives, especially for GAN-based methods on large-scale datasets like ImageNet. In this paper, we propose a new method, called AdvDiff, to generate unrestricted adversarial examples with diffusion models. We design two novel adversarial guidance techniques to conduct adversarial sampling in the reverse generation process of diffusion models. These two techniques are effective and stable in generating high-quality, realistic adversarial examples by integrating gradients of the target classifier interpretably. Experimental results on MNIST and ImageNet datasets demonstrate that AdvDiff is effective in generating unrestricted adversarial examples, which outperforms state-of-the-art unrestricted adversarial attack methods in terms of attack performance and generation quality.
Authors: Chanwut Kittivorawong, Yongming Ge, Yousef Helal, Alvin Cheung
Abstract: Videos that are shot using commodity hardware such as phones and surveillance cameras record various metadata such as time and location. We encounter such geospatial videos on a daily basis and such videos have been growing in volume significantly. Yet, we do not have data management systems that allow users to interact with such data effectively. In this paper, we describe Spatialyze, a new framework for end-to-end querying of geospatial videos. Spatialyze comes with a domain-specific language where users can construct geospatial video analytic workflows using a 3-step, declarative, build-filter-observe paradigm. Internally, Spatialyze leverages the declarative nature of such workflows, the temporal-spatial metadata stored with videos, and physical behavior of real-world objects to optimize the execution of workflows. Our results using real-world videos and workflows show that Spatialyze can reduce execution time by up to 5.3x, while maintaining up to 97.1% accuracy compared to unoptimized execution.
Authors: Grzegorz Rype\'s\'c, Daniel Marczak, Sebastian Cygert, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski
Abstract: Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old knowledge. However, this strategy restricts the model's ability to adapt and effectively distinguish new categories. To address this, we introduce a novel technique integrating a learnable projector with feature distillation, thus enhancing model adaptability without sacrificing past knowledge. The resulting distribution shift of the previously learned categories is mitigated with the auxiliary category adaptation network. We demonstrate that while each component offers modest benefits individually, their combination - dubbed CAMP (Category Adaptation Meets Projected distillation) - significantly improves the balance between learning new information and retaining old. CAMP exhibits superior performance across several GCCD and Class Incremental Learning scenarios. The code is available at https://github.com/grypesc/CAMP.
Authors: Chiao-Yi Wang, Faranguisse Kakhi Sadrieh, Yi-Ting Shen, Shih-En Chen, Sarah Kim, Victoria Chen, Achyut Raghavendra, Dongyi Wang, Osamah Saeedi, Yang Tao
Abstract: The measurement of retinal blood flow (RBF) in capillaries can provide a powerful biomarker for the early diagnosis and treatment of ocular diseases. However, no single modality can determine capillary flowrates with high precision. Combining erythrocyte-mediated angiography (EMA) with optical coherence tomography angiography (OCTA) has the potential to achieve this goal, as EMA can measure the absolute 2D RBF of retinal microvasculature and OCTA can provide the 3D structural images of capillaries. However, multimodal retinal image registration between these two modalities remains largely unexplored. To fill this gap, we establish MEMO, the first public multimodal EMA and OCTA retinal image dataset. A unique challenge in multimodal retinal image registration between these modalities is the relatively large difference in vessel density (VD). To address this challenge, we propose a segmentation-based deep-learning framework (VDD-Reg) and a new evaluation metric (MSD), which provide robust results despite differences in vessel density. VDD-Reg consists of a vessel segmentation module and a registration module. To train the vessel segmentation module, we further designed a two-stage semi-supervised learning framework (LVD-Seg) combining supervised and unsupervised losses. We demonstrate that VDD-Reg outperforms baseline methods quantitatively and qualitatively for cases of both small VD differences (using the CF-FA dataset) and large VD differences (using our MEMO dataset). Moreover, VDD-Reg requires as few as three annotated vessel segmentation masks to maintain its accuracy, demonstrating its feasibility.
Authors: Sneha Silwal, Karmesh Yadav, Tingfan Wu, Jay Vakil, Arjun Majumdar, Sergio Arnaud, Claire Chen, Vincent-Pierre Berges, Dhruv Batra, Aravind Rajeswaran, Mrinal Kalakrishnan, Franziska Meier, Oleksandr Maksymets
Abstract: We present a large empirical investigation on the use of pre-trained visual representations (PVRs) for training downstream policies that execute real-world tasks. Our study involves five different PVRs, each trained for five distinct manipulation or indoor navigation tasks. We performed this evaluation using three different robots and two different policy learning paradigms. From this effort, we can arrive at three insights: 1) the performance trends of PVRs in the simulation are generally indicative of their trends in the real world, 2) the use of PVRs enables a first-of-its-kind result with indoor ImageNav (zero-shot transfer to a held-out scene in the real world), and 3) the benefits from variations in PVRs, primarily data-augmentation and fine-tuning, also transfer to the real-world performance. See project website for additional details and visuals.
Authors: Jingjing Zheng, Wanglong Lu, Wenzhe Wang, Yankai Cao, Xiaoqin Zhang, Xianta Jiang
Abstract: Recently, numerous tensor singular value decomposition (t-SVD)-based tensor recovery methods have shown promise in processing visual data, such as color images and videos. However, these methods often suffer from severe performance degradation when confronted with tensor data exhibiting non-smooth changes. It has been commonly observed in real-world scenarios but ignored by the traditional t-SVD-based methods. In this work, we introduce a novel tensor recovery model with a learnable tensor nuclear norm to address such a challenge. We develop a new optimization algorithm named the Alternating Proximal Multiplier Method (APMM) to iteratively solve the proposed tensor completion model. Theoretical analysis demonstrates the convergence of the proposed APMM to the Karush-Kuhn-Tucker (KKT) point of the optimization problem. In addition, we propose a multi-objective tensor recovery framework based on APMM to efficiently explore the correlations of tensor data across its various dimensions, providing a new perspective on extending the t-SVD-based method to higher-order tensor cases. Numerical experiments demonstrated the effectiveness of the proposed method in tensor completion.
Authors: Chollette C. Olisah
Abstract: Despite the advancement in computational modeling towards brain tumor segmentation, of which several models have been developed, it is evident from the computational complexity of existing models which are still at an all-time high, that performance and efficiency under clinical application scenarios are limited. Therefore, this paper proposes a shallow encoder and decoder network named SEDNet for brain tumor segmentation. The proposed network is adapted from the U-Net structure. Though brain tumors do not assume complex structures like the task the traditional U-Net was designed for, their variance in appearance, shape, and ambiguity of boundaries makes it a compelling complex task to solve. SEDNet architecture design is inspired by the localized nature of brain tumors in brain images, thus consists of sufficient hierarchical convolutional blocks in the encoding pathway capable of learning the intrinsic features of brain tumors in brain slices, and a decoding pathway with selective skip path sufficient for capturing miniature local-level spatial features alongside the global-level features of brain tumor. SEDNet with the integration of the proposed preprocessing algorithm and optimization function on the BraTS2020 set reserved for testing achieves impressive dice and Hausdorff scores of 0.9308, 0.9451, 0.9026, and 0.7040, 1.2866, 0.7762 for non-enhancing tumor core (NTC), peritumoral edema (ED), and enhancing tumor (ET), respectively. Furthermore, through transfer learning with initialized SEDNet pre-trained weights, termed SEDNetX, a performance increase is observed. The dice and Hausdorff scores recorded are 0.9336, 0.9478, 0.9061, 0.6983, 1.2691, and 0.7711 for NTC, ED, and ET, respectively. With about 1.3 million parameters and impressive performance in comparison to the state-of-the-art, SEDNet(X) is shown to be computationally efficient for real-time clinical diagnosis.
Authors: Alessandro Bombini, Fernando Garc\'ia-Avello Bof\'ias, Caterina Bracci, Michele Ginolfi, Chiara Ruberto
Abstract: Extended Vision techniques are ubiquitous in physics. However, the data cubes steaming from such analysis often pose a challenge in their interpretation, due to the intrinsic difficulty in discerning the relevant information from the spectra composing the data cube. Furthermore, the huge dimensionality of data cube spectra poses a complex task in its statistical interpretation; nevertheless, this complexity contains a massive amount of statistical information that can be exploited in an unsupervised manner to outline some essential properties of the case study at hand, e.g.~it is possible to obtain an image segmentation via (deep) clustering of data-cube's spectra, performed in a suitably defined low-dimensional embedding space. To tackle this topic, we explore the possibility of applying unsupervised clustering methods in encoded space, i.e. perform deep clustering on the spectral properties of datacube pixels. A statistical dimensional reduction is performed by an ad hoc trained (Variational) AutoEncoder, in charge of mapping spectra into lower dimensional metric spaces, while the clustering process is performed by a (learnable) iterative K-Means clustering algorithm. We apply this technique to two different use cases, of different physical origins: a set of Macro mapping X-Ray Fluorescence (MA-XRF) synthetic data on pictorial artworks, and a dataset of simulated astrophysical observations.
Authors: Salman Ul Hassan Dar, Marvin Seyfarth, Jannik Kahmann, Isabelle Ayx, Theano Papavassiliu, Stefan O. Schoenberg, Norbert Frey, Bettina Bae{\ss}ler, Sebastian Foersch, Daniel Truhn, Jakob Nikolas Kather, Sandy Engelhardt
Abstract: AI models present a wide range of applications in the field of medicine. However, achieving optimal performance requires access to extensive healthcare data, which is often not readily available. Furthermore, the imperative to preserve patient privacy restricts patient data sharing with third parties and even within institutes. Recently, generative AI models have been gaining traction for facilitating open-data sharing by proposing synthetic data as surrogates of real patient data. Despite the promise, these models are susceptible to patient data memorization, where models generate patient data copies instead of novel synthetic samples. Considering the importance of the problem, it has received little attention in the medical imaging community. To this end, we assess memorization in unconditional latent diffusion models. We train 2D and 3D latent diffusion models on CT, MR, and X-ray datasets for synthetic data generation. Afterwards, we detect the amount of training data memorized utilizing our self-supervised approach and further investigate various factors that can influence memorization. Our findings show a surprisingly high degree of patient data memorization across all datasets, with approximately 40.9% of patient data being memorized and 78.5% of synthetic samples identified as patient data copies on average in our experiments. Further analyses reveal that using augmentation strategies during training can reduce memorization while over-training the models can enhance it. Although increasing the dataset size does not reduce memorization and might even enhance it, it does lower the probability of a synthetic sample being a patient data copy. Collectively, our results emphasize the importance of carefully training generative models on private medical imaging datasets, and examining the synthetic data to ensure patient privacy before sharing it for medical research and applications.
Authors: Jiwen Zhang, Jihao Wu, Yihua Teng, Minghui Liao, Nuo Xu, Xiao Xiao, Zhongyu Wei, Duyu Tang
Abstract: Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual observations, existing studies typically consider little semantic information carried out by intermediate screenshots and screen operations. To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions should be performed and the outcomes led by the chosen action. We demonstrate that, in a zero-shot setting upon three off-the-shelf LMMs, CoAT significantly improves the action prediction compared to previous proposed context modeling. To further facilitate the research in this line, we construct a dataset Android-In-The-Zoo (AitZ), which contains 18,643 screen-action pairs together with chain-of-action-thought annotations. Experiments show that fine-tuning a 1B model (i.e. AUTO-UI-base) on our AitZ dataset achieves on-par performance with CogAgent-Chat-18B.
Authors: Anh Bui, Khanh Doan, Trung Le, Paul Montague, Tamas Abraham, Dinh Phung
Abstract: Diffusion models have shown remarkable capability in generating visually impressive content from textual descriptions. However, these models are trained on vast internet data, much of which contains undesirable elements such as sensitive content, copyrighted material, and unethical or harmful concepts. Therefore, beyond generating high-quality content, it is crucial to ensure these models do not propagate these undesirable elements. To address this issue, we propose a novel method to remove undesirable concepts from text-to-image diffusion models by incorporating a learnable prompt into the cross-attention module. This learnable prompt acts as additional memory, capturing the knowledge of undesirable concepts and reducing their dependency on the model parameters and corresponding textual inputs. By transferring this knowledge to the prompt, erasing undesirable concepts becomes more stable and has minimal negative impact on other concepts. We demonstrate the effectiveness of our method on the Stable Diffusion model, showcasing its superiority over state-of-the-art erasure methods in removing undesirable content while preserving unrelated elements.
Authors: Gaurav Singh, Sanket Kalwar, Md Faizal Karim, Bipasha Sen, Nagamanikandan Govindan, Srinath Sridhar, K Madhava Krishna
Abstract: Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requiring a deep understanding of the local geometry to generate grasps efficiently on the specified constrained regions. Existing methods only explore settings involving table-top/small objects and require augmented datasets to train, limiting their performance on complex objects. We propose CGDF: Constrained Grasp Diffusion Fields, a diffusion-based grasp generative model that generalizes to objects with arbitrary geometries, as well as generates dense grasps on the target regions. CGDF uses a part-guided diffusion approach that enables it to get high sample efficiency in constrained grasping without explicitly training on massive constraint-augmented datasets. We provide qualitative and quantitative comparisons using analytical metrics and in simulation, in both unconstrained and constrained settings to show that our method can generalize to generate stable grasps on complex objects, especially useful for dual-arm manipulation settings, while existing methods struggle to do so.
Authors: Georgy Perevozchikov, Nancy Mehta, Mahmoud Afifi, Radu Timofte
Abstract: Modern smartphone camera quality heavily relies on the image signal processor (ISP) to enhance captured raw images, utilizing carefully designed modules to produce final output images encoded in a standard color space (e.g., sRGB). Neural-based end-to-end learnable ISPs offer promising advancements, potentially replacing traditional ISPs with their ability to adapt without requiring extensive tuning for each new camera model, as is often the case for nearly every module in traditional ISPs. However, the key challenge with the recent learning-based ISPs is the urge to collect large paired datasets for each distinct camera model due to the influence of intrinsic camera characteristics on the formation of input raw images. This paper tackles this challenge by introducing a novel method for unpaired learning of raw-to-raw translation across diverse cameras. Specifically, we propose Rawformer, an unsupervised Transformer-based encoder-decoder method for raw-to-raw translation. It accurately maps raw images captured by a certain camera to the target camera, facilitating the generalization of learnable ISPs to new unseen cameras. Our method demonstrates superior performance on real camera datasets, achieving higher accuracy compared to previous state-of-the-art techniques, and preserving a more robust correlation between the original and translated raw images. The codes and the pretrained models are available at https://github.com/gosha20777/rawformer.
Authors: Haoyi Qiu, Wenbo Hu, Zi-Yi Dou, Nanyun Peng
Abstract: Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs, undermining their reliability. A comprehensive quantitative evaluation is necessary to identify and understand the extent of hallucinations in these models. However, existing benchmarks are often limited in scope, focusing mainly on object hallucinations. Furthermore, current evaluation methods struggle to effectively address the subtle semantic distinctions between model outputs and reference data, as well as the balance between hallucination and informativeness. To address these issues, we introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases. Moreover, we propose a large language model (LLM)-based two-stage evaluation framework that generalizes the popular CHAIR metric and incorporates both faithfulness and coverage into the evaluation. Experiments on 10 established LVLMs demonstrate that our evaluation metric is more comprehensive and better correlated with humans than existing work when evaluating on our challenging human-annotated benchmark dataset. Our work also highlights the critical balance between faithfulness and coverage of model outputs, and encourages future works to address hallucinations in LVLMs while keeping their outputs informative.
Authors: Johannes Hugger, Virginie Uhlmann
Abstract: Soft targets combined with the cross-entropy loss have shown to improve generalization performance of deep neural networks on supervised classification tasks. The standard cross-entropy loss however assumes data to be categorically distributed, which may often not be the case in practice. In contrast, InfoNCE does not rely on such an explicit assumption but instead implicitly estimates the true conditional through negative sampling. Unfortunately, it cannot be combined with soft targets in its standard formulation, hindering its use in combination with sophisticated training strategies. In this paper, we address this limitation by proposing a loss function that is compatible with probabilistic targets. Our new soft target InfoNCE loss is conceptually simple, efficient to compute, and can be motivated through the framework of noise contrastive estimation. Using a toy example, we demonstrate shortcomings of the categorical distribution assumption of cross-entropy, and discuss implications of sampling from soft distributions. We observe that soft target InfoNCE performs on par with strong soft target cross-entropy baselines and outperforms hard target NLL and InfoNCE losses on popular benchmarks, including ImageNet. Finally, we provide a simple implementation of our loss, geared towards supervised classification and fully compatible with deep classification models trained with cross-entropy.
Authors: Reihaneh Teimouri, Marta Kersten-Oertel, Yiming Xiao
Abstract: Efficient and accurate brain ventricle segmentation from clinical CT scans is critical for emergency surgeries like ventriculostomy. With the challenges in poor soft tissue contrast and a scarcity of well-annotated databases for clinical brain CTs, we introduce a novel uncertainty-aware ventricle segmentation technique without the need of CT segmentation ground truths by leveraging diffusion-model-based domain adaptation. Specifically, our method employs the diffusion Schr\"odinger Bridge and an attention recurrent residual U-Net to capitalize on unpaired CT and MRI scans to derive automatic CT segmentation from those of the MRIs, which are more accessible. Importantly, we propose an end-to-end, joint training framework of image translation and segmentation tasks, and demonstrate its benefit over training individual tasks separately. By comparing the proposed method against similar setups using two different GAN models for domain adaptation (CycleGAN and CUT), we also reveal the advantage of diffusion models towards improved segmentation and image translation quality. With a Dice score of 0.78$\pm$0.27, our proposed method outperformed the compared methods, including SynSeg-Net, while providing intuitive uncertainty measures to further facilitate quality control of the automatic segmentation outcomes. The implementation of our proposed method is available at: https://github.com/HealthX-Lab/DiffusionSynCTSeg.
Authors: Krishanu Maity, A. S. Poornash, Sriparna Saha, Pushpak Bhattacharyya
Abstract: In an era of rapidly evolving internet technology, the surge in multimodal content, including videos, has expanded the horizons of online communication. However, the detection of toxic content in this diverse landscape, particularly in low-resource code-mixed languages, remains a critical challenge. While substantial research has addressed toxic content detection in textual data, the realm of video content, especially in non-English languages, has been relatively underexplored. This paper addresses this research gap by introducing a benchmark dataset, the first of its kind, consisting of 931 videos with 4021 code-mixed Hindi-English utterances collected from YouTube. Each utterance within this dataset has been meticulously annotated for toxicity, severity, and sentiment labels. We have developed an advanced Multimodal Multitask framework built for Toxicity detection in Video Content by leveraging Language Models (LMs), crafted for the primary objective along with the additional tasks of conducting sentiment and severity analysis. ToxVidLM incorporates three key modules - the Encoder module, Cross-Modal Synchronization module, and Multitask module - crafting a generic multimodal LM customized for intricate video classification tasks. Our experiments reveal that incorporating multiple modalities from the videos substantially enhances the performance of toxic content detection by achieving an Accuracy and Weighted F1 score of 94.29% and 94.35%, respectively.
Authors: Jan Hagnberger, Marimuthu Kalimuthu, Daniel Musekamp, Mathias Niepert
Abstract: Transformer models are increasingly used for solving Partial Differential Equations (PDEs). Several adaptations have been proposed, all of which suffer from the typical problems of Transformers, such as quadratic memory and time complexity. Furthermore, all prevalent architectures for PDE solving lack at least one of several desirable properties of an ideal surrogate model, such as (i) generalization to PDE parameters not seen during training, (ii) spatial and temporal zero-shot super-resolution, (iii) continuous temporal extrapolation, (iv) support for 1D, 2D, and 3D PDEs, and (v) efficient inference for longer temporal rollouts. To address these limitations, we propose Vectorized Conditional Neural Fields (VCNeFs), which represent the solution of time-dependent PDEs as neural fields. Contrary to prior methods, however, VCNeFs compute, for a set of multiple spatio-temporal query points, their solutions in parallel and model their dependencies through attention mechanisms. Moreover, VCNeF can condition the neural field on both the initial conditions and the parameters of the PDEs. An extensive set of experiments demonstrates that VCNeFs are competitive with and often outperform existing ML-based surrogate models.
Authors: Jialiang Zhao, Yuxiang Ma, Lirui Wang, Edward H. Adelson
Abstract: This paper presents T3: Transferable Tactile Transformers, a framework for tactile representation learning that scales across multi-sensors and multi-tasks. T3 is designed to overcome the contemporary issue that camera-based tactile sensing is extremely heterogeneous, i.e. sensors are built into different form factors, and existing datasets were collected for disparate tasks. T3 captures the shared latent information across different sensor-task pairings by constructing a shared trunk transformer with sensor-specific encoders and task-specific decoders. The pre-training of T3 utilizes a novel Foundation Tactile (FoTa) dataset, which is aggregated from several open-sourced datasets and it contains over 3 million data points gathered from 13 sensors and 11 tasks. FoTa is the largest and most diverse dataset in tactile sensing to date and it is made publicly available in a unified format. Across various sensors and tasks, experiments show that T3 pre-trained with FoTa achieved zero-shot transferability in certain sensor-task pairings, can be further fine-tuned with small amounts of domain-specific data, and its performance scales with bigger network sizes. T3 is also effective as a tactile encoder for long horizon contact-rich manipulation. Results from sub-millimeter multi-pin electronics insertion tasks show that T3 achieved a task success rate 25% higher than that of policies trained with tactile encoders trained from scratch, or 53% higher than without tactile sensing. Data, code, and model checkpoints are open-sourced at https://t3.alanz.info.
URLs: https://t3.alanz.info.
Authors: Georgios Tziafas, Hamidreza Kasaei
Abstract: The ability to grasp objects in-the-wild from open-ended language instructions constitutes a fundamental challenge in robotics. An open-world grasping system should be able to combine high-level contextual with low-level physical-geometric reasoning in order to be applicable in arbitrary scenarios. Recent works exploit the web-scale knowledge inherent in large language models (LLMs) to plan and reason in robotic context, but rely on external vision and action models to ground such knowledge into the environment and parameterize actuation. This setup suffers from two major bottlenecks: a) the LLM's reasoning capacity is constrained by the quality of visual grounding, and b) LLMs do not contain low-level spatial understanding of the world, which is essential for grasping in contact-rich scenarios. In this work we demonstrate that modern vision-language models (VLMs) are capable of tackling such limitations, as they are implicitly grounded and can jointly reason about semantics and geometry. We propose OWG, an open-world grasping pipeline that combines VLMs with segmentation and grasp synthesis models to unlock grounded world understanding in three stages: open-ended referring segmentation, grounded grasp planning and grasp ranking via contact reasoning, all of which can be applied zero-shot via suitable visual prompting mechanisms. We conduct extensive evaluation in cluttered indoor scene datasets to showcase OWG's robustness in grounding from open-ended language, as well as open-world robotic grasping experiments in both simulation and hardware that demonstrate superior performance compared to previous supervised and zero-shot LLM-based methods.
Authors: Pandiyaraju V, Shravan Venkatraman, Pavan Kumar S, Santhosh Malarvannan, Kannan A
Abstract: Breast cancer poses a profound threat to lives globally, claiming numerous lives each year. Therefore, timely detection is crucial for early intervention and improved chances of survival. Accurately diagnosing and classifying breast tumors using ultrasound images is a persistent challenge in medicine, demanding cutting-edge solutions for improved treatment strategies. This research introduces multiattention-enhanced deep learning (DL) frameworks designed for the classification and segmentation of breast cancer tumors from ultrasound images. A spatial channel attention mechanism is proposed for segmenting tumors from ultrasound images, utilizing a novel LinkNet DL framework with an InceptionResNet backbone. Following this, the paper proposes a deep convolutional neural network with an integrated multi-attention framework (DCNNIMAF) to classify the segmented tumor as benign, malignant, or normal. From experimental results, it is observed that the segmentation model has recorded an accuracy of 98.1%, with a minimal loss of 0.6%. It has also achieved high Intersection over Union (IoU) and Dice Coefficient scores of 96.9% and 97.2%, respectively. Similarly, the classification model has attained an accuracy of 99.2%, with a low loss of 0.31%. Furthermore, the classification framework has achieved outstanding F1-Score, precision, and recall values of 99.1%, 99.3%, and 99.1%, respectively. By offering a robust framework for early detection and accurate classification of breast cancer, this proposed work significantly advances the field of medical image analysis, potentially improving diagnostic precision and patient outcomes.
Authors: Rui Li, Mikhail Kudryashev, Artur Yakimovich
Abstract: Optic deconvolution in light microscopy (LM) refers to recovering the object details from images, revealing the ground truth of samples. Traditional explicit methods in LM rely on the point spread function (PSF) during image acquisition. Yet, these approaches often fall short due to inaccurate PSF models and noise artifacts, hampering the overall restoration quality. In this paper, we approached the optic deconvolution as an inverse problem. Motivated by the nonstandard-form compression scheme introduced by Beylkin, Coifman, and Rokhlin (BCR), we proposed an innovative physics-informed neural network Multi-Stage Residual-BCR Net (m-rBCR) to approximate the optic deconvolution. We validated the m-rBCR model on four microscopy datasets - two simulated microscopy datasets from ImageNet and BioSR, real dSTORM microscopy images, and real widefield microscopy images. In contrast to the explicit deconvolution methods (e.g. Richardson-Lucy) and other state-of-the-art NN models (U-Net, DDPM, CARE, DnCNN, ESRGAN, RCAN, Noise2Noise, MPRNet, and MIMO-U-Net), the m-rBCR model demonstrates superior performance to other candidates by PSNR and SSIM in two real microscopy datasets and the simulated BioSR dataset. In the simulated ImageNet dataset, m-rBCR ranks the second-best place (right after MIMO-U-Net). With the backbone from the optical physics, m-rBCR exploits the trainable parameters with better performances (from ~30 times fewer than the benchmark MIMO-U-Net to ~210 times than ESRGAN). This enables m-rBCR to achieve a shorter runtime (from ~3 times faster than MIMO-U-Net to ~300 times faster than DDPM). To summarize, by leveraging physics constraints our model reduced potentially redundant parameters significantly in expertise-oriented NN candidates and achieved high efficiency with superior performance.
Authors: Yuxuan Yan, Na Lu, Ruofan Yan
Abstract: Combining machine clustering with deep models has shown remarkable superiority in deep clustering. It modifies the data processing pipeline into two alternating phases: feature clustering and model training. However, such alternating schedule may lead to instability and computational burden issues. We propose a centerless clustering algorithm called Probability Aggregation Clustering (PAC) to proactively adapt deep learning technologies, enabling easy deployment in online deep clustering. PAC circumvents the cluster center and aligns the probability space and distribution space by formulating clustering as an optimization problem with a novel objective function. Based on the computation mechanism of the PAC, we propose a general online probability aggregation module to perform stable and flexible feature clustering over mini-batch data and further construct a deep visual clustering framework deep PAC (DPAC). Extensive experiments demonstrate that PAC has superior clustering robustness and performance and DPAC remarkably outperforms the state-of-the-art deep clustering methods.
Authors: Chunwei Tian, Menghua Zheng, Chia-Wen Lin, Zhiwu Li, David Zhang
Abstract: Deep networks can usually depend on extracting more structural information to improve denoising results. However, they may ignore correlation between pixels from an image to pursue better denoising performance. Window transformer can use long- and short-distance modeling to interact pixels to address mentioned problem. To make a tradeoff between distance modeling and denoising time, we propose a heterogeneous window transformer (HWformer) for image denoising. HWformer first designs heterogeneous global windows to capture global context information for improving denoising effects. To build a bridge between long and short-distance modeling, global windows are horizontally and vertically shifted to facilitate diversified information without increasing denoising time. To prevent the information loss phenomenon of independent patches, sparse idea is guided a feed-forward network to extract local information of neighboring patches. The proposed HWformer only takes 30% of popular Restormer in terms of denoising time.
Authors: Qi Li, Ziyi Shen, Qianye Yang, Dean C. Barratt, Matthew J. Clarkson, Tom Vercauteren, Yipeng Hu
Abstract: Reconstructing 2D freehand Ultrasound (US) frames into 3D space without using a tracker has recently seen advances with deep learning. Predicting good frame-to-frame rigid transformations is often accepted as the learning objective, especially when the ground-truth labels from spatial tracking devices are inherently rigid transformations. Motivated by a) the observed nonrigid deformation due to soft tissue motion during scanning, and b) the highly sensitive prediction of rigid transformation, this study investigates the methods and their benefits in predicting nonrigid transformations for reconstructing 3D US. We propose a novel co-optimisation algorithm for simultaneously estimating rigid transformations among US frames, supervised by ground-truth from a tracker, and a nonrigid deformation, optimised by a regularised registration network. We show that these two objectives can be either optimised using meta-learning or combined by weighting. A fast scattered data interpolation is also developed for enabling frequent reconstruction and registration of non-parallel US frames, during training. With a new data set containing over 357,000 frames in 720 scans, acquired from 60 subjects, the experiments demonstrate that, due to an expanded thus easier-to-optimise solution space, the generalisation is improved with the added deformation estimation, with respect to the rigid ground-truth. The global pixel reconstruction error (assessing accumulative prediction) is lowered from 18.48 to 16.51 mm, compared with baseline rigid-transformation-predicting methods. Using manually identified landmarks, the proposed co-optimisation also shows potentials in compensating nonrigid tissue motion at inference, which is not measurable by tracker-provided ground-truth. The code and data used in this paper are made publicly available at https://github.com/QiLi111/NR-Rec-FUS.
Authors: Xiangyu Liao, Tianheng Zheng, Jiayu Zhong, Pingping Zhang, Chao Ren
Abstract: In recent years, self-supervised denoising methods have gained significant success and become critically important in the field of image restoration. Among them, the blind spot network based methods are the most typical type and have attracted the attentions of a large number of researchers. Although the introduction of blind spot operations can prevent identity mapping from noise to noise, it imposes stringent requirements on the receptive fields in the network design, thereby limiting overall performance. To address this challenge, we propose a single mask scheme for self-supervised denoising training, which eliminates the need for blind spot operation and thereby removes constraints on the network structure design. Furthermore, to achieve denoising across entire image during inference, we propose a multi-mask scheme. Our method, featuring the asymmetric mask scheme in training and inference, achieves state-of-the-art performance on existing real noisy image datasets. All the source code will be made available to the public.
Authors: Ruofei Wang, Qing Guo, Haoliang Li, Renjie Wan
Abstract: As asynchronous event data is more frequently engaged in various vision tasks, the risk of backdoor attacks becomes more evident. However, research into the potential risk associated with backdoor attacks in asynchronous event data has been scarce, leaving related tasks vulnerable to potential threats. This paper has uncovered the possibility of directly poisoning event data streams by proposing Event Trojan framework, including two kinds of triggers, i.e., immutable and mutable triggers. Specifically, our two types of event triggers are based on a sequence of simulated event spikes, which can be easily incorporated into any event stream to initiate backdoor attacks. Additionally, for the mutable trigger, we design an adaptive learning mechanism to maximize its aggressiveness. To improve the stealthiness, we introduce a novel loss function that constrains the generated contents of mutable triggers, minimizing the difference between triggers and original events while maintaining effectiveness. Extensive experiments on public event datasets show the effectiveness of the proposed backdoor triggers. We hope that this paper can draw greater attention to the potential threats posed by backdoor attacks on event-based tasks. Our code is available at https://github.com/rfww/EventTrojan.
Authors: Yasra Chandio, Momin A. Khan, Khotso Selialia, Luis Garcia, Joseph DeGol, Fatima M. Anwar
Abstract: Autonomous robots, autonomous vehicles, and humans wearing mixed-reality headsets require accurate and reliable tracking services for safety-critical applications in dynamically changing real-world environments. However, the existing tracking approaches, such as Simultaneous Localization and Mapping (SLAM), do not adapt well to environmental changes and boundary conditions despite extensive manual tuning. On the other hand, while deep learning-based approaches can better adapt to environmental changes, they typically demand substantial data for training and often lack flexibility in adapting to new domains. To solve this problem, we propose leveraging the neurosymbolic program synthesis approach to construct adaptable SLAM pipelines that integrate the domain knowledge from traditional SLAM approaches while leveraging data to learn complex relationships. While the approach can synthesize end-to-end SLAM pipelines, we focus on synthesizing the feature extraction module. We first devise a domain-specific language (DSL) that can encapsulate domain knowledge on the important attributes for feature extraction and the real-world performance of various feature extractors. Our neurosymbolic architecture then undertakes adaptive feature extraction, optimizing parameters via learning while employing symbolic reasoning to select the most suitable feature extractor. Our evaluations demonstrate that our approach, neurosymbolic Feature EXtraction (nFEX), yields higher-quality features. It also reduces the pose error observed for the state-of-the-art baseline feature extractors ORB and SIFT by up to 90% and up to 66%, respectively, thereby enhancing the system's efficiency and adaptability to novel environments.