Authors: Yifan Zhang, Chunzhen Lin, Donglin Cao, Dazhen Lin
The goal of fine-grained image description generation techniques is to learn detailed information from images and simulate human-like descriptions that provide coherent and comprehensive textual details about the image content. Currently, most of these methods face two main challenges: description repetition and omission. Moreover, the existing evaluation metrics cannot clearly reflect the performance of models on these two issues. To address these challenges, we propose an innovative Fine-grained Image Description Generation model based on Joint Objectives. Furthermore, we introduce new object-based evaluation metrics to more intuitively assess the model's performance in handling description repetition and omission. This novel approach combines visual features at both the image level and object level to maximize their advantages and incorporates an object penalty mechanism to reduce description repetition. Experimental results demonstrate that our proposed method significantly improves the CIDEr evaluation metric, indicating its excellent performance in addressing description repetition and omission issues.
Authors: Zhendong Liu, Jie Zhang, Qiangqiang He, Chongjun Wang
In the realm of visual recognition, data augmentation stands out as a pivotal technique to amplify model robustness. Yet, a considerable number of existing methodologies lean heavily on heuristic foundations, rendering their intrinsic mechanisms ambiguous. This manuscript takes both a theoretical and empirical approach to understanding the phenomenon. Theoretically, we frame the discourse around data augmentation within game theory's constructs. Venturing deeper, our empirical evaluations dissect the intricate mechanisms of emblematic data augmentation strategies, illuminating that these techniques primarily stimulate mid- and high-order game interactions. Beyond the foundational exploration, our experiments span multiple datasets and diverse augmentation techniques, underscoring the universal applicability of our findings. Recognizing the vast array of robustness metrics with intricate correlations, we unveil a streamlined proxy. This proxy not only simplifies robustness assessment but also offers invaluable insights, shedding light on the inherent dynamics of model game interactions and their relation to overarching system robustness. These insights provide a novel lens through which we can re-evaluate model safety and robustness in visual recognition tasks.
Authors: Md Nasim, Anter El-Azab, Xinghang Zhang, Yexiang Xue
The availability of tera-byte scale experiment data calls for AI driven approaches which automatically discover scientific models from data. Nonetheless, significant challenges present in AI-driven scientific discovery: (i) The annotation of large scale datasets requires fundamental re-thinking in developing scalable crowdsourcing tools. (ii) The learning of scientific models from data calls for innovations beyond black-box neural nets. (iii) Novel visualization and diagnosis tools are needed for the collaboration of experimental and theoretical physicists, and computer scientists. We present Phase-Field-Lab platform for end-to-end phase field model discovery, which automatically discovers phase field physics models from experiment data, integrating experimentation, crowdsourcing, simulation and learning. Phase-Field-Lab combines (i) a streamlined annotation tool which reduces the annotation time (by ~50-75%), while increasing annotation accuracy compared to baseline; (ii) an end-to-end neural model which automatically learns phase field models from data by embedding phase field simulation and existing domain knowledge into learning; and (iii) novel interfaces and visualizations to integrate our platform into the scientific discovery cycle of domain scientists. Our platform is deployed in the analysis of nano-structure evolution in materials under extreme conditions (high temperature and irradiation). Our approach reveals new properties of nano-void defects, which otherwise cannot be detected via manual analysis.
Authors: Alice Delbosc (TALEP, LIS, AMU), Magalie Ochs (LIS, AMU, TALEP), Nicolas Sabouret (LISN), Brian Ravenet (LISN), Stéphane Ayache (AMU, LIS, QARMA)
This paper introduces a new model to generate rhythmically relevant non-verbal facial behaviors for virtual agents while they speak. The model demonstrates perceived performance comparable to behaviors directly extracted from the data and replayed on a virtual agent, in terms of synchronization with speech and believability. Interestingly, we found that training the model with two different sets of data, instead of one, did not necessarily improve its performance. The expressiveness of the people in the dataset and the shooting conditions are key elements. We also show that employing an adversarial model, in which fabricated fake examples are introduced during the training phase, increases the perception of synchronization with speech. A collection of videos demonstrating the results and code can be accessed at: https://github.com/aldelb/non_verbal_facial_animation.
Authors: Jihun Lee, SP Choi, Bumsoo Kang, Hyekyoung Seok, Hyoungseok Ahn, Sanghee Jung
In current navigating platforms, the user's orientation is typically estimated based on the difference between two consecutive locations. In other words, the orientation cannot be identified until the second location is taken. This asynchronous location-orientation identification often leads to our real-life question: Why does my navigator tell the wrong direction of my car at the beginning? We propose DeepCompass to identify the user's orientation by bridging the gap between the street-view and the user-view images. First, we explore suitable model architectures and design corresponding input configuration. Second, we demonstrate artificial transformation techniques (e.g., style transfer and road segmentation) to minimize the disparity between the street-view and the user's real-time experience. We evaluate DeepCompass with extensive evaluation in various driving conditions. DeepCompass does not require additional hardware and is also not susceptible to external interference, in contrast to magnetometer-based navigator. This highlights the potential of DeepCompass as an add-on to existing sensor-based orientation detection methods.
Authors: Jaewoong Lee, Wonseok Lee, Jihan Kim
We have developed MatGD (Material Graph Digitizer), which is a tool for digitizing a data line from scientific graphs. The algorithm behind the tool consists of four steps: (1) identifying graphs within subfigures, (2) separating axes and data sections, (3) discerning the data lines by eliminating irrelevant graph objects and matching with the legend, and (4) data extraction and saving. From the 62,534 papers in the areas of batteries, catalysis, and MOFs, 501,045 figures were mined. Remarkably, our tool showcased performance with over 99% accuracy in legend marker and text detection. Moreover, its capability for data line separation stood at 66%, which is much higher compared to other existing figure mining tools. We believe that this tool will be integral to collecting both past and future data from publications, and these data can be used to train various machine learning models that can enhance material predictions and new materials discovery.
Authors: V. D. Volokitin, E. P. Vasiliev, E. A. Kozinov, V. D. Kustikova, A. V. Liniov, Y. A. Rodimkov, A. V. Sysoyev, I. B. Meyerov
The development of an open and free RISC-V architecture is of great interest for a wide range of areas, including high-performance computing and numerical simulation in mathematics, physics, chemistry and other problem domains. In this paper, we discuss the possibilities of accelerating computations on available RISC-V processors by improving the vectorization of several computer vision and machine learning algorithms in the widely used OpenCV library. It is shown that improved vectorization speeds up computations on existing prototypes of RISC-V devices by tens of percent.
Authors: Joanna Zyla, Michal Marczyk, Wojciech Prazuch, Marek Socha, Aleksandra Suwalska, Agata Durawa, Malgorzata Jelitto-Gorska, Katarzyna Dziadziuszko, Edyta Szurowska, Witold Rzyman, Piotr Widlak, Joanna Polanska
Due to its predominantly asymptomatic or mildly symptomatic progression, lung cancer is often diagnosed in advanced stages, resulting in poorer survival rates for patients. As with other cancers, early detection significantly improves the chances of successful treatment. Early diagnosis can be facilitated through screening programs designed to detect lung tissue tumors when they are still small, typically around 3mm in size. However, the analysis of extensive screening program data is hampered by limited access to medical experts. In this study, we developed a procedure for identifying potential malignant neoplastic lesions within lung parenchyma. The system leverages machine learning (ML) techniques applied to two types of measurements: low-dose Computed Tomography-based radiomics and metabolomics. Using data from two Polish screening programs, two ML algorithms were tested, along with various integration methods, to create a final model that combines both modalities to support lung cancer screening.
Authors: Ali Kargarandehkordi, Matti Kaisti, Peter Washington
Mobile digital therapeutics for autism spectrum disorder (ASD) often target emotion recognition and evocation, which is a challenge for children with ASD. While such mobile applications often use computer vision machine learning (ML) models to guide the adaptive nature of the digital intervention, a single model is usually deployed and applied to all children. Here, we explore the potential of model personalization, or training a single emotion recognition model per person, to improve the performance of these underlying emotion recognition models used to guide digital health therapies for children with ASD. We conducted experiments on the Emognition dataset, a video dataset of human subjects evoking a series of emotions. For a subset of 10 individuals in the dataset with a sufficient representation of at least two ground truth emotion labels, we trained a personalized version of three classical ML models on a set of 51 features extracted from each video frame. We measured the importance of each facial feature for all personalized models and observed differing ranked lists of top features across subjects, motivating the need for model personalization. We then compared the personalized models against a generalized model trained using data from all 10 participants. The mean F1-scores achieved by the personalized models were 90.48%, 92.66%, and 86.40%, respectively. By contrast, the mean F1-scores reached by non-personalized models trained on different human subjects and evaluated using the same test set were 88.55%, 91.78%, and 80.42%, respectively. The personalized models outperformed the generalized models for 7 out of 10 participants. PCA analyses on the remaining 3 participants revealed relatively facial configuration differences between emotion labels within each subject, suggesting that personalized ML will fail when the variation among data points within a subjects data is too low.
Authors: Dekai Zhang, Matthew Williams, Francesca Toni
Neural networks (NNs) can learn to rely on spurious signals in the training data, leading to poor generalisation. Recent methods tackle this problem by training NNs with additional ground-truth annotations of such signals. These methods may, however, let spurious signals re-emerge in deep convolutional NNs (CNNs). We propose Targeted Activation Penalty (TAP), a new method tackling the same problem by penalising activations to control the re-emergence of spurious signals in deep CNNs, while also lowering training times and memory usage. In addition, ground-truth annotations can be expensive to obtain. We show that TAP still works well with annotations generated by pre-trained models as effective substitutes of ground-truth annotations. We demonstrate the power of TAP against two state-of-the-art baselines on the MNIST benchmark and on two clinical image datasets, using four different CNN architectures.
Authors: Zhichao Wang, Xinhai Chen, Junjun Yan, Jie Liu
In CFD, mesh smoothing methods are commonly utilized to refine the mesh quality to achieve high-precision numerical simulations. Specifically, optimization-based smoothing is used for high-quality mesh smoothing, but it incurs significant computational overhead. Pioneer works improve its smoothing efficiency by adopting supervised learning to learn smoothing methods from high-quality meshes. However, they pose difficulty in smoothing the mesh nodes with varying degrees and also need data augmentation to address the node input sequence problem. Additionally, the required labeled high-quality meshes further limit the applicability of the proposed method. In this paper, we present GMSNet, a lightweight neural network model for intelligent mesh smoothing. GMSNet adopts graph neural networks to extract features of the node's neighbors and output the optimal node position. During smoothing, we also introduce a fault-tolerance mechanism to prevent GMSNet from generating negative volume elements. With a lightweight model, GMSNet can effectively smoothing mesh nodes with varying degrees and remain unaffected by the order of input data. A novel loss function, MetricLoss, is also developed to eliminate the need for high-quality meshes, which provides a stable and rapid convergence during training. We compare GMSNet with commonly used mesh smoothing methods on two-dimensional triangle meshes. The experimental results show that GMSNet achieves outstanding mesh smoothing performances with 5% model parameters of the previous model, and attains 8.62 times faster than optimization-based smoothing.
Authors: Dwith Chenna
Convolutional Neural Networks (CNNs) have greatly influenced the field of Embedded Vision and Edge Artificial Intelligence (AI), enabling powerful machine learning capabilities on resource-constrained devices. This article explores the relationship between CNN compute requirements and memory bandwidth in the context of Edge AI. We delve into the historical progression of CNN architectures, from the early pioneering models to the current state-of-the-art designs, highlighting the advancements in compute-intensive operations. We examine the impact of increasing model complexity on both computational requirements and memory access patterns. The paper presents a comparison analysis of the evolving trade-off between compute demands and memory bandwidth requirements in CNNs. This analysis provides insights into designing efficient architectures and potential hardware accelerators in enhancing CNN performance on edge devices.
Authors: Binzhe Li, Bolin Chen, Zhao Wang, Shiqi Wang, Yan Ye
In this letter, we envision a new metaverse communication paradigm for virtual avatar faces, and develop the semantic face compression with compact 3D facial descriptors. The fundamental principle is that the communication of virtual avatar faces primarily emphasizes the conveyance of semantic information. In light of this, the proposed scheme offers the advantages of being highly flexible, efficient and semantically meaningful. The semantic face compression, which allows the communication of the descriptors for artificial intelligence based understanding, could facilitate numerous applications without the involvement of humans in metaverse. The promise of the proposed paradigm is also demonstrated by performance comparisons with the state-of-the-art video coding standard, Versatile Video Coding. A significant improvement in terms of rate-accuracy performance has been achieved. The proposed scheme is expected to enable numerous applications, such as digital human communication based on machine analysis, and to form the cornerstone of interaction and communication in the metaverse.
Authors: Zhimin Fan, Pengpei Hong, Jie Guo, Changqing Zou, Yanwen Guo, Ling-Qi Yan
Complex visual effects such as caustics are often produced by light paths containing multiple consecutive specular vertices (dubbed specular chains), which pose a challenge to unbiased estimation in Monte Carlo rendering. In this work, we study the light transport behavior within a sub-path that is comprised of a specular chain and two non-specular separators. We show that the specular manifolds formed by all the sub-paths could be exploited to provide coherence among sub-paths. By reconstructing continuous energy distributions from historical and coherent sub-paths, seed chains can be generated in the context of importance sampling and converge to admissible chains through manifold walks. We verify that importance sampling the seed chain in the continuous space reaches the goal of importance sampling the discrete admissible specular chain. Based on these observations and theoretical analyses, a progressive pipeline, manifold path guiding, is designed and implemented to importance sample challenging paths featuring long specular chains. To our best knowledge, this is the first general framework for importance sampling discrete specular chains in regular Monte Carlo rendering. Extensive experiments demonstrate that our method outperforms state-of-the-art unbiased solutions with up to 40x variance reduction, especially in typical scenes containing long specular chains and complex visibility.
Authors: Drew Linsley, Thomas Serre
Bowers and colleagues argue that DNNs are poor models of biological vision because they often learn to rival human accuracy by relying on strategies that differ markedly from those of humans. We show that this problem is worsening as DNNs are becoming larger-scale and increasingly more accurate, and prescribe methods for building DNNs that can reliably model biological vision.
Authors: Hongcheng Liu, Zhe Chen, Hui Li, Pingjie Wang, Yanfeng Wang, Yu Wang
Generating dialogue grounded in videos requires a high level of understanding and reasoning about the visual scenes in the videos. However, existing large visual-language models are not effective due to their latent features and decoder-only structure, especially with respect to spatio-temporal relationship reasoning. In this paper, we propose a novel approach named MSG-BART, which enhances the integration of video information by incorporating a multi-granularity spatio-temporal scene graph into an encoder-decoder pre-trained language model. Specifically, we integrate the global and local scene graph into the encoder and decoder, respectively, to improve both overall perception and target reasoning capability. To further improve the information selection capability, we propose a multi-pointer network to facilitate selection between text and video. Extensive experiments are conducted on three video-grounded dialogue benchmarks, which show the significant superiority of the proposed MSG-BART compared to a range of state-of-the-art approaches.
Authors: David Minnen, Nick Johnston
The rate-distortion performance of neural image compression models has exceeded the state-of-the-art for non-learned codecs, but neural codecs are still far from widespread deployment and adoption. The largest obstacle is having efficient models that are feasible on a wide variety of consumer hardware. Comparative research and evaluation is difficult due to the lack of standard benchmarking platforms and due to variations in hardware architectures and test environments. Through our rate-distortion-computation (RDC) study we demonstrate that neither floating-point operations (FLOPs) nor runtime are sufficient on their own to accurately rank neural compression methods. We also explore the RDC frontier, which leads to a family of model architectures with the best empirical trade-off between computational requirements and RD performance. Finally, we identify a novel neural compression architecture that yields state-of-the-art RD performance with rate savings of 23.1% over BPG (7.0% over VTM and 3.0% over ELIC) without requiring significantly more FLOPs than other learning-based codecs.
Authors: Niful Islam, Md. Mehedi Hasan Jony, Emam Hasan, Sunny Sutradhar, Atikur Rahman, Md. Motaharul Islam
Improper disposal of e-waste poses global environmental and health risks, raising serious concerns. The accurate classification of e-waste images is critical for efficient management and recycling. In this paper, we have presented a comprehensive dataset comprised of eight different classes of images of electronic devices named the E-Waste Vision Dataset. We have also presented EWasteNet, a novel two-stream approach for precise e-waste image classification based on a data-efficient image transformer (DeiT). The first stream of EWasteNet passes through a sobel operator that detects the edges while the second stream is directed through an Atrous Spatial Pyramid Pooling and attention block where multi-scale contextual information is captured. We train both of the streams simultaneously and their features are merged at the decision level. The DeiT is used as the backbone of both streams. Extensive analysis of the e-waste dataset indicates the usefulness of our method, providing 96% accuracy in e-waste classification. The proposed approach demonstrates significant usefulness in addressing the global concern of e-waste management. It facilitates efficient waste management and recycling by accurately classifying e-waste images, reducing health and safety hazards associated with improper disposal.
Authors: Julien Lalanne, Raphael Bournet, Yi Yu
Live commenting on video, a popular feature of live streaming platforms, enables viewers to engage with the content and share their comments, reactions, opinions, or questions with the streamer or other viewers while watching the video or live stream. It presents a challenging testbed for AI agents, which involves the simultaneous understanding of audio-visual multimodal contexts from live streams and the ability to interact with human viewers through dialogue. As existing live streaming-based comments datasets contain limited categories and lack a diversity, we create a large-scale audio-visual multimodal dialogue dataset to facilitate the development of live commenting technologies. The data is collected from Twitch, with 11 different categories and 575 streamers for a total of 438 hours of video and 3.2 million comments. Moreover, we propose a novel multimodal generation model capable of generating live comments that align with the temporal and spatial events within the video, as well as with the ongoing multimodal dialogue context. Our initial results have demonstrated the effectiveness of the proposed model, providing a robust foundation for further research and practical applications in the field of live video interaction.
Authors: Wenwen Zhang, Arvin Tashakori, Zenan Jiang, Amir Servati, Harishkumar Narayana, Saeid Soltanian, Rou Yi Yeap, Meng Han Ma, Lauren Toy, Peyman Servati
The kinematics of human movements and locomotion are closely linked to the activation and contractions of muscles. To investigate this, we present a multimodal dataset with benchmarks collected using a novel pair of Intelligent Knee Sleeves (Texavie MarsWear Knee Sleeves) for human pose estimation. Our system utilizes synchronized datasets that comprise time-series data from the Knee Sleeves and the corresponding ground truth labels from the visualized motion capture camera system. We employ these to generate 3D human models solely based on the wearable data of individuals performing different activities. We demonstrate the effectiveness of this camera-free system and machine learning algorithms in the assessment of various movements and exercises, including extension to unseen exercises and individuals. The results show an average error of 7.21 degrees across all eight lower body joints when compared to the ground truth, indicating the effectiveness and reliability of the Knee Sleeve system for the prediction of different lower body joints beyond the knees. The results enable human pose estimation in a seamless manner without being limited by visual occlusion or the field of view of cameras. Our results show the potential of multimodal wearable sensing in a variety of applications from home fitness to sports, healthcare, and physical rehabilitation focusing on pose and movement estimation.
Authors: Kaiyuan Tang, Chaoli Wang
Due to its conceptual simplicity and generality, compressive neural representation has emerged as a promising alternative to traditional compression methods for managing massive volumetric datasets. The state-of-the-art neural compression solution, neurcomp, however, utilizes a single large multilayer perceptron (MLP) to encode the global volume, incurring slow training and inference. This paper presents an efficient compressive neural representation (ECNR) solution that improves upon neurcomp to handle large-scale time-varying datasets. At the heart of our approach is a multiscale structure that uses the Laplacian pyramid for adaptive signal fitting via implicit neural representation. We leverage multiple small MLPs at each scale for fitting local content or residual blocks. By assigning similar blocks to the same MLP via size uniformization, we enable balanced parallelization among MLPs to significantly speed up training and inference. A deep compression strategy is then employed to compact the resulting model. We demonstrate the effectiveness of ECNR with multiple datasets and compare it with neurcomp and two state-of-the-art conventional compression methods (SZ3 and TTHRESH). Our results position ECNR as a promising alternative to neurcomp for scientific data compression.
Authors: Haotian Xue, Chumeng Liang, Xiaoyu Wu, Yongxin Chen
While generative diffusion models excel in producing high-quality images, they can also be misused to mimic authorized images, posing a significant threat to AI systems. Efforts have been made to add calibrated perturbations to protect images from diffusion-based mimicry pipelines. However, most of the existing methods are too ineffective and even impractical to be used by individual users due to their high computation and memory requirements. In this work, we present novel findings on attacking latent diffusion models (LDM) and propose new plug-and-play strategies for more effective protection. In particular, we explore the bottleneck in attacking an LDM, discovering that the encoder module rather than the denoiser module is the vulnerable point. Based on this insight, we present our strategy using Score Distillation Sampling (SDS) to double the speed of protection and reduce memory occupation by half without compromising its strength. Additionally, we provide a robust protection strategy by counterintuitively minimizing the semantic loss, which can assist in generating more natural perturbations. Finally, we conduct extensive experiments to substantiate our findings and comprehensively evaluate our newly proposed strategies. We hope our insights and protective measures can contribute to better defense against malicious diffusion-based mimicry, advancing the development of secure AI systems. The code is available in https://github.com/xavihart/Diff-Protect
Authors: Xianjing Liu, Bo Li, Meike W. Vernooij, Eppo B. Wolvius, Gennady V. Roshchupkin, Esther E. Bron
AI has greatly enhanced medical image analysis, yet its use in epidemiological population imaging studies remains limited due to visualization challenges in non-linear models and lack of confounder control. Addressing this, we introduce an AI method emphasizing semantic feature interpretation and resilience against multiple confounders. Our approach's merits are tested in three scenarios: extracting confounder-free features from a 2D synthetic dataset; examining the association between prenatal alcohol exposure and children's facial shapes using 3D mesh data; exploring the relationship between global cognition and brain images with a 3D MRI dataset. Results confirm our method effectively reduces confounder influences, establishing less confounded associations. Additionally, it provides a unique visual representation, highlighting specific image alterations due to identified correlations.
Authors: Qiyu Wei, Wei Zhao, Xiaoyan Zheng, Zeng Zeng
As the globalization of semiconductor design and manufacturing processes continues, the demand for defect detection during integrated circuit fabrication stages is becoming increasingly critical, playing a significant role in enhancing the yield of semiconductor products. Traditional wafer map defect pattern detection methods involve manual inspection using electron microscopes to collect sample images, which are then assessed by experts for defects. This approach is labor-intensive and inefficient. Consequently, there is a pressing need to develop a model capable of automatically detecting defects as an alternative to manual operations. In this paper, we propose a method that initially employs a pre-trained VAE model to obtain the fault distribution information of the wafer map. This information serves as guidance, combined with the original image set for semi-supervised model training. During the semi-supervised training, we utilize a teacher-student network for iterative learning. The model presented in this paper is validated on the benchmark dataset WM-811K wafer dataset. The experimental results demonstrate superior classification accuracy and detection performance compared to state-of-the-art models, fulfilling the requirements for industrial applications. Compared to the original architecture, we have achieved significant performance improvement.
Authors: Clemens Schlegel, Dirk Alexander Molitor, Christian Kubik, Daniel Michael Martin, Peter Groche
The extend of tool wear significantly affects blanking processes and has a decisive impact on product quality and productivity. For this reason, numerous scientists have addressed their research to wear monitoring systems in order to identify or even predict critical wear at an early stage. Existing approaches are mainly based on indirect monitoring using time series, which are used to detect critical wear states via thresholds or machine learning models. Nevertheless, differentiation between types of wear phenomena affecting the tool during blanking as well as quantification of worn surfaces is still limited in practice. While time series data provides partial insights into wear occurrence and evolution, direct monitoring techniques utilizing image data offer a more comprehensive perspective and increased robustness when dealing with varying process parameters. However, acquiring and processing this data in real-time is challenging. In particular, high dynamics combined with increasing strokes rates as well as the high dimensionality of image data have so far prevented the development of direct image-based monitoring systems. For this reason, this paper demonstrates how high-resolution images of tools at 600 spm can be captured and subsequently processed using semantic segmentation deep learning algorithms, more precisely Fully Convolutional Networks (FCN). 125,000 images of the tool are taken from successive strokes, and microscope images are captured to investigate the worn surfaces. Based on findings from the microscope images, selected images are labeled pixel by pixel according to their wear condition and used to train a FCN (U-Net).
Authors: Guian Fang, Mengsha Liu, Yi Zhong, Zhuolin Zhang, Jiehui Huang, Zhenchao Tang, Calvin Yu-Chian Chen
Alzheimer's disease is a progressive neurological disorder characterized by cognitive impairment and memory loss. With the increasing aging population, the incidence of AD is continuously rising, making early diagnosis and intervention an urgent need. In recent years, a considerable number of teams have applied computer-aided diagnostic techniques to early classification research of AD. Most studies have utilized imaging modalities such as magnetic resonance imaging (MRI), positron emission tomography (PET), and electroencephalogram (EEG). However, there have also been studies that attempted to use other modalities as input features for the models, such as sound, posture, biomarkers, cognitive assessment scores, and their fusion. Experimental results have shown that the combination of multiple modalities often leads to better performance compared to a single modality. Therefore, this paper will focus on different modalities and their fusion, thoroughly elucidate the mechanisms of various modalities, explore which methods should be combined to better harness their utility, analyze and summarize the literature in the field of early classification of AD in recent years, in order to explore more possibilities of modality combinations.
Authors: Sadia Basar, Mushtaq Ali, Abdul Waheed, Muneer Ahmad, Mahdi H. Miraz
The motion or out-of-focus effect in digital images is the main reason for the blurred regions in defocused-blurred images. It may adversely affect various image features such as texture, pixel, and region. Therefore, it is important to detect in-focused objects in defocused-blurred images after the segmentation of blurred and non-blurred regions. The state-of-the-art techniques are prone to noisy pixels, and their local descriptors for developing segmentation metrics are also complex. To address these issues, this research, therefore, proposed a novel and hybrid-focused detection approach based on Discrete Cosine Transform (DCT) coefficients and PC Neural Net (PCNN) structure. The proposed approach partially resolves the limitations of the existing contrast schemes to detect in-focused smooth objects from the out-of-focused smooth regions in the defocus dataset. The visual and quantitative evaluation illustrates that the proposed approach outperformed in terms of accuracy and efficiency to referenced algorithms. The highest F-score of the proposed approach on Zhao's dataset is 0.7940 whereas on Shi's dataset is 0.9178.
Authors: Junlei Zhou, Jiashi Gao, Ziwei Wang, Xuetao Wei
Web-based AI image generation has become an innovative art form that can generate novel artworks with the rapid development of the diffusion model. However, this new technique brings potential copyright infringement risks as it may incorporate the existing artworks without the owners' consent. Copyright infringement quantification is the primary and challenging step towards AI-generated image copyright traceability. Previous work only focused on data attribution from the training data perspective, which is unsuitable for tracing and quantifying copyright infringement in practice because of the following reasons: (1) the training datasets are not always available in public; (2) the model provider is the responsible party, not the image. Motivated by this, in this paper, we propose CopyScope, a new framework to quantify the infringement of AI-generated images from the model level. We first rigorously identify pivotal components within the AI image generation pipeline. Then, we propose to take advantage of Fr\'echet Inception Distance (FID) to effectively capture the image similarity that fits human perception naturally. We further propose the FID-based Shapley algorithm to evaluate the infringement contribution among models. Extensive experiments demonstrate that our work not only reveals the intricacies of infringement quantification but also effectively depicts the infringing models quantitatively, thus promoting accountability in AI image-generation tasks.
Authors: Kecen Li, Chen Gong, Zhixiang Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang
Differential Privacy (DP) image data synthesis, which leverages the DP technique to generate synthetic data to replace the sensitive data, allowing organizations to share and utilize synthetic images without privacy concerns. Previous methods incorporate the advanced techniques of generative models and pre-training on a public dataset to produce exceptional DP image data, but suffer from problems of unstable training and massive computational resource demands. This paper proposes a novel DP image synthesis method, termed PRIVIMAGE, which meticulously selects pre-training data, promoting the efficient creation of DP datasets with high fidelity and utility. PRIVIMAGE first establishes a semantic query function using a public dataset. Then, this function assists in querying the semantic distribution of the sensitive dataset, facilitating the selection of data from the public dataset with analogous semantics for pre-training. Finally, we pre-train an image generative model using the selected data and then fine-tune this model on the sensitive dataset using Differentially Private Stochastic Gradient Descent (DP-SGD). PRIVIMAGE allows us to train a lightly parameterized generative model, reducing the noise in the gradient during DP-SGD training and enhancing training stability. Extensive experiments demonstrate that PRIVIMAGE uses only 1% of the public dataset for pre-training and 7.6% of the parameters in the generative model compared to the state-of-the-art method, whereas achieves superior synthetic performance and conserves more computational resources. On average, PRIVIMAGE achieves 30.1% lower FID and 12.6% higher Classification Accuracy than the state-of-the-art method. The replication package and datasets can be accessed online.
Authors: Romain Xu-Darme (LSL, LIG), Julien Girard-Satabin (LSL), Darryl Hond (TRT UK), Gabriele Incorvaia (TRT UK), Zakaria Chihani (LSL)
In this work, we propose CODE, an extension of existing work from the field of explainable AI that identifies class-specific recurring patterns to build a robust Out-of-Distribution (OoD) detection method for visual classifiers. CODE does not require any classifier retraining and is OoD-agnostic, i.e., tuned directly to the training dataset. Crucially, pattern identification allows us to provide images from the In-Distribution (ID) dataset as reference data to provide additional context to the confidence scores. In addition, we introduce a new benchmark based on perturbations of the ID dataset that provides a known and quantifiable measure of the discrepancy between the ID and OoD datasets serving as a reference value for the comparison between OoD detection methods.
Authors: Bishal Shrestha, Griwan Khakurel, Kritika Simkhada, Badri Adhikari
Reading dirty license plates accurately in moving vehicles is challenging for automatic license plate recognition systems. Moreover, license plates are often intentionally tampered with a malicious intent to avoid police apprehension. Usually, such groups and individuals know how to fool the existing recognition systems by making minor unnoticeable plate changes. Designing and developing deep learning methods resilient to such real-world 'attack' practices remains an active research problem. As a solution, this work develops a resilient method to recognize license plate characters. Extracting 1057 character images from 160 Nepalese vehicles, as the first step, we trained several standard deep convolutional neural networks to obtain 99.5% character classification accuracy. On adversarial images generated to simulate malicious tampering, however, our model's accuracy dropped to 25%. Next, we enriched our dataset by generating and adding geometrically masked images, retrained our models, and investigated the models' predictions. The proposed approach of training with generated adversarial images helped our adversarial attack-aware license plate character recognition (AA-LPCR) model achieves an accuracy of 99.7%. This near-perfect accuracy demonstrates that the proposed idea of random geometric masking is highly effective for improving the accuracy of license plate recognition models. Furthermore, by performing interpretability studies to understand why our models work, we identify and highlight attack-prone regions in the input character images. In sum, although Nepal's embossed license plate detection systems are vulnerable to malicious attacks, our findings suggest that these systems can be upgraded to close to 100% resilience.
Authors: Yasser Khalafaoui (Alteca, ETIS), Basarab Matei (LIPN), Nistor Grozavu (ETIS), Martino Lovisetto (Alteca)
Data is increasingly being collected from multiple sources and described by multiple views. These multi-view data provide richer information than traditional single-view data. Fusing the former for specific tasks is an essential component of multi-view clustering. Since the goal of multi-view clustering algorithms is to discover the common latent structure shared by multiple views, the majority of proposed solutions overlook the advantages of incorporating knowledge derived from horizontal collaboration between multi-view data and the final consensus. To fill this gap, we propose the Joint Multi-View Collaborative Clustering (JMVCC) solution, which involves the generation of basic partitions using Non-negative Matrix Factorization (NMF) and the horizontal collaboration principle, followed by the fusion of these local partitions using ensemble clustering. Furthermore, we propose a weighting method to reduce the risk of negative collaboration (i.e., views with low quality) during the generation and fusion of local partitions. The experimental results, which were obtained using a variety of data sets, demonstrate that JMVCC outperforms other multi-view clustering algorithms and is robust to noisy views.
Authors: Romain Xu-Darme (LSL, LIG), Jenny Benois-Pineau (LaBRI), Romain Giot (LaBRI), Georges Quénot (LIG), Zakaria Chihani (LSL), Marie-Christine Rousset (LIG), Alexey Zhukov (LaBRI)
In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this work, we study the articulation between the stability, correctness and plausibility of explanations based on feature importance for image classifiers. We show that the existing metrics for evaluating these properties do not always agree, raising the issue of what constitutes a good evaluation metric for explanations. Finally, in the particular case of stability and correctness, we show the possible limitations of some evaluation metrics and propose new ones that take into account the local behaviour of the model under test.
Authors: Haotian Tang, Shang Yang, Zhijian Liu, Ke Hong, Zhongming Yu, Xiuyu Li, Guohao Dai, Yu Wang, Song Han
Sparse convolution plays a pivotal role in emerging workloads, including point cloud processing in AR/VR, autonomous driving, and graph understanding in recommendation systems. Since the computation pattern is sparse and irregular, specialized high-performance kernels are required. Existing GPU libraries offer two dataflow types for sparse convolution. The gather-GEMM-scatter dataflow is easy to implement but not optimal in performance, while the dataflows with overlapped computation and memory access (e.g.implicit GEMM) are highly performant but have very high engineering costs. In this paper, we introduce TorchSparse++, a new GPU library that achieves the best of both worlds. We create a highly efficient Sparse Kernel Generator that generates performant sparse convolution kernels at less than one-tenth of the engineering cost of the current state-of-the-art system. On top of this, we design the Sparse Autotuner, which extends the design space of existing sparse convolution libraries and searches for the best dataflow configurations for training and inference workloads. Consequently, TorchSparse++ achieves 2.9x, 3.3x, 2.2x and 1.7x measured end-to-end speedup on an NVIDIA A100 GPU over state-of-the-art MinkowskiEngine, SpConv 1.2, TorchSparse and SpConv v2 in inference; and is 1.2-1.3x faster than SpConv v2 in mixed precision training across seven representative autonomous driving benchmarks. It also seamlessly supports graph convolutions, achieving 2.6-7.6x faster inference speed compared with state-of-the-art graph deep learning libraries.
Authors: Mingjie Zhou
In multimodal machine learning tasks, it is due to the complexity of the assignments that the network structure, in most cases, is assembled in a sophisticated way. The holistic architecture can be separated into several logical parts according to the respective ends that the modules are devised to achieve. As the number of modalities of information representation increases, constructing ad hoc subnetworks for processing the data from divergent modalities while mediating the fusion of different information types has become a cumbersome and expensive problem. In this paper, we present an approach to facilitate the question with a reusable and composable neural unit; by connecting the units in series or parallel, the arduous network constructing of multimodal machine learning tasks will be accomplished in a much straightforward way. Additionally, through parameter sharing (weights replication) among the units, the space complexity will be significantly reduced. We have conducted experiments on three commonly used datasets; our method achieves impressive performance compared to several video QA baselines.
Authors: Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, Siyuan Huang
Leveraging massive knowledge and learning schemes from large language models (LLMs), recent machine learning models show notable successes in building generalist agents that exhibit the capability of general-purpose task solving in diverse domains, including natural language processing, computer vision, and robotics. However, a significant challenge remains as these models exhibit limited ability in understanding and interacting with the 3D world. We argue this limitation significantly hinders the current models from performing real-world tasks and further achieving general intelligence. To this end, we introduce an embodied multi-modal and multi-task generalist agent that excels in perceiving, grounding, reasoning, planning, and acting in the 3D world. Our proposed agent, referred to as LEO, is trained with shared LLM-based model architectures, objectives, and weights in two stages: (i) 3D vision-language alignment and (ii) 3D vision-language-action instruction tuning. To facilitate the training, we meticulously curate and generate an extensive dataset comprising object-level and scene-level multi-modal tasks with exceeding scale and complexity, necessitating a deep understanding of and interaction with the 3D world. Through rigorous experiments, we demonstrate LEO's remarkable proficiency across a wide spectrum of tasks, including 3D captioning, question answering, embodied reasoning, embodied navigation, and robotic manipulation. Our ablation results further provide valuable insights for the development of future embodied generalist agents.
Authors: José María Rodríguez Corral, Javier Civit-Masot, Francisco Luna-Perejón, Ignacio Díaz-Cano, Arturo Morgado-Estévez, Manuel Domínguez-Morales
In this work, we evaluate the energy usage of fully embedded medical diagnosis aids based on both segmentation and classification of medical images implemented on Edge TPU and embedded GPU processors. We use glaucoma diagnosis based on color fundus images as an example to show the possibility of performing segmentation and classification in real time on embedded boards and to highlight the different energy requirements of the studied implementations.
Several other works develop the use of segmentation and feature extraction techniques to detect glaucoma, among many other pathologies, with deep neural networks. Memory limitations and low processing capabilities of embedded accelerated systems (EAS) limit their use for deep network-based system training. However, including specific acceleration hardware, such as NVIDIA's Maxwell GPU or Google's Edge TPU, enables them to perform inferences using complex pre-trained networks in very reasonable times.
In this study, we evaluate the timing and energy performance of two EAS equipped with Machine Learning (ML) accelerators executing an example diagnostic tool developed in a previous work. For optic disc (OD) and cup (OC) segmentation, the obtained prediction times per image are under 29 and 43 ms using Edge TPUs and Maxwell GPUs, respectively. Prediction times for the classification subsystem are lower than 10 and 14 ms for Edge TPUs and Maxwell GPUs, respectively. Regarding energy usage, in approximate terms, for OD segmentation Edge TPUs and Maxwell GPUs use 38 and 190 mJ per image, respectively. For fundus classification, Edge TPUs and Maxwell GPUs use 45 and 70 mJ, respectively.
Authors: Honglin Li, Yunlong Zhang, Chenglu Zhu, Jiatong Cai, Sunyi Zheng, Lin Yang
Histopathology image analysis is the golden standard of clinical diagnosis for Cancers. In doctors daily routine and computer-aided diagnosis, the Whole Slide Image (WSI) of histopathology tissue is used for analysis. Because of the extremely large scale of resolution, previous methods generally divide the WSI into a large number of patches, then aggregate all patches within a WSI by Multi-Instance Learning (MIL) to make the slide-level prediction when developing computer-aided diagnosis tools. However, most previous WSI-MIL models using global-attention without pairwise interaction and any positional information, or self-attention with absolute position embedding can not well handle shape varying large WSIs, e.g. testing WSIs after model deployment may be larger than training WSIs, since the model development set is always limited due to the difficulty of histopathology WSIs collection. To deal with the problem, in this paper, we propose to amend position embedding for shape varying long-contextual WSI by introducing Linear Bias into Attention, and adapt it from 1-d long sequence into 2-d long-contextual WSI which helps model extrapolate position embedding to unseen or under-fitted positions. We further utilize Flash-Attention module to tackle the computational complexity of Transformer, which also keep full self-attention performance compared to previous attention approximation work. Our method, Long-contextual MIL (Long-MIL) are evaluated on extensive experiments including 4 dataset including WSI classification and survival prediction tasks to validate the superiority on shape varying WSIs. The source code will be open-accessed soon.
Authors: Zuozhuo Dai, Zhenghao Zhang, Yao Yao, Bingxue Qiu, Siyu Zhu, Long Qin, Weizhi Wang
Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and motion strength guidance, enabling precise control the movable area and its motion speed. This results in enhanced alignment between the animated visual elements and the prompting text, thereby facilitating a fine-grained and interactive animation generation process for intricate motion sequences. We validate the effectiveness of our method through rigorous experiments on an open-domain dataset, with the results showcasing its superior performance. The source code and model will be made publicly available upon publication.
Authors: Bowen Jiang, Zhijun Zhuang, Camillo Jose Taylor
This work presents an enhanced approach to generating scene graphs by incorporating a relationship hierarchy and commonsense knowledge. Specifically, we propose a Bayesian classification head that exploits an informative hierarchical structure. It jointly predicts the super-category or type of relationship between the two objects, along with the detailed relationship under each super-category. We design a commonsense validation pipeline that uses a large language model to critique the results from the scene graph prediction system and then use that feedback to enhance the model performance. The system requires no external large language model assistance at test time, making it more convenient for practical applications. Experiments on the Visual Genome and the OpenImage V6 datasets demonstrate that harnessing hierarchical relationships enhances the model performance by a large margin. The proposed Bayesian head can also be incorporated as a portable module in existing scene graph generation algorithms to improve their results. In addition, the commonsense validation enables the model to generate an extensive set of reasonable predictions beyond dataset annotations.
Authors: Minghe Gao, Juncheng Li, Hao Fei, Wei Ji, Guoming Wang, Wenqiao Zhang, Siliang Tang, Yueting Zhuang
Visual programming, a modular and generalizable paradigm, integrates different modules and Python operators to solve various vision-language tasks. Unlike end-to-end models that need task-specific data, it advances in performing visual processing and reasoning in an unsupervised manner. Current visual programming methods generate programs in a single pass for each task where the ability to evaluate and optimize based on feedback, unfortunately, is lacking, which consequentially limits their effectiveness for complex, multi-step problems. Drawing inspiration from benders decomposition, we introduce De-fine, a general framework that automatically decomposes complex tasks into simpler subtasks and refines programs through auto-feedback. This model-agnostic approach can improve logical reasoning performance by integrating the strengths of multiple models. Our experiments across various visual tasks show that De-fine creates more accurate and robust programs, setting new benchmarks in the field.
Authors: Yuxin Liu, Minshan Xie, Hanyuan Liu, Tien-Tsin Wong
This paper introduces a novel approach to synthesize texture to dress up a given 3D object, given a text prompt. Based on the pretrained text-to-image (T2I) diffusion model, existing methods usually employ a project-and-inpaint approach, in which a view of the given object is first generated and warped to another view for inpainting. But it tends to generate inconsistent texture due to the asynchronous diffusion of multiple views. We believe such asynchronous diffusion and insufficient information sharing among views are the root causes of the inconsistent artifact. In this paper, we propose a synchronized multi-view diffusion approach that allows the diffusion processes from different views to reach a consensus of the generated content early in the process, and hence ensures the texture consistency. To synchronize the diffusion, we share the denoised content among different views in each denoising step, specifically blending the latent content in the texture domain from views with overlap. Our method demonstrates superior performance in generating consistent, seamless, highly detailed textures, comparing to state-of-the-art methods.
Authors: Ruimin Feng, Qing Wu, Jie Feng, Huajun She, Chunlei Liu, Yuyao Zhang, Hongjiang Wei
Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5$\mathbf{\times}$ and 6$\mathbf{\times}$ accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI.
Authors: Jiageng Zhong, Ming Li, Yinliang Chen, Zihang Wei, Fan Yang, Haoran Shen
For intelligent quadcopter UAVs, a robust and reliable autonomous planning system is crucial. Most current trajectory planning methods for UAVs are suitable for static environments but struggle to handle dynamic obstacles, which can pose challenges and even dangers to flight. To address this issue, this paper proposes a vision-based planning system that combines tracking and trajectory prediction of dynamic obstacles to achieve efficient and reliable autonomous flight. We use a lightweight object detection algorithm to identify dynamic obstacles and then use Kalman Filtering to track and estimate their motion states. During the planning phase, we not only consider static obstacles but also account for the potential movements of dynamic obstacles. For trajectory generation, we use a B-spline-based trajectory search algorithm, which is further optimized with various constraints to enhance safety and alignment with the UAV's motion characteristics. We conduct experiments in both simulation and real-world environments, and the results indicate that our approach can successfully detect and avoid obstacles in dynamic environments in real-time, offering greater reliability compared to existing approaches. Furthermore, with the advancements in Natural Language Processing (NLP) technology demonstrating exceptional zero-shot generalization capabilities, more user-friendly human-machine interactions have become feasible, and this study also explores the integration of autonomous planning systems with Large Language Models (LLMs).
Authors: Xiu-Shen Wei, Yang Shen, Xuhao Sun, Peng Wang, Yuxin Peng
Our work focuses on tackling large-scale fine-grained image retrieval as ranking the images depicting the concept of interests (i.e., the same sub-category labels) highest based on the fine-grained details in the query. It is desirable to alleviate the challenges of both fine-grained nature of small inter-class variations with large intra-class variations and explosive growth of fine-grained data for such a practical task. In this paper, we propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes to not only make the retrieval process efficient, but also establish explicit correspondences between hash codes and visual attributes. Specifically, based on the captured visual representations by attention, we develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors from the appearance-specific visual representations without attribute annotations. Our models are also equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities. Then, driven by preserving original entities' similarity, the required hash codes can be generated from these attribute-specific vectors and thus become attribute-aware. Furthermore, to combat simplicity bias in deep hashing, we consider the model design from the perspective of the self-consistency principle and propose to further enhance models' self-consistency by equipping an additional image reconstruction path. Comprehensive quantitative experiments under diverse empirical settings on six fine-grained retrieval datasets and two generic retrieval datasets show the superiority of our models over competing methods.
Authors: Bram Wallace, Meihua Dang, Rafael Rafailov, Linqi Zhou, Aaron Lou, Senthil Purushwalkam, Stefano Ermon, Caiming Xiong, Shafiq Joty, Nikhil Naik
Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely explored in text-to-image diffusion models; the best existing approach is to fine-tune a pretrained model using carefully curated high quality images and captions to improve visual appeal and text alignment. We propose Diffusion-DPO, a method to align diffusion models to human preferences by directly optimizing on human comparison data. Diffusion-DPO is adapted from the recently developed Direct Preference Optimization (DPO), a simpler alternative to RLHF which directly optimizes a policy that best satisfies human preferences under a classification objective. We re-formulate DPO to account for a diffusion model notion of likelihood, utilizing the evidence lower bound to derive a differentiable objective. Using the Pick-a-Pic dataset of 851K crowdsourced pairwise preferences, we fine-tune the base model of the state-of-the-art Stable Diffusion XL (SDXL)-1.0 model with Diffusion-DPO. Our fine-tuned base model significantly outperforms both base SDXL-1.0 and the larger SDXL-1.0 model consisting of an additional refinement model in human evaluation, improving visual appeal and prompt alignment. We also develop a variant that uses AI feedback and has comparable performance to training on human preferences, opening the door for scaling of diffusion model alignment methods.
Authors: Supreeth Mysore Venkatesh, Antonio Macaluso, Marlon Nuske, Matthias Klusch, Andreas Dengel
In this study, we present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel-wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology of the D-Wave Advantage device, offering superior scalability over existing quantum approaches and outperforming state-of-the-art classical methods. Our empirical evaluations on synthetic datasets reveal that Q-Seg offers better runtime performance against the classical optimizer Gurobi. Furthermore, we evaluate our method on segmentation of Earth Observation images, an area of application where the amount of labeled data is usually very limited. In this case, Q-Seg demonstrates near-optimal results in flood mapping detection with respect to classical supervised state-of-the-art machine learning methods. Also, Q-Seg provides enhanced segmentation for forest coverage compared to existing annotated masks. Thus, Q-Seg emerges as a viable alternative for real-world applications using available quantum hardware, particularly in scenarios where the lack of labeled data and computational runtime are critical.
Authors: Quazi Mishkatul Alam, Bilel Tarchoun, Ihsen Alouani, Nael Abu-Ghazaleh
The latest generation of transformer-based vision models have proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attributed to their remarkable prowess in relation modeling. Deformable vision transformers significantly reduce the quadratic complexity of modeling attention by using sparse attention structures, enabling them to be used in larger scale applications such as multi-view vision systems. Recent work demonstrated adversarial attacks against transformers; we show that these attacks do not transfer to deformable transformers due to their sparse attention structure. Specifically, attention in deformable transformers is modeled using pointers to the most relevant other tokens. In this work, we contribute for the first time adversarial attacks that manipulate the attention of deformable transformers, distracting them to focus on irrelevant parts of the image. We also develop new collaborative attacks where a source patch manipulates attention to point to a target patch that adversarially attacks the system. In our experiments, we find that only 1% patched area of the input field can lead to 0% AP. We also show that the attacks provide substantial versatility to support different attacker scenarios because of their ability to redirect attention under the attacker control.
Authors: Gengyuan Zhang, Jinhe Bi, Jindong Gu, Volker Tresp
Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-training paradigm for learning joint representations and showcased remarkable potential in video understanding tasks. However, videos can be multi-event and multi-grained, while these video-text pairs usually contain only broad-level video captions. This raises a question: with such weak supervision, can video representation in video-language models gain the ability to distinguish even factual discrepancies in textual description and understand fine-grained events? To address this, we introduce SPOT Prober, to benchmark existing video-language models's capacities of distinguishing event-level discrepancies as an indicator of models' event understanding ability. Our approach involves extracting events as tuples (<Subject, Predicate, Object, Attribute, Timestamps>) from videos and generating false event tuples by manipulating tuple components systematically. We reevaluate the existing video-language models with these positive and negative captions and find they fail to distinguish most of the manipulated events. Based on our findings, we propose to plug in these manipulated event captions as hard negative samples and find them effective in enhancing models for event understanding.
Authors: Ahmed Sharshar, Aleksandr Matsun
In the realm of aerial image analysis, object detection plays a pivotal role, with significant implications for areas such as remote sensing, urban planning, and disaster management. This study addresses the inherent challenges in this domain, notably the detection of small objects, managing densely packed elements, and accounting for diverse orientations. We present an in-depth evaluation of an object detection model that integrates the Large Selective Kernel Network (LSKNet)as its backbone with the DiffusionDet head, utilizing the iSAID dataset for empirical analysis. Our approach encompasses the introduction of novel methodologies and extensive ablation studies. These studies critically assess various aspects such as loss functions, box regression techniques, and classification strategies to refine the model's precision in object detection. The paper details the experimental application of the LSKNet backbone in synergy with the DiffusionDet heads, a combination tailored to meet the specific challenges in aerial image object detection. The findings of this research indicate a substantial enhancement in the model's performance, especially in the accuracy-time tradeoff. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement, outperforming the RCNN model by 4.7% on the same dataset. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis, paving the way for more accurate and efficient object detection methodologies. The code is publicly available at https://github.com/SashaMatsun/LSKDiffDet
Authors: Amine Ouasfi, Adnane Boukhayma
Feedforward generalizable models for implicit shape reconstruction from unoriented point cloud present multiple advantages, including high performance and inference speed. However, they still suffer from generalization issues, ranging from underfitting the input point cloud, to misrepresenting samples outside of the training data distribution, or with toplogies unseen at training. We propose here an efficient mechanism to remedy some of these limitations at test time. We combine the inter-shape data prior of the network with an intra-shape regularization prior of a Nystr\"om Kernel Ridge Regression, that we further adapt by fitting its hyperprameters to the current shape. The resulting shape function defined in a shape specific Reproducing Kernel Hilbert Space benefits from desirable stability and efficiency properties and grants a shape adaptive expressiveness-robustness trade-off. We demonstrate the improvement obtained through our method with respect to baselines and the state-of-the-art using synthetic and real data.
Authors: Yueqian Lin, Jingyang Zhang, Yiran Chen, Hai Li
Robustly evaluating deep learning image classifiers is challenging due to some limitations of standard datasets. Natural Adversarial Examples (NAEs), arising naturally from the environment and capable of deceiving classifiers, are instrumental in identifying vulnerabilities in trained models. Existing works collect such NAEs by filtering from a huge set of real images, a process that is passive and lacks control. In this work, we propose to actively synthesize NAEs with the state-of-the-art Stable Diffusion. Specifically, our method formulates a controlled optimization process, where we perturb the token embedding that corresponds to a specified class to synthesize NAEs. The generation is guided by the gradient of loss from the target classifier so that the created image closely mimics the ground-truth class yet fools the classifier. Named SD-NAE (Stable Diffusion for Natural Adversarial Examples), our innovative method is effective in producing valid and useful NAEs, which is demonstrated through a meticulously designed experiment. Our work thereby provides a valuable method for obtaining challenging evaluation data, which in turn can potentially advance the development of more robust deep learning models. Code is available at https://github.com/linyueqian/SD-NAE.
Authors: Federico Rollo, Andrea Zunino, Gennaro Raiola, Fabio Amadio, Arash Ajoudani, Nikolaos Tsagarakis
Human-robot interaction (HRI) has become a crucial enabler in houses and industries for facilitating operational flexibility. When it comes to mobile collaborative robots, this flexibility can be further increased due to the autonomous mobility and navigation capacity of the robotic agents, expanding their workspace and consequently, the personalizable assistance they can provide to the human operators. This however requires that the robot is capable of detecting and identifying the human counterpart in all stages of the collaborative task, and in particular while following a human in crowded workplaces. To respond to this need, we developed a unified perception and navigation framework, which enables the robot to identify and follow a target person using a combination of visual Re-Identification (Re-ID), hand gestures detection, and collision-free navigation. The Re-ID module can autonomously learn the features of a target person and use the acquired knowledge to visually re-identify the target. The navigation stack is used to follow the target avoiding obstacles and other individuals in the environment. Experiments are conducted with few subjects in a laboratory setting where some unknown dynamic obstacles are introduced.
Authors: Irina Korotkova, Natalia Efremova
Crop mapping is one of the most common tasks in artificial intelligence for agriculture due to higher food demands from a growing population and increased awareness of climate change. In case of vineyards, the texture is very important for crop segmentation: with higher resolution satellite imagery the texture is easily detected by majority of state-of-the-art algorithms. However, this task becomes increasingly more difficult as the resolution of satellite imagery decreases and the information about the texture becomes unavailable. In this paper we aim to explore the main machine learning methods that can be used with freely available satellite imagery and discuss how and when they can be applied for vineyard segmentation problem. We assess the effectiveness of various widely-used machine learning techniques and offer guidance on selecting the most suitable model for specific scenarios.
Authors: Janis Postels, Yannick Strümpler, Klara Reichard, Luc Van Gool, Federico Tombari
Neural Fields (NFs) have gained momentum as a tool for compressing various data modalities - e.g. images and videos. This work leverages previous advances and proposes a novel NF-based compression algorithm for 3D data. We derive two versions of our approach - one tailored to watertight shapes based on Signed Distance Fields (SDFs) and, more generally, one for arbitrary non-watertight shapes using Unsigned Distance Fields (UDFs). We demonstrate that our method excels at geometry compression on 3D point clouds as well as meshes. Moreover, we show that, due to the NF formulation, it is straightforward to extend our compression algorithm to compress both geometry and attribute (e.g. color) of 3D data.
Authors: Ken C. L. Wong, Levente Klein, Ademir Ferreira da Silva, Hongzhi Wang, Jitendra Singh, Tanveer Syeda-Mahmood
Soil organic carbon (SOC) sequestration is the transfer and storage of atmospheric carbon dioxide in soils, which plays an important role in climate change mitigation. SOC concentration can be improved by proper land use, thus it is beneficial if SOC can be estimated at a regional or global scale. As multispectral satellite data can provide SOC-related information such as vegetation and soil properties at a global scale, estimation of SOC through satellite data has been explored as an alternative to manual soil sampling. Although existing studies show promising results, they are mainly based on pixel-based approaches with traditional machine learning methods, and convolutional neural networks (CNNs) are uncommon. To study the use of CNNs on SOC remote sensing, here we propose the FNO-DenseNet based on the Fourier neural operator (FNO). By combining the advantages of the FNO and DenseNet, the FNO-DenseNet outperformed the FNO in our experiments with hundreds of times fewer parameters. The FNO-DenseNet also outperformed a pixel-based random forest by 18% in the mean absolute percentage error.
Authors: Yifan Yang, Yixian Zhang, Daoyang Li, Shuju Sun, Junhong Duan, Junzhou He, Qingyang Wu, Hao Liu
Geographic privacy, a crucial aspect of personal security, often goes unnoticed in daily activities. This paper addresses the underestimation of this privacy in the context of increasing online data sharing and the advancements in information gathering technologies. With the surge in the use of Large Multimodal Models, such as GPT-4, for Open Source Intelligence (OSINT), the potential risks associated with geographic privacy breaches have intensified. This study highlights the criticality of these developments, focusing on their implications for individual privacy. The primary objective is to demonstrate the capabilities of advanced AI tools, specifically a GPT-4 based model named "Dr. Watson," in identifying and potentially compromising geographic privacy through online shared content. We developed "Dr. Watson" to analyze and extract geographic information from publicly available data sources. The study involved five experimental cases, each offering different perspectives on the tool's application in extracting precise location data from partial images and social media content. The experiments revealed that "Dr. Watson" could successfully identify specific geographic details, thereby exposing the vulnerabilities in current geo-privacy measures. These findings underscore the ease with which geographic information can be unintentionally disclosed. The paper concludes with a discussion on the broader implications of these findings for individuals and the community at large. It emphasizes the urgency for enhanced awareness and protective measures against geo-privacy leakage in the era of advanced AI and widespread social media usage.
Authors: Mohamed A. Suliman, Logan Z. J. Williams, Abdulah Fawaz, Emma C. Robinson
This paper introduces GeoMorph, a novel geometric deep-learning framework designed for image registration of cortical surfaces. The registration process consists of two main steps. First, independent feature extraction is performed on each input surface using graph convolutions, generating low-dimensional feature representations that capture important cortical surface characteristics. Subsequently, features are registered in a deep-discrete manner to optimize the overlap of common structures across surfaces by learning displacements of a set of control points. To ensure smooth and biologically plausible deformations, we implement regularization through a deep conditional random field implemented with a recurrent neural network. Experimental results demonstrate that GeoMorph surpasses existing deep-learning methods by achieving improved alignment with smoother deformations. Furthermore, GeoMorph exhibits competitive performance compared to classical frameworks. Such versatility and robustness suggest strong potential for various neuroscience applications.
Authors: Lahiru Wijayasingha, Homa Alemzadeh, John A. Stankovic
Monocular depth estimation is an important step in many downstream tasks in machine vision. We address the topic of estimating monocular depth from defocus blur which can yield more accurate results than the semantic based depth estimation methods. The existing monocular depth from defocus techniques are sensitive to the particular camera that the images are taken from. We show how several camera-related parameters affect the defocus blur using optical physics equations and how they make the defocus blur depend on these parameters. The simple correction procedure we propose can alleviate this problem which does not require any retraining of the original model. We created a synthetic dataset which can be used to test the camera independent performance of depth from defocus blur models. We evaluate our model on both synthetic and real datasets (DDFF12 and NYU depth V2) obtained with different cameras and show that our methods are significantly more robust to the changes of cameras. Code: https://github.com/sleekEagle/defocus_camind.git
Authors: Jiacheng Wang, Hao Li, Dewei Hu, Yuankai K. Tao, Ipek Oguz
High-resolution Optical Coherence Tomography (OCT) images are crucial for ophthalmology studies but are limited by their relatively narrow field of view (FoV). Image mosaicking is a technique for aligning multiple overlapping images to obtain a larger FoV. Current mosaicking pipelines often struggle with substantial noise and considerable displacement between the input sub-fields. In this paper, we propose a versatile pipeline for stitching multi-view OCT/OCTA \textit{en face} projection images. Our method combines the strengths of learning-based feature matching and robust pixel-based registration to align multiple images effectively. Furthermore, we advance the application of a trained foundational model, Segment Anything Model (SAM), to validate mosaicking results in an unsupervised manner. The efficacy of our pipeline is validated using an in-house dataset and a large public dataset, where our method shows superior performance in terms of both accuracy and computational efficiency. We also made our evaluation tool for image mosaicking and the corresponding pipeline publicly available at \url{https://github.com/MedICL-VU/OCT-mosaicking}.
Authors: Amirhossein Kazerouni, Sanaz Karimijafarbigloo, Reza Azad, Yury Velichko, Ulas Bagci, Dorit Merhof
Semantic segmentation, a crucial task in computer vision, often relies on labor-intensive and costly annotated datasets for training. In response to this challenge, we introduce FuseNet, a dual-stream framework for self-supervised semantic segmentation that eliminates the need for manual annotation. FuseNet leverages the shared semantic dependencies between the original and augmented images to create a clustering space, effectively assigning pixels to semantically related clusters, and ultimately generating the segmentation map. Additionally, FuseNet incorporates a cross-modal fusion technique that extends the principles of CLIP by replacing textual data with augmented images. This approach enables the model to learn complex visual representations, enhancing robustness against variations similar to CLIP's text invariance. To further improve edge alignment and spatial consistency between neighboring pixels, we introduce an edge refinement loss. This loss function considers edge information to enhance spatial coherence, facilitating the grouping of nearby pixels with similar visual features. Extensive experiments on skin lesion and lung segmentation datasets demonstrate the effectiveness of our method. \href{https://github.com/xmindflow/FuseNet}{Codebase.}
Authors: Vladimir Arkhipkin, Zein Shaheen, Viacheslav Vasilev, Elizaveta Dakhova, Andrey Kuznetsov, Denis Dimitrov
Multimedia generation approaches occupy a prominent place in artificial intelligence research. Text-to-image models achieved high-quality results over the last few years. However, video synthesis methods recently started to develop. This paper presents a new two-stage latent diffusion text-to-video generation architecture based on the text-to-image diffusion model. The first stage concerns keyframes synthesis to figure the storyline of a video, while the second one is devoted to interpolation frames generation to make movements of the scene and objects smooth. We compare several temporal conditioning approaches for keyframes generation. The results show the advantage of using separate temporal blocks over temporal layers in terms of metrics reflecting video generation quality aspects and human preference. The design of our interpolation model significantly reduces computational costs compared to other masked frame interpolation approaches. Furthermore, we evaluate different configurations of MoVQ-based video decoding scheme to improve consistency and achieve higher PSNR, SSIM, MSE, and LPIPS scores. Finally, we compare our pipeline with existing solutions and achieve top-2 scores overall and top-1 among open-source solutions: CLIPSIM = 0.2976 and FVD = 433.054. Project page: https://ai-forever.github.io/kandinsky-video/
Authors: Shin'ya Yamaguchi, Takuma Fukuda
Synthetic samples from diffusion models are promising for leveraging in training discriminative models as replications of real training datasets. However, we found that the synthetic datasets degrade classification performance over real datasets even when using state-of-the-art diffusion models. This means that modern diffusion models do not perfectly represent the data distribution for the purpose of replicating datasets for training discriminative tasks. This paper investigates the gap between synthetic and real samples by analyzing the synthetic samples reconstructed from real samples through the diffusion and reverse process. By varying the time steps starting the reverse process in the reconstruction, we can control the trade-off between the information in the original real data and the information added by diffusion models. Through assessing the reconstructed samples and trained models, we found that the synthetic data are concentrated in modes of the training data distribution as the reverse step increases, and thus, they are difficult to cover the outer edges of the distribution. Our findings imply that modern diffusion models are insufficient to replicate training data distribution perfectly, and there is room for the improvement of generative modeling in the replication of training datasets.
Authors: Yixin Liu, Kaidi Xu, Xun Chen, Lichao Sun
The open source of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these open-source image datasets being exploited by unauthorized third parties to train deep learning models for commercial or illegal purposes. To avoid the abuse of public data, a poisoning-based technique, the unlearnable example, is proposed to significantly degrade the generalization performance of models by adding a kind of imperceptible noise to the data. To further enhance its robustness against adversarial training, existing works leverage iterative adversarial training on both the defensive noise and the surrogate model. However, it still remains unknown whether the robustness of unlearnable examples primarily comes from the effect of enhancement in the surrogate model or the defensive noise. Observing that simply removing the adversarial noise on the training process of the defensive noise can improve the performance of robust unlearnable examples, we identify that solely the surrogate model's robustness contributes to the performance. Furthermore, we found a negative correlation exists between the robustness of defensive noise and the protection performance, indicating defensive noise's instability issue. Motivated by this, to further boost the robust unlearnable example, we introduce stable error-minimizing noise (SEM), which trains the defensive noise against random perturbation instead of the time-consuming adversarial perturbation to improve the stability of defensive noise. Through extensive experiments, we demonstrate that SEM achieves a new state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet Subset in terms of both effectiveness and efficiency. The code is available at https://github.com/liuyixin-louis/Stable-Unlearnable-Example.
Authors: Yutao Feng, Yintong Shang, Xuan Li, Tianjia Shao, Chenfanfu Jiang, Yin Yang
We show that physics-based simulations can be seamlessly integrated with NeRF to generate high-quality elastodynamics of real-world objects. Unlike existing methods, we discretize nonlinear hyperelasticity in a meshless way, obviating the necessity for intermediate auxiliary shape proxies like a tetrahedral mesh or voxel grid. A quadratic generalized moving least square (Q-GMLS) is employed to capture nonlinear dynamics and large deformation on the implicit model. Such meshless integration enables versatile simulations of complex and codimensional shapes. We adaptively place the least-square kernels according to the NeRF density field to significantly reduce the complexity of the nonlinear simulation. As a result, physically realistic animations can be conveniently synthesized using our method for a wide range of hyperelastic materials at an interactive rate. For more information, please visit our project page at https://fytalon.github.io/pienerf/.
Authors: Andrew M. Nguyen, Tejas Sudharshan Mathai, Liangchen Liu, Jianfei Liu, Ronald M. Summers
Pericoronary adipose tissue (PCAT) is the deposition of fat in the vicinity of the coronary arteries. It is an indicator of coronary inflammation and associated with coronary artery disease. Non-invasive coronary CT angiography (CCTA) is presently used to obtain measures of the thickness, volume, and attenuation of fat deposition. However, prior works solely focus on measuring PCAT using semi-automated approaches at the right coronary artery (RCA) over the left coronary artery (LCA). In this pilot work, we developed a fully automated approach for the measurement of PCAT mean attenuation and volume in the region around both coronary arteries. First, we used a large subset of patients from the public ImageCAS dataset (n = 735) to train a 3D full resolution nnUNet to segment LCA and RCA. Then, we automatically measured PCAT in the surrounding arterial regions. We evaluated our method on a held-out test set of patients (n = 183) from the same dataset. A mean Dice score of 83% and PCAT attenuation of -73.81 $\pm$ 12.69 HU was calculated for the RCA, while a mean Dice score of 81% and PCAT attenuation of -77.51 $\pm$ 7.94 HU was computed for the LCA. To the best of our knowledge, we are the first to develop a fully automated method to measure PCAT attenuation and volume at both the RCA and LCA. Our work underscores how automated PCAT measurement holds promise as a biomarker for identification of inflammation and cardiac disease.
Authors: Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Hao Bai, Yuexiang Zhai, Benjamin D. Haeffele, Yi Ma
In this paper, we contend that a natural objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a low-dimensional Gaussian mixture supported on incoherent subspaces. The goodness of such a representation can be evaluated by a principled measure, called sparse rate reduction, that simultaneously maximizes the intrinsic information gain and extrinsic sparsity of the learned representation. From this perspective, popular deep network architectures, including transformers, can be viewed as realizing iterative schemes to optimize this measure. Particularly, we derive a transformer block from alternating optimization on parts of this objective: the multi-head self-attention operator compresses the representation by implementing an approximate gradient descent step on the coding rate of the features, and the subsequent multi-layer perceptron sparsifies the features. This leads to a family of white-box transformer-like deep network architectures, named CRATE, which are mathematically fully interpretable. We show, by way of a novel connection between denoising and compression, that the inverse to the aforementioned compressive encoding can be realized by the same class of CRATE architectures. Thus, the so-derived white-box architectures are universal to both encoders and decoders. Experiments show that these networks, despite their simplicity, indeed learn to compress and sparsify representations of large-scale real-world image and text datasets, and achieve performance very close to highly engineered transformer-based models: ViT, MAE, DINO, BERT, and GPT2. We believe the proposed computational framework demonstrates great potential in bridging the gap between theory and practice of deep learning, from a unified perspective of data compression. Code is available at: https://ma-lab-berkeley.github.io/CRATE .
Authors: Zhen Zhao, Can Huang, Binghong Wu, Chunhui Lin, Hao Liu, Zhizhong Zhang, Xin Tan, Jingqun Tang, Yuan Xie
Scene text recognition (STR) in the wild frequently encounters challenges when coping with domain variations, font diversity, shape deformations, etc. A straightforward solution is performing model fine-tuning tailored to a specific scenario, but it is computationally intensive and requires multiple model copies for various scenarios. Recent studies indicate that large language models (LLMs) can learn from a few demonstration examples in a training-free manner, termed "In-Context Learning" (ICL). Nevertheless, applying LLMs as a text recognizer is unacceptably resource-consuming. Moreover, our pilot experiments on LLMs show that ICL fails in STR, mainly attributed to the insufficient incorporation of contextual information from diverse samples in the training stage. To this end, we introduce E$^2$STR, a STR model trained with context-rich scene text sequences, where the sequences are generated via our proposed in-context training strategy. E$^2$STR demonstrates that a regular-sized model is sufficient to achieve effective ICL capabilities in STR. Extensive experiments show that E$^2$STR exhibits remarkable training-free adaptation in various scenarios and outperforms even the fine-tuned state-of-the-art approaches on public benchmarks.
Authors: Zhiqin Chen, Qimin Chen, Hang Zhou, Hao Zhang
We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. To maximize the expressive power of the part templates, we introduce a per-part deformation network to enable the modeling of diverse parts with substantial geometry variations, while imposing constraints on the deformation capacity to ensure fidelity to the originally represented parts. We also propose a training scheme to effectively overcome local minima. Architecturally, our network is a branched autoencoder, with a CNN encoder taking a voxel shape as input and producing per-part transformation matrices, latent codes, and part existence scores, and the decoder outputting point occupancies to define the reconstruction loss. Our network, coined DAE-Net for Deforming Auto-Encoder, can achieve unsupervised 3D shape co-segmentation that yields fine-grained, compact, and meaningful parts that are consistent across diverse shapes. We conduct extensive experiments on the ShapeNet Part dataset, DFAUST, and an animal subset of Objaverse to show superior performance over prior methods.
Authors: Yixin Liu, Chenrui Fan, Yutong Dai, Xun Chen, Pan Zhou, Lichao Sun
Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this problem, existing poisoning-based approaches perturb user images in an imperceptible way to render them "unlearnable" from malicious uses. We identify two limitations of these defending approaches: i) sub-optimal due to the hand-crafted heuristics for solving the intractable bilevel optimization and ii) lack of robustness against simple data transformations like Gaussian filtering. To solve these challenges, we propose MetaCloak, which solves the bi-level poisoning problem with a meta-learning framework with an additional transformation sampling process to craft transferable and robust perturbation. Specifically, we employ a pool of surrogate diffusion models to craft transferable and model-agnostic perturbation. Furthermore, by incorporating an additional transformation process, we design a simple denoising-error maximization loss that is sufficient for causing transformation-robust semantic distortion and degradation in a personalized generation. Extensive experiments on the VGGFace2 and CelebA-HQ datasets show that MetaCloak outperforms existing approaches. Notably, MetaCloak can successfully fool online training services like Replicate, in a black-box manner, demonstrating the effectiveness of MetaCloak in real-world scenarios. Our code is available at https://github.com/liuyixin-louis/MetaCloak.
Authors: Guangming Cao, Xuehui Yu, Wenwen Yu, Xumeng Han, Xue Yang, Guorong Li, Jianbin Jiao, Zhenjun Han
Oriented object detection, a specialized subfield in computer vision, finds applications across diverse scenarios, excelling particularly when dealing with objects of arbitrary orientations. Conversely, point annotation, which treats objects as single points, offers a cost-effective alternative to rotated and horizontal bounding boxes but sacrifices performance due to the loss of size and orientation information. In this study, we introduce the P2RBox network, which leverages point annotations and a mask generator to create mask proposals, followed by filtration through our Inspector Module and Constrainer Module. This process selects high-quality masks, which are subsequently converted into rotated box annotations for training a fully supervised detector. Specifically, we've thoughtfully crafted an Inspector Module rooted in multi-instance learning principles to evaluate the semantic score of masks. We've also proposed a more robust mask quality assessment in conjunction with the Constrainer Module. Furthermore, we've introduced a Symmetry Axis Estimation (SAE) Module inspired by the spectral theorem for symmetric matrices to transform the top-performing mask proposal into rotated bounding boxes. P2RBox performs well with three fully supervised rotated object detectors: RetinaNet, Rotated FCOS, and Oriented R-CNN. By combining with Oriented R-CNN, P2RBox achieves 62.26% on DOTA-v1.0 test dataset. As far as we know, this is the first attempt at training an oriented object detector with point supervision.
Authors: Zhihong Zhang, Runzhao Yang, Jinli Suo, Yuxiao Cheng, Qionghai Dai
The compact cameras recording high-speed scenes with high resolution are highly demanded, but the required high bandwidth often leads to bulky, heavy systems, which limits their applications on low-capacity platforms. Adopting a coded exposure setup to encode a frame sequence into a blurry snapshot and retrieve the latent sharp video afterward can serve as a lightweight solution. However, restoring motion from blur is quite challenging due to the high ill-posedness of motion blur decomposition, intrinsic ambiguity in motion direction, and diverse motions in natural videos. In this work, by leveraging classical coded exposure imaging technique and emerging implicit neural representation for videos, we tactfully embed the motion direction cues into the blurry image during the imaging process and develop a novel self-recursive neural network to sequentially retrieve the latent video sequence from the blurry image utilizing the embedded motion direction cues. To validate the effectiveness and efficiency of the proposed framework, we conduct extensive experiments on benchmark datasets and real-captured blurry images. The results demonstrate that our proposed framework significantly outperforms existing methods in quality and flexibility. The code for our work is available at https://github.com/zhihongz/BDINR
Authors: Mengyang Feng, Jinlin Liu, Miaomiao Cui, Xuansong Xie
This is a technical report on the 360-degree panoramic image generation task based on diffusion models. Unlike ordinary 2D images, 360-degree panoramic images capture the entire $360^\circ\times 180^\circ$ field of view. So the rightmost and the leftmost sides of the 360 panoramic image should be continued, which is the main challenge in this field. However, the current diffusion pipeline is not appropriate for generating such a seamless 360-degree panoramic image. To this end, we propose a circular blending strategy on both the denoising and VAE decoding stages to maintain the geometry continuity. Based on this, we present two models for \textbf{Text-to-360-panoramas} and \textbf{Single-Image-to-360-panoramas} tasks. The code has been released as an open-source project at \href{https://github.com/ArcherFMY/SD-T2I-360PanoImage}{https://github.com/ArcherFMY/SD-T2I-360PanoImage} and \href{https://www.modelscope.cn/models/damo/cv_diffusion_text-to-360panorama-image_generation/summary}{ModelScope}
Authors: Marlon Bran Lorenzana, Feng Liu, Shekhar S. Chandra
Popular methods in compressed sensing (CS) are dependent on deep learning (DL), where large amounts of data are used to train non-linear reconstruction models. However, ensuring generalisability over and access to multiple datasets is challenging to realise for real-world applications. To address these concerns, this paper proposes a single image, self-supervised (SS) CS-MRI framework that enables a joint deep and sparse regularisation of CS artefacts. The approach effectively dampens structured CS artefacts, which can be difficult to remove assuming sparse reconstruction, or relying solely on the inductive biases of CNN to produce noise-free images. Image quality is thereby improved compared to either approach alone. Metrics are evaluated using Cartesian 1D masks on a brain and knee dataset, with PSNR improving by 2-4dB on average.
Authors: Tuan-Anh Vu, Srinjay Sarkar, Zhiyuan Zhang, Binh-Son Hua, Sai-Kit Yeung
Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the performance of the downstream tasks drops significantly. This work explores test-time augmentation (TTA) for 3D point clouds. We are inspired by the recent revolution of learning implicit representation and point cloud upsampling, which can produce high-quality 3D surface reconstruction and proximity-to-surface, respectively. Our idea is to leverage the implicit field reconstruction or point cloud upsampling techniques as a systematic way to augment point cloud data. Mainly, we test both strategies by sampling points from the reconstructed results and using the sampled point cloud as test-time augmented data. We show that both strategies are effective in improving accuracy. We observed that point cloud upsampling for test-time augmentation can lead to more significant performance improvement on downstream tasks such as object classification and segmentation on the ModelNet40, ShapeNet, ScanObjectNN, and SemanticKITTI datasets, especially for sparse point clouds.
Authors: Jianwei Feng, Prateek Singhal
Style transfer for human face has been widely researched in recent years. Majority of the existing approaches work in 2D image domain and have 3D inconsistency issue when applied on different viewpoints of the same face. In this paper, we tackle the problem of 3D face style transfer which aims at generating stylized novel views of a 3D human face with multi-view consistency. We propose to use a neural radiance field (NeRF) to represent 3D human face and combine it with 2D style transfer to stylize the 3D face. We find that directly training a NeRF on stylized images from 2D style transfer brings in 3D inconsistency issue and causes blurriness. On the other hand, training a NeRF jointly with 2D style transfer objectives shows poor convergence due to the identity and head pose gap between style image and content image. It also poses challenge in training time and memory due to the need of volume rendering for full image to apply style transfer loss functions. We therefore propose a hybrid framework of NeRF and mesh rasterization to combine the benefits of high fidelity geometry reconstruction of NeRF and fast rendering speed of mesh. Our framework consists of three stages: 1. Training a NeRF model on input face images to learn the 3D geometry; 2. Extracting a mesh from the trained NeRF model and optimizing it with style transfer objectives via differentiable rasterization; 3. Training a new color network in NeRF conditioned on a style embedding to enable arbitrary style transfer to the 3D face. Experiment results show that our approach generates high quality face style transfer with great 3D consistency, while also enabling a flexible style control.
Authors: Zheng Zhang, Kevin Wells, Gustavo Carneiro
The advent of learning with noisy labels (LNL), multi-rater learning, and human-AI collaboration has revolutionised the development of robust classifiers, enabling them to address the challenges posed by different types of data imperfections and complex decision processes commonly encountered in real-world applications. While each of these methodologies has individually made significant strides in addressing their unique challenges, the development of techniques that can simultaneously tackle these three problems remains underexplored. This paper addresses this research gap by integrating noisy-label learning, multi-rater learning, and human-AI collaboration with new benchmarks and the innovative Learning to Complement with Multiple Humans (LECOMH) approach. LECOMH optimises the level of human collaboration during testing, aiming to optimise classification accuracy while minimising collaboration costs that vary from 0 to M, where M is the maximum number of human collaborators. We quantitatively compare LECOMH with leading human-AI collaboration methods using our proposed benchmarks. LECOMH consistently outperforms the competition, with accuracy improving as collaboration costs increase. Notably, LECOMH is the only method enhancing human labeller performance across all benchmarks.
Authors: Annesha Ghosh, Gordon Wetzstein, Mert Pilanci, Sara Fridovich-Keil
Off-resonance artifacts in magnetic resonance imaging (MRI) are visual distortions that occur when the actual resonant frequencies of spins within the imaging volume differ from the expected frequencies used to encode spatial information. These discrepancies can be caused by a variety of factors, including magnetic field inhomogeneities, chemical shifts, or susceptibility differences within the tissues. Such artifacts can manifest as blurring, ghosting, or misregistration of the reconstructed image, and they often compromise its diagnostic quality. We propose to resolve these artifacts by lifting the 2D MRI reconstruction problem to 3D, introducing an additional "spectral" dimension to model this off-resonance. Our approach is inspired by recent progress in modeling radiance fields, and is capable of reconstructing both static and dynamic MR images as well as separating fat and water, which is of independent clinical interest. We demonstrate our approach in the context of PROPELLER (Periodically Rotated Overlapping ParallEL Lines with Enhanced Reconstruction) MRI acquisitions, which are popular for their robustness to motion artifacts. Our method operates in a few minutes on a single GPU, and to our knowledge is the first to correct for chemical shift in gradient echo PROPELLER MRI reconstruction without additional measurements or pretraining data.
Authors: Xingyu Chen, Xinyu Zhang, Qiyue Xia, Xinmin Fang, Chris Xiaoxuan Lu, Zhengxiong Li
Millimeter wave (mmWave) sensing is an emerging technology with applications in 3D object characterization and environment mapping. However, realizing precise 3D reconstruction from sparse mmWave signals remains challenging. Existing methods rely on data-driven learning, constrained by dataset availability and difficulty in generalization. We propose DiffSBR, a differentiable framework for mmWave-based 3D reconstruction. DiffSBR incorporates a differentiable ray tracing engine to simulate radar point clouds from virtual 3D models. A gradient-based optimizer refines the model parameters to minimize the discrepancy between simulated and real point clouds. Experiments using various radar hardware validate DiffSBR's capability for fine-grained 3D reconstruction, even for novel objects unseen by the radar previously. By integrating physics-based simulation with gradient optimization, DiffSBR transcends the limitations of data-driven approaches and pioneers a new paradigm for mmWave sensing.
Authors: Somayeh Hussaini, Michael Milford, Tobias Fischer
In robotics, Spiking Neural Networks (SNNs) are increasingly recognized for their largely-unrealized potential energy efficiency and low latency particularly when implemented on neuromorphic hardware. Our paper highlights three advancements for SNNs in Visual Place Recognition (VPR). First, we propose Modular SNNs, where each SNN represents a set of non-overlapping geographically distinct places, enabling scalable networks for large environments. Secondly, we present Ensembles of Modular SNNs, where multiple networks represent the same place, significantly enhancing accuracy compared to single-network models. Our SNNs are compact and small, comprising only 1500 neurons and 474k synapses, which makes them ideally suited for ensembling due to this small size. Lastly, we investigate the role of sequence matching in SNN-based VPR, a technique where consecutive images are used to refine place recognition. We analyze the responsiveness of SNNs to ensembling and sequence matching compared to other VPR techniques. Our contributions highlight the viability of SNNs for VPR, offering scalable and robust solutions, paving the way for their application in various energy-sensitive robotic tasks.
Authors: Chenhao Li, Taishi Ono, Takeshi Uemori, Hajime Mihara, Alexander Gatto, Hajime Nagahara, Yuseke Moriuchi
Multi-view inverse rendering is the problem of estimating the scene parameters such as shapes, materials, or illuminations from a sequence of images captured under different viewpoints. Many approaches, however, assume single light bounce and thus fail to recover challenging scenarios like inter-reflections. On the other hand, simply extending those methods to consider multi-bounced light requires more assumptions to alleviate the ambiguity. To address this problem, we propose Neural Incident Stokes Fields (NeISF), a multi-view inverse rendering framework that reduces ambiguities using polarization cues. The primary motivation for using polarization cues is that it is the accumulation of multi-bounced light, providing rich information about geometry and material. Based on this knowledge, the proposed incident Stokes field efficiently models the accumulated polarization effect with the aid of an original physically-based differentiable polarimetric renderer. Lastly, experimental results show that our method outperforms the existing works in synthetic and real scenarios.
Authors: Yonghui Wang, Wengang Zhou, Hao Feng, Keyi Zhou, Houqiang Li
In the field of document understanding, significant advances have been made in the fine-tuning of Multimodal Large Language Models (MLLMs) with instruction-following data. Nevertheless, the potential of text-grounding capability within text-rich scenarios remains underexplored. In this paper, we present a text-grounding document understanding model, termed TGDoc, which addresses this deficiency by enhancing MLLMs with the ability to discern the spatial positioning of text within images. Empirical evidence suggests that text-grounding improves the model's interpretation of textual content, thereby elevating its proficiency in comprehending text-rich images. Specifically, we compile a dataset containing 99K PowerPoint presentations sourced from the internet. We formulate instruction tuning tasks including text detection, recognition, and spotting to facilitate the cohesive alignment between the visual encoder and large language model. Moreover, we curate a collection of text-rich images and prompt the text-only GPT-4 to generate 12K high-quality conversations, featuring textual locations within text-rich scenarios. By integrating text location data into the instructions, TGDoc is adept at discerning text locations during the visual question process. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple text-rich benchmarks, validating the effectiveness of our method.
Authors: Lei Qi, Peng Dong, Tan Xiong, Hui Xue, Xin Geng
Object detection in urban scenarios is crucial for autonomous driving in intelligent traffic systems. However, unlike conventional object detection tasks, urban-scene images vary greatly in style. For example, images taken on sunny days differ significantly from those taken on rainy days. Therefore, models trained on sunny day images may not generalize well to rainy day images. In this paper, we aim to solve the single-domain generalizable object detection task in urban scenarios, meaning that a model trained on images from one weather condition should be able to perform well on images from any other weather conditions. To address this challenge, we propose a novel Double AUGmentation (DoubleAUG) method that includes image- and feature-level augmentation schemes. In the image-level augmentation, we consider the variation in color information across different weather conditions and propose a Color Perturbation (CP) method that randomly exchanges the RGB channels to generate various images. In the feature-level augmentation, we propose to utilize a Dual-Style Memory (DSM) to explore the diverse style information on the entire dataset, further enhancing the model's generalization capability. Extensive experiments demonstrate that our proposed method outperforms state-of-the-art methods. Furthermore, ablation studies confirm the effectiveness of each module in our proposed method. Moreover, our method is plug-and-play and can be integrated into existing methods to further improve model performance.
Authors: Zijian Kuang, Lihang Ying, Shi Jin
The Differentiable Rendering and Implicit Function-based model (DRIFu) draws its roots from the Pixel-aligned Implicit Function (PIFU), a pioneering 3D digitization technique initially designed for clothed human bodies. PIFU excels in capturing nuanced body shape variations within a low-dimensional space and has been extensively trained on human 3D scans. However, the application of PIFU to live animals poses significant challenges, primarily due to the inherent difficulty in obtaining the cooperation of animals for 3D scanning. In response to this challenge, we introduce the DRIFu model, specifically tailored for animal digitization. To train DRIFu, we employ a curated set of synthetic 3D animal models, encompassing diverse shapes, sizes, and even accounting for variations such as baby birds. Our innovative alignment tools play a pivotal role in mapping these diverse synthetic animal models onto a unified template, facilitating precise predictions of animal shape and texture. Crucially, our template alignment strategy establishes a shared shape space, allowing for the seamless sampling of new animal shapes, posing them realistically, animating them, and aligning them with real-world data. This groundbreaking approach revolutionizes our capacity to comprehensively understand and represent avian forms. For further details and access to the project, the project website can be found at https://github.com/kuangzijian/drifu-for-animals
Authors: Xiyu Qi, Yifan Wu, Yongqiang Mao, Wenhui Zhang, Yidan Zhang
The Segment Anything Model (SAM) exhibits remarkable versatility and zero-shot learning abilities, owing largely to its extensive training data (SA-1B). Recognizing SAM's dependency on manual guidance given its category-agnostic nature, we identified unexplored potential within few-shot semantic segmentation tasks for remote sensing imagery. This research introduces a structured framework designed for the automation of few-shot semantic segmentation. It utilizes the SAM model and facilitates a more efficient generation of semantically discernible segmentation outcomes. Central to our methodology is a novel automatic prompt learning approach, leveraging prior guided masks to produce coarse pixel-wise prompts for SAM. Extensive experiments on the DLRSD datasets underline the superiority of our approach, outperforming other available few-shot methodologies.
Authors: Junyu Gao, Xuan Yao, Changsheng Xu
Vision-and-Language Navigation (VLN) has witnessed significant advancements in recent years, largely attributed to meticulously curated datasets and proficiently trained models. Nevertheless, when tested in diverse environments, the trained models inevitably encounter significant shifts in data distribution, highlighting that relying solely on pre-trained and fixed navigation models is insufficient. To enhance models' generalization ability, test-time adaptation (TTA) demonstrates significant potential in the computer vision field by leveraging unlabeled test samples for model updates. However, simply applying existing TTA methods to the VLN task cannot well handle the adaptability-stability dilemma of VLN models, i.e., frequent updates can result in drastic changes in model parameters, while occasional updates can make the models ill-equipped to handle dynamically changing environments. Therefore, we propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for VLN by performing decomposition-accumulation analysis for both gradients and parameters in a unified framework. Specifically, in the fast update phase, gradients generated during the recent multi-step navigation process are decomposed into components with varying levels of consistency. Then, these components are adaptively accumulated to pinpoint a concordant direction for fast model adaptation. In the slow update phase, historically recorded parameters are gathered, and a similar decomposition-accumulation analysis is conducted to revert the model to a stable state. Extensive experiments show that our method obtains impressive performance gains on four popular benchmarks.
Authors: Hasan Murad, Mohammed Eunus Ali
Retrieving textual information from natural scene images is an active research area in the field of computer vision with numerous practical applications. Detecting text regions and extracting text from signboards is a challenging problem due to special characteristics like reflecting lights, uneven illumination, or shadows found in real-life natural scene images. With the advent of deep learning-based methods, different sophisticated techniques have been proposed for text detection and text recognition from the natural scene. Though a significant amount of effort has been devoted to extracting natural scene text for resourceful languages like English, little has been done for low-resource languages like Bangla. In this research work, we have proposed an end-to-end system with deep learning-based models for efficiently detecting, recognizing, correcting, and parsing address information from Bangla signboards. We have created manually annotated datasets and synthetic datasets to train signboard detection, address text detection, address text recognition, address text correction, and address text parser models. We have conducted a comparative study among different CTC-based and Encoder-Decoder model architectures for Bangla address text recognition. Moreover, we have designed a novel address text correction model using a sequence-to-sequence transformer-based network to improve the performance of Bangla address text recognition model by post-correction. Finally, we have developed a Bangla address text parser using the state-of-the-art transformer-based pre-trained language model.
Authors: Kai Yang, Jian Tao, Jiafei Lyu, Chunjiang Ge, Jiaxin Chen, Qimai Li, Weihan Shen, Xiaolong Zhu, Xiu Li
Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to fine-tune the underlying models. However, crafting an efficient reward model demands extensive datasets, optimal architecture, and manual hyperparameter tuning, making the process both time and cost-intensive. The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model. However, the extensive GPU memory requirement of the diffusion model's denoising process hinders the direct application of the DPO method. To address this issue, we introduce the Direct Preference for Denoising Diffusion Policy Optimization (D3PO) method to directly fine-tune diffusion models. The theoretical analysis demonstrates that although D3PO omits training a reward model, it effectively functions as the optimal reward model trained using human feedback data to guide the learning process. This approach requires no training of a reward model, proving to be more direct, cost-effective, and minimizing computational overhead. In experiments, our method uses the relative scale of objectives as a proxy for human preference, delivering comparable results to methods using ground-truth rewards. Moreover, D3PO demonstrates the ability to reduce image distortion rates and generate safer images, overcoming challenges lacking robust reward models.
Authors: Huimin Xiong, Kunle Li, Kaiyuan Tan, Yang Feng, Joey Tianyi Zhou, Jin Hao, Haochao Ying, Jian Wu, Zuozhu Liu
Optical Intraoral Scanners (IOS) are widely used in digital dentistry to provide detailed 3D information of dental crowns and the gingiva. Accurate 3D tooth segmentation in IOSs is critical for various dental applications, while previous methods are error-prone at complicated boundaries and exhibit unsatisfactory results across patients. In this paper, we propose TSegFormer which captures both local and global dependencies among different teeth and the gingiva in the IOS point clouds with a multi-task 3D transformer architecture. Moreover, we design a geometry-guided loss based on a novel point curvature to refine boundaries in an end-to-end manner, avoiding time-consuming post-processing to reach clinically applicable segmentation. In addition, we create a dataset with 16,000 IOSs, the largest ever IOS dataset to the best of our knowledge. The experimental results demonstrate that our TSegFormer consistently surpasses existing state-of-the-art baselines. The superiority of TSegFormer is corroborated by extensive analysis, visualizations and real-world clinical applicability tests. Our code is available at https://github.com/huiminxiong/TSegFormer.
Authors: Yuxiang Lu, Suizhi Huang, Yuwen Yang, Shalayiding Sirejiding, Yue Ding, Hongtao Lu
Federated Learning (FL) enables joint training across distributed clients using their local data privately. Federated Multi-Task Learning (FMTL) builds on FL to handle multiple tasks, assuming model congruity that identical model architecture is deployed in each client. To relax this assumption and thus extend real-world applicability, we introduce a novel problem setting, Hetero-Client Federated Multi-Task Learning (HC-FMTL), to accommodate diverse task setups. The main challenge of HC-FMTL is the model incongruity issue that invalidates conventional aggregation methods. It also escalates the difficulties in accurate model aggregation to deal with data and task heterogeneity inherent in FMTL. To address these challenges, we propose the FedHCA$^2$ framework, which allows for federated training of personalized models by modeling relationships among heterogeneous clients. Drawing on our theoretical insights into the difference between multi-task and federated optimization, we propose the Hyper Conflict-Averse Aggregation scheme to mitigate conflicts during encoder updates. Additionally, inspired by task interaction in MTL, the Hyper Cross Attention Aggregation scheme uses layer-wise cross attention to enhance decoder interactions while alleviating model incongruity. Moreover, we employ learnable Hyper Aggregation Weights for each client to customize personalized parameter updates. Extensive experiments demonstrate the superior performance of FedHCA$^2$ in various HC-FMTL scenarios compared to representative methods. Our code will be made publicly available.
Authors: Zhe Zhang, Gaochang Wu, Jing Zhang, Chunhua Shen, Dacheng Tao, Tianyou Chai
Video semantic segmentation is a pivotal aspect of video representation learning. However, significant domain shifts present a challenge in effectively learning invariant spatio-temporal features across the labeled source domain and unlabeled target domain for video semantic segmentation. To solve the challenge, we propose a novel DA-STC method for domain adaptive video semantic segmentation, which incorporates a bidirectional multi-level spatio-temporal fusion module and a category-aware spatio-temporal feature alignment module to facilitate consistent learning for domain-invariant features. Firstly, we perform bidirectional spatio-temporal fusion at the image sequence level and shallow feature level, leading to the construction of two fused intermediate video domains. This prompts the video semantic segmentation model to consistently learn spatio-temporal features of shared patch sequences which are influenced by domain-specific contexts, thereby mitigating the feature gap between the source and target domain. Secondly, we propose a category-aware feature alignment module to promote the consistency of spatio-temporal features, facilitating adaptation to the target domain. Specifically, we adaptively aggregate the domain-specific deep features of each category along spatio-temporal dimensions, which are further constrained to achieve cross-domain intra-class feature alignment and inter-class feature separation. Extensive experiments demonstrate the effectiveness of our method, which achieves state-of-the-art mIOUs on multiple challenging benchmarks. Furthermore, we extend the proposed DA-STC to the image domain, where it also exhibits superior performance for domain adaptive semantic segmentation. The source code and models will be made available at \url{https://github.com/ZHE-SAPI/DA-STC}.
Authors: Yangyi Chen, Xingyao Wang, Manling Li, Derek Hoiem, Heng Ji
State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-organized structured format. Second, we introduce curriculum-based learning for VLMs to progressively comprehend visual structures, from fundamental visual concepts to intricate event structures. Our intuition is that lower-level knowledge may contribute to complex visual structure understanding. Furthermore, we compile and release a collection of datasets tailored for visual structural knowledge extraction. We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web. In experiments, we evaluate ViStruct on visual structure prediction tasks, demonstrating its effectiveness in improving the understanding of visual structures. The code is public at \url{https://github.com/Yangyi-Chen/vi-struct}.
Authors: Maren Høibø, André Pedersen, Vibeke Grotnes Dale, Sissel Marie Berget, Borgny Ytterhus, Cecilia Lindskog, Elisabeth Wik, Lars A. Akslen, Ingerid Reinertsen, Erik Smistad, Marit Valla
Digital pathology enables automatic analysis of histopathological sections using artificial intelligence (AI). Automatic evaluation could improve diagnostic efficiency and help find associations between morphological features and clinical outcome. For development of such prediction models, identifying invasive epithelial cells, and separating these from benign epithelial cells and in situ lesions would be the first step. In this study, we aimed to develop an AI model for segmentation of epithelial cells in sections from breast cancer. We generated epithelial ground truth masks by restaining hematoxylin and eosin (HE) sections with cytokeratin (CK) AE1/AE3, and by pathologists' annotations. HE/CK image pairs were used to train a convolutional neural network, and data augmentation was used to make the model more robust. Tissue microarrays (TMAs) from 839 patients, and whole slide images from two patients were used for training and evaluation of the models. The sections were derived from four cohorts of breast cancer patients. TMAs from 21 patients from a fifth cohort was used as a second test set. In quantitative evaluation, a mean Dice score of 0.70, 0.79, and 0.75 for invasive epithelial cells, benign epithelial cells, and in situ lesions, respectively, were achieved. In qualitative scoring (0-5) by pathologists, results were best for all epithelium and invasive epithelium, with scores of 4.7 and 4.4. Scores for benign epithelium and in situ lesions were 3.7 and 2.0. The proposed model segmented epithelial cells in HE stained breast cancer slides well, but further work is needed for accurate division between the classes. Immunohistochemistry, together with pathologists' annotations, enabled the creation of accurate ground truths. The model is made freely available in FastPathology and the code is available at https://github.com/AICAN-Research/breast-epithelium-segmentation
Authors: Yaqi Liu, Chao Xia, Song Xiao, Qingxiao Guan, Wenqian Dong, Yifan Zhang, Nenghai Yu
Copy-move forgery detection aims at detecting duplicated regions in a suspected forged image, and deep learning based copy-move forgery detection methods are in the ascendant. These deep learning based methods heavily rely on synthetic training data, and the performance will degrade when facing new tasks. In this paper, we propose a Transformer-style copy-move forgery detection network named as CMFDFormer, and provide a novel PCSD (Pooled Cube and Strip Distillation) continual learning framework to help CMFDFormer handle new tasks. CMFDFormer consists of a MiT (Mix Transformer) backbone network and a PHD (Pluggable Hybrid Decoder) mask prediction network. The MiT backbone network is a Transformer-style network which is adopted on the basis of comprehensive analyses with CNN-style and MLP-style backbones. The PHD network is constructed based on self-correlation computation, hierarchical feature integration, a multi-scale cycle fully-connected block and a mask reconstruction block. The PHD network is applicable to feature extractors of different styles for hierarchical multi-scale information extraction, achieving comparable performance. Last but not least, we propose a PCSD continual learning framework to improve the forgery detectability and avoid catastrophic forgetting when handling new tasks. Our continual learning framework restricts intermediate features from the PHD network, and takes advantage of both cube pooling and strip pooling. Extensive experiments on publicly available datasets demonstrate the good performance of CMFDFormer and the effectiveness of the PCSD continual learning framework.
Authors: Seongyoon Kim, Gihun Lee, Jaehoon Oh, Se-Young Yun
Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In our study, we observe that as data heterogeneity increases, feature representation in the FedAVG model deteriorates more significantly compared to classifier weight. Additionally, we observe that as data heterogeneity increases, the gap between higher feature norms for observed classes, obtained from local models, and feature norms of unobserved classes widens, in contrast to the behavior of classifier weight norms. This widening gap extends to encompass the feature norm disparities between local and the global models. To address these issues, we introduce Federated Averaging with Feature Normalization Update (FedFN), a straightforward learning method. We demonstrate the superior performance of FedFN through extensive experiments, even when applied to pretrained ResNet18. Subsequently, we confirm the applicability of FedFN to foundation models.
Authors: Tim Elsner, Julia Berger, Tong Wu, Victor Czech, Lin Gao, Leif Kobbelt
Seam carving is an image editing method that enable content-aware resizing, including operations like removing objects. However, the seam-finding strategy based on dynamic programming or graph-cut limits its applications to broader visual data formats and degrees of freedom for editing. Our observation is that describing the editing and retargeting of images more generally by a displacement field yields a generalisation of content-aware deformations. We propose to learn a deformation with a neural network that keeps the output plausible while trying to deform it only in places with low information content. This technique applies to different kinds of visual data, including images, 3D scenes given as neural radiance fields, or even polygon meshes. Experiments conducted on different visual data show that our method achieves better content-aware retargeting compared to previous methods.
Authors: Xiao Song, Jiafan Liu, Yun Li, Wenbin Lei, Ruxin Wang
Radiology Report Generation (RRG) draws attention as an interaction between vision and language fields. Previous works inherited the ideology of vision-to-language generation tasks,aiming to generate paragraphs with high consistency as reports. However, one unique characteristic of RRG, the independence between diseases, was neglected, leading to the injection of the spurious confounder, i.e., the disease co-occurrence. Unfortunately, this confounder confuses the process of report generation worse because of the biased RRG data distribution. In this paper, to rethink this issue thoroughly, we reason about its causes and effects from a novel perspective of statistics and causality, where the Joint Vision Coupling and the Conditional Sentence Coherence Coupling are two aspects prone to implicitly decrease the accuracy of reports. Then, a counterfactual augmentation strategy that contains the Counterfactual Sample Synthesis and the Counterfactual Report Reconstruction sub-methods is proposed to break these two aspects of spurious effects. Experimental results and further analyses on two widely used datasets justify our reasoning and proposed methods.
Authors: Yuxuan Zhou, Liangcai Gao, Zhi Tang, Baole Wei
Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR). Previous methods predominantly employ discriminative Convolutional Neural Networks (CNNs) augmented with diverse forms of text guidance to address this issue. Nevertheless, they remain deficient when confronted with severely blurred images, due to their insufficient generation capability when little structural or semantic information can be extracted from original images. Therefore, we introduce RGDiffSR, a Recognition-Guided Diffusion model for scene text image Super-Resolution, which exhibits great generative diversity and fidelity even in challenging scenarios. Moreover, we propose a Recognition-Guided Denoising Network, to guide the diffusion model generating LR-consistent results through succinct semantic guidance. Experiments on the TextZoom dataset demonstrate the superiority of RGDiffSR over prior state-of-the-art methods in both text recognition accuracy and image fidelity.
Authors: Ekin Yagis, Shahab Aslani, Yashvardhan Jain, Yang Zhou, Shahrokh Rahmani, Joseph Brunet, Alexandre Bellier, Christopher Werlein, Maximilian Ackermann, Danny Jonigk, Paul Tafforeau, Peter D Lee, Claire Walsh
Automated blood vessel segmentation is vital for biomedical imaging, as vessel changes indicate many pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. We present a thorough literature review, highlighting the state of machine learning techniques across diverse organs. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation in a new imaging modality, Hierarchical Phase Contrast Tomography (HiP CT). Introduced in 2020 at the European Synchrotron Radiation Facility, HiP CT enables 3D imaging of complete organs at an unprecedented resolution of ca. 20mm per voxel, with the capability for localized zooms in selected regions down to 1mm per voxel without sectioning. We have created a training dataset with double annotator validated vascular data from three kidneys imaged with HiP CT in the context of the Human Organ Atlas Project. Finally, utilising the nnU Net model, we conduct experiments to assess the models performance on both familiar and unseen samples, employing vessel specific metrics. Our results show that while segmentations yielded reasonably high scores such as clDice values ranging from 0.82 to 0.88, certain errors persisted. Large vessels that collapsed due to the lack of hydrostatic pressure (HiP CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors obstruct the understanding of the structures by interrupting vascular tree connectivity. Through our review and outputs, we aim to set a benchmark for subsequent model evaluations using various modalities, especially with the HiP CT imaging database.
Authors: Daniel Marczak, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski
In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, recent studies have highlighted the strengths of self-supervised continual representation learning. The improved transferability of representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In this work, we depart from this observation and reexamine the role of supervision in continual representation learning. We reckon that additional information, such as human annotations, should not deteriorate the quality of representations. Our findings show that supervised models when enhanced with a multi-layer perceptron head, can outperform self-supervised models in continual representation learning.
Authors: Jin Wang, Changlin Song
Artificial intelligence has made significant progress in the Close World problem, being able to accurately recognize old knowledge through training and classification. However, AI faces significant challenges in the Open World problem, as it involves a new and unknown exploration journey. AI is not inherently proactive in exploration, and its challenge lies in not knowing how to approach and adapt to the unknown world. How do humans acquire knowledge of the unknown world. Humans identify new knowledge through intrinsic cognition. In the process of recognizing new colors, the cognitive cues are different from known color features and involve hue, saturation, brightness, and other characteristics. When AI encounters objects with different features in the new world, it faces another challenge: where are the distinguishing features between influential features of new and old objects? AI often mistakes a new world's brown bear for a known dog because it has not learned the differences in feature distributions between knowledge systems. This is because things in the new and old worlds have different units and dimensions for their features. This paper proposes an open-world model and elemental feature system that focuses on fundamentally recognizing the distribution differences in objective features between the new and old worlds. The quantum tunneling effect of learning ability in the new and old worlds is realized through the tractive force of meta-characteristic. The outstanding performance of the model system in learning new knowledge (using pedestrian re-identification datasets as an example) demonstrates that AI has acquired the ability to recognize the new world with an accuracy of $96.71\%$ at most and has gained the capability to explore new knowledge, similar to humans.
Authors: Lamyanba Laishram, Muhammad Shaheryar, Jong Taek Lee, Soon Ki Jung
Caricature is an exaggerated form of artistic portraiture that accentuates unique yet subtle characteristics of human faces. Recently, advancements in deep end-to-end techniques have yielded encouraging outcomes in capturing both style and elevated exaggerations in creating face caricatures. Most of these approaches tend to produce cartoon-like results that could be more practical for real-world applications. In this study, we proposed a high-quality, unpaired face caricature method that is appropriate for use in the real world and uses computer vision techniques and GAN models. We attain the exaggeration of facial features and the stylization of appearance through a two-step process: Face caricature generation and face caricature projection. The face caricature generation step creates new caricature face datasets from real images and trains a generative model using the real and newly created caricature datasets. The Face caricature projection employs an encoder trained with real and caricature faces with the pretrained generator to project real and caricature faces. We perform an incremental facial exaggeration from the real image to the caricature faces using the encoder and generator's latent space. Our projection preserves the facial identity, attributes, and expressions from the input image. Also, it accounts for facial occlusions, such as reading glasses or sunglasses, to enhance the robustness of our model. Furthermore, we conducted a comprehensive comparison of our approach with various state-of-the-art face caricature methods, highlighting our process's distinctiveness and exceptional realism.
Authors: Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu
Classifying patterns of known classes and rejecting ambiguous and novel (also called as out-of-distribution (OOD)) inputs are involved in open world pattern recognition. Deep neural network models usually excel in closed-set classification while performing poorly in rejecting OOD. To tackle this problem, numerous methods have been designed to perform open set recognition (OSR) or OOD rejection/detection tasks. Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes. In this paper, we attempt to build a unified framework for building open set classifiers for both classification and OOD rejection. We formulate the open set recognition of $ K $-known-class as a $ (K + 1) $-class classification problem with model trained on known-class samples only. By decomposing the $ K $-class problem into $ K $ one-versus-all (OVA) binary classification tasks and binding some parameters, we show that combining the scores of OVA classifiers can give $ (K + 1) $-class posterior probabilities, which enables classification and OOD rejection in a unified framework. To maintain the closed-set classification accuracy of the OVA trained classifier, we propose a hybrid training strategy combining OVA loss and multi-class cross-entropy loss. We implement the OVA framework and hybrid training strategy on the recently proposed convolutional prototype network. Experiments on popular OSR and OOD detection datasets demonstrate that the proposed framework, using a single multi-class classifier, yields competitive performance in closed-set classification, OOD detection, and misclassification detection.
Authors: Xiuwen Wu, Rongjie Hu, Jie Liang, Yanming Wang, Bensheng Qiu, Xiaoxiao Wang
Eye-tracking research has proven valuable in understanding numerous cognitive functions. Recently, Frey et al. provided an exciting deep learning method for learning eye movements from fMRI data. However, it needed to co-register fMRI into standard space to obtain eyeballs masks, and thus required additional templates and was time consuming. To resolve this issue, in this paper, we propose a framework named MRGazer for predicting eye gaze points from fMRI in individual space. The MRGazer consisted of eyeballs extraction module and a residual network-based eye gaze prediction. Compared to the previous method, the proposed framework skips the fMRI co-registration step, simplifies the processing protocol and achieves end-to-end eye gaze regression. The proposed method achieved superior performance in a variety of eye movement tasks than the co-registration-based method, and delivered objective results within a shorter time (~ 0.02 Seconds for each volume) than prior method (~0.3 Seconds for each volume).
Authors: Lianne Feenstra, Stefan D.van der Stel, Marcos Da Silva Guimaraes, Theo J.M Ruers, Behdad Dashtbozorg
Validation of newly developed optical tissue sensing techniques for tumor detection during cancer surgery requires an accurate correlation with histological results. Additionally, such accurate correlation facilitates precise data labeling for developing high-performance machine-learning tissue classification models. In this paper, a newly developed Point Projection Mapping system will be introduced, which allows non-destructive tracking of the measurement locations on tissue specimens. Additionally, a framework for accurate registration, validation, and labeling with histopathology results is proposed and validated on a case study. The proposed framework provides a more robust and accurate method for tracking and validation of optical tissue sensing techniques, which saves time and resources compared to conventional techniques available.
Authors: Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam, Jaerin Lee, Kyoung Mu Lee
With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due to their training strategies using 3D scan dataset that is far from the real-world. To address such limitation, we propose LucidDreamer, a domain-free scene generation pipeline by fully leveraging the power of existing large-scale diffusion-based generative model. Our LucidDreamer has two alternate steps: Dreaming and Alignment. First, to generate multi-view consistent images from inputs, we set the point cloud as a geometrical guideline for each image generation. Specifically, we project a portion of point cloud to the desired view and provide the projection as a guidance for inpainting using the generative model. The inpainted images are lifted to 3D space with estimated depth maps, composing a new points. Second, to aggregate the new points into the 3D scene, we propose an aligning algorithm which harmoniously integrates the portions of newly generated 3D scenes. The finally obtained 3D scene serves as initial points for optimizing Gaussian splats. LucidDreamer produces Gaussian splats that are highly-detailed compared to the previous 3D scene generation methods, with no constraint on domain of the target scene.
Authors: Yuxin Du, Fan Bai, Tiejun Huang, Bo Zhao
Precise image segmentation provides clinical study with meaningful and well-structured information. Despite the remarkable progress achieved in medical image segmentation, there is still an absence of foundation segmentation model that can segment a wide range of anatomical categories with easy user interaction. In this paper, we propose a universal and interactive volumetric medical image segmentation model, named SegVol. By training on 90k unlabeled Computed Tomography (CT) volumes and 6k labeled CTs, this foundation model supports the segmentation of over 200 anatomical categories using semantic and spatial prompts. Extensive experiments verify that SegVol outperforms the state of the art by a large margin on multiple segmentation benchmarks. Notably, on three challenging lesion datasets, our method achieves around 20% higher Dice score than nnU-Net. The model and data are publicly available at: https://github.com/BAAI-DCAI/SegVol.
Authors: Jaeyoung Chung, Jeongtaek Oh, Kyoung Mu Lee
In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting. Representing a 3D scene by combining numerous Gaussian splats has yielded outstanding visual quality. However, it tends to overfit the training views when only a small number of images are available. To address this issue, we introduce a dense depth map as a geometry guide to mitigate overfitting. We obtained the depth map using a pre-trained monocular depth estimation model and aligning the scale and offset using sparse COLMAP feature points. The adjusted depth aids in the color-based optimization of 3D Gaussian splatting, mitigating floating artifacts, and ensuring adherence to geometric constraints. We verify the proposed method on the NeRF-LLFF dataset with varying numbers of few images. Our approach demonstrates robust geometry compared to the original method that relies solely on images.
Authors: Keyang Ye, Tianjia Shao, Kun Zhou
We present a novel animatable 3D Gaussian model for rendering high-fidelity free-view human motions in real time. Compared to existing NeRF-based methods, the model owns better capability in synthesizing high-frequency details without the jittering problem across video frames. The core of our model is a novel augmented 3D Gaussian representation, which attaches each Gaussian with a learnable code. The learnable code serves as a pose-dependent appearance embedding for refining the erroneous appearance caused by geometric transformation of Gaussians, based on which an appearance refinement model is learned to produce residual Gaussian properties to match the appearance in target pose. To force the Gaussians to learn the foreground human only without background interference, we further design a novel alpha loss to explicitly constrain the Gaussians within the human body. We also propose to jointly optimize the human joint parameters to improve the appearance accuracy. The animatable 3D Gaussian model can be learned with shallow MLPs, so new human motions can be synthesized in real time (66 fps on avarage). Experiments show that our model has superior performance over NeRF-based methods.
Authors: Yuxi Wang, Haibin Ling, Bingyao Huang
Full projector compensation is a practical task of projector-camera systems. It aims to find a projector input image, named compensation image, such that when projected it cancels the geometric and photometric distortions due to the physical environment and hardware. State-of-the-art methods use deep learning to address this problem and show promising performance for low-resolution setups. However, directly applying deep learning to high-resolution setups is impractical due to the long training time and high memory cost. To address this issue, this paper proposes a practical full compensation solution. Firstly, we design an attention-based grid refinement network to improve geometric correction quality. Secondly, we integrate a novel sampling scheme into an end-to-end compensation network to alleviate computation and introduce attention blocks to preserve key features. Finally, we construct a benchmark dataset for high-resolution projector full compensation. In experiments, our method demonstrates clear advantages in both efficiency and quality.
Authors: Shehan Munasinghe, Rusiru Thushara, Muhammad Maaz, Hanoona Abdul Rasheed, Salman Khan, Mubarak Shah, Fahad Khan
Extending image-based Large Multimodal Models (LMM) to videos is challenging due to the inherent complexity of video data. The recent approaches extending image-based LMM to videos either lack the grounding capabilities (e.g., VideoChat, Video-ChatGPT, Video-LLaMA) or do not utilize the audio-signals for better video understanding (e.g., Video-ChatGPT). Addressing these gaps, we propose Video-LLaVA, the first LMM with pixel-level grounding capability, integrating audio cues by transcribing them into text to enrich video-context understanding. Our framework uses an off-the-shelf tracker and a novel grounding module, enabling it to spatially and temporally localize objects in videos following user instructions. We evaluate Video-LLaVA using video-based generative and question-answering benchmarks and introduce new benchmarks specifically designed to measure prompt-based object grounding performance in videos. Further, we propose the use of Vicuna over GPT-3.5, as utilized in Video-ChatGPT, for video-based conversation benchmarking, ensuring reproducibility of results which is a concern with the proprietary nature of GPT-3.5. Our framework builds on SoTA image-based LLaVA model and extends its advantages to the video domain, delivering promising gains on video-based conversation and grounding tasks. Project Page: https://github.com/mbzuai-oryx/Video-LLaVA
Authors: Qinqing Zheng, Matt Le, Neta Shaul, Yaron Lipman, Aditya Grover, Ricky T. Q. Chen
Classifier-free guidance is a key component for improving the performance of conditional generative models for many downstream tasks. It drastically improves the quality of samples produced, but has so far only been used for diffusion models. Flow Matching (FM), an alternative simulation-free approach, trains Continuous Normalizing Flows (CNFs) based on regressing vector fields. It remains an open question whether classifier-free guidance can be performed for Flow Matching models, and to what extent does it improve performance. In this paper, we explore the usage of Guided Flows for a variety of downstream applications involving conditional image generation, speech synthesis, and reinforcement learning. In particular, we are the first to apply flow models to the offline reinforcement learning setting. We also show that Guided Flows significantly improves the sample quality in image generation and zero-shot text-to-speech synthesis, and can make use of drastically low amounts of computation without affecting the agent's overall performance.
Authors: Chao Fan, Jingzhe Ma, Dongyang Jin, Chuanfu Shen, Shiqi Yu
The choice of the representations is essential for deep gait recognition methods. The binary silhouettes and skeletal coordinates are two dominant representations in recent literature, achieving remarkable advances in many scenarios. However, inherent challenges remain, in which silhouettes are not always guaranteed in unconstrained scenes, and structural cues have not been fully utilized from skeletons. In this paper, we introduce a novel skeletal gait representation named Skeleton Map, together with SkeletonGait, a skeleton-based method to exploit structural information from human skeleton maps. Specifically, the skeleton map represents the coordinates of human joints as a heatmap with Gaussian approximation, exhibiting a silhouette-like image devoid of exact body structure. Beyond achieving state-of-the-art performances over five popular gait datasets, more importantly, SkeletonGait uncovers novel insights about how important structural features are in describing gait and when do they play a role. Furthermore, we propose a multi-branch architecture, named SkeletonGait++, to make use of complementary features from both skeletons and silhouettes. Experiments indicate that SkeletonGait++ outperforms existing state-of-the-art methods by a significant margin in various scenarios. For instance, it achieves an impressive rank-1 accuracy of over $85\%$ on the challenging GREW dataset. All the source code will be available at https://github.com/ShiqiYu/OpenGait.
Authors: Shahinur Alam, Jinsoo Uh, Alexander Dresner, Chia-ho Hua, Khaled Khairy
Magnetic Resonance Imaging (MRI) is a non-invasive diagnostic and radiotherapy (RT) planning tool, offering detailed insights into the anatomy of the human body. The extensive scan time is stressful for patients, who must remain motionless in a prolonged imaging procedure that prioritizes reduction of imaging artifacts. This is challenging for pediatric patients who may require measures for managing voluntary motions such as anesthesia. Several computational approaches reduce scan time (fast MRI), by recording fewer measurements and digitally recovering full information via post-acquisition reconstruction. However, most fast MRI approaches were developed for diagnostic imaging, without addressing reconstruction challenges specific to RT planning. In this work, we developed a deep learning-based method (DeepMRIRec) for MRI reconstruction from undersampled data acquired with RT-specific receiver coil arrangements. We evaluated our method against fully sampled data of T1-weighted MR images acquired from 73 children with brain tumors/surgical beds using loop and posterior coils (12 channels), with and without applying virtual compression of coil elements. DeepMRIRec reduced scanning time by a factor of four producing a structural similarity score surpassing the evaluated state-of-the-art method (0.960 vs 0.896), thereby demonstrating its potential for accelerating MRI scanning for RT planning.
Authors: Amir Hamza, Badis Lekouaghet, Yassine Himeur
Timely identification and treatment of rapidly progressing skin cancers can significantly contribute to the preservation of patients' health and well-being. Dermoscopy, a dependable and accessible tool, plays a pivotal role in the initial stages of skin cancer detection. Consequently, the effective processing of digital dermoscopy images holds significant importance in elevating the accuracy of skin cancer diagnoses. Multilevel thresholding is a key tool in medical imaging that extracts objects within the image to facilitate its analysis. In this paper, an enhanced version of the Mud Ring Algorithm hybridized with the Whale Optimization Algorithm, named WMRA, is proposed. The proposed approach utilizes bubble-net attack and mud ring strategy to overcome stagnation in local optima and obtain optimal thresholds. The experimental results show that WMRA is powerful against a cluster of recent methods in terms of fitness, Peak Signal to Noise Ratio (PSNR), and Mean Square Error (MSE).
Authors: Archit Rathod, Veer Pariawala, Mokshit Surana, Kumkum Saxena
Natural disasters act as a serious threat globally, requiring effective and efficient disaster management and recovery. This paper focuses on classifying natural disaster images using Convolutional Neural Networks (CNNs). Multiple CNN architectures were built and trained on a dataset containing images of earthquakes, floods, wildfires, and volcanoes. A stacked CNN ensemble approach proved to be the most effective, achieving 95% accuracy and an F1 score going up to 0.96 for individual classes. Tuning hyperparameters of individual models for optimization was critical to maximize the models' performance. The stacking of CNNs with XGBoost acting as the meta-model utilizes the strengths of the CNN and ResNet models to improve the overall accuracy of the classification. Results obtained from the models illustrated the potency of CNN-based models for automated disaster image classification. This lays the foundation for expanding these techniques to build robust systems for disaster response, damage assessment, and recovery management.
Authors: Yangyang Xu, Shengfeng He, Wenqi Shao, Kwan-Yee K. Wong, Yu Qiao, Ping Luo
In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose guidance for alpha matte prediction, our approach treats image matting as a sequential refinement learning process. This process begins with the addition of noise to trimaps and iteratively denoises them using a pre-trained diffusion model, which incrementally guides the prediction towards a clean alpha matte. The key innovation of our framework is a correction module that adjusts the output at each denoising step, ensuring that the final result is consistent with the input image's structures. We also introduce the Alpha Reliability Propagation, a novel technique designed to maximize the utility of available guidance by selectively enhancing the trimap regions with confident alpha information, thus simplifying the correction task. To train the correction module, we devise specialized loss functions that target the accuracy of the alpha matte's edges and the consistency of its opaque and transparent regions. We evaluate our model across several image matting benchmarks, and the results indicate that DiffusionMat consistently outperforms existing methods. Project page at~\url{https://cnnlstm.github.io/DiffusionMat
Authors: Farnaz Khun Jush, Tuan Truong, Steffen Vogler, Matthias Lenga
A wide range of imaging techniques and data formats available for medical images make accurate retrieval from image databases challenging.
Efficient retrieval systems are crucial in advancing medical research, enabling large-scale studies and innovative diagnostic tools. Thus, addressing the challenges of medical image retrieval is essential for the continued enhancement of healthcare and research.
In this study, we evaluated the feasibility of employing four state-of-the-art pretrained models for medical image retrieval at modality, body region, and organ levels and compared the results of two similarity indexing approaches. Since the employed networks take 2D images, we analyzed the impacts of weighting and sampling strategies to incorporate 3D information during retrieval of 3D volumes. We showed that medical image retrieval is feasible using pretrained networks without any additional training or fine-tuning steps. Using pretrained embeddings, we achieved a recall of 1 for various tasks at modality, body region, and organ level.
Authors: Fan Jia, Weixin Mao, Yingfei Liu, Yucheng Zhao, Yuqing Wen, Chi Zhang, Xiangyu Zhang, Tiancai Wang
Typically, autonomous driving adopts a modular design, which divides the full stack into perception, prediction, planning and control parts. Though interpretable, such modular design tends to introduce a substantial amount of redundancy. Recently, multimodal large language models (MLLM) and diffusion techniques have demonstrated their superior performance on comprehension and generation ability. In this paper, we first introduce the concept of interleaved vision-action pair, which unifies the format of visual features and control signals. Based on the vision-action pairs, we construct a general world model based on MLLM and diffusion model for autonomous driving, termed ADriver-I. It takes the vision-action pairs as inputs and autoregressively predicts the control signal of the current frame. The generated control signals together with the historical vision-action pairs are further conditioned to predict the future frames. With the predicted next frame, ADriver-I performs further control signal prediction. Such a process can be repeated infinite times, ADriver-I achieves autonomous driving in the world created by itself. Extensive experiments are conducted on nuScenes and our large-scale private datasets. ADriver-I shows impressive performance compared to several constructed baselines. We hope our ADriver-I can provide some new insights for future autonomous driving and embodied intelligence.
Authors: Youssef Elmir, Sid Ahmed Laouar, Larbi Hamdaoui
Traditional surveillance systems rely on human attention, limiting their effectiveness. This study employs convolutional neural networks and transfer learning to develop a real-time computer vision system for automatic handgun detection. Comprehensive analysis of online handgun detection methods is conducted, emphasizing reducing false positives and learning time. Transfer learning is demonstrated as an effective approach. Despite technical challenges, the proposed system achieves a precision rate of 84.74%, demonstrating promising performance comparable to related works, enabling faster learning and accurate automatic handgun detection for enhanced security. This research advances security measures by reducing human monitoring dependence, showcasing the potential of transfer learning-based approaches for efficient and reliable handgun detection.
Authors: Junhao Chen, Peng Rong, Jingbo Sun, Chao Li, Xiang Li, Hongwu Lv
Image style transfer occupies an important place in both computer graphics and computer vision. However, most current methods require reference to stylized images and cannot individually stylize specific objects. To overcome this limitation, we propose the "Soulstyler" framework, which allows users to guide the stylization of specific objects in an image through simple textual descriptions. We introduce a large language model to parse the text and identify stylization goals and specific styles. Combined with a CLIP-based semantic visual embedding encoder, the model understands and matches text and image content. We also introduce a novel localized text-image block matching loss that ensures that style transfer is performed only on specified target objects, while non-target regions remain in their original style. Experimental results demonstrate that our model is able to accurately perform style transfer on target objects according to textual descriptions without affecting the style of background regions. Our code will be available at https://github.com/yisuanwang/Soulstyler.
Authors: Katja Schwarz, Seung Wook Kim, Jun Gao, Sanja Fidler, Andreas Geiger, Karsten Kreis
Modern learning-based approaches to 3D-aware image synthesis achieve high photorealism and 3D-consistent viewpoint changes for the generated images. Existing approaches represent instances in a shared canonical space. However, for in-the-wild datasets a shared canonical system can be difficult to define or might not even exist. In this work, we instead model instances in view space, alleviating the need for posed images and learned camera distributions. We find that in this setting, existing GAN-based methods are prone to generating flat geometry and struggle with distribution coverage. We hence propose WildFusion, a new approach to 3D-aware image synthesis based on latent diffusion models (LDMs). We first train an autoencoder that infers a compressed latent representation, which additionally captures the images' underlying 3D structure and enables not only reconstruction but also novel view synthesis. To learn a faithful 3D representation, we leverage cues from monocular depth prediction. Then, we train a diffusion model in the 3D-aware latent space, thereby enabling synthesis of high-quality 3D-consistent image samples, outperforming recent state-of-the-art GAN-based methods. Importantly, our 3D-aware LDM is trained without any direct supervision from multiview images or 3D geometry and does not require posed images or learned pose or camera distributions. It directly learns a 3D representation without relying on canonical camera coordinates. This opens up promising research avenues for scalable 3D-aware image synthesis and 3D content creation from in-the-wild image data. See https://katjaschwarz.github.io/wildfusion for videos of our 3D results.
Authors: Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Jiashi Feng, Mike Zheng Shou
Recent advances in 3D-aware GAN models have enabled the generation of realistic and controllable human body images. However, existing methods focus on the control of major body joints, neglecting the manipulation of expressive attributes, such as facial expressions, jaw poses, hand poses, and so on. In this work, we present XAGen, the first 3D generative model for human avatars capable of expressive control over body, face, and hands. To enhance the fidelity of small-scale regions like face and hands, we devise a multi-scale and multi-part 3D representation that models fine details. Based on this representation, we propose a multi-part rendering technique that disentangles the synthesis of body, face, and hands to ease model training and enhance geometric quality. Furthermore, we design multi-part discriminators that evaluate the quality of the generated avatars with respect to their appearance and fine-grained control capabilities. Experiments show that XAGen surpasses state-of-the-art methods in terms of realism, diversity, and expressive control abilities. Code and data will be made available at https://showlab.github.io/xagen.
Authors: Qing Jiang, Feng Li, Tianhe Ren, Shilong Liu, Zhaoyang Zeng, Kent Yu, Lei Zhang
We introduce T-Rex, an interactive object counting model designed to first detect and then count any objects. We formulate object counting as an open-set object detection task with the integration of visual prompts. Users can specify the objects of interest by marking points or boxes on a reference image, and T-Rex then detects all objects with a similar pattern. Guided by the visual feedback from T-Rex, users can also interactively refine the counting results by prompting on missing or falsely-detected objects. T-Rex has achieved state-of-the-art performance on several class-agnostic counting benchmarks. To further exploit its potential, we established a new counting benchmark encompassing diverse scenarios and challenges. Both quantitative and qualitative results show that T-Rex possesses exceptional zero-shot counting capabilities. We also present various practical application scenarios for T-Rex, illustrating its potential in the realm of visual prompting.
Authors: Viraj Shah, Nataniel Ruiz, Forrester Cole, Erika Lu, Svetlana Lazebnik, Yuanzhen Li, Varun Jampani
Methods for finetuning generative models for concept-driven personalization generally achieve strong results for subject-driven or style-driven generation. Recently, low-rank adaptations (LoRA) have been proposed as a parameter-efficient way of achieving concept-driven personalization. While recent work explores the combination of separate LoRAs to achieve joint generation of learned styles and subjects, existing techniques do not reliably address the problem; they often compromise either subject fidelity or style fidelity. We propose ZipLoRA, a method to cheaply and effectively merge independently trained style and subject LoRAs in order to achieve generation of any user-provided subject in any user-provided style. Experiments on a wide range of subject and style combinations show that ZipLoRA can generate compelling results with meaningful improvements over baselines in subject and style fidelity while preserving the ability to recontextualize. Project page: https://ziplora.github.io
Authors: Feng Li, Qing Jiang, Hao Zhang, Tianhe Ren, Shilong Liu, Xueyan Zou, Huaizhe Xu, Hongyang Li, Chunyuan Li, Jianwei Yang, Lei Zhang, Jianfeng Gao
In-context prompting in large language models (LLMs) has become a prevalent approach to improve zero-shot capabilities, but this idea is less explored in the vision domain. Existing visual prompting methods focus on referring segmentation to segment the most relevant object, falling short of addressing many generic vision tasks like open-set segmentation and detection. In this paper, we introduce a universal visual in-context prompting framework for both tasks. In particular, we build on top of an encoder-decoder architecture, and develop a versatile prompt encoder to support a variety of prompts like strokes, boxes, and points. We further enhance it to take an arbitrary number of reference image segments as the context. Our extensive explorations show that the proposed visual in-context prompting elicits extraordinary referring and generic segmentation capabilities to refer and detect, yielding competitive performance to close-set in-domain datasets and showing promising results on many open-set segmentation datasets. By joint training on COCO and SA-1B, our model achieves $57.7$ PQ on COCO and $23.2$ PQ on ADE20K. Code will be available at https://github.com/UX-Decoder/DINOv.
Authors: Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi, Kiyoharu Aizawa
Content-aware graphic layout generation aims to automatically arrange visual elements along with a given content, such as an e-commerce product image. In this paper, we argue that the current layout generation approaches suffer from the limited training data for the high-dimensional layout structure. We show that a simple retrieval augmentation can significantly improve the generation quality. Our model, which is named Retrieval-Augmented Layout Transformer (RALF), retrieves nearest neighbor layout examples based on an input image and feeds these results into an autoregressive generator. Our model can apply retrieval augmentation to various controllable generation tasks and yield high-quality layouts within a unified architecture. Our extensive experiments show that RALF successfully generates content-aware layouts in both constrained and unconstrained settings and significantly outperforms the baselines.
Authors: Kevin Strauss, Artem Savkin, Federico Tombari
Synthetic data became already an essential component of machine learning-based perception in the field of autonomous driving. Yet it still cannot replace real data completely due to the sim2real domain shift. In this work, we propose a method that leverages the advantages of the augmentation process and adversarial training to synthesize realistic data for the pedestrian recognition task. Our approach utilizes an attention mechanism driven by an adversarial loss to learn domain discrepancies and improve sim2real adaptation. Our experiments confirm that the proposed adaptation method is robust to such discrepancies and reveals both visual realism and semantic consistency. Furthermore, we evaluate our data generation pipeline on the task of pedestrian recognition and demonstrate that generated data resemble properties of the real domain.
Authors: Jiaqi Gao, Zhizhong Huang, Yiming Lei, Hongming Shan, James Z. Wang, Fei-Yue Wang, Junping Zhang
Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a large quantity of costly and time-intensive pixel-level annotations for training supervision. One way to mitigate the intensive labeling effort and improve counting accuracy is to leverage large amounts of unlabeled images. This is attributed to the inherent self-structural information and rank consistency within a single image, offering additional qualitative relation supervision during training. Contrary to earlier methods that utilized the rank relations at the original image level, we explore such rank-consistency relation within the latent feature spaces. This approach enables the incorporation of numerous pyramid partial orders, strengthening the model representation capability. A notable advantage is that it can also increase the utilization ratio of unlabeled samples. Specifically, we propose a Deep Rank-consistEnt pyrAmid Model (DREAM), which makes full use of rank consistency across coarse-to-fine pyramid features in latent spaces for enhanced crowd counting with massive unlabeled images. In addition, we have collected a new unlabeled crowd counting dataset, FUDAN-UCC, comprising 4,000 images for training purposes. Extensive experiments on four benchmark datasets, namely UCF-QNRF, ShanghaiTech PartA and PartB, and UCF-CC-50, show the effectiveness of our method compared with previous semi-supervised methods. The codes are available at https://github.com/bridgeqiqi/DREAM.
Authors: H. Linander, O. Balabanov, H. Yang, B. Mehlig
Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output. By looking at these posterior distributions, one can separate the origin of uncertainty into aleatoric and epistemic contributions. One goal of uncertainty quantification is to inform on prediction accuracy. Here we show that prediction accuracy depends on both epistemic and aleatoric uncertainty in an intricate fashion that cannot be understood in terms of marginalized uncertainty distributions alone. How the accuracy relates to epistemic and aleatoric uncertainties depends not only on the model architecture, but also on the properties of the dataset. We discuss the significance of these results for active learning and introduce a novel acquisition function that outperforms common uncertainty-based methods. To arrive at our results, we approximated the posteriors using deep ensembles, for fully-connected, convolutional and attention-based neural networks.
Authors: Usma Niyaz, Abhishek Singh Sambyal, Deepti R. Bathula
Learning style refers to a type of training mechanism adopted by an individual to gain new knowledge. As suggested by the VARK model, humans have different learning preferences, like Visual (V), Auditory (A), Read/Write (R), and Kinesthetic (K), for acquiring and effectively processing information. Our work endeavors to leverage this concept of knowledge diversification to improve the performance of model compression techniques like Knowledge Distillation (KD) and Mutual Learning (ML). Consequently, we use a single-teacher and two-student network in a unified framework that not only allows for the transfer of knowledge from teacher to students (KD) but also encourages collaborative learning between students (ML). Unlike the conventional approach, where the teacher shares the same knowledge in the form of predictions or feature representations with the student network, our proposed approach employs a more diversified strategy by training one student with predictions and the other with feature maps from the teacher. We further extend this knowledge diversification by facilitating the exchange of predictions and feature maps between the two student networks, enriching their learning experiences. We have conducted comprehensive experiments with three benchmark datasets for both classification and segmentation tasks using two different network architecture combinations. These experimental results demonstrate that knowledge diversification in a combined KD and ML framework outperforms conventional KD or ML techniques (with similar network configuration) that only use predictions with an average improvement of 2%. Furthermore, consistent improvement in performance across different tasks, with various network architectures, and over state-of-the-art techniques establishes the robustness and generalizability of the proposed model
Authors: Taehoon Kim, Bohyung Han
We propose a novel domain generalization technique, referred to as Randomized Adversarial Style Perturbation (RASP), which is motivated by the observation that the characteristics of each domain are captured by the feature statistics corresponding to style. The proposed algorithm perturbs the style of a feature in an adversarial direction towards a randomly selected class, and makes the model learn against being misled by the unexpected styles observed in unseen target domains. While RASP is effective to handle domain shifts, its naive integration into the training procedure might degrade the capability of learning knowledge from source domains because it has no restriction on the perturbations of representations. This challenge is alleviated by Normalized Feature Mixup (NFM), which facilitates the learning of the original features while achieving robustness to perturbed representations via their mixup during training. We evaluate the proposed algorithm via extensive experiments on various benchmarks and show that our approach improves domain generalization performance, especially in large-scale benchmarks.
Authors: Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim
We propose LASER, a neuro-symbolic approach to learn semantic video representations that capture rich spatial and temporal properties in video data by leveraging high-level logic specifications. In particular, we formulate the problem in terms of alignment between raw videos and spatio-temporal logic specifications. The alignment algorithm leverages a differentiable symbolic reasoner and a combination of contrastive, temporal, and semantics losses. It effectively and efficiently trains low-level perception models to extract fine-grained video representation in the form of a spatio-temporal scene graph that conforms to the desired high-level specification. In doing so, we explore a novel methodology that weakly supervises the learning of video semantic representations through logic specifications. We evaluate our method on two datasets with rich spatial and temporal specifications: 20BN-Something-Something and MUGEN. We demonstrate that our method learns better fine-grained video semantics than existing baselines.
Authors: Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu
Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and large CFG weights. In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i.e., $7.5$). We further present various improvements in the design space for text-to-3D such as distillation time schedule and density initialization, which are orthogonal to the distillation algorithm yet not well explored. Our overall approach, dubbed ProlificDreamer, can generate high rendering resolution (i.e., $512\times512$) and high-fidelity NeRF with rich structure and complex effects (e.g., smoke and drops). Further, initialized from NeRF, meshes fine-tuned by VSD are meticulously detailed and photo-realistic. Project page and codes: https://ml.cs.tsinghua.edu.cn/prolificdreamer/
Authors: Kaleab A. Kinfu, Rene Vidal
While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance. However, the quadratic computational complexity of ViTs has limited their applicability for processing high-resolution images. In this paper, we propose three methods for reducing ViT's computational complexity, which are based on selecting and processing a small number of most informative patches while disregarding others. The first two methods leverage a lightweight pose estimation network to guide the patch selection process, while the third method utilizes a set of learnable joint tokens to ensure that the selected patches contain the most important information about body joints. Experiments across six benchmarks show that our proposed methods achieve a significant reduction in computational complexity, ranging from 30% to 44%, with only a minimal drop in accuracy between 0% and 3.5%.
Authors: Qimin Chen, Zhiqin Chen, Hang Zhou, Hao Zhang
We present ShaDDR, an example-based deep generative neural network which produces a high-resolution textured 3D shape through geometry detailization and conditional texture generation applied to an input coarse voxel shape. Trained on a small set of detailed and textured exemplar shapes, our method learns to detailize the geometry via multi-resolution voxel upsampling and generate textures on voxel surfaces via differentiable rendering against exemplar texture images from a few views. The generation is interactive, taking less than 1 second to produce a 3D model with voxel resolutions up to 512^3. The generated shape preserves the overall structure of the input coarse voxel model, while the style of the generated geometric details and textures can be manipulated through learned latent codes. In the experiments, we show that our method can generate higher-resolution shapes with plausible and improved geometric details and clean textures compared to prior works. Furthermore, we showcase the ability of our method to learn geometric details and textures from shapes reconstructed from real-world photos. In addition, we have developed an interactive modeling application to demonstrate the generalizability of our method to various user inputs and the controllability it offers, allowing users to interactively sculpt a coarse voxel shape to define the overall structure of the detailized 3D shape. Code and data are available at https://github.com/qiminchen/ShaDDR.
Authors: Shaoting Zhang, Dimitris Metaxas
This article discusses the opportunities, applications and future directions of large-scale pre-trained models, i.e., foundation models, for analyzing medical images. Medical foundation models have immense potential in solving a wide range of downstream tasks, as they can help to accelerate the development of accurate and robust models, reduce the large amounts of required labeled data, preserve the privacy and confidentiality of patient data. Specifically, we illustrate the "spectrum" of medical foundation models, ranging from general vision models, modality-specific models, to organ/task-specific models, highlighting their challenges, opportunities and applications. We also discuss how foundation models can be leveraged in downstream medical tasks to enhance the accuracy and efficiency of medical image analysis, leading to more precise diagnosis and treatment decisions.
The tomato is one of the most important fruits on earth. It plays an important and useful role in the agricultural production of any country. This research propose a novel smart technique for early detection of late blight diseases in tomatoes. This work improve the dataset with an increase in images from the field (the Plant Village dataset) and proposed a hybrid algorithm composed of support vector machines (SVM) and histogram-oriented gradients (HOG) for real-time detection of late blight tomato disease. To propose a HOG-based SVM model for early detection of late blight tomato leaf disease. To check the performance of the proposed model in terms of MSE, accuracy, precision, and recall as compared to Decision Tree and KNN. The integration of advanced technology in agriculture has the potential to revolutionize the industry, making it more efficient, sustainable, and profitable. This research work on the early detection of tomato diseases contributes to the growing importance of smart farming, the need for climate-smart agriculture, the rising need to more efficiently utilize natural resources, and the demand for higher crop yields. The proposed hybrid algorithm of SVM and HOG has significant potential for the early detection of late blight disease in tomato plants. The performance of the proposed model against decision tree and KNN algorithms and the results may assist in selecting the best algorithm for future applications. The research work can help farmers make data-driven decisions to optimize crop yield and quality while also reducing the environmental impact of farming practices.
Authors: Haoyi Jiang, Tianheng Cheng, Naiyu Gao, Haoyang Zhang, Tianwei Lin, Wenyu Liu, Xinggang Wang
`3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal undertaking in autonomous driving, aiming to predict voxel occupancy within volumetric scenes. However, prevailing methodologies primarily focus on voxel-wise feature aggregation, while neglecting instance semantics and scene context. In this paper, we present a novel paradigm termed Symphonies (Scene-from-Insts), that delves into the integration of instance queries to orchestrate 2D-to-3D reconstruction and 3D scene modeling. Leveraging our proposed Serial Instance-Propagated Attentions, Symphonies dynamically encodes instance-centric semantics, facilitating intricate interactions between image-based and volumetric domains. Simultaneously, Symphonies enables holistic scene comprehension by capturing context through the efficient fusion of instance queries, alleviating geometric ambiguity such as occlusion and perspective errors through contextual scene reasoning. Experimental results demonstrate that Symphonies achieves state-of-the-art performance on challenging benchmarks SemanticKITTI and SSCBench-KITTI-360, yielding remarkable mIoU scores of 15.04 and 18.58, respectively. These results showcase the paradigm's promising advancements. The code is available at https://github.com/hustvl/Symphonies.
Authors: Mozhgan Pourkeshavarz, Mohammad Sabokrou, Amir Rasouli
In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor attack against trajectory prediction models as a means of studying their potential vulnerabilities. Our attack affects the victim at training time via naturalistic, hence stealthy, poisoned samples crafted using a novel two-step approach. First, the triggers are crafted by perturbing the trajectory of attacking vehicle and then disguised by transforming the scene using a bi-level optimization technique. The proposed attack does not depend on a particular model architecture and operates in a black-box manner, thus can be effective without any knowledge of the victim model. We conduct extensive empirical studies using state-of-the-art prediction models on two benchmark datasets using metrics customized for trajectory prediction. We show that the proposed attack is highly effective, as it can significantly hinder the performance of prediction models, unnoticeable by the victims, and efficient as it forces the victim to generate malicious behavior even under constrained conditions. Via ablative studies, we analyze the impact of different attack design choices followed by an evaluation of existing defence mechanisms against the proposed attack.
Authors: Federico Rollo, Gennaro Raiola, Andrea Zunino, Nikolaos Tsagarakis, Arash Ajoudani
Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be able to comprehend the contextual information of its surroundings. This work focuses on classifying and localising objects within a map, which is under construction (SLAM) or already built. To further explore this direction, we propose a framework that can autonomously detect and localize predefined objects in a known environment using a multi-modal sensor fusion approach (combining RGB and depth data from an RGB-D camera and a lidar). The framework consists of three key elements: understanding the environment through RGB data, estimating depth through multi-modal sensor fusion, and managing artifacts (i.e., filtering and stabilizing measurements). The experiments show that the proposed framework can accurately detect 98% of the objects in the real sample environment, without post-processing, while 85% and 80% of the objects were mapped using the single RGBD camera or RGB + lidar setup respectively. The comparison with single-sensor (camera or lidar) experiments is performed to show that sensor fusion allows the robot to accurately detect near and far obstacles, which would have been noisy or imprecise in a purely visual or laser-based approach.
Authors: Wenbo Hu, Yifan Xu, Yi Li, Weiyue Li, Zeyuan Chen, Zhuowen Tu
Vision Language Models (VLMs), which extend Large Language Models (LLM) by incorporating visual understanding capability, have demonstrated significant advancements in addressing open-ended visual question-answering (VQA) tasks. However, these models cannot accurately interpret images infused with text, a common occurrence in real-world scenarios. Standard procedures for extracting information from images often involve learning a fixed set of query embeddings. These embeddings are designed to encapsulate image contexts and are later used as soft prompt inputs in LLMs. Yet, this process is limited to the token count, potentially curtailing the recognition of scenes with text-rich context. To improve upon them, the present study introduces BLIVA: an augmented version of InstructBLIP with Visual Assistant. BLIVA incorporates the query embeddings from InstructBLIP and also directly projects encoded patch embeddings into the LLM, a technique inspired by LLaVA. This approach assists the model to capture intricate details potentially missed during the query decoding process. Empirical evidence demonstrates that our model, BLIVA, significantly enhances performance in processing text-rich VQA benchmarks (up to 17.76% in OCR-VQA benchmark) and in undertaking general (not particularly text-rich) VQA benchmarks (up to 7.9% in Visual Spatial Reasoning benchmark), comparing to our baseline InstructBLIP. BLIVA demonstrates significant capability in decoding real-world images, irrespective of text presence. To demonstrate the broad industry applications enabled by BLIVA, we evaluate the model using a new dataset comprising YouTube thumbnails paired with question-answer sets across 11 diverse categories. For researchers interested in further exploration, our code and models are freely accessible at https://github.com/mlpc-ucsd/BLIVA.
Authors: Adrian Cosma, Emilian Radoi
Psychological trait estimation from external factors such as movement and appearance is a challenging and long-standing problem in psychology, and is principally based on the psychological theory of embodiment. To date, attempts to tackle this problem have utilized private small-scale datasets with intrusive body-attached sensors. Potential applications of an automated system for psychological trait estimation include estimation of occupational fatigue and psychology, and marketing and advertisement. In this work, we propose PsyMo (Psychological traits from Motion), a novel, multi-purpose and multi-modal dataset for exploring psychological cues manifested in walking patterns. We gathered walking sequences from 312 subjects in 7 different walking variations and 6 camera angles. In conjunction with walking sequences, participants filled in 6 psychological questionnaires, totalling 17 psychometric attributes related to personality, self-esteem, fatigue, aggressiveness and mental health. We propose two evaluation protocols for psychological trait estimation. Alongside the estimation of self-reported psychological traits from gait, the dataset can be used as a drop-in replacement to benchmark methods for gait recognition. We anonymize all cues related to the identity of the subjects and publicly release only silhouettes, 2D / 3D human skeletons and 3D SMPL human meshes.
Authors: Milad Ramezani, Liang Wang, Joshua Knights, Zhibin Li, Pauline Pounds, Peyman Moghadam
This paper proposes a pose-graph attentional graph neural network, called P-GAT, which compares (key)nodes between sequential and non-sequential sub-graphs for place recognition tasks as opposed to a common frame-to-frame retrieval problem formulation currently implemented in SOTA place recognition methods. P-GAT uses the maximum spatial and temporal information between neighbour cloud descriptors -- generated by an existing encoder -- utilising the concept of pose-graph SLAM. Leveraging intra- and inter-attention and graph neural network, P-GAT relates point clouds captured in nearby locations in Euclidean space and their embeddings in feature space. Experimental results on the large-scale publically available datasets demonstrate the effectiveness of our approach in scenes lacking distinct features and when training and testing environments have different distributions (domain adaptation). Further, an exhaustive comparison with the state-of-the-art shows improvements in performance gains. Code is available at https://github.com/csiro-robotics/P-GAT.
Authors: Manogna Sreenivas, Goirik Chakrabarty, Soma Biswas
Test Time Adaptation (TTA) is a pivotal concept in machine learning, enabling models to perform well in real-world scenarios, where test data distribution differs from training. In this work, we propose a novel approach called pseudo Source guided Target Clustering (pSTarC) addressing the relatively unexplored area of TTA under real-world domain shifts. This method draws inspiration from target clustering techniques and exploits the source classifier for generating pseudo-source samples. The test samples are strategically aligned with these pseudo-source samples, facilitating their clustering and thereby enhancing TTA performance. pSTarC operates solely within the fully test-time adaptation protocol, removing the need for actual source data. Experimental validation on a variety of domain shift datasets, namely VisDA, Office-Home, DomainNet-126, CIFAR-100C verifies pSTarC's effectiveness. This method exhibits significant improvements in prediction accuracy along with efficient computational requirements. Furthermore, we also demonstrate the universality of the pSTarC framework by showing its effectiveness for the continuous TTA framework. The source code for our method is available at https://manogna-s.github.io/pstarc
Authors: Yuxiang Yang, Yingqi Deng, Jing Zhang, Jiahao Nie, Zheng-Jun Zha
3D Single Object Tracking (SOT) is a fundamental task of computer vision, proving essential for applications like autonomous driving. It remains challenging to localize the target from surroundings due to appearance variations, distractors, and the high sparsity of point clouds. The spatial information indicating objects' spatial adjacency across consecutive frames is crucial for effective object tracking. However, existing trackers typically employ point-wise representation with irregular formats, leading to insufficient use of this important spatial knowledge. As a result, these trackers usually require elaborate designs and solving multiple subtasks. In this paper, we propose BEVTrack, a simple yet effective baseline that performs tracking in Bird's-Eye View (BEV). This representation greatly retains spatial information owing to its ordered structure and inherently encodes the implicit motion relations of the target as well as distractors. To achieve accurate regression for targets with diverse attributes (\textit{e.g.}, sizes and motion patterns), BEVTrack constructs the likelihood function with the learned underlying distributions adapted to different targets, rather than making a fixed Laplace or Gaussian assumption as in previous works. This provides valuable priors for tracking and thus further boosts performance. While only using a single regression loss with a plain convolutional architecture, BEVTrack achieves state-of-the-art performance on three large-scale datasets, KITTI, NuScenes, and Waymo Open Dataset while maintaining a high inference speed of about 200 FPS. The code will be released at https://github.com/xmm-prio/BEVTrack.
Authors: Yiqian Yang, Zhengqiao Zhao, Qian Wang, Yan Yang, Jingdong Chen
Existing approaches to modeling associations between visual stimuli and brain responses are facing difficulties in handling between-subject variance and model generalization. Inspired by the recent progress in modeling speech-brain response, we propose in this work a "match-vs-mismatch" deep learning model to classify whether a video clip induces excitatory responses in recorded EEG signals and learn associations between the visual content and corresponding neural recordings. Using an exclusive experimental dataset, we demonstrate that the proposed model is able to achieve the highest accuracy on unseen subjects as compared to other baseline models. Furthermore, we analyze the inter-subject noise using a subject-level silhouette score in the embedding space and show that the developed model is able to mitigate inter-subject noise and significantly reduce the silhouette score. Moreover, we examine the Grad-CAM activation score and show that the brain regions associated with language processing contribute most to the model predictions, followed by regions associated with visual processing. These results have the potential to facilitate the development of neural recording-based video reconstruction and its related applications.
Authors: Jinfeng Liu, Lingtong Kong, Jie Yang, Wei Liu
Depth estimation plays an important role in the robotic perception system. Self-supervised monocular paradigm has gained significant attention since it can free training from the reliance on depth annotations. Despite recent advancements, existing self-supervised methods still underutilize the available training data, limiting their generalization ability. In this paper, we take two data augmentation techniques, namely Resizing-Cropping and Splitting-Permuting, to fully exploit the potential of training datasets. Specifically, the original image and the generated two augmented images are fed into the training pipeline simultaneously and we leverage them to conduct self-distillation. Additionally, we introduce the detail-enhanced DepthNet with an extra full-scale branch in the encoder and a grid decoder to enhance the restoration of fine details in depth maps. Experimental results demonstrate our method can achieve state-of-the-art performance on the KITTI benchmark, with both raw ground truth and improved ground truth. Moreover, our models also show superior generalization performance when transferring to Make3D and NYUv2 datasets. Our codes are available at https://github.com/Sauf4896/BDEdepth.
Authors: Ruian He, Zhen Xing, Weimin Tan, Bo Yan
Unsupervised learning of facial representations has gained increasing attention for face understanding ability without heavily relying on large-scale annotated datasets. However, it remains unsolved due to the coupling of facial identities, expressions, and external factors like pose and light. Prior methods primarily focus on 2D factors and pixel-level consistency, leading to incomplete disentangling and suboptimal performance in downstream tasks. In this paper, we propose LatentFace, a novel unsupervised disentangling framework for facial expression and identity representation. We suggest the disentangling problem should be performed in latent space and propose the solution using a 3D-aware latent diffusion model. First, we introduce a 3D-aware autoencoder to encode face images into 3D latent embeddings. Second, we propose a novel representation diffusion model (RDM) to disentangle 3D latent into facial identity and expression. Consequently, our method achieves state-of-the-art performance in facial expression recognition and face verification among unsupervised facial representation learning models. Codes are available at \url{https://github.com/ryanhe312/LatentFace}.
Authors: Xiaofan Li, Bo Peng, Jie Hu, Changyou Ma, Daipeng Yang, Zhuyang Xie
Unsupervised skin lesion segmentation offers several benefits, including conserving expert human resources, reducing discrepancies due to subjective human labeling, and adapting to novel environments. However, segmenting dermoscopic images without manual labeling guidance presents significant challenges due to dermoscopic image artifacts such as hair noise, blister noise, and subtle edge differences. To address these challenges, we introduce an innovative Uncertainty Self-Learning Network (USL-Net) designed for skin lesion segmentation. The USL-Net can effectively segment a range of lesions, eliminating the need for manual labeling guidance. Initially, features are extracted using contrastive learning, followed by the generation of Class Activation Maps (CAMs) as saliency maps using these features. The different CAM locations correspond to the importance of the lesion region based on their saliency. High-saliency regions in the map serve as pseudo-labels for lesion regions while low-saliency regions represent the background. However, intermediate regions can be hard to classify, often due to their proximity to lesion edges or interference from hair or blisters. Rather than risk potential pseudo-labeling errors or learning confusion by forcefully classifying these regions, we consider them as uncertainty regions, exempting them from pseudo-labeling and allowing the network to self-learn. Further, we employ connectivity detection and centrality detection to refine foreground pseudo-labels and reduce noise-induced errors. The application of cycle refining enhances performance further. Our method underwent thorough experimental validation on the ISIC-2017, ISIC-2018, and PH2 datasets, demonstrating that its performance is on par with weakly supervised and supervised methods, and exceeds that of other existing unsupervised methods.
Authors: Vicente Vivanco Cepeda, Gaurav Kumar Nayak, Mubarak Shah
Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. This task has considerable challenges due to immense variation in geographic landscapes. The image-to-image retrieval-based approaches fail to solve this problem on a global scale as it is not feasible to construct a large gallery of images covering the entire world. Instead, existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. However, their performance is limited by the predefined classes and often results in inaccurate localizations when an image's location significantly deviates from its class center. To overcome these limitations, we propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations. GeoCLIP's location encoder models the Earth as a continuous function by employing positional encoding through random Fourier features and constructing a hierarchical representation that captures information at varying resolutions to yield a semantically rich high-dimensional feature suitable to use even beyond geo-localization. To the best of our knowledge, this is the first work employing GPS encoding for geo-localization. We demonstrate the efficacy of our method via extensive experiments and ablations on benchmark datasets. We achieve competitive performance with just 20% of training data, highlighting its effectiveness even in limited-data settings. Furthermore, we qualitatively demonstrate geo-localization using a text query by leveraging CLIP backbone of our image encoder. The project webpage is available at: https://vicentevivan.github.io/GeoCLIP
Authors: Chaoyue Xing, Wei Mao, Miaomiao Liu
In this paper, we tackle the problem of scene-aware 3D human motion forecasting. A key challenge of this task is to predict future human motions that are consistent with the scene by modeling the human-scene interactions. While recent works have demonstrated that explicit constraints on human-scene interactions can prevent the occurrence of ghost motion, they only provide constraints on partial human motion e.g., the global motion of the human or a few joints contacting the scene, leaving the rest of the motion unconstrained. To address this limitation, we propose to model the human-scene interaction with the mutual distance between the human body and the scene. Such mutual distances constrain both the local and global human motion, resulting in a whole-body motion constrained prediction. In particular, mutual distance constraints consist of two components, the signed distance of each vertex on the human mesh to the scene surface and the distance of basis scene points to the human mesh. We further introduce a global scene representation learned from a signed distance function (SDF) volume to ensure coherence between the global scene representation and the explicit constraint from the mutual distance. We develop a pipeline with two sequential steps: predicting the future mutual distances first, followed by forecasting future human motion. During training, we explicitly encourage consistency between predicted poses and mutual distances. Extensive evaluations on the existing synthetic and real datasets demonstrate that our approach consistently outperforms the state-of-the-art methods.
Authors: Yifei Zhang, Siyi Gu, Bo Pan, Guangji Bai, Xiaofeng Yang, Liang Zhao
Explanation(attention)-guided learning is a method that enhances a model's predictive power by incorporating human understanding during the training phase. While attention-guided learning has shown promising results, it often involves time-consuming and computationally expensive model retraining. To address this issue, we introduce the attention-prompted prediction technique, which enables direct prediction guided by the attention prompt without the need for model retraining. However, this approach presents several challenges, including: 1) How to incorporate the visual attention prompt into the model's decision-making process and leverage it for future predictions even in the absence of a prompt? and 2) How to handle the incomplete information from the visual attention prompt? To tackle these challenges, we propose a novel framework called Visual Attention-Prompted Prediction and Learning, which seamlessly integrates visual attention prompts into the model's decision-making process and adapts to images both with and without attention prompts for prediction. To address the incomplete information of the visual attention prompt, we introduce a perturbation-based attention map modification method. Additionally, we propose an optimization-based mask aggregation method with a new weight learning function for adaptive perturbed annotation aggregation in the attention map modification process. Our overall framework is designed to learn in an attention-prompt guided multi-task manner to enhance future predictions even for samples without attention prompts and trained in an alternating manner for better convergence. Extensive experiments conducted on two datasets demonstrate the effectiveness of our proposed framework in enhancing predictions for samples, both with and without provided prompts.
Authors: Jina Lee, Youngtaek Hong, Dawun Jeong, Yeonggul Jang, Jaeik Jeon, Sihyeon Jeong, Taekgeun Jung, Yeonyee E. Yoon, Inki Moon, Seung-Ah Lee, Hyuk-Jae Chang
Radiomics, a medical imaging technique, extracts quantitative handcrafted features from images to predict diseases. Harmonization in those features ensures consistent feature extraction across various imaging devices and protocols. Methods for harmonization include standardized imaging protocols, statistical adjustments, and evaluating feature robustness. Myocardial diseases such as Left Ventricular Hypertrophy (LVH) and Hypertensive Heart Disease (HHD) are diagnosed via echocardiography, but variable imaging settings pose challenges. Harmonization techniques are crucial for applying handcrafted features in disease diagnosis in such scenario. Self-supervised learning (SSL) enhances data understanding within limited datasets and adapts to diverse data settings. ConvNeXt-V2 integrates convolutional layers into SSL, displaying superior performance in various tasks. This study focuses on convolutional filters within SSL, using them as preprocessing to convert images into feature maps for handcrafted feature harmonization. Our proposed method excelled in harmonization evaluation and exhibited superior LVH classification performance compared to existing methods.
Authors: Jianwei Zuo, Fei Feng, Zhuhui Wang, James A. Ashton-Miller, John O.L. Delancey, Jiajia Luo
The semantic segmentation of pelvic organs via MRI has important clinical significance. Recently, deep learning-enabled semantic segmentation has facilitated the three-dimensional geometric reconstruction of pelvic floor organs, providing clinicians with accurate and intuitive diagnostic results. However, the task of labeling pelvic floor MRI segmentation, typically performed by clinicians, is labor-intensive and costly, leading to a scarcity of labels. Insufficient segmentation labels limit the precise segmentation and reconstruction of pelvic floor organs. To address these issues, we propose a semi-supervised framework for pelvic organ segmentation. The implementation of this framework comprises two stages. In the first stage, it performs self-supervised pre-training using image restoration tasks. Subsequently, fine-tuning of the self-supervised model is performed, using labeled data to train the segmentation model. In the second stage, the self-supervised segmentation model is used to generate pseudo labels for unlabeled data. Ultimately, both labeled and unlabeled data are utilized in semi-supervised training. Upon evaluation, our method significantly enhances the performance in the semantic segmentation and geometric reconstruction of pelvic organs, Dice coefficient can increase by 2.65% averagely. Especially for organs that are difficult to segment, such as the uterus, the accuracy of semantic segmentation can be improved by up to 3.70%.
Authors: Weiwen Chen, Qiuhong Ke, Zinuo Li
Image enhancement is a significant research area in the fields of computer vision and image processing. In recent years, many learning-based methods for image enhancement have been developed, where the Look-up-table (LUT) has proven to be an effective tool. In this paper, we delve into the potential of Contrastive Language-Image Pre-Training (CLIP) Guided Prompt Learning, proposing a simple structure called CLIP-LUT for image enhancement. We found that the prior knowledge of CLIP can effectively discern the quality of degraded images, which can provide reliable guidance. To be specific, We initially learn image-perceptive prompts to distinguish between original and target images using CLIP model, in the meanwhile, we introduce a very simple network by incorporating a simple baseline to predict the weights of three different LUT as enhancement network. The obtained prompts are used to steer the enhancement network like a loss function and improve the performance of model. We demonstrate that by simply combining a straightforward method with CLIP, we can obtain satisfactory results.
Authors: Ahmed Emam, Mohamed Farag, Ribana Roscher
Protected natural areas are regions that have been minimally affected by human activities such as urbanization, agriculture, and other human interventions. To better understand and map the naturalness of these areas, machine learning models can be used to analyze satellite imagery. Specifically, explainable machine learning methods show promise in uncovering patterns that contribute to the concept of naturalness within these protected environments. Additionally, addressing the uncertainty inherent in machine learning models is crucial for a comprehensive understanding of this concept. However, existing approaches have limitations. They either fail to provide explanations that are both valid and objective or struggle to offer a quantitative metric that accurately measures the contribution of specific patterns to naturalness, along with the associated confidence. In this paper, we propose a novel framework called the Confident Naturalness Explanation (CNE) framework. This framework combines explainable machine learning and uncertainty quantification to assess and explain naturalness. We introduce a new quantitative metric that describes the confident contribution of patterns to the concept of naturalness. Furthermore, we generate an uncertainty-aware segmentation mask for each input sample, highlighting areas where the model lacks knowledge. To demonstrate the effectiveness of our framework, we apply it to a study site in Fennoscandia using two open-source satellite datasets.
Authors: Jiageng Mao, Junjie Ye, Yuxi Qian, Marco Pavone, Yue Wang
Human-level driving is an ultimate goal of autonomous driving. Conventional approaches formulate autonomous driving as a perception-prediction-planning framework, yet their systems do not capitalize on the inherent reasoning ability and experiential knowledge of humans. In this paper, we propose a fundamental paradigm shift from current pipelines, exploiting Large Language Models (LLMs) as a cognitive agent to integrate human-like intelligence into autonomous driving systems. Our approach, termed Agent-Driver, transforms the traditional autonomous driving pipeline by introducing a versatile tool library accessible via function calls, a cognitive memory of common sense and experiential knowledge for decision-making, and a reasoning engine capable of chain-of-thought reasoning, task planning, motion planning, and self-reflection. Powered by LLMs, our Agent-Driver is endowed with intuitive common sense and robust reasoning capabilities, thus enabling a more nuanced, human-like approach to autonomous driving. We evaluate our approach on the large-scale nuScenes benchmark, and extensive experiments substantiate that our Agent-Driver significantly outperforms the state-of-the-art driving methods by a large margin. Our approach also demonstrates superior interpretability and few-shot learning ability to these methods. Code will be released.
Authors: Yixun Liang, Xin Yang, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen
The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.
Authors: Tony Lindeberg
This paper develops an in-depth treatment concerning the problem of approximating the Gaussian smoothing and Gaussian derivative computations in scale-space theory for application on discrete data. With close connections to previous axiomatic treatments of continuous and discrete scale-space theory, we consider three main ways discretizing these scale-space operations in terms of explicit discrete convolutions, based on either (i) sampling the Gaussian kernels and the Gaussian derivative kernels, (ii) locally integrating the Gaussian kernels and the Gaussian derivative kernels over each pixel support region and (iii) basing the scale-space analysis on the discrete analogue of the Gaussian kernel, and then computing derivative approximations by applying small-support central difference operators to the spatially smoothed image data.
We study the properties of these three main discretization methods both theoretically and experimentally, and characterize their performance by quantitative measures, including the results they give rise to with respect to the task of scale selection, investigated for four different use cases, and with emphasis on the behaviour at fine scales. The results show that the sampled Gaussian kernels and derivatives as well as the integrated Gaussian kernels and derivatives perform very poorly at very fine scales. At very fine scales, the discrete analogue of the Gaussian kernel with its corresponding discrete derivative approximations performs substantially better. The sampled Gaussian kernel and the sampled Gaussian derivatives do, on the other hand, lead to numerically very good approximations of the corresponding continuous results, when the scale parameter is sufficiently large, in the experiments presented in the paper, when the scale parameter is greater than a value of about 1, in units of the grid spacing.
Authors: Georg Wölflein, Dyke Ferber, Asier Rabasco Meneghetti, Omar S. M. El Nahhas, Daniel Truhn, Zunamys I. Carrero, David J. Harrison, Ognjen Arandjelović, Jakob N. Kather
Deep learning is revolutionising pathology, offering novel opportunities in disease prognosis and personalised treatment. Historically, stain normalisation has been a crucial preprocessing step in computational pathology pipelines, and persists into the deep learning era. Yet, with the emergence of feature extractors trained using self-supervised learning (SSL) on diverse pathology datasets, we call this practice into question. In an empirical evaluation of publicly available feature extractors, we find that omitting stain normalisation and image augmentations does not compromise downstream performance, while incurring substantial savings in memory and compute. Further, we show that the top-performing feature extractors are remarkably robust to variations in stain and augmentations like rotation in their latent space. Contrary to previous patch-level benchmarking studies, our approach emphasises clinical relevance by focusing on slide-level prediction tasks in a weakly supervised setting with external validation cohorts. This work represents the most comprehensive robustness evaluation of public pathology SSL feature extractors to date, involving more than 6,000 training runs across nine tasks, five datasets, three downstream architectures, and various preprocessing setups. Our findings stand to streamline digital pathology workflows by minimising preprocessing needs and informing the selection of feature extractors.
Authors: Leon Ericsson, Adam Hjalmarsson, Muhammad Usman Akbar, Edward Ferdian, Mia Bonini, Brandon Hardy, Jonas Schollenberger, Maria Aristova, Patrick Winter, Nicholas Burris, Alexander Fyrdahl, Andreas Sigfridsson, Susanne Schnell, C. Alberto Figueroa, David Nordsletten, Alistair A. Young, David Marlevi
4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive measurement technique capable of quantifying blood flow across the cardiovascular system. While practical use is limited by spatial resolution and image noise, incorporation of trained super-resolution (SR) networks has potential to enhance image quality post-scan. However, these efforts have predominantly been restricted to narrowly defined cardiovascular domains, with limited exploration of how SR performance extends across the cardiovascular system; a task aggravated by contrasting hemodynamic conditions apparent across the cardiovasculature. The aim of our study was to explore the generalizability of SR 4D Flow MRI using a combination of heterogeneous training sets and dedicated ensemble learning. With synthetic training data generated across three disparate domains (cardiac, aortic, cerebrovascular), varying convolutional base and ensemble learners were evaluated as a function of domain and architecture, quantifying performance on both in-silico and acquired in-vivo data from the same three domains. Results show that both bagging and stacking ensembling enhance SR performance across domains, accurately predicting high-resolution velocities from low-resolution input data in-silico. Likewise, optimized networks successfully recover native resolution velocities from downsampled in-vivo data, as well as show qualitative potential in generating denoised SR-images from clinical level input data. In conclusion, our work presents a viable approach for generalized SR 4D Flow MRI, with ensemble learning extending utility across various clinical areas of interest.
Authors: Rohit Bharadwaj, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan
In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD. We present a novel approach to transform existing closed-set detectors into open-set detectors. This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through our cooperative mechanism. Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, we establish new benchmarks in object detection performance. Our method achieves 17.42 mAP in novel object detection and 42.08 mAP for known objects on the challenging LVIS dataset. Adapting our approach to the COCO OVD split, we surpass the current state-of-the-art by a margin of 7.2 $ \text{AP}_{50} $ for novel classes. Our code is available at https://github.com/rohit901/cooperative-foundational-models .
Authors: Yu Huang, Yue Chen, Zhu Li
Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. Recently powered by large language models (LLMs), chat systems, such as chatGPT and PaLM, emerge and rapidly become a promising direction to achieve artificial general intelligence (AGI) in natural language processing (NLP). There comes a natural thinking that we could employ these abilities to reformulate autonomous driving. By combining LLM with foundation models, it is possible to utilize the human knowledge, commonsense and reasoning to rebuild autonomous driving systems from the current long-tailed AI dilemma. In this paper, we investigate the techniques of foundation models and LLMs applied for autonomous driving, categorized as simulation, world model, data annotation and planning or E2E solutions etc.
Authors: Ayush Kumar Shah, Bryan Manrique Amador, Abhisek Dey, Ming Creekmore, Blake Ocampo, Scott Denmark, Richard Zanibbi
Existing visual parsers for molecule diagrams translate pixel-based raster images such as PNGs to chemical structure representations (e.g., SMILES). However, PDFs created by word processors including LaTeX and Word provide explicit locations and shapes for characters, lines, and polygons. We extract symbols from born-digital PDF molecule images and then apply simple graph transformations to capture both visual and chemical structure in editable ChemDraw files (CDXML). Our fast ( PDF $\rightarrow$ visual graph $\rightarrow$ chemical graph ) pipeline does not require GPUs, Optical Character Recognition (OCR) or vectorization. We evaluate on standard benchmarks using SMILES strings, along with a novel evaluation that provides graph-based metrics and error compilation using LgEval. The geometric information in born-digital PDFs produces a highly accurate parser, motivating generating training data for visual parsers that recognize from raster images, with extracted graphics, visual structure, and chemical structure as annotations. To do this we render SMILES strings in Indigo, parse molecule structure, and then validate recognized structure to select correct files.
Authors: Tianyi Xie, Zeshun Zong, Yuxing Qiu, Xuan Li, Yutao Feng, Yin Yang, Chenfanfu Jiang
We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, "cage meshes," or any other geometry embedding, highlighting the principle of "what you see is what you simulate (WS$^2$)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements. Our project page is at: https://xpandora.github.io/PhysGaussian/
Authors: Han Liu, Yubo Fan, Zhoubing Xu, Benoit M. Dawant, Ipek Oguz
Unsupervised cross-modality domain adaptation is a challenging task in medical image analysis, and it becomes more challenging when source and target domain data are collected from multiple institutions. In this paper, we present our solution to tackle the multi-institutional unsupervised domain adaptation for the crossMoDA 2023 challenge. First, we perform unpaired image translation to translate the source domain images to the target domain, where we design a dynamic network to generate synthetic target domain images with controllable, site-specific styles. Afterwards, we train a segmentation model using the synthetic images and further reduce the domain gap by self-training. Our solution achieved the 1st place during both the validation and testing phases of the challenge. The code repository is publicly available at https://github.com/MedICL-VU/crossmoda2023.
Authors: Hyogun Lee, Kyungho Bae, Seong Jong Ha, Yumin Ko, Gyeong-Moon Park, Jinwoo Choi
In this work, we tackle the challenging problem of unsupervised video domain adaptation (UVDA) for action recognition. We specifically focus on scenarios with a substantial domain gap, in contrast to existing works primarily deal with small domain gaps between labeled source domains and unlabeled target domains. To establish a more realistic setting, we introduce a novel UVDA scenario, denoted as Kinetics->BABEL, with a more considerable domain gap in terms of both temporal dynamics and background shifts. To tackle the temporal shift, i.e., action duration difference between the source and target domains, we propose a global-local view alignment approach. To mitigate the background shift, we propose to learn temporal order sensitive representations by temporal order learning and background invariant representations by background augmentation. We empirically validate that the proposed method shows significant improvement over the existing methods on the Kinetics->BABEL dataset with a large domain gap. The code is available at https://github.com/KHUVLL/GLAD.
Authors: Zhen Chen, Yuhao Zhai, Jun Zhang, Jinqiao Wang
To assist surgeons in the operating theatre, surgical phase recognition is critical for developing computer-assisted surgical systems, which requires comprehensive understanding of surgical videos. Although existing studies made great progress, there are still two significant limitations worthy of improvement. First, due to the compromise of resource consumption, frame-wise visual features are extracted by 2D networks and disregard spatial and temporal knowledge of surgical actions, which hinders subsequent inter-frame modeling for phase prediction. Second, these works simply utilize ordinary classification loss with one-hot phase labels to optimize the phase predictions, and cannot fully explore surgical videos under inadequate supervision. To overcome these two limitations, we propose a Surgical Temporal Action-aware Network with sequence Regularization, named STAR-Net, to recognize surgical phases more accurately from input videos. Specifically, we propose an efficient multi-scale surgical temporal action (MS-STA) module, which integrates visual features with spatial and temporal knowledge of surgical actions at the cost of 2D networks. Moreover, we devise the dual-classifier sequence regularization (DSR) to facilitate the training of STAR-Net by the sequence guidance of an auxiliary classifier with a smaller capacity. Our STAR-Net with MS-STA and DSR can exploit visual features of surgical actions with effective regularization, thereby leading to the superior performance of surgical phase recognition. Extensive experiments on a large-scale gastrectomy surgery dataset and the public Cholec80 benchmark prove that our STAR-Net significantly outperforms state-of-the-arts of surgical phase recognition.
Authors: Radu Horaud, Fadi Dornaika
Whenever a sensor is mounted on a robot hand it is important to know the relationship between the sensor and the hand. The problem of determining this relationship is referred to as hand-eye calibration, which is important in at least two types of tasks: (i) map sensor centered measurements into the robot workspace and (ii) allow the robot to precisely move the sensor. In the past some solutions were proposed in the particular case of a camera. With almost no exception, all existing solutions attempt to solve the homogeneous matrix equation AX=XB. First we show that there are two possible formulations of the hand-eye calibration problem. One formulation is the classical one that we just mentioned. A second formulation takes the form of the following homogeneous matrix equation: MY=M'YB. The advantage of the latter is that the extrinsic and intrinsic camera parameters need not be made explicit. Indeed, this formulation directly uses the 3 by 4 perspective matrices (M and M') associated with two positions of the camera. Moreover, this formulation together with the classical one cover a wider range of camera-based sensors to be calibrated with respect to the robot hand. Second, we develop a common mathematical framework to solve for the hand-eye calibration problem using either of the two formulations. We present two methods, (i) a rotation then translation and (ii) a non-linear solver for rotation and translation. Third, we perform a stability analysis both for our two methods and for the classical linear method of Tsai and Lenz (1989). In the light of this comparison, the non-linear optimization method, that solves for rotation and translation simultaneously, seems to be the most robust one with respect to noise and to measurement errors.
Authors: Renu Sharma, Redwan Sony, Arun Ross
Deep neural networks (DNNs) exhibit superior performance in various machine learning tasks, e.g., image classification, speech recognition, biometric recognition, object detection, etc. However, it is essential to analyze their sensitivity to parameter perturbations before deploying them in real-world applications. In this work, we assess the sensitivity of DNNs against perturbations to their weight and bias parameters. The sensitivity analysis involves three DNN architectures (VGG, ResNet, and DenseNet), three types of parameter perturbations (Gaussian noise, weight zeroing, and weight scaling), and two settings (entire network and layer-wise). We perform experiments in the context of iris presentation attack detection and evaluate on two publicly available datasets: LivDet-Iris-2017 and LivDet-Iris-2020. Based on the sensitivity analysis, we propose improved models simply by perturbing parameters of the network without undergoing training. We further combine these perturbed models at the score-level and at the parameter-level to improve the performance over the original model. The ensemble at the parameter-level shows an average improvement of 43.58% on the LivDet-Iris-2017 dataset and 9.25% on the LivDet-Iris-2020 dataset. The source code is available at https://github.com/redwankarimsony/WeightPerturbation-MSU.
Authors: Maksim Golyadkin, Alexander Gambashidze, Ildar Nurgaliev, Ilya Makarov
In response to the growing demand for 3D object detection in applications such as autonomous driving, robotics, and augmented reality, this work focuses on the evaluation of semi-supervised learning approaches for point cloud data. The point cloud representation provides reliable and consistent observations regardless of lighting conditions, thanks to advances in LiDAR sensors. Data annotation is of paramount importance in the context of LiDAR applications, and automating 3D data annotation with semi-supervised methods is a pivotal challenge that promises to reduce the associated workload and facilitate the emergence of cost-effective LiDAR solutions. Nevertheless, the task of semi-supervised learning in the context of unordered point cloud data remains formidable due to the inherent sparsity and incomplete shapes that hinder the generation of accurate pseudo-labels. In this study, we consider these challenges by posing the question: "To what extent does unlabelled data contribute to the enhancement of model performance?" We show that improvements from previous semi-supervised methods may not be as profound as previously thought. Our results suggest that simple grid search hyperparameter tuning applied to a supervised model can lead to state-of-the-art performance on the ONCE dataset, while the contribution of unlabelled data appears to be comparatively less exceptional.
Authors: Abdul Muqeet, Kyuchul Lee, Bumsoo Kim, Yohan Hong, Hyungrae Lee, Woonggon Kim, Kwang Hee Lee
Video face re-aging deals with altering the apparent age of a person to the target age in videos. This problem is challenging due to the lack of paired video datasets maintaining temporal consistency in identity and age. Most re-aging methods process each image individually without considering the temporal consistency of videos. While some existing works address the issue of temporal coherence through video facial attribute manipulation in latent space, they often fail to deliver satisfactory performance in age transformation. To tackle the issues, we propose (1) a novel synthetic video dataset that features subjects across a diverse range of age groups; (2) a baseline architecture designed to validate the effectiveness of our proposed dataset, and (3) the development of three novel metrics tailored explicitly for evaluating the temporal consistency of video re-aging techniques. Our comprehensive experiments on public datasets, such as VFHQ and CelebV-HQ, show that our method outperforms the existing approaches in terms of both age transformation and temporal consistency.