Authors: BahaaEddin AlAila, Zahra Jandaghi, Abolfazl Farahani, Mohammad Ziad Al-Saad
Abstract: The problem of image-to-image translation is one that is intruiging and challenging at the same time, for the impact potential it can have on a wide variety of other computer vision applications like colorization, inpainting, segmentation and others. Given the high-level of sophistication needed to extract patterns from one domain and successfully applying them to another, especially, in a completely unsupervised (unpaired) manner, this problem has gained much attention as of the last few years. It is one of the first problems where successful applications to deep generative models, and especially Generative Adversarial Networks achieved astounding results that are actually of realworld impact, rather than just a show of theoretical prowess; the such that has been dominating the GAN world. In this work, we study some of the failure cases of a seminal work in the field, CycleGAN [1] and hypothesize that they are GAN-stability related, and propose two general models to try to alleviate these problems. We also reach the same conclusion of the problem being ill-posed that has been also circulating in the literature lately.
Authors: Kui Zhao, Siyang Wu, Chang Liu, Yue Wu, Natalia Efremova
Abstract: Food security has grown in significance due to the changing climate and its warming effects. To support the rising demand for agricultural products and to minimize the negative impact of climate change and mass cultivation, precision agriculture has become increasingly important for crop cultivation. This study employs deep learning and pixel-based machine learning methods to accurately segment lavender fields for precision agriculture, utilizing various spectral band combinations extracted from Sentinel-2 satellite imagery. Our fine-tuned final model, a U-Net architecture, can achieve a Dice coefficient of 0.8324. Additionally, our investigation highlights the unexpected efficacy of the pixel-based method and the RGB spectral band combination in this task.
Authors: Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker
Abstract: We present the Qualitative Explainable Graph (QXG): a unified symbolic and qualitative representation for scene understanding in urban mobility. QXG enables the interpretation of an automated vehicle's environment using sensor data and machine learning models. It leverages spatio-temporal graphs and qualitative constraints to extract scene semantics from raw sensor inputs, such as LiDAR and camera data, offering an intelligible scene model. Crucially, QXG can be incrementally constructed in real-time, making it a versatile tool for in-vehicle explanations and real-time decision-making across various sensor types. Our research showcases the transformative potential of QXG, particularly in the context of automated driving, where it elucidates decision rationales by linking the graph with vehicle actions. These explanations serve diverse purposes, from informing passengers and alerting vulnerable road users (VRUs) to enabling post-analysis of prior behaviours.
Authors: Pum Jun Kim, Seojun Kim, Jaejun Yoo
Abstract: Image generative models have made significant progress in generating realistic and diverse images, supported by comprehensive guidance from various evaluation metrics. However, current video generative models struggle to generate even short video clips, with limited tools that provide insights for improvements. Current video evaluation metrics are simple adaptations of image metrics by switching the embeddings with video embedding networks, which may underestimate the unique characteristics of video. Our analysis reveals that the widely used Frechet Video Distance (FVD) has a stronger emphasis on the spatial aspect than the temporal naturalness of video and is inherently constrained by the input size of the embedding networks used, limiting it to 16 frames. Additionally, it demonstrates considerable instability and diverges from human evaluations. To address the limitations, we propose STREAM, a new video evaluation metric uniquely designed to independently evaluate spatial and temporal aspects. This feature allows comprehensive analysis and evaluation of video generative models from various perspectives, unconstrained by video length. We provide analytical and experimental evidence demonstrating that STREAM provides an effective evaluation tool for both visual and temporal quality of videos, offering insights into area of improvement for video generative models. To the best of our knowledge, STREAM is the first evaluation metric that can separately assess the temporal and spatial aspects of videos. Our code is available at STREAM.
Authors: Guy Lutsker, Hagai Rossman, Nastya Godiva, Eran Segal
Abstract: Substantial advances in multi-modal Artificial Intelligence (AI) facilitate the combination of diverse medical modalities to achieve holistic health assessments. We present COMPRER , a novel multi-modal, multi-objective pretraining framework which enhances medical-image representation, diagnostic inferences, and prognosis of diseases. COMPRER employs a multi-objective training framework, where each objective introduces distinct knowledge to the model. This includes a multimodal loss that consolidates information across different imaging modalities; A temporal loss that imparts the ability to discern patterns over time; Medical-measure prediction adds appropriate medical insights; Lastly, reconstruction loss ensures the integrity of image structure within the latent space. Despite the concern that multiple objectives could weaken task performance, our findings show that this combination actually boosts outcomes on certain tasks. Here, we apply this framework to both fundus images and carotid ultrasound, and validate our downstream tasks capabilities by predicting both current and future cardiovascular conditions. COMPRER achieved higher Area Under the Curve (AUC) scores in evaluating medical conditions compared to existing models on held-out data. On the Out-of-distribution (OOD) UK-Biobank dataset COMPRER maintains favorable performance over well-established models with more parameters, even though these models were trained on $75\times$ more data than COMPRER. In addition, to better assess our model's performance in contrastive learning, we introduce a novel evaluation metric, providing deeper understanding of the effectiveness of the latent space pairing.
Authors: Rio Aguina-Kang, Maxim Gumin, Do Heon Han, Stewart Morris, Seung Jean Yoo, Aditya Ganeshan, R. Kenny Jones, Qiuhong Anna Wei, Kailiang Fu, Daniel Ritchie
Abstract: We present a system for generating indoor scenes in response to text prompts. The prompts are not limited to a fixed vocabulary of scene descriptions, and the objects in generated scenes are not restricted to a fixed set of object categories -- we call this setting indoor scene generation. Unlike most prior work on indoor scene generation, our system does not require a large training dataset of existing 3D scenes. Instead, it leverages the world knowledge encoded in pre-trained large language models (LLMs) to synthesize programs in a domain-specific layout language that describe objects and spatial relations between them. Executing such a program produces a specification of a constraint satisfaction problem, which the system solves using a gradient-based optimization scheme to produce object positions and orientations. To produce object geometry, the system retrieves 3D meshes from a database. Unlike prior work which uses databases of category-annotated, mutually-aligned meshes, we develop a pipeline using vision-language models (VLMs) to retrieve meshes from massive databases of un-annotated, inconsistently-aligned meshes. Experimental evaluations show that our system outperforms generative models trained on 3D data for traditional, closed-universe scene generation tasks; it also outperforms a recent LLM-based layout generation method on open-universe scene generation.
Authors: Ikhyun Cho, Changyeon Park, Julia Hockenmaier
Abstract: Machine unlearning (MUL) is an arising field in machine learning that seeks to erase the learned information of specific training data points from a trained model. Despite the recent active research in MUL within computer vision, the majority of work has focused on ResNet-based models. Given that Vision Transformers (ViT) have become the predominant model architecture, a detailed study of MUL specifically tailored to ViT is essential. In this paper, we present comprehensive experiments on ViTs using recent MUL algorithms and datasets. We anticipate that our experiments, ablation studies, and findings could provide valuable insights and inspire further research in this field.
Authors: Yushu Pan, Elias Bareinboim
Abstract: Counterfactual image editing is an important task in generative AI, which asks how an image would look if certain features were different. The current literature on the topic focuses primarily on changing individual features while remaining silent about the causal relationships between these features, as present in the real world. In this paper, we formalize the counterfactual image editing task using formal language, modeling the causal relationships between latent generative factors and images through a special type of model called augmented structural causal models (ASCMs). Second, we show two fundamental impossibility results: (1) counterfactual editing is impossible from i.i.d. image samples and their corresponding labels alone; (2) even when the causal relationships between the latent generative factors and images are available, no guarantees regarding the output of the model can be provided. Third, we propose a relaxation for this challenging problem by approximating non-identifiable counterfactual distributions with a new family of counterfactual-consistent estimators. This family exhibits the desirable property of preserving features that the user cares about across both factual and counterfactual worlds. Finally, we develop an efficient algorithm to generate counterfactual images by leveraging neural causal models.
Authors: Alex Glinsky, Alexey Sokolsky
Abstract: It is evident that, currently, generative models are surpassed in quality by human professionals. However, with the advancements in Artificial Intelligence, this gap will narrow, leading to scenarios where individuals who have dedicated years of their lives to mastering a skill become obsolete due to their high costs, which are inherently linked to the time they require to complete a task -- a task that AI could accomplish in minutes or seconds. To avoid future social upheavals, we must, even now, contemplate how to fairly assess the contributions of such individuals in training generative models and how to compensate them for the reduction or complete loss of their incomes. In this work, we propose a method to structure collaboration between model developers and data providers. To achieve this, we employ Shapley Values to quantify the contribution of artist(s) in an image generated by the Stable Diffusion-v1.5 model and to equitably allocate the reward among them.
Authors: Nicolas Chahine, Sira Ferradans, Jean Ponce
Abstract: Blind image quality assessment (BIQA) approaches, while promising for automating image quality evaluation, often fall short in real-world scenarios due to their reliance on a generic quality standard applied uniformly across diverse images. This one-size-fits-all approach overlooks the crucial perceptual relationship between image content and quality, leading to a 'domain shift' challenge where a single quality metric inadequately represents various content types. Furthermore, BIQA techniques typically overlook the inherent differences in the human visual system among different observers. In response to these challenges, this paper introduces PICNIQ, an innovative pairwise comparison framework designed to bypass the limitations of conventional BIQA by emphasizing relative, rather than absolute, quality assessment. PICNIQ is specifically designed to assess the quality differences between image pairs. The proposed framework implements a carefully crafted deep learning architecture, a specialized loss function, and a training strategy optimized for sparse comparison settings. By employing psychometric scaling algorithms like TrueSkill, PICNIQ transforms pairwise comparisons into just-objectionable-difference (JOD) quality scores, offering a granular and interpretable measure of image quality. We conduct our research using comparison matrices from the PIQ23 dataset, which are published in this paper. Our extensive experimental analysis showcases PICNIQ's broad applicability and superior performance over existing models, highlighting its potential to set new standards in the field of BIQA.
Authors: Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr
Abstract: Different from traditional task-specific vision models, recent large VLMs can readily adapt to different vision tasks by simply using different textual instructions, i.e., prompts. However, a well-known concern about traditional task-specific vision models is that they can be misled by imperceptible adversarial perturbations. Furthermore, the concern is exacerbated by the phenomenon that the same adversarial perturbations can fool different task-specific models. Given that VLMs rely on prompts to adapt to different tasks, an intriguing question emerges: Can a single adversarial image mislead all predictions of VLMs when a thousand different prompts are given? This question essentially introduces a novel perspective on adversarial transferability: cross-prompt adversarial transferability. In this work, we propose the Cross-Prompt Attack (CroPA). This proposed method updates the visual adversarial perturbation with learnable prompts, which are designed to counteract the misleading effects of the adversarial image. By doing this, CroPA significantly improves the transferability of adversarial examples across prompts. Extensive experiments are conducted to verify the strong cross-prompt adversarial transferability of CroPA with prevalent VLMs including Flamingo, BLIP-2, and InstructBLIP in various different tasks. Our source code is available at \url{https://github.com/Haochen-Luo/CroPA}.
Authors: Yifan Li, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Ji-Rong Wen
Abstract: In this paper, we study the harmlessness alignment problem of multimodal large language models~(MLLMs). We conduct a systematic empirical analysis of the harmlessness performance of representative MLLMs and reveal that the image input poses the alignment vulnerability of MLLMs. Inspired by this, we propose a novel jailbreak method named HADES, which hides and amplifies the harmfulness of the malicious intent within the text input, using meticulously crafted images. Experimental results show that HADES can effectively jailbreak existing MLLMs, which achieves an average Attack Success Rate~(ASR) of 90.26% for LLaVA-1.5 and 71.60% for Gemini Pro Vision. Our code and data will be publicly released.
Authors: Tomas Hodan, Martin Sundermeyer, Yann Labbe, Van Nguyen Nguyen, Gu Wang, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Jiri Matas
Abstract: We present the evaluation methodology, datasets and results of the BOP Challenge 2023, the fifth in a series of public competitions organized to capture the state of the art in model-based 6D object pose estimation from an RGB/RGB-D image and related tasks. Besides the three tasks from 2022 (model-based 2D detection, 2D segmentation, and 6D localization of objects seen during training), the 2023 challenge introduced new variants of these tasks focused on objects unseen during training. In the new tasks, methods were required to learn new objects during a short onboarding stage (max 5 minutes, 1 GPU) from provided 3D object models. The best 2023 method for 6D localization of unseen objects (GenFlow) notably reached the accuracy of the best 2020 method for seen objects (CosyPose), although being noticeably slower. The best 2023 method for seen objects (GPose) achieved a moderate accuracy improvement but a significant 43% run-time improvement compared to the best 2022 counterpart (GDRNPP). Since 2017, the accuracy of 6D localization of seen objects has improved by more than 50% (from 56.9 to 85.6 AR_C). The online evaluation system stays open and is available at: http://bop.felk.cvut.cz/.
Authors: Md Salman Shamil, Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao
Abstract: 3D hand poses are an under-explored modality for action recognition. Poses are compact yet informative and can greatly benefit applications with limited compute budgets. However, poses alone offer an incomplete understanding of actions, as they cannot fully capture objects and environments with which humans interact. To efficiently model hand-object interactions, we propose HandFormer, a novel multimodal transformer. HandFormer combines 3D hand poses at a high temporal resolution for fine-grained motion modeling with sparsely sampled RGB frames for encoding scene semantics. Observing the unique characteristics of hand poses, we temporally factorize hand modeling and represent each joint by its short-term trajectories. This factorized pose representation combined with sparse RGB samples is remarkably efficient and achieves high accuracy. Unimodal HandFormer with only hand poses outperforms existing skeleton-based methods at 5x fewer FLOPs. With RGB, we achieve new state-of-the-art performance on Assembly101 and H2O with significant improvements in egocentric action recognition.
Authors: Ning Cheng, You Li, Jing Gao, Bin Fang, Jinan Xu, Wenjuan Han
Abstract: Tactility provides crucial support and enhancement for the perception and interaction capabilities of both humans and robots. Nevertheless, the multimodal research related to touch primarily focuses on visual and tactile modalities, with limited exploration in the domain of language. Beyond vocabulary, sentence-level descriptions contain richer semantics. Based on this, we construct a touch-language-vision dataset named TLV (Touch-Language-Vision) by human-machine cascade collaboration, featuring sentence-level descriptions for multimode alignment. The new dataset is used to fine-tune our proposed lightweight training framework, TLV-Link (Linking Touch, Language, and Vision through Alignment), achieving effective semantic alignment with minimal parameter adjustments (1%). Project Page: https://xiaoen0.github.io/touch.page/.
Authors: Jiayi Wu, Xiaomin Lin, Shahriar Negahdaripour, Cornelia Ferm\"uller, Yiannis Aloimonos
Abstract: Tasks such as autonomous navigation, 3D reconstruction, and object recognition near the water surfaces are crucial in marine robotics applications. However, challenges arise due to dynamic disturbances, e.g., light reflections and refraction from the random air-water interface, irregular liquid flow, and similar factors, which can lead to potential failures in perception and navigation systems. Traditional computer vision algorithms struggle to differentiate between real and virtual image regions, significantly complicating tasks. A virtual image region is an apparent representation formed by the redirection of light rays, typically through reflection or refraction, creating the illusion of an object's presence without its actual physical location. This work proposes a novel approach for segmentation on real and virtual image regions, exploiting synthetic images combined with domain-invariant information, a Motion Entropy Kernel, and Epipolar Geometric Consistency. Our segmentation network does not need to be re-trained if the domain changes. We show this by deploying the same segmentation network in two different domains: simulation and the real world. By creating realistic synthetic images that mimic the complexities of the water surface, we provide fine-grained training data for our network (MARVIS) to discern between real and virtual images effectively. By motion & geometry-aware design choices and through comprehensive experimental analysis, we achieve state-of-the-art real-virtual image segmentation performance in unseen real world domain, achieving an IoU over 78% and a F1-Score over 86% while ensuring a small computational footprint. MARVIS offers over 43 FPS (8 FPS) inference rates on a single GPU (CPU core). Our code and dataset are available here https://github.com/jiayi-wu-umd/MARVIS.
Authors: Fangqiang Ding, Yunzhou Zhu, Xiangyu Wen, Chris Xiaoxuan Lu
Abstract: In this work, we present ThermoHands, a new benchmark for thermal image-based egocentric 3D hand pose estimation, aimed at overcoming challenges like varying lighting and obstructions (e.g., handwear). The benchmark includes a diverse dataset from 28 subjects performing hand-object and hand-virtual interactions, accurately annotated with 3D hand poses through an automated process. We introduce a bespoken baseline method, TheFormer, utilizing dual transformer modules for effective egocentric 3D hand pose estimation in thermal imagery. Our experimental results highlight TheFormer's leading performance and affirm thermal imaging's effectiveness in enabling robust 3D hand pose estimation in adverse conditions.
Authors: Zhiming Hu, Syn Schmitt, Daniel Haeufle, Andreas Bulling
Abstract: We present GazeMotion, a novel method for human motion forecasting that combines information on past human poses with human eye gaze. Inspired by evidence from behavioural sciences showing that human eye and body movements are closely coordinated, GazeMotion first predicts future eye gaze from past gaze, then fuses predicted future gaze and past poses into a gaze-pose graph, and finally uses a residual graph convolutional network to forecast body motion. We extensively evaluate our method on the MoGaze, ADT, and GIMO benchmark datasets and show that it outperforms state-of-the-art methods by up to 7.4% improvement in mean per joint position error. Using head direction as a proxy to gaze, our method still achieves an average improvement of 5.5%. We finally report an online user study showing that our method also outperforms prior methods in terms of perceived realism. These results show the significant information content available in eye gaze for human motion forecasting as well as the effectiveness of our method in exploiting this information.
Authors: Vishal Asnani, John Collomosse, Tu Bui, Xiaoming Liu, Shruti Agarwal
Abstract: Generative AI (GenAI) is transforming creative workflows through the capability to synthesize and manipulate images via high-level prompts. Yet creatives are not well supported to receive recognition or reward for the use of their content in GenAI training. To this end, we propose ProMark, a causal attribution technique to attribute a synthetically generated image to its training data concepts like objects, motifs, templates, artists, or styles. The concept information is proactively embedded into the input training images using imperceptible watermarks, and the diffusion models (unconditional or conditional) are trained to retain the corresponding watermarks in generated images. We show that we can embed as many as $2^{16}$ unique watermarks into the training data, and each training image can contain more than one watermark. ProMark can maintain image quality whilst outperforming correlation-based attribution. Finally, several qualitative examples are presented, providing the confidence that the presence of the watermark conveys a causative relationship between training data and synthetic images.
Authors: Li Lin, Sarah Papabathini, Xin Wang, Shu Hu
Abstract: Human affective behavior analysis aims to delve into human expressions and behaviors to deepen our understanding of human emotions. Basic expression categories (EXPR) and Action Units (AUs) are two essential components in this analysis, which categorize emotions and break down facial movements into elemental units, respectively. Despite advancements, existing approaches in expression classification and AU detection often necessitate complex models and substantial computational resources, limiting their applicability in everyday settings. In this work, we introduce the first lightweight framework adept at efficiently tackling both expression classification and AU detection. This framework employs a frozen CLIP image encoder alongside a trainable multilayer perceptron (MLP), enhanced with Conditional Value at Risk (CVaR) for robustness and a loss landscape flattening strategy for improved generalization. Experimental results on the Aff-wild2 dataset demonstrate superior performance in comparison to the baseline while maintaining minimal computational demands, offering a practical solution for affective behavior analysis. The code is available at https://github.com/Purdue-M2/Affective_Behavior_Analysis_M2_PURDUE
URLs: https://github.com/Purdue-M2/Affective_Behavior_Analysis_M2_PURDUE
Authors: Atif Belal, Akhil Meethal, Francisco Perdigon Romero, Marco Pedersoli, Eric Granger
Abstract: Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple annotated source datasets, and unlabeled target data to improve the accuracy and robustness of the detection model. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. This is challenging since the objects have unique modal information due to variations in object appearance across domains. A recent prototype-based approach proposed a class-wise alignment, yet it suffers from error accumulation due to noisy pseudo-labels which can negatively affect adaptation with imbalanced data. To overcome these limitations, we propose an attention-based class-conditioned alignment scheme for MSDA that aligns instances of each object category across domains. In particular, an attention module coupled with an adversarial domain classifier allows learning domain-invariant and class-specific instance representations. Experimental results on multiple benchmarking MSDA datasets indicate that our method outperforms the state-of-the-art methods and is robust to class imbalance. Our code is available at https://github.com/imatif17/ACIA.
Authors: Joel Shor, Carson McNeil, Yotam Intrator, Joseph R Ledsam, Hiro-o Yamano, Daisuke Tsurumaru, Hiroki Kayama, Atsushi Hamabe, Koji Ando, Mitsuhiko Ota, Haruei Ogino, Hiroshi Nakase, Kaho Kobayashi, Masaaki Miyo, Eiji Oki, Ichiro Takemasa, Ehud Rivlin, Roman Goldenberg
Abstract: Background and aims Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. Methods We use a "Masked Siamese Network" (MSN) to identify novel phenomena in unseen data and predict polyp detector performance. MSN is trained to predict masked out regions of polyp images, without any labels. We test MSN's ability to be trained on data only from Israel and detect unseen techniques, narrow-band imaging (NBI) and chromendoscoy (CE), on colonoscopes from Japan (354 videos, 128 hours). We also test MSN's ability to predict performance of Computer Aided Detection (CADe) of polyps on colonoscopies from both countries, even though MSN is not trained on data from Japan. Results MSN correctly identifies NBI and CE as less similar to Israel whitelight than Japan whitelight (bootstrapped z-test, |z| > 496, p < 10-8 for both) using the label-free Frechet distance. MSN detects NBI with 99% accuracy, predicts CE better than our heuristic (90% vs 79% accuracy) despite being trained only on whitelight, and is the only method that is robust to noisy labels. MSN predicts CADe polyp detector performance on in-domain Israel and out-of-domain Japan colonoscopies (r=0.79, 0.37 respectively). With few examples of Japan detector performance to train on, MSN prediction of Japan performance improves (r=0.56). Conclusion Our technique can identify distribution shifts in clinical data and can predict CADe detector performance on unseen data, without labels. Our self-supervised approach can aid in detecting when data in practice is different from training, such as between hospitals or data has meaningfully shifted from training. MSN has potential for application to medical image domains beyond colonoscopy.
Authors: Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Alessandro Bruno
Abstract: Neural network quantization is an essential technique for deploying models on resource-constrained devices. However, its impact on model perceptual fields, particularly regarding class activation maps (CAMs), remains a significant area of investigation. In this study, we explore how quantization alters the spatial recognition ability of the perceptual field of vision models, shedding light on the alignment between CAMs and visual saliency maps across various architectures. Leveraging a dataset of 10,000 images from ImageNet, we rigorously evaluate six diverse foundational CNNs: VGG16, ResNet50, EfficientNet, MobileNet, SqueezeNet, and DenseNet. We uncover nuanced changes in CAMs and their alignment with human visual saliency maps through systematic quantization techniques applied to these models. Our findings reveal the varying sensitivities of different architectures to quantization and underscore its implications for real-world applications in terms of model performance and interpretability. The primary contribution of this work revolves around deepening our understanding of neural network quantization, providing insights crucial for deploying efficient and interpretable models in practical settings.
Authors: Aymen Sekhri, Marouane Tliba, Mohamed Amine Kerkouri, Yassine Nasser, Aladine Chetouani, Alessandro Bruno, Rachid Jennane
Abstract: Conventional imaging diagnostics frequently encounter bottlenecks due to manual inspection, which can lead to delays and inconsistencies. Although deep learning offers a pathway to automation and enhanced accuracy, foundational models in computer vision often emphasize global context at the expense of local details, which are vital for medical imaging diagnostics. To address this, we harness the Swin Transformer's capacity to discern extended spatial dependencies within images through the hierarchical framework. Our novel contribution lies in refining local feature representations, orienting them specifically toward the final distribution of the classifier. This method ensures that local features are not only preserved but are also enriched with task-specific information, enhancing their relevance and detail at every hierarchical level. By implementing this strategy, our model demonstrates significant robustness and precision, as evidenced by extensive validation of two established benchmarks for Knee OsteoArthritis (KOA) grade classification. These results highlight our approach's effectiveness and its promising implications for the future of medical imaging diagnostics. Our implementation is available on https://github.com/mtliba/KOA_NLCS2024
Authors: Zhixiu Lu, Hailong Li, Lili He
Abstract: The integration of artificial intelligence (AI) with radiology has marked a transformative era in medical diagnostics. Vision foundation models have been adopted to enhance radiologic imaging analysis. However, the distinct complexities of radiological imaging, including the interpretation of 2D and 3D radiological data, pose unique challenges that existing models, trained on general non-medical images, fail to address adequately. To bridge this gap and capitalize on the diagnostic precision required in medical imaging, we introduce RadCLIP: a pioneering cross-modal foundational model that harnesses Contrastive Language-Image Pre-training (CLIP) to refine radiologic image analysis. RadCLIP incorporates a novel 3D slice pooling mechanism tailored for volumetric image analysis and is trained using a comprehensive and diverse dataset of radiologic image-text pairs. Our evaluations demonstrate that RadCLIP effectively aligns radiological images with their corresponding textual annotations, and in the meantime, offers a robust vision backbone for radiologic imagery with significant promise.
Authors: Bo Song, Yuanhao Xu, Yichao Wu
Abstract: Machine learning models have achieved significant milestones in various domains, for example, computer vision models have an exceptional result in object recognition, and in natural language processing, where Large Language Models (LLM) like GPT can start a conversation with human-like proficiency. However, abstract reasoning remains a challenge for these models, Can AI really thinking like a human? still be a question yet to be answered. Raven Progressive Matrices (RPM) is a metric designed to assess human reasoning capabilities. It presents a series of eight images as a problem set, where the participant should try to discover the underlying rules among these images and select the most appropriate image from eight possible options that best completes the sequence. This task always be used to test human reasoning abilities and IQ. Zhang et al proposed a dataset called RAVEN which can be used to test Machine Learning model abstract reasoning ability. In this paper, we purposed Vision Transformer Contrastive Network which build on previous work with the Contrastive Perceptual Inference network (CoPiNet), which set a new benchmark for permutationinvariant models Raven Progressive Matrices by incorporating contrast effects from psychology, cognition, and education, and extends this foundation by leveraging the cutting-edge Vision Transformer architecture. This integration aims to further refine the machine ability to process and reason about spatial-temporal information from pixel-level inputs and global wise features on RAVEN dataset.
Authors: Xiaohang Yu, Zhengxian Yang, Shi Pan, Yuqi Han, Haoxiang Wang, Jun Zhang, Shi Yan, Borong Lin, Lei Yang, Tao Yu, Lu Fang
Abstract: We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios. Our aim is to contribute to the development of popular 3D scene reconstruction algorithms such as IBRnet, NeRF, and 3D Gaussian splitting. More importantly, the collected dataset, which is much denser than existing datasets, may also inspire space-oriented light field reconstruction, which is potentially different from object-centric 3D reconstruction, for immersive VR/AR experiences. We utilized a total of 40 GoPro 10 cameras, capturing images of 5k resolution. The number of photos captured for each scene is no less than 1000, and the average density (view number within a unit sphere) is 134.68. It is also worth noting that our system is capable of efficiently capturing large outdoor scenes. Addressing the current lack of large-space and dense light field datasets, we made efforts to include elements such as sky, reflections, lights and shadows that are of interest to researchers in the field of 3D reconstruction during the data capture process. Finally, we validated the effectiveness of our provided dataset on three popular algorithms and also integrated the reconstructed 3DGS results into the Unity engine, demonstrating the potential of utilizing our datasets to enhance the realism of virtual reality (VR) and create feasible interactive spaces. The dataset is available at our project website.
Authors: Enguang Wang, Zhimao Peng, Zhengyuan Xie, Xialei Liu, Ming-Ming Cheng
Abstract: Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old classes, leveraging the class concepts learned from labeled samples. Current GCD methods only use a single visual modality of information, resulting in poor classification of visually similar classes. Though certain classes are visually confused, their text information might be distinct, motivating us to introduce text information into the GCD task. However, the lack of class names for unlabelled data makes it impractical to utilize text information. To tackle this challenging problem, in this paper, we propose a Text Embedding Synthesizer (TES) to generate pseudo text embeddings for unlabelled samples. Specifically, our TES leverages the property that CLIP can generate aligned vision-language features, converting visual embeddings into tokens of the CLIP's text encoder to generate pseudo text embeddings. Besides, we employ a dual-branch framework, through the joint learning and instance consistency of different modality branches, visual and semantic information mutually enhance each other, promoting the interaction and fusion of visual and text embedding space. Our method unlocks the multi-modal potentials of CLIP and outperforms the baseline methods by a large margin on all GCD benchmarks, achieving new state-of-the-art. The code will be released at \url{https://github.com/enguangW/GET}.
Authors: Yi Xu, Kunyu Peng, Di Wen, Ruiping Liu, Junwei Zheng, Yufan Chen, Jiaming Zhang, Alina Roitberg, Kailun Yang, Rainer Stiefelhagen
Abstract: Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model's training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so far. In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark. Observations reveal that these baselines yield only marginal performance when dealing with sparse skeleton data. Consequently, we introduce a novel methodology, NoiseEraSAR, which integrates global sample selection, co-teaching, and Cross-Modal Mixture-of-Experts (CM-MOE) strategies, aimed at mitigating the adverse impacts of label noise. Our proposed approach demonstrates better performance on the established benchmark, setting new state-of-the-art standards. The source code for this study will be made accessible at https://github.com/xuyizdby/NoiseEraSAR.
Authors: Xiaohuan Pei, Tao Huang, Chang Xu
Abstract: Prior efforts in light-weight model development mainly centered on CNN and Transformer-based designs yet faced persistent challenges. CNNs adept at local feature extraction compromise resolution while Transformers offer global reach but escalate computational demands $\mathcal{O}(N^2)$. This ongoing trade-off between accuracy and efficiency remains a significant hurdle. Recently, state space models (SSMs), such as Mamba, have shown outstanding performance and competitiveness in various tasks such as language modeling and computer vision, while reducing the time complexity of global information extraction to $\mathcal{O}(N)$. Inspired by this, this work proposes to explore the potential of visual state space models in light-weight model design and introduce a novel efficient model variant dubbed EfficientVMamba. Concretely, our EfficientVMamba integrates a atrous-based selective scan approach by efficient skip sampling, constituting building blocks designed to harness both global and local representational features. Additionally, we investigate the integration between SSM blocks and convolutions, and introduce an efficient visual state space block combined with an additional convolution branch, which further elevate the model performance. Experimental results show that, EfficientVMamba scales down the computational complexity while yields competitive results across a variety of vision tasks. For example, our EfficientVMamba-S with $1.3$G FLOPs improves Vim-Ti with $1.5$G FLOPs by a large margin of $5.6\%$ accuracy on ImageNet. Code is available at: \url{https://github.com/TerryPei/EfficientVMamba}.
Authors: Zhiqi Li, Yiming Chen, Lingzhe Zhao, Peidong Liu
Abstract: While text-to-3D and image-to-3D generation tasks have received considerable attention, one important but under-explored field between them is controllable text-to-3D generation, which we mainly focus on in this work. To address this task, 1) we introduce Multi-view ControlNet (MVControl), a novel neural network architecture designed to enhance existing pre-trained multi-view diffusion models by integrating additional input conditions, such as edge, depth, normal, and scribble maps. Our innovation lies in the introduction of a conditioning module that controls the base diffusion model using both local and global embeddings, which are computed from the input condition images and camera poses. Once trained, MVControl is able to offer 3D diffusion guidance for optimization-based 3D generation. And, 2) we propose an efficient multi-stage 3D generation pipeline that leverages the benefits of recent large reconstruction models and score distillation algorithm. Building upon our MVControl architecture, we employ a unique hybrid diffusion guidance method to direct the optimization process. In pursuit of efficiency, we adopt 3D Gaussians as our representation instead of the commonly used implicit representations. We also pioneer the use of SuGaR, a hybrid representation that binds Gaussians to mesh triangle faces. This approach alleviates the issue of poor geometry in 3D Gaussians and enables the direct sculpting of fine-grained geometry on the mesh. Extensive experiments demonstrate that our method achieves robust generalization and enables the controllable generation of high-quality 3D content.
Authors: Zhiqiang Pang, Hong Wang, Qi Xie, Deyu Meng, Zongben Xu
Abstract: Exploring and modeling rain generation mechanism is critical for augmenting paired data to ease training of rainy image processing models. Against this task, this study proposes a novel deep learning based rain generator, which fully takes the physical generation mechanism underlying rains into consideration and well encodes the learning of the fundamental rain factors (i.e., shape, orientation, length, width and sparsity) explicitly into the deep network. Its significance lies in that the generator not only elaborately design essential elements of the rain to simulate expected rains, like conventional artificial strategies, but also finely adapt to complicated and diverse practical rainy images, like deep learning methods. By rationally adopting filter parameterization technique, we first time achieve a deep network that is finely controllable with respect to rain factors and able to learn the distribution of these factors purely from data. Our unpaired generation experiments demonstrate that the rain generated by the proposed rain generator is not only of higher quality, but also more effective for deraining and downstream tasks compared to current state-of-the-art rain generation methods. Besides, the paired data augmentation experiments, including both in-distribution and out-of-distribution (OOD), further validate the diversity of samples generated by our model for in-distribution deraining and OOD generalization tasks.
Authors: Yu Du, Yu Song, Ce Guo, Xiaojing Tian, Dong Liu, Ming Cong
Abstract: Due to their complex spatial structure and diverse geometric features, achieving high-precision and robust point cloud registration for complex Die Castings has been a significant challenge in the die-casting industry. Existing point cloud registration methods primarily optimize network models using well-established high-quality datasets, often neglecting practical application in real scenarios. To address this gap, this paper proposes a high-precision adaptive registration method called Multiscale Efficient Deep Closest Point (MEDPNet) and introduces a die-casting point cloud dataset, DieCastCloud, specifically designed to tackle the challenges of point cloud registration in the die-casting industry. The MEDPNet method performs coarse die-casting point cloud data registration using the Efficient-DCP method, followed by precision registration using the Multiscale feature fusion dual-channel registration (MDR) method. We enhance the modeling capability and computational efficiency of the model by replacing the attention mechanism of the Transformer in DCP with Efficient Attention and implementing a collaborative scale mechanism through the combination of serial and parallel blocks. Additionally, we propose the MDR method, which utilizes multilayer perceptrons (MLP), Normal Distributions Transform (NDT), and Iterative Closest Point (ICP) to achieve learnable adaptive fusion, enabling high-precision, scalable, and noise-resistant global point cloud registration. Our proposed method demonstrates excellent performance compared to state-of-the-art geometric and learning-based registration methods when applied to complex die-casting point cloud data.
Authors: Zhixing Hou, Yuzhang Shang, Yan Yan
Abstract: This paper presents a novel Fully Binary Point Cloud Transformer (FBPT) model which has the potential to be widely applied and expanded in the fields of robotics and mobile devices. By compressing the weights and activations of a 32-bit full-precision network to 1-bit binary values, the proposed binary point cloud Transformer network significantly reduces the storage footprint and computational resource requirements of neural network models for point cloud processing tasks, compared to full-precision point cloud networks. However, achieving a fully binary point cloud Transformer network, where all parts except the modules specific to the task are binary, poses challenges and bottlenecks in quantizing the activations of Q, K, V and self-attention in the attention module, as they do not adhere to simple probability distributions and can vary with input data. Furthermore, in our network, the binary attention module undergoes a degradation of the self-attention module due to the uniform distribution that occurs after the softmax operation. The primary focus of this paper is on addressing the performance degradation issue caused by the use of binary point cloud Transformer modules. We propose a novel binarization mechanism called dynamic-static hybridization. Specifically, our approach combines static binarization of the overall network model with fine granularity dynamic binarization of data-sensitive components. Furthermore, we make use of a novel hierarchical training scheme to obtain the optimal model and binarization parameters. These above improvements allow the proposed binarization method to outperform binarization methods applied to convolution neural networks when used in point cloud Transformer structures. To demonstrate the superiority of our algorithm, we conducted experiments on two different tasks: point cloud classification and place recognition.
Authors: Jingyi Xu, Weidong Yang, Lingdong Kong, Youquan Liu, Rui Zhang, Qingyuan Zhou, Ben Fei
Abstract: Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D point cloud data and mitigating the absence of labels when facing a newly defined domain. Various methods of utilizing images to enhance the performance of cross-domain 3D segmentation have recently emerged. However, the pseudo labels, which are generated from models trained on the source domain and provide additional supervised signals for the unseen domain, are inadequate when utilized for 3D segmentation due to their inherent noisiness and consequently restrict the accuracy of neural networks. With the advent of 2D visual foundation models (VFMs) and their abundant knowledge prior, we propose a novel pipeline VFMSeg to further enhance the cross-modal unsupervised domain adaptation framework by leveraging these models. In this work, we study how to harness the knowledge priors learned by VFMs to produce more accurate labels for unlabeled target domains and improve overall performance. We first utilize a multi-modal VFM, which is pre-trained on large scale image-text pairs, to provide supervised labels (VFM-PL) for images and point clouds from the target domain. Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing). Finally, we merge class-wise prediction across modalities to produce more accurate annotations for unlabeled target domains. Our method is evaluated on various autonomous driving datasets and the results demonstrate a significant improvement for 3D segmentation task.
Authors: Xiangtian Xue, Jiasong Wu, Youyong Kong, Lotfi Senhadji, Huazhong Shu
Abstract: We present a novel image editing scenario termed Text-grounded Object Generation (TOG), defined as generating a new object in the real image spatially conditioned by textual descriptions. Existing diffusion models exhibit limitations of spatial perception in complex real-world scenes, relying on additional modalities to enforce constraints, and TOG imposes heightened challenges on scene comprehension under the weak supervision of linguistic information. We propose a universal framework ST-LDM based on Swin-Transformer, which can be integrated into any latent diffusion model with training-free backward guidance. ST-LDM encompasses a global-perceptual autoencoder with adaptable compression scales and hierarchical visual features, parallel with deformable multimodal transformer to generate region-wise guidance for the subsequent denoising process. We transcend the limitation of traditional attention mechanisms that only focus on existing visual features by introducing deformable feature alignment to hierarchically refine spatial positioning fused with multi-scale visual and linguistic information. Extensive Experiments demonstrate that our model enhances the localization of attention mechanisms while preserving the generative capabilities inherent to diffusion models.
Authors: Qi Jiang, Zhonghua Yi, Shaohua Gao, Yao Gao, Xiaolong Qian, Hao Shi, Lei Sun, Zhijie Xu, Kailun Yang, Kaiwei Wang
Abstract: Relying on paired synthetic data, existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap, which leads to suboptimal performance in real-world applications. In this paper, in contrast to improving the simulation pipeline, we deliver a novel insight into real-world CAC from the perspective of Unsupervised Domain Adaptation (UDA). By incorporating readily accessible unpaired real-world data into training, we formalize the Domain Adaptive CAC (DACAC) task, and then introduce a comprehensive Real-world aberrated images (Realab) dataset to benchmark it. The setup task presents a formidable challenge due to the intricacy of understanding the target aberration domain. To this intent, we propose a novel Quntized Domain-Mixing Representation (QDMR) framework as a potent solution to the issue. QDMR adapts the CAC model to the target domain from three key aspects: (1) reconstructing aberrated images of both domains by a VQGAN to learn a Domain-Mixing Codebook (DMC) which characterizes the degradation-aware priors; (2) modulating the deep features in CAC model with DMC to transfer the target domain knowledge; and (3) leveraging the trained VQGAN to generate pseudo target aberrated images from the source ones for convincing target domain supervision. Extensive experiments on both synthetic and real-world benchmarks reveal that the models with QDMR consistently surpass the competitive methods in mitigating the synthetic-to-real gap, which produces visually pleasant real-world CAC results with fewer artifacts. Codes and datasets will be made publicly available.
Authors: Mohammad Shifat E Rabbi, Naqib Sad Pathan, Shiying Li, Yan Zhuang, Abu Hasnat Mohammad Rubaiyat, Gustavo K Rohde
Abstract: Learning from point sets is an essential component in many computer vision and machine learning applications. Native, unordered, and permutation invariant set structure space is challenging to model, particularly for point set classification under spatial deformations. Here we propose a framework for classifying point sets experiencing certain types of spatial deformations, with a particular emphasis on datasets featuring affine deformations. Our approach employs the Linear Optimal Transport (LOT) transform to obtain a linear embedding of set-structured data. Utilizing the mathematical properties of the LOT transform, we demonstrate its capacity to accommodate variations in point sets by constructing a convex data space, effectively simplifying point set classification problems. Our method, which employs a nearest-subspace algorithm in the LOT space, demonstrates label efficiency, non-iterative behavior, and requires no hyper-parameter tuning. It achieves competitive accuracies compared to state-of-the-art methods across various point set classification tasks. Furthermore, our approach exhibits robustness in out-of-distribution scenarios where training and test distributions vary in terms of deformation magnitudes.
Authors: Minyoung Oh, Jae-Young Sim
Abstract: Lifelong person re-identification (LReID) assumes a practical scenario where the model is sequentially trained on continuously incoming datasets while alleviating the catastrophic forgetting in the old datasets. However, not only the training datasets but also the gallery images are incrementally accumulated, that requires a huge amount of computational complexity and storage space to extract the features at the inference phase. In this paper, we address the above mentioned problem by incorporating the backward-compatibility to LReID for the first time. We train the model using the continuously incoming datasets while maintaining the model's compatibility toward the previously trained old models without re-computing the features of the old gallery images. To this end, we devise the cross-model compatibility loss based on the contrastive learning with respect to the replay features across all the old datasets. Moreover, we also develop the knowledge consolidation method based on the part classification to learn the shared representation across different datasets for the backward-compatibility. We suggest a more practical methodology for performance evaluation as well where all the gallery and query images are considered together. Experimental results demonstrate that the proposed method achieves a significantly higher performance of the backward-compatibility compared with the existing methods. It is a promising tool for more practical scenarios of LReID.
Authors: Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim
Abstract: Vision Transformer (ViT) has emerged as a prominent backbone for computer vision. For more efficient ViTs, recent works lessen the quadratic cost of the self-attention layer by pruning or fusing the redundant tokens. However, these works faced the speed-accuracy trade-off caused by the loss of information. Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss. In this paper, we propose a Multi-criteria Token Fusion (MCTF), that gradually fuses the tokens based on multi-criteria (e.g., similarity, informativeness, and size of fused tokens). Further, we utilize the one-step-ahead attention, which is the improved approach to capture the informativeness of the tokens. By training the model equipped with MCTF using a token reduction consistency, we achieve the best speed-accuracy trade-off in the image classification (ImageNet1K). Experimental results prove that MCTF consistently surpasses the previous reduction methods with and without training. Specifically, DeiT-T and DeiT-S with MCTF reduce FLOPs by about 44% while improving the performance (+0.5%, and +0.3%) over the base model, respectively. We also demonstrate the applicability of MCTF in various Vision Transformers (e.g., T2T-ViT, LV-ViT), achieving at least 31% speedup without performance degradation. Code is available at https://github.com/mlvlab/MCTF.
Authors: Yiheng Li, Hongyang Li, Zehao Huang, Hong Chang, Naiyan Wang
Abstract: Multi-modal 3D object detection has exhibited significant progress in recent years. However, most existing methods can hardly scale to long-range scenarios due to their reliance on dense 3D features, which substantially escalate computational demands and memory usage. In this paper, we introduce SparseFusion, a novel multi-modal fusion framework fully built upon sparse 3D features to facilitate efficient long-range perception. The core of our method is the Sparse View Transformer module, which selectively lifts regions of interest in 2D image space into the unified 3D space. The proposed module introduces sparsity from both semantic and geometric aspects which only fill grids that foreground objects potentially reside in. Comprehensive experiments have verified the efficiency and effectiveness of our framework in long-range 3D perception. Remarkably, on the long-range Argoverse2 dataset, SparseFusion reduces memory footprint and accelerates the inference by about two times compared to dense detectors. It also achieves state-of-the-art performance with mAP of 41.2% and CDS of 32.1%. The versatility of SparseFusion is also validated in the temporal object detection task and 3D lane detection task. Codes will be released upon acceptance.
Authors: Dongze Hao, Jian Jia, Longteng Guo, Qunbo Wang, Te Yang, Yan Li, Yanhua Cheng, Bo Wang, Quan Chen, Han Li, Jing Liu
Abstract: Knowledge-based visual question answering (KB-VQA) is a challenging task, which requires the model to leverage external knowledge for comprehending and answering questions grounded in visual content. Recent studies retrieve the knowledge passages from external knowledge bases and then use them to answer questions. However, these retrieved knowledge passages often contain irrelevant or noisy information, which limits the performance of the model. To address the challenge, we propose two synergistic models: Knowledge Condensation model and Knowledge Reasoning model. We condense the retrieved knowledge passages from two perspectives. First, we leverage the multimodal perception and reasoning ability of the visual-language models to distill concise knowledge concepts from retrieved lengthy passages, ensuring relevance to both the visual content and the question. Second, we leverage the text comprehension ability of the large language models to summarize and condense the passages into the knowledge essence which helps answer the question. These two types of condensed knowledge are then seamlessly integrated into our Knowledge Reasoning model, which judiciously navigates through the amalgamated information to arrive at the conclusive answer. Extensive experiments validate the superiority of the proposed method. Compared to previous methods, our method achieves state-of-the-art performance on knowledge-based VQA datasets (65.1% on OK-VQA and 60.1% on A-OKVQA) without resorting to the knowledge produced by GPT-3 (175B).
Authors: Peiran Wu, Yang Liu, Jiayu Huo, Gongyu Zhang, Christos Bergeles, Rachel Sparks, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin
Abstract: Video-based surgical instrument segmentation plays an important role in robot-assisted surgeries. Unlike supervised settings, unsupervised segmentation relies heavily on motion cues, which are challenging to discern due to the typically lower quality of optical flow in surgical footage compared to natural scenes. This presents a considerable burden for the advancement of unsupervised segmentation techniques. In our work, we address the challenge of enhancing model performance despite the inherent limitations of low-quality optical flow. Our methodology employs a three-pronged approach: extracting boundaries directly from the optical flow, selectively discarding frames with inferior flow quality, and employing a fine-tuning process with variable frame rates. We thoroughly evaluate our strategy on the EndoVis2017 VOS dataset and Endovis2017 Challenge dataset, where our model demonstrates promising results, achieving a mean Intersection-over-Union (mIoU) of 0.75 and 0.72, respectively. Our findings suggest that our approach can greatly decrease the need for manual annotations in clinical environments and may facilitate the annotation process for new datasets. The code is available at https://github.com/wpr1018001/Rethinking-Low-quality-Optical-Flow.git
URLs: https://github.com/wpr1018001/Rethinking-Low-quality-Optical-Flow.git
Authors: Tao Wu, Xuewei Li, Zhongang Qi, Di Hu, Xintao Wang, Ying Shan, Xi Li
Abstract: Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains.However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation.In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images.For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images.Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion.For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic.Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images.With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.
Authors: Jiahao Lyu, Jin Wei, Gangyan Zeng, Zeng Li, Enze Xie, Wei Wang, Yu Zhou
Abstract: Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus spotting pipeline of human beings and impressive performances of Pre-trained Language Models (PLMs) on visual tasks, we ask: 1) "Can machines spot texts without precise detection just like human beings?", and if yes, 2) "Is text block another alternative for scene text spotting other than word or character?" To this end, our proposed scene text spotter leverages advanced PLMs to enhance performance without fine-grained detection. Specifically, we first use a simple detector for block-level text detection to obtain rough positional information. Then, we finetune a PLM using a large-scale OCR dataset to achieve accurate recognition. Benefiting from the comprehensive language knowledge gained during the pre-training phase, the PLM-based recognition module effectively handles complex scenarios, including multi-line, reversed, occluded, and incomplete-detection texts. Taking advantage of the fine-tuned language model on scene recognition benchmarks and the paradigm of text block detection, extensive experiments demonstrate the superior performance of our scene text spotter across multiple public benchmarks. Additionally, we attempt to spot texts directly from an entire scene image to demonstrate the potential of PLMs, even Large Language Models (LLMs).
Authors: Tian-Xing Xu, Wenbo Hu, Yu-Kun Lai, Ying Shan, Song-Hai Zhang
Abstract: 3D Gaussian splatting, emerging as a groundbreaking approach, has drawn increasing attention for its capabilities of high-fidelity reconstruction and real-time rendering. However, it couples the appearance and geometry of the scene within the Gaussian attributes, which hinders the flexibility of editing operations, such as texture swapping. To address this issue, we propose a novel approach, namely Texture-GS, to disentangle the appearance from the geometry by representing it as a 2D texture mapped onto the 3D surface, thereby facilitating appearance editing. Technically, the disentanglement is achieved by our proposed texture mapping module, which consists of a UV mapping MLP to learn the UV coordinates for the 3D Gaussian centers, a local Taylor expansion of the MLP to efficiently approximate the UV coordinates for the ray-Gaussian intersections, and a learnable texture to capture the fine-grained appearance. Extensive experiments on the DTU dataset demonstrate that our method not only facilitates high-fidelity appearance editing but also achieves real-time rendering on consumer-level devices, e.g. a single RTX 2080 Ti GPU.
Authors: Daehee Park, Jaeseok Jeong, Sung-Hoon Yoon, Jaewoo Jeong, Kuk-Jin Yoon
Abstract: Trajectory prediction is a challenging problem that requires considering interactions among multiple actors and the surrounding environment. While data-driven approaches have been used to address this complex problem, they suffer from unreliable predictions under distribution shifts during test time. Accordingly, several online learning methods have been proposed using regression loss from the ground truth of observed data leveraging the auto-labeling nature of trajectory prediction task. We mainly tackle the following two issues. First, previous works underfit and overfit as they only optimize the last layer of the motion decoder. To this end, we employ the masked autoencoder (MAE) for representation learning to encourage complex interaction modeling in shifted test distribution for updating deeper layers. Second, utilizing the sequential nature of driving data, we propose an actor-specific token memory that enables the test-time learning of actor-wise motion characteristics. Our proposed method has been validated across various challenging cross-dataset distribution shift scenarios including nuScenes, Lyft, Waymo, and Interaction. Our method surpasses the performance of existing state-of-the-art online learning methods in terms of both prediction accuracy and computational efficiency. The code is available at https://github.com/daeheepark/T4P.
Authors: Wu Liang, X. -G. Ma
Abstract: Since the advent of the Segment Anything Model(SAM) approximately one year ago, it has engendered significant academic interest and has spawned a large number of investigations and publications from various perspectives. However, the deployment of SAM in practical assembly line scenarios has yet to materialize due to its large image encoder, which weighs in at an imposing 632M. In this study, we have replaced the heavyweight image encoder with a lightweight one, thereby enabling the deployment of SAM in practical assembly line scenarios. Specifically, we have employed decoupled distillation to train the encoder of MobileSAM in a resource-limited setting. The entire knowledge distillation experiment can be completed in a single day on a single RTX 4090. The resulting lightweight SAM, referred to as Group-Mix SAM, had 37.63% (2.16M) fewer parameters and 42.5% (15614.7M) fewer floating-point operations compared to MobileSAM. However, on our constructed industrial dataset, MALSD, its mIoU was only marginally lower than that of MobileSAM, at 0.615. Finally, we conducted a comprehensive comparative experiment to demonstrate the superiority of Group-Mix SAM in the industrial domain. With its exceptional performance, our Group-Mix SAM is more suitable for practical assembly line applications.
Authors: Bejamin A. Huerfano, Fernando Jimenez
Abstract: Digital image processing (DIP) is of great importance in validating and guaranteeing parameters that ensure the quality of mass-produced products. Therefore, this article focused on developing an industrial automation method for a zone of a production line model using the DIP. The neo-cascade methodology employed allowed for defining each of the stages in an adequate way, ensuring the inclusion of the relevant methods for its development, which finally incurred in the modeling, design, implementation, and testing of an optimal route generation system for a warehouse area, using DIP with optimization guidelines, in conjunction with an embedded platform and the connection to programmable logic controllers (PLCs) for its execution. The system was based on the OpenCV library; tool focused on artificial vision, which was implemented on an object-oriented programming (OOP) platform based on Java language. It generated the optimal route for the automation of processes in a scale warehouse area, using the segmentation of objects and the optimization of flow in networks as pillars, ending with the connection to PLCs as a method of action, which in case of implementation would eliminate constraints such as process inefficiency, the use of manpower to perform these tasks, inadequate use of resources, among others
Authors: Anirban Mukherjee, Monjoy Narayan Choudhury, Dinesh Babu Jayagopi
Abstract: Face de-identification in videos is a challenging task in the domain of computer vision, primarily used in privacy-preserving applications. Despite the considerable progress achieved through generative vision models, there remain multiple challenges in the latest approaches. They lack a comprehensive discussion and evaluation of aspects such as realism, temporal coherence, and preservation of non-identifiable features. In our work, we propose RID-Twin: a novel pipeline that leverages the state-of-the-art generative models, and decouples identity from motion to perform automatic face de-identification in videos. We investigate the task from a holistic point of view and discuss how our approach addresses the pertinent existing challenges in this domain. We evaluate the performance of our methodology on the widely employed VoxCeleb2 dataset, and also a custom dataset designed to accommodate the limitations of certain behavioral variations absent in the VoxCeleb2 dataset. We discuss the implications and advantages of our work and suggest directions for future research.
Authors: Ziyu Shan, Yujie Zhang, Qi Yang, Haichen Yang, Yiling Xu, Shan Liu
Abstract: No-reference point cloud quality assessment (NR-PCQA) aims to automatically predict the perceptual quality of point clouds without reference, which has achieved remarkable performance due to the utilization of deep learning-based models. However, these data-driven models suffer from the scarcity of labeled data and perform unsatisfactorily in cross-dataset evaluations. To address this problem, we propose a self-supervised pre-training framework using masked autoencoders (PAME) to help the model learn useful representations without labels. Specifically, after projecting point clouds into images, our PAME employs dual-branch autoencoders, reconstructing masked patches from distorted images into the original patches within reference and distorted images. In this manner, the two branches can separately learn content-aware features and distortion-aware features from the projected images. Furthermore, in the model fine-tuning stage, the learned content-aware features serve as a guide to fuse the point cloud quality features extracted from different perspectives. Extensive experiments show that our method outperforms the state-of-the-art NR-PCQA methods on popular benchmarks in terms of prediction accuracy and generalizability.
Authors: Ziyu Shan, Yujie Zhang, Qi Yang, Haichen Yang, Yiling Xu, Jenq-Neng Hwang, Xiaozhong Xu, Shan Liu
Abstract: No-reference point cloud quality assessment (NR-PCQA) aims to automatically evaluate the perceptual quality of distorted point clouds without available reference, which have achieved tremendous improvements due to the utilization of deep neural networks. However, learning-based NR-PCQA methods suffer from the scarcity of labeled data and usually perform suboptimally in terms of generalization. To solve the problem, we propose a novel contrastive pre-training framework tailored for PCQA (CoPA), which enables the pre-trained model to learn quality-aware representations from unlabeled data. To obtain anchors in the representation space, we project point clouds with different distortions into images and randomly mix their local patches to form mixed images with multiple distortions. Utilizing the generated anchors, we constrain the pre-training process via a quality-aware contrastive loss following the philosophy that perceptual quality is closely related to both content and distortion. Furthermore, in the model fine-tuning stage, we propose a semantic-guided multi-view fusion module to effectively integrate the features of projected images from multiple perspectives. Extensive experiments show that our method outperforms the state-of-the-art PCQA methods on popular benchmarks. Further investigations demonstrate that CoPA can also benefit existing learning-based PCQA models.
Authors: Wanfang Su, Lixing Chen, Yang Bai, Xi Lin, Gaolei Li, Zhe Qu, Pan Zhou
Abstract: Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.
Authors: Han Lu, Yichen Xie, Xiaokang Yang, Junchi Yan
Abstract: The pretraining-finetuning paradigm has gained widespread adoption in vision tasks and other fields, yet it faces the significant challenge of high sample annotation costs. To mitigate this, the concept of active finetuning has emerged, aiming to select the most appropriate samples for model finetuning within a limited budget. Traditional active learning methods often struggle in this setting due to their inherent bias in batch selection. Furthermore, the recent active finetuning approach has primarily concentrated on aligning the distribution of selected subsets with the overall data pool, focusing solely on diversity. In this paper, we propose a Bi-Level Active Finetuning framework to select the samples for annotation in one shot, which includes two stages: core sample selection for diversity, and boundary sample selection for uncertainty. The process begins with the identification of pseudo-class centers, followed by an innovative denoising method and an iterative strategy for boundary sample selection in the high-dimensional feature space, all without relying on ground-truth labels. Our comprehensive experiments provide both qualitative and quantitative evidence of our method's efficacy, outperforming all the existing baselines.
Authors: Baoquan Zhang, Huaibin Wang, Luo Chuyao, Xutao Li, Liang Guotao, Yunming Ye, Xiaochen Qi, Yao He
Abstract: Vector-Quantized Image Modeling (VQIM) is a fundamental research problem in image synthesis, which aims to represent an image with a discrete token sequence. Existing studies effectively address this problem by learning a discrete codebook from scratch and in a code-independent manner to quantize continuous representations into discrete tokens. However, learning a codebook from scratch and in a code-independent manner is highly challenging, which may be a key reason causing codebook collapse, i.e., some code vectors can rarely be optimized without regard to the relationship between codes and good codebook priors such that die off finally. In this paper, inspired by pretrained language models, we find that these language models have actually pretrained a superior codebook via a large number of text corpus, but such information is rarely exploited in VQIM. To this end, we propose a novel codebook transfer framework with part-of-speech, called VQCT, which aims to transfer a well-trained codebook from pretrained language models to VQIM for robust codebook learning. Specifically, we first introduce a pretrained codebook from language models and part-of-speech knowledge as priors. Then, we construct a vision-related codebook with these priors for achieving codebook transfer. Finally, a novel codebook transfer network is designed to exploit abundant semantic relationships between codes contained in pretrained codebooks for robust VQIM codebook learning. Experimental results on four datasets show that our VQCT method achieves superior VQIM performance over previous state-of-the-art methods.
Authors: Xinli Yue, Ningping Mou, Qian Wang, Lingchen Zhao
Abstract: Deep neural networks are vulnerable to adversarial attacks, often leading to erroneous outputs. Adversarial training has been recognized as one of the most effective methods to counter such attacks. However, existing adversarial training techniques have predominantly been tested on balanced datasets, whereas real-world data often exhibit a long-tailed distribution, casting doubt on the efficacy of these methods in practical scenarios. In this paper, we delve into adversarial training under long-tailed distributions. Through an analysis of the previous work "RoBal", we discover that utilizing Balanced Softmax Loss alone can achieve performance comparable to the complete RoBal approach while significantly reducing training overheads. Additionally, we reveal that, similar to uniform distributions, adversarial training under long-tailed distributions also suffers from robust overfitting. To address this, we explore data augmentation as a solution and unexpectedly discover that, unlike results obtained with balanced data, data augmentation not only effectively alleviates robust overfitting but also significantly improves robustness. We further investigate the reasons behind the improvement of robustness through data augmentation and identify that it is attributable to the increased diversity of examples. Extensive experiments further corroborate that data augmentation alone can significantly improve robustness. Finally, building on these findings, we demonstrate that compared to RoBal, the combination of BSL and data augmentation leads to a +6.66% improvement in model robustness under AutoAttack on CIFAR-10-LT. Our code is available at https://github.com/NISPLab/AT-BSL .
Authors: Alhassan Mumuni, Fuseini Mumuni, Nana Kobina Gerrar
Abstract: The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task. However, in many scenarios, it is often challenging to obtain sufficient image data for the target task. Data augmentation is a way to mitigate this challenge. A common practice is to explicitly transform existing images in desired ways so as to create the required volume and variability of training data necessary to achieve good generalization performance. In situations where data for the target domain is not accessible, a viable workaround is to synthesize training data from scratch--i.e., synthetic data augmentation. This paper presents an extensive review of synthetic data augmentation techniques. It covers data synthesis approaches based on realistic 3D graphics modeling, neural style transfer (NST), differential neural rendering, and generative artificial intelligence (AI) techniques such as generative adversarial networks (GANs) and variational autoencoders (VAEs). For each of these classes of methods, we focus on the important data generation and augmentation techniques, general scope of application and specific use-cases, as well as existing limitations and possible workarounds. Additionally, we provide a summary of common synthetic datasets for training computer vision models, highlighting the main features, application domains and supported tasks. Finally, we discuss the effectiveness of synthetic data augmentation methods. Since this is the first paper to explore synthetic data augmentation methods in great detail, we are hoping to equip readers with the necessary background information and in-depth knowledge of existing methods and their attendant issues.
Authors: Chong Wang, Yi Yu, Lanqing Guo, Bihan Wen
Abstract: Shadow removal is a task aimed at erasing regional shadows present in images and reinstating visually pleasing natural scenes with consistent illumination. While recent deep learning techniques have demonstrated impressive performance in image shadow removal, their robustness against adversarial attacks remains largely unexplored. Furthermore, many existing attack frameworks typically allocate a uniform budget for perturbations across the entire input image, which may not be suitable for attacking shadow images. This is primarily due to the unique characteristic of spatially varying illumination within shadow images. In this paper, we propose a novel approach, called shadow-adaptive adversarial attack. Different from standard adversarial attacks, our attack budget is adjusted based on the pixel intensity in different regions of shadow images. Consequently, the optimized adversarial noise in the shadowed regions becomes visually less perceptible while permitting a greater tolerance for perturbations in non-shadow regions. The proposed shadow-adaptive attacks naturally align with the varying illumination distribution in shadow images, resulting in perturbations that are less conspicuous. Building on this, we conduct a comprehensive empirical evaluation of existing shadow removal methods, subjecting them to various levels of attack on publicly available datasets.
Authors: Huilin Xu, Tao Chen, Feng Xu
Abstract: The ability to model the underlying dynamics of visual scenes and reason about the future is central to human intelligence. Many attempts have been made to empower intelligent systems with such physical understanding and prediction abilities. However, most existing methods focus on pixel-to-pixel prediction, which suffers from heavy computational costs while lacking a deep understanding of the physical dynamics behind videos. Recently, object-centric prediction methods have emerged and attracted increasing interest. Inspired by it, this paper proposes an unsupervised object-centric prediction model that makes future predictions by learning visual dynamics between objects. Our model consists of two modules, perceptual, and dynamic module. The perceptual module is utilized to decompose images into several objects and synthesize images with a set of object-centric representations. The dynamic module fuses contextual information, takes environment-object and object-object interaction into account, and predicts the future trajectory of objects. Extensive experiments are conducted to validate the effectiveness of the proposed method. Both quantitative and qualitative experimental results demonstrate that our model generates higher visual quality and more physically reliable predictions compared to the state-of-the-art methods.
Authors: Tingbing Yan, Wenzheng Zeng, Yang Xiao, Xingyu Tong, Bo Tan, Zhiwen Fang, Zhiguo Cao, Joey Tianyi Zhou
Abstract: Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e.g., joint location), and may suffer from local information loss and low generalization ability. To alleviate these, we propose to leverage text description generated from large language models (LLM) that contain high-level human knowledge, to guide feature learning, in a global-local-global way. Particularly, during training, we design $2$ prompts to gain global and local text descriptions of each action from an LLM. We first utilize the global text description to guide the skeleton encoder focus on informative joints (i.e.,global-to-local). Then we build non-local interaction between local text and joint features, to form the final global representation (i.e., local-to-global). To mitigate the asymmetry issue between the training and inference phases, we further design a dual-branch architecture that allows the model to perform novel class inference without any text input, also making the additional inference cost neglectable compared with the base skeleton encoder. Extensive experiments on three different benchmarks show that CrossGLG consistently outperforms the existing SOTA methods with large margins, and the inference cost (model size) is only $2.8$\% than the previous SOTA. CrossGLG can also serve as a plug-and-play module that can substantially enhance the performance of different SOTA skeleton encoders with a neglectable cost during inference. The source code will be released soon.
Authors: Guiyu Zhao, Zewen Du, Zhentao Guo, Hongbin Ma
Abstract: Addressing the challenges posed by the substantial gap in point cloud data collected from diverse sensors, achieving robust cross-source point cloud registration becomes a formidable task. In response, we present a novel framework for point cloud registration with broad applicability, suitable for both homologous and cross-source registration scenarios. To tackle the issues arising from different densities and distributions in cross-source point cloud data, we introduce a feature representation based on spherical voxels. Furthermore, addressing the challenge of numerous outliers and mismatches in cross-source registration, we propose a hierarchical correspondence filtering approach. This method progressively filters out mismatches, yielding a set of high-quality correspondences. Our method exhibits versatile applicability and excels in both traditional homologous registration and challenging cross-source registration scenarios. Specifically, in homologous registration using the 3DMatch dataset, we achieve the highest registration recall of 95.1% and an inlier ratio of 87.8%. In cross-source point cloud registration, our method attains the best RR on the 3DCSR dataset, demonstrating a 9.3 percentage points improvement. The code is available at https://github.com/GuiyuZhao/VRHCF.
Authors: Junzhuo Chen, Zonghan Lu, Shitong Kang
Abstract: In the wake of the global spread of monkeypox, accurate disease recognition has become crucial. This study introduces an improved SE-InceptionV3 model, embedding the SENet module and incorporating L2 regularization into the InceptionV3 framework to enhance monkeypox disease detection. Utilizing the Kaggle monkeypox dataset, which includes images of monkeypox and similar skin conditions, our model demonstrates a noteworthy accuracy of 96.71% on the test set, outperforming conventional methods and deep learning models. The SENet modules channel attention mechanism significantly elevates feature representation, while L2 regularization ensures robust generalization. Extensive experiments validate the models superiority in precision, recall, and F1 score, highlighting its effectiveness in differentiating monkeypox lesions in diverse and complex cases. The study not only provides insights into the application of advanced CNN architectures in medical diagnostics but also opens avenues for further research in model optimization and hyperparameter tuning for enhanced disease recognition. https://github.com/jzc777/SE-inceptionV3-L2
Authors: Qianjiang Hu, Zhimin Zhang, Wei Hu
Abstract: Autonomous driving demands high-quality LiDAR data, yet the cost of physical LiDAR sensors presents a significant scaling-up challenge. While recent efforts have explored deep generative models to address this issue, they often consume substantial computational resources with slow generation speeds while suffering from a lack of realism. To address these limitations, we introduce RangeLDM, a novel approach for rapidly generating high-quality range-view LiDAR point clouds via latent diffusion models. We achieve this by correcting range-view data distribution for accurate projection from point clouds to range images via Hough voting, which has a critical impact on generative learning. We then compress the range images into a latent space with a variational autoencoder, and leverage a diffusion model to enhance expressivity. Additionally, we instruct the model to preserve 3D structural fidelity by devising a range-guided discriminator. Experimental results on KITTI-360 and nuScenes datasets demonstrate both the robust expressiveness and fast speed of our LiDAR point cloud generation.
Authors: Nan Gao, Jia Li, Huaibo Huang, Zhi Zeng, Ke Shang, Shuwu Zhang, Ran He
Abstract: Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of degradation patterns. Current methods have low generalization across photorealistic and heterogeneous domains. In this paper, we propose a Diffusion-Information-Diffusion (DID) framework to tackle diffusion manifold hallucination correction (DiffMAC), which achieves high-generalization face restoration in diverse degraded scenes and heterogeneous domains. Specifically, the first diffusion stage aligns the restored face with spatial feature embedding of the low-quality face based on AdaIN, which synthesizes degradation-removal results but with uncontrollable artifacts for some hard cases. Based on Stage I, Stage II considers information compression using manifold information bottleneck (MIB) and finetunes the first diffusion model to improve facial fidelity. DiffMAC effectively fights against blind degradation patterns and synthesizes high-quality faces with attribute and identity consistencies. Experimental results demonstrate the superiority of DiffMAC over state-of-the-art methods, with a high degree of generalization in real-world and heterogeneous settings. The source code and models will be public.
Authors: Ruida Zhang, Chenyangguang Zhang, Yan Di, Fabian Manhardt, Xingyu Liu, Federico Tombari, Xiangyang Ji
Abstract: In this paper, we present KP-RED, a unified KeyPoint-driven REtrieval and Deformation framework that takes object scans as input and jointly retrieves and deforms the most geometrically similar CAD models from a pre-processed database to tightly match the target. Unlike existing dense matching based methods that typically struggle with noisy partial scans, we propose to leverage category-consistent sparse keypoints to naturally handle both full and partial object scans. Specifically, we first employ a lightweight retrieval module to establish a keypoint-based embedding space, measuring the similarity among objects by dynamically aggregating deformation-aware local-global features around extracted keypoints. Objects that are close in the embedding space are considered similar in geometry. Then we introduce the neural cage-based deformation module that estimates the influence vector of each keypoint upon cage vertices inside its local support region to control the deformation of the retrieved shape. Extensive experiments on the synthetic dataset PartNet and the real-world dataset Scan2CAD demonstrate that KP-RED surpasses existing state-of-the-art approaches by a large margin. Codes and trained models will be released in https://github.com/lolrudy/KP-RED.
Authors: Huiqiang Sun, Xingyi Li, Liao Shen, Xinyi Ye, Ke Xian, Zhiguo Cao
Abstract: Recent advancements in dynamic neural radiance field methods have yielded remarkable outcomes. However, these approaches rely on the assumption of sharp input images. When faced with motion blur, existing dynamic NeRF methods often struggle to generate high-quality novel views. In this paper, we propose DyBluRF, a dynamic radiance field approach that synthesizes sharp novel views from a monocular video affected by motion blur. To account for motion blur in input images, we simultaneously capture the camera trajectory and object Discrete Cosine Transform (DCT) trajectories within the scene. Additionally, we employ a global cross-time rendering approach to ensure consistent temporal coherence across the entire scene. We curate a dataset comprising diverse dynamic scenes that are specifically tailored for our task. Experimental results on our dataset demonstrate that our method outperforms existing approaches in generating sharp novel views from motion-blurred inputs while maintaining spatial-temporal consistency of the scene.
Authors: Xiaotong Yu, Ruihan Xie, Zhihe Zhao, Chang-Wen Chen
Abstract: While we enjoy the richness and informativeness of multimodal data, it also introduces interference and redundancy of information. To achieve optimal domain interpretation with limited resources, we propose CSDNet, a lightweight \textbf{C}ross \textbf{S}hallow and \textbf{D}eep Perception \textbf{Net}work designed to integrate two modalities with less coherence, thereby discarding redundant information or even modality. We implement our CSDNet for Salient Object Detection (SOD) task in robotic perception. The proposed method capitalises on spatial information prescreening and implicit coherence navigation across shallow and deep layers of the depth-thermal (D-T) modality, prioritising integration over fusion to maximise the scene interpretation. To further refine the descriptive capabilities of the encoder for the less-known D-T modalities, we also propose SAMAEP to guide an effective feature mapping to the generalised feature space. Our approach is tested on the VDT-2048 dataset, leveraging the D-T modality outperforms those of SOTA methods using RGB-T or RGB-D modalities for the first time, achieves comparable performance with the RGB-D-T triple-modality benchmark method with 5.97 times faster at runtime and demanding 0.0036 times fewer FLOPs. Demonstrates the proposed CSDNet effectively integrates the information from the D-T modality. The code will be released upon acceptance.
Authors: Hang Zhang, Wenxiao Zhang, Haoxuan Qu, Jun Liu
Abstract: Human-centered dynamic scene understanding plays a pivotal role in enhancing the capability of robotic and autonomous systems, in which Video-based Human-Object Interaction (V-HOI) detection is a crucial task in semantic scene understanding, aimed at comprehensively understanding HOI relationships within a video to benefit the behavioral decisions of mobile robots and autonomous driving systems. Although previous V-HOI detection models have made significant strides in accurate detection on specific datasets, they still lack the general reasoning ability like human beings to effectively induce HOI relationships. In this study, we propose V-HOI Multi-LLMs Collaborated Reasoning (V-HOI MLCR), a novel framework consisting of a series of plug-and-play modules that could facilitate the performance of current V-HOI detection models by leveraging the strong reasoning ability of different off-the-shelf pre-trained large language models (LLMs). We design a two-stage collaboration system of different LLMs for the V-HOI task. Specifically, in the first stage, we design a Cross-Agents Reasoning scheme to leverage the LLM conduct reasoning from different aspects. In the second stage, we perform Multi-LLMs Debate to get the final reasoning answer based on the different knowledge in different LLMs. Additionally, we devise an auxiliary training strategy that utilizes CLIP, a large vision-language model to enhance the base V-HOI models' discriminative ability to better cooperate with LLMs. We validate the superiority of our design by demonstrating its effectiveness in improving the prediction accuracy of the base V-HOI model via reasoning from multiple perspectives.
Authors: Bo Xu, Ziao Liu, Mengqi Guo, Jiancheng Li, Gim Hee Li
Abstract: We propose a novel rolling shutter bundle adjustment method for neural radiance fields (NeRF), which utilizes the unordered rolling shutter (RS) images to obtain the implicit 3D representation. Existing NeRF methods suffer from low-quality images and inaccurate initial camera poses due to the RS effect in the image, whereas, the previous method that incorporates the RS into NeRF requires strict sequential data input, limiting its widespread applicability. In constant, our method recovers the physical formation of RS images by estimating camera poses and velocities, thereby removing the input constraints on sequential data. Moreover, we adopt a coarse-to-fine training strategy, in which the RS epipolar constraints of the pairwise frames in the scene graph are used to detect the camera poses that fall into local minima. The poses detected as outliers are corrected by the interpolation method with neighboring poses. The experimental results validate the effectiveness of our method over state-of-the-art works and demonstrate that the reconstruction of 3D representations is not constrained by the requirement of video sequence input.
Authors: Yu Liu, Wenlin Zhang, Shaochu Wang, Fangyu Zuo, Peiguang Jing, Yong Ji
Abstract: Early diagnosis of Alzheimer's Disease (AD) is very important for following medical treatments, and eye movements under special visual stimuli may serve as a potential non-invasive biomarker for detecting cognitive abnormalities of AD patients. In this paper, we propose an Depth-induced saliency comparison network (DISCN) for eye movement analysis, which may be used for diagnosis the Alzheimers disease. In DISCN, a salient attention module fuses normal eye movements with RGB and depth maps of visual stimuli using hierarchical salient attention (SAA) to evaluate comprehensive saliency maps, which contain information from both visual stimuli and normal eye movement behaviors. In addition, we introduce serial attention module (SEA) to emphasis the most abnormal eye movement behaviors to reduce personal bias for a more robust result. According to our experiments, the DISCN achieves consistent validity in classifying the eye movements between the AD patients and normal controls.
Authors: Changhong Hou, Junchuan Yu, Daqing Ge, Liu Yang, Laidian Xi, Yunxuan Pang, Yi Wen
Abstract: Landslides are one of the most destructive natural disasters in the world, posing a serious threat to human life and safety. The development of foundation models has provided a new research paradigm for large-scale landslide detection. The Segment Anything Model (SAM) has garnered widespread attention in the field of image segmentation. However, our experiment found that SAM performed poorly in the task of landslide segmentation. We propose TransLandSeg, which is a transfer learning approach for landslide semantic segmentation based on a vision foundation model (VFM). TransLandSeg outperforms traditional semantic segmentation models on both the Landslide4Sense dataset and the Bijie landslide dataset. Our proposed adaptive transfer learning (ATL) architecture enables the powerful segmentation capability of SAM to be transferred to landslide detection by training only 1.3% of the number of the parameters of SAM, which greatly improves the training efficiency of the model. Finally we also conducted ablation experiments on models with different ATL structures, concluded that the deployment location and residual connection of ATL play an important role in TransLandSeg accuracy improvement.
Authors: Tianrui Huang, Pu Cao, Lu Yang, Chun Liu, Mengjie Hu, Zhiwei Liu, Qing Song
Abstract: Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications. While current editing approaches have made improvements under text guidance, most of them have only focused on preserving the information of the input image, disregarding the importance of editability and alignment to the target prompt. In this paper, we prioritize the editability by proposing a zero-shot image editing method, named \textbf{E}nhance \textbf{E}ditability for text-based image \textbf{E}diting via \textbf{E}fficient \textbf{C}LIP guidance (\textbf{E4C}), which only requires inference-stage optimization to explicitly enhance the edibility and text alignment. Specifically, we develop a unified dual-branch feature-sharing pipeline that enables the preservation of the structure or texture of the source image while allowing the other to be adapted based on the editing task. We further integrate CLIP guidance into our pipeline by utilizing our novel random-gateway optimization mechanism to efficiently enhance the semantic alignment with the target prompt. Comprehensive quantitative and qualitative experiments demonstrate that our method effectively resolves the text alignment issues prevalent in existing methods while maintaining the fidelity to the source image, and performs well across a wide range of editing tasks.
Authors: Ruiyang Hao, Siqi Fan, Yingru Dai, Zhenlin Zhang, Chenxi Li, Yuntian Wang, Haibao Yu, Wenxian Yang, Jirui Yuan, Zaiqing Nie
Abstract: The value of roadside perception, which could extend the boundaries of autonomous driving and traffic management, has gradually become more prominent and acknowledged in recent years. However, existing roadside perception approaches only focus on the single-infrastructure sensor system, which cannot realize a comprehensive understanding of a traffic area because of the limited sensing range and blind spots. Orienting high-quality roadside perception, we need Roadside Cooperative Perception (RCooper) to achieve practical area-coverage roadside perception for restricted traffic areas. Rcooper has its own domain-specific challenges, but further exploration is hindered due to the lack of datasets. We hence release the first real-world, large-scale RCooper dataset to bloom the research on practical roadside cooperative perception, including detection and tracking. The manually annotated dataset comprises 50k images and 30k point clouds, including two representative traffic scenes (i.e., intersection and corridor). The constructed benchmarks prove the effectiveness of roadside cooperation perception and demonstrate the direction of further research. Codes and dataset can be accessed at: https://github.com/AIR-THU/DAIR-RCooper.
Authors: Hao Li, Yuanyuan Gao, Dingwen Zhang, Chenming Wu, Yalun Dai, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han
Abstract: This paper presents GGRt, a novel approach to generalizable novel view synthesis that alleviates the need for real camera poses, complexity in processing high-resolution images, and lengthy optimization processes, thus facilitating stronger applicability of 3D Gaussian Splatting (3D-GS) in real-world scenarios. Specifically, we design a novel joint learning framework that consists of an Iterative Pose Optimization Network (IPO-Net) and a Generalizable 3D-Gaussians (G-3DG) model. With the joint learning mechanism, the proposed framework can inherently estimate robust relative pose information from the image observations and thus primarily alleviate the requirement of real camera poses. Moreover, we implement a deferred back-propagation mechanism that enables high-resolution training and inference, overcoming the resolution constraints of previous methods. To enhance the speed and efficiency, we further introduce a progressive Gaussian cache module that dynamically adjusts during training and inference. As the first pose-free generalizable 3D-GS framework, GGRt achieves inference at $\ge$ 5 FPS and real-time rendering at $\ge$ 100 FPS. Through extensive experimentation, we demonstrate that our method outperforms existing NeRF-based pose-free techniques in terms of inference speed and effectiveness. It can also approach the real pose-based 3D-GS methods. Our contributions provide a significant leap forward for the integration of computer vision and computer graphics into practical applications, offering state-of-the-art results on LLFF, KITTI, and Waymo Open datasets and enabling real-time rendering for immersive experiences.
Authors: Yogesh Kumar, Pekka Marttinen
Abstract: We introduce eCLIP, an enhanced version of the CLIP model that integrates expert annotations in the form of radiologist eye-gaze heatmaps. It tackles key challenges in contrastive multi-modal medical imaging analysis, notably data scarcity and the "modality gap" -- a significant disparity between image and text embeddings that diminishes the quality of representations and hampers cross-modal interoperability. eCLIP integrates a heatmap processor and leverages mixup augmentation to efficiently utilize the scarce expert annotations, thus boosting the model's learning effectiveness. eCLIP is designed to be generally applicable to any variant of CLIP without requiring any modifications of the core architecture. Through detailed evaluations across several tasks, including zero-shot inference, linear probing, cross-modal retrieval, and Retrieval Augmented Generation (RAG) of radiology reports using a frozen Large Language Model, eCLIP showcases consistent improvements in embedding quality. The outcomes reveal enhanced alignment and uniformity, affirming eCLIP's capability to harness high-quality annotations for enriched multi-modal analysis in the medical imaging domain.
Authors: Fadillah Adamsyah Maani, Numan Saeed, Aleksandr Matsun, Mohammad Yaqub
Abstract: Deep learning (DL) models have been advancing automatic medical image analysis on various modalities, including echocardiography, by offering a comprehensive end-to-end training pipeline. This approach enables DL models to regress ejection fraction (EF) directly from 2D+time echocardiograms, resulting in superior performance. However, the end-to-end training pipeline makes the learned representations less explainable. The representations may also fail to capture the continuous relation among echocardiogram clips, indicating the existence of spurious correlations, which can negatively affect the generalization. To mitigate this issue, we propose CoReEcho, a novel training framework emphasizing continuous representations tailored for direct EF regression. Our extensive experiments demonstrate that CoReEcho: 1) outperforms the current state-of-the-art (SOTA) on the largest echocardiography dataset (EchoNet-Dynamic) with MAE of 3.90 & R2 of 82.44, and 2) provides robust and generalizable features that transfer more effectively in related downstream tasks. The code is publicly available at https://github.com/fadamsyah/CoReEcho.
Authors: Peng Zheng, Tao Liu, Zili Yi, Rui Ma
Abstract: With the development of neural radiance fields and generative models, numerous methods have been proposed for learning 3D human generation from 2D images. These methods allow control over the pose of the generated 3D human and enable rendering from different viewpoints. However, none of these methods explore semantic disentanglement in human image synthesis, i.e., they can not disentangle the generation of different semantic parts, such as the body, tops, and bottoms. Furthermore, existing methods are limited to synthesize images at $512^2$ resolution due to the high computational cost of neural radiance fields. To address these limitations, we introduce SemanticHuman-HD, the first method to achieve semantic disentangled human image synthesis. Notably, SemanticHuman-HD is also the first method to achieve 3D-aware image synthesis at $1024^2$ resolution, benefiting from our proposed 3D-aware super-resolution module. By leveraging the depth maps and semantic masks as guidance for the 3D-aware super-resolution, we significantly reduce the number of sampling points during volume rendering, thereby reducing the computational cost. Our comparative experiments demonstrate the superiority of our method. The effectiveness of each proposed component is also verified through ablation studies. Moreover, our method opens up exciting possibilities for various applications, including 3D garment generation, semantic-aware image synthesis, controllable image synthesis, and out-of-domain image synthesis.
Authors: Andr\'es Mu\~noz, Daniel Borrajo
Abstract: User Interface (UI) understanding has been an increasingly popular topic over the last few years. So far, there has been a vast focus solely on web and mobile applications. In this paper, we introduce the harder task of computer UI understanding. With the goal of enabling research in this field, we have generated a dataset with a set of videos where a user is performing a sequence of actions and each image shows the desktop contents at that time point. We also present a framework that is composed of a synthetic sample generation pipeline to augment the dataset with relevant characteristics, and a contrastive learning method to classify images in the videos. We take advantage of the natural conditional, tree-like, relationship of the images' characteristics to regularize the learning of the representations by dealing with multiple partial tasks simultaneously. Experimental results show that the proposed framework outperforms previously proposed hierarchical multi-label contrastive losses in fine-grain UI classification.
Authors: Soikat Hasan Ahmed, Jan Finkbeiner, Emre Neftci
Abstract: Event cameras offer high temporal resolution and dynamic range with minimal motion blur, making them promising for object detection tasks. While Spiking Neural Networks (SNNs) are a natural match for event-based sensory data and enable ultra-energy efficient and low latency inference on neuromorphic hardware, Artificial Neural Networks (ANNs) tend to display more stable training dynamics and faster convergence resulting in greater task performance. Hybrid SNN-ANN approaches are a promising alternative, enabling to leverage the strengths of both SNN and ANN architectures. In this work, we introduce the first Hybrid Attention-based SNN-ANN backbone for object detection using event cameras. We propose a novel Attention-based SNN-ANN bridge module to capture sparse spatial and temporal relations from the SNN layer and convert them into dense feature maps for the ANN part of the backbone. Experimental results demonstrate that our proposed method surpasses baseline hybrid and SNN-based approaches by significant margins, with results comparable to existing ANN-based methods. Extensive ablation studies confirm the effectiveness of our proposed modules and architectural choices. These results pave the way toward a hybrid SNN-ANN architecture that achieves ANN like performance at a drastically reduced parameter budget. We implemented the SNN blocks on digital neuromorphic hardware to investigate latency and power consumption and demonstrate the feasibility of our approach.
Authors: Mingxiao Li, Bo Wan, Marie-Francine Moens, Tinne Tuytelaars
Abstract: In recent years, diffusion models have made remarkable strides in text-to-video generation, sparking a quest for enhanced control over video outputs to more accurately reflect user intentions. Traditional efforts predominantly focus on employing either semantic cues, like images or depth maps, or motion-based conditions, like moving sketches or object bounding boxes. Semantic inputs offer a rich scene context but lack detailed motion specificity; conversely, motion inputs provide precise trajectory information but miss the broader semantic narrative. For the first time, we integrate both semantic and motion cues within a diffusion model for video generation, as demonstrated in Fig 1. To this end, we introduce the Scene and Motion Conditional Diffusion (SMCD), a novel methodology for managing multimodal inputs. It incorporates a recognized motion conditioning module and investigates various approaches to integrate scene conditions, promoting synergy between different modalities. For model training, we separate the conditions for the two modalities, introducing a two-stage training pipeline. Experimental results demonstrate that our design significantly enhances video quality, motion precision, and semantic coherence.
Authors: Chen Zhou, Mohit Prabhushankar, Ghassan AlRegib
Abstract: Annotators exhibit disagreement during data labeling, which can be termed as annotator label uncertainty. Annotator label uncertainty manifests in variations of labeling quality. Training with a single low-quality annotation per sample induces model reliability degradations. In this work, we first examine the effects of annotator label uncertainty in terms of the model's generalizability and prediction uncertainty. We observe that the model's generalizability and prediction uncertainty degrade with the presence of low-quality noisy labels. Meanwhile, our evaluation of existing uncertainty estimation algorithms indicates their incapability in response to annotator label uncertainty. To mitigate performance degradation, prior methods show that training models with labels collected from multiple independent annotators can enhance generalizability. However, they require massive annotations. Hence, we introduce a novel perceptual quality-based model training framework to objectively generate multiple labels for model training to enhance reliability, while avoiding massive annotations. Specifically, we first select a subset of samples with low perceptual quality scores ranked by statistical regularities of visual signals. We then assign de-aggregated labels to each sample in this subset to obtain a training set with multiple labels. Our experiments and analysis demonstrate that training with the proposed framework alleviates the degradation of generalizability and prediction uncertainty caused by annotator label uncertainty.
Authors: Chuang Lin, Yi Jiang, Lizhen Qu, Zehuan Yuan, Jianfei Cai
Abstract: In recent research, significant attention has been devoted to the open-vocabulary object detection task, aiming to generalize beyond the limited number of classes labeled during training and detect objects described by arbitrary category names at inference. Compared with conventional object detection, open vocabulary object detection largely extends the object detection categories. However, it relies on calculating the similarity between image regions and a set of arbitrary category names with a pretrained vision-and-language model. This implies that, despite its open-set nature, the task still needs the predefined object categories during the inference stage. This raises the question: What if we do not have exact knowledge of object categories during inference? In this paper, we call such a new setting as generative open-ended object detection, which is a more general and practical problem. To address it, we formulate object detection as a generative problem and propose a simple framework named GenerateU, which can detect dense objects and generate their names in a free-form way. Particularly, we employ Deformable DETR as a region proposal generator with a language model translating visual regions to object names. To assess the free-form object detection task, we introduce an evaluation method designed to quantitatively measure the performance of generative outcomes. Extensive experiments demonstrate strong zero-shot detection performance of our GenerateU. For example, on the LVIS dataset, our GenerateU achieves comparable results to the open-vocabulary object detection method GLIP, even though the category names are not seen by GenerateU during inference. Code is available at: https:// github.com/FoundationVision/GenerateU .
Authors: Feng Li, Yixuan Wu, Zichao Liang, Runmin Cong, Huihui Bai, Yao Zhao, Meng Wang
Abstract: Diffusion models (DM) have achieved remarkable promise in image super-resolution (SR). However, most of them are tailored to solving non-blind inverse problems with fixed known degradation settings, limiting their adaptability to real-world applications that involve complex unknown degradations. In this work, we propose BlindDiff, a DM-based blind SR method to tackle the blind degradation settings in SISR. BlindDiff seamlessly integrates the MAP-based optimization into DMs, which constructs a joint distribution of the low-resolution (LR) observation, high-resolution (HR) data, and degradation kernels for the data and kernel priors, and solves the blind SR problem by unfolding MAP approach along with the reverse process. Unlike most DMs, BlindDiff firstly presents a modulated conditional transformer (MCFormer) that is pre-trained with noise and kernel constraints, further serving as a posterior sampler to provide both priors simultaneously. Then, we plug a simple yet effective kernel-aware gradient term between adjacent sampling iterations that guides the diffusion model to learn degradation consistency knowledge. This also enables to joint refine the degradation model as well as HR images by observing the previous denoised sample. With the MAP-based reverse diffusion process, we show that BlindDiff advocates alternate optimization for blur kernel estimation and HR image restoration in a mutual reinforcing manner. Experiments on both synthetic and real-world datasets show that BlindDiff achieves the state-of-the-art performance with significant model complexity reduction compared to recent DM-based methods. Code will be available at \url{https://github.com/lifengcs/BlindDiff}
Authors: Marcos Fern\'andez-Rodr\'iguez, Bruno Silva, Sandro Queir\'os, Helena R. Torres, Bruno Oliveira, Pedro Morais, Lukas R. Buschle, Jorge Correia-Pinto, Estev\~ao Lima, Jo\~ao L. Vila\c{c}a
Abstract: Surgical instrument segmentation in laparoscopy is essential for computer-assisted surgical systems. Despite the Deep Learning progress in recent years, the dynamic setting of laparoscopic surgery still presents challenges for precise segmentation. The nnU-Net framework excelled in semantic segmentation analyzing single frames without temporal information. The framework's ease of use, including its ability to be automatically configured, and its low expertise requirements, have made it a popular base framework for comparisons. Optical flow (OF) is a tool commonly used in video tasks to estimate motion and represent it in a single frame, containing temporal information. This work seeks to employ OF maps as an additional input to the nnU-Net architecture to improve its performance in the surgical instrument segmentation task, taking advantage of the fact that instruments are the main moving objects in the surgical field. With this new input, the temporal component would be indirectly added without modifying the architecture. Using CholecSeg8k dataset, three different representations of movement were estimated and used as new inputs, comparing them with a baseline model. Results showed that the use of OF maps improves the detection of classes with high movement, even when these are scarce in the dataset. To further improve performance, future work may focus on implementing other OF-preserving augmentations.
Authors: Yueqian Wang, Xiaojun Meng, Jianxin Liang, Yuxuan Wang, Qun Liu, Dongyan Zhao
Abstract: Video-text Large Language Models (video-text LLMs) have shown remarkable performance in answering questions and holding conversations on simple videos. However, they perform almost the same as random on grounding text queries in long and complicated videos, having little ability to understand and reason about temporal information, which is the most fundamental difference between videos and images. In this paper, we propose HawkEye, one of the first video-text LLMs that can perform temporal video grounding in a fully text-to-text manner. To collect training data that is applicable for temporal video grounding, we construct InternVid-G, a large-scale video-text corpus with segment-level captions and negative spans, with which we introduce two new time-aware training objectives to video-text LLMs. We also propose a coarse-grained method of representing segments in videos, which is more robust and easier for LLMs to learn and follow than other alternatives. Extensive experiments show that HawkEye is better at temporal video grounding and comparable on other video-text tasks with existing video-text LLMs, which verifies its superior video-text multi-modal understanding abilities.
Authors: Wei Lin, Antoni B. Chan
Abstract: Existing class-agnostic counting models typically rely on a single type of prompt, e.g., box annotations. This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for concerned objects indicated by various prompt types, such as box, point, and text. To achieve this goal, we begin by converting prompts from different modalities into prompt masks without requiring training. These masks are then integrated into a class-agnostic counting methodology for predicting density maps. Furthermore, we introduce a fixed-point inference along with an associated loss function to improve counting accuracy, all without introducing new parameters. The effectiveness of this method is substantiated both theoretically and experimentally. Additionally, a contrastive training scheme is implemented to mitigate dataset bias inherent in current class-agnostic counting datasets, a strategy whose effectiveness is confirmed by our ablation study. Our model excels in prominent class-agnostic datasets and exhibits superior performance in cross-dataset adaptation tasks.
Authors: Qijun Feng, Zhen Xing, Zuxuan Wu, Yu-Gang Jiang
Abstract: Reconstructing detailed 3D objects from single-view images remains a challenging task due to the limited information available. In this paper, we introduce FDGaussian, a novel two-stage framework for single-image 3D reconstruction. Recent methods typically utilize pre-trained 2D diffusion models to generate plausible novel views from the input image, yet they encounter issues with either multi-view inconsistency or lack of geometric fidelity. To overcome these challenges, we propose an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, enabling the generation of consistent multi-view images. Moreover, we further accelerate the state-of-the-art Gaussian Splatting incorporating epipolar attention to fuse images from different viewpoints. We demonstrate that FDGaussian generates images with high consistency across different views and reconstructs high-quality 3D objects, both qualitatively and quantitatively. More examples can be found at our website https://qjfeng.net/FDGaussian/.
Authors: Yukun Li, Guansong Pang, Wei Suo, Chenchen Jing, Yuling Xi, Lingqiao Liu, Hao Chen, Guoqiang Liang, Peng Wang
Abstract: This paper explores the problem of continual learning (CL) of vision-language models (VLMs) in open domains, where the models need to perform continual updating and inference on a streaming of datasets from diverse seen and unseen domains with novel classes. Such a capability is crucial for various applications in open environments, e.g., AI assistants, autonomous driving systems, and robotics. Current CL studies mostly focus on closed-set scenarios in a single domain with known classes. Large pre-trained VLMs like CLIP have demonstrated superior zero-shot recognition ability, and a number of recent studies leverage this ability to mitigate catastrophic forgetting in CL, but they focus on closed-set CL in a single domain dataset. Open-domain CL of large VLMs is significantly more challenging due to 1) large class correlations and domain gaps across the datasets and 2) the forgetting of zero-shot knowledge in the pre-trained VLMs in addition to the knowledge learned from the newly adapted datasets. In this work we introduce a novel approach, termed CoLeCLIP, that learns an open-domain CL model based on CLIP. It addresses these challenges by a joint learning of a set of task prompts and a cross-domain class vocabulary. Extensive experiments on 11 domain datasets show that CoLeCLIP outperforms state-of-the-art methods for open-domain CL under both task- and class-incremental learning settings.
Authors: Meixuan Li, Tianyu Li, Guoqing Wang, Peng Wang, Yang Yang, Heng Tao Shen
Abstract: In this study, we address the intricate challenge of multi-task dense prediction, encompassing tasks such as semantic segmentation, depth estimation, and surface normal estimation, particularly when dealing with partially annotated data (MTPSL). The complexity arises from the absence of complete task labels for each training image. Given the inter-related nature of these pixel-wise dense tasks, our focus is on mining and capturing cross-task relationships. Existing solutions typically rely on learning global image representations for global cross-task image matching, imposing constraints that, unfortunately, sacrifice the finer structures within the images. Attempting local matching as a remedy faces hurdles due to the lack of precise region supervision, making local alignment a challenging endeavor. The introduction of Segment Anything Model (SAM) sheds light on addressing local alignment challenges by providing free and high-quality solutions for region detection. Leveraging SAM-detected regions, the subsequent challenge lies in aligning the representations within these regions. Diverging from conventional methods that directly learn a monolithic image representation, our proposal involves modeling region-wise representations using Gaussian Distributions. Aligning these distributions between corresponding regions from different tasks imparts higher flexibility and capacity to capture intra-region structures, accommodating a broader range of tasks. This innovative approach significantly enhances our ability to effectively capture cross-task relationships, resulting in improved overall performance in partially supervised multi-task dense prediction scenarios. Extensive experiments conducted on two widely used benchmarks underscore the superior effectiveness of our proposed method, showcasing state-of-the-art performance even when compared to fully supervised methods.
Authors: Pingping Zhang, Yuhao Wang, Yang Liu, Zhengzheng Tu, Huchuan Lu
Abstract: Single-modal object re-identification (ReID) faces great challenges in maintaining robustness within complex visual scenarios. In contrast, multi-modal object ReID utilizes complementary information from diverse modalities, showing great potentials for practical applications. However, previous methods may be easily affected by irrelevant backgrounds and usually ignore the modality gaps. To address above issues, we propose a novel learning framework named \textbf{EDITOR} to select diverse tokens from vision Transformers for multi-modal object ReID. We begin with a shared vision Transformer to extract tokenized features from different input modalities. Then, we introduce a Spatial-Frequency Token Selection (SFTS) module to adaptively select object-centric tokens with both spatial and frequency information. Afterwards, we employ a Hierarchical Masked Aggregation (HMA) module to facilitate feature interactions within and across modalities. Finally, to further reduce the effect of backgrounds, we propose a Background Consistency Constraint (BCC) and an Object-Centric Feature Refinement (OCFR). They are formulated as two new loss functions, which improve the feature discrimination with background suppression. As a result, our framework can generate more discriminative features for multi-modal object ReID. Extensive experiments on three multi-modal ReID benchmarks verify the effectiveness of our methods. The code is available at https://github.com/924973292/EDITOR.
Authors: Jinseok Kim, Tae-Kyun Kim
Abstract: Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods, however, generate images only at fixed-scale magnification and suffer from over-smoothing and artifacts. Additionally, they do not offer enough diversity of output images nor image consistency at different scales. Most relevant work applied Implicit Neural Representation (INR) to the denoising diffusion model to obtain continuous-resolution yet diverse and high-quality SR results. Since this model operates in the image space, the larger the resolution of image is produced, the more memory and inference time is required, and it also does not maintain scale-specific consistency. We propose a novel pipeline that can super-resolve an input image or generate from a random noise a novel image at arbitrary scales. The method consists of a pretrained auto-encoder, a latent diffusion model, and an implicit neural decoder, and their learning strategies. The proposed method adopts diffusion processes in a latent space, thus efficient, yet aligned with output image space decoded by MLPs at arbitrary scales. More specifically, our arbitrary-scale decoder is designed by the symmetric decoder w/o up-scaling from the pretrained auto-encoder, and Local Implicit Image Function (LIIF) in series. The latent diffusion process is learnt by the denoising and the alignment losses jointly. Errors in output images are backpropagated via the fixed decoder, improving the quality of output images. In the extensive experiments using multiple public benchmarks on the two tasks i.e. image super-resolution and novel image generation at arbitrary scales, the proposed method outperforms relevant methods in metrics of image quality, diversity and scale consistency. It is significantly better than the relevant prior-art in the inference speed and memory usage.
Authors: Yuting Xu, Jian Liang, Lijun Sheng, Xiao-Yu Zhang
Abstract: The deepfake threats to society and cybersecurity have provoked significant public apprehension, driving intensified efforts within the realm of deepfake video detection. Current video-level methods are mostly based on {3D CNNs} resulting in high computational demands, although have achieved good performance. This paper introduces an elegantly simple yet effective strategy named Thumbnail Layout (TALL), which transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies. This transformation process involves sequentially masking frames at the same positions within each frame. These frames are then resized into sub-frames and reorganized into the predetermined layout, forming thumbnails. TALL is model-agnostic and has remarkable simplicity, necessitating only minimal code modifications. Furthermore, we introduce a graph reasoning block (GRB) and semantic consistency (SC) loss to strengthen TALL, culminating in TALL++. GRB enhances interactions between different semantic regions to capture semantic-level inconsistency clues. The semantic consistency loss imposes consistency constraints on semantic features to improve model generalization ability. Extensive experiments on intra-dataset, cross-dataset, diffusion-generated image detection, and deepfake generation method recognition show that TALL++ achieves results surpassing or comparable to the state-of-the-art methods, demonstrating the effectiveness of our approaches for various deepfake detection problems. The code is available at https://github.com/rainy-xu/TALL4Deepfake.
Authors: Fangming Yuan, Stefan Schubert, Peter Protzel, Peer Neubert
Abstract: Large-scale applications of Visual Place Recognition (VPR) require computationally efficient approaches. Further, a well-balanced combination of data-based and training-free approaches can decrease the required amount of training data and effort and can reduce the influence of distribution shifts between the training and application phases. This paper proposes a runtime and data-efficient hierarchical VPR pipeline that extends existing approaches and presents novel ideas. There are three main contributions: First, we propose Local Positional Graphs (LPG), a training-free and runtime-efficient approach to encode spatial context information of local image features. LPG can be combined with existing local feature detectors and descriptors and considerably improves the image-matching quality compared to existing techniques in our experiments. Second, we present Attentive Local SPED (ATLAS), an extension of our previous local features approach with an attention module that improves the feature quality while maintaining high data efficiency. The influence of the proposed modifications is evaluated in an extensive ablation study. Third, we present a hierarchical pipeline that exploits hyperdimensional computing to use the same local features as holistic HDC-descriptors for fast candidate selection and for candidate reranking. We combine all contributions in a runtime and data-efficient VPR pipeline that shows benefits over the state-of-the-art method Patch-NetVLAD on a large collection of standard place recognition datasets with 15$\%$ better performance in VPR accuracy, 54$\times$ faster feature comparison speed, and 55$\times$ less descriptor storage occupancy, making our method promising for real-world high-performance large-scale VPR in changing environments. Code will be made available with publication of this paper.
Authors: Tian Meng, Yang Tao, Ruilin Lyu, Wuliang Yin
Abstract: The task of few-shot image classification and segmentation (FS-CS) involves classifying and segmenting target objects in a query image, given only a few examples of the target classes. We introduce the Vision-Instructed Segmentation and Evaluation (VISE) method that transforms the FS-CS problem into the Visual Question Answering (VQA) problem, utilising Vision-Language Models (VLMs), and addresses it in a training-free manner. By enabling a VLM to interact with off-the-shelf vision models as tools, the proposed method is capable of classifying and segmenting target objects using only image-level labels. Specifically, chain-of-thought prompting and in-context learning guide the VLM to answer multiple-choice questions like a human; vision models such as YOLO and Segment Anything Model (SAM) assist the VLM in completing the task. The modular framework of the proposed method makes it easily extendable. Our approach achieves state-of-the-art performance on the Pascal-5i and COCO-20i datasets.
Authors: M\"ujde Akdeniz, Claudia Alessandra Manetti, Tijmen Koopsen, Hani Nozari Mirar, Sten Roar Snare, Svein Arne Aase, Joost Lumens, Jurica \v{S}prem, Kristin Sarah McLeod
Abstract: How well the heart is functioning can be quantified through measurements of myocardial deformation via echocardiography. Clinical assessment of cardiac function is generally focused on global indices of relative shortening, however, territorial, and segmental strain indices have shown to be abnormal in regions of myocardial disease, such as scar. In this work, we propose a single framework to predict myocardial disease substrates at global, territorial, and segmental levels using regional myocardial strain traces as input to a convolutional neural network (CNN)-based classification algorithm. An anatomically meaningful representation of the input data from the clinically standard bullseye representation to a multi-channel 2D image is proposed, to formulate the task as an image classification problem, thus enabling the use of state-of-the-art neural network configurations. A Fully Convolutional Network (FCN) is trained to detect and localize myocardial scar from regional left ventricular (LV) strain patterns. Simulated regional strain data from a controlled dataset of virtual patients with varying degrees and locations of myocardial scar is used for training and validation. The proposed method successfully detects and localizes the scars on 98% of the 5490 left ventricle (LV) segments of the 305 patients in the test set using strain traces only. Due to the sparse existence of scar, only 10% of the LV segments in the virtual patient cohort have scar. Taking the imbalance into account, the class balanced accuracy is calculated as 95%. The performance is reported on global, territorial, and segmental levels. The proposed method proves successful on the strain traces of the virtual cohort and offers the potential to solve the regional myocardial scar detection problem on the strain traces of the real patient cohorts.
Authors: Huy-Hoang Bui, Bach-Thuan Bui, Dinh-Tuan Tran, Joo-Ho Lee
Abstract: Classical structural-based visual localization methods offer high accuracy but face trade-offs in terms of storage, speed, and privacy. A recent innovation, keypoint scene coordinate regression (KSCR) named D2S addresses these issues by leveraging graph attention networks to enhance keypoint relationships and predict their 3D coordinates using a simple multilayer perceptron (MLP). Camera pose is then determined via PnP+RANSAC, using established 2D-3D correspondences. While KSCR achieves competitive results, rivaling state-of-the-art image-retrieval methods like HLoc across multiple benchmarks, its performance is hindered when data samples are limited due to the deep learning model's reliance on extensive data. This paper proposes a solution to this challenge by introducing a pipeline for keypoint descriptor synthesis using Neural Radiance Field (NeRF). By generating novel poses and feeding them into a trained NeRF model to create new views, our approach enhances the KSCR's generalization capabilities in data-scarce environments. The proposed system could significantly improve localization accuracy by up to 50\% and cost only a fraction of time for data synthesis. Furthermore, its modular design allows for the integration of multiple NeRFs, offering a versatile and efficient solution for visual localization. The implementation is publicly available at: https://github.com/ais-lab/DescriptorSynthesis4Feat2Map.
URLs: https://github.com/ais-lab/DescriptorSynthesis4Feat2Map.
Authors: Qin Xu, Sitong Li, Jiahui Wang, Bo Jiang, Jinhui Tang
Abstract: Exploring and mining subtle yet distinctive features between sub-categories with similar appearances is crucial for fine-grained visual categorization (FGVC). However, less effort has been devoted to assessing the quality of extracted visual representations. Intuitively, the network may struggle to capture discriminative features from low-quality samples, which leads to a significant decline in FGVC performance. To tackle this challenge, we propose a weakly supervised Context-Semantic Quality Awareness Network (CSQA-Net) for FGVC. In this network, to model the spatial contextual relationship between rich part descriptors and global semantics for capturing more discriminative details within the object, we design a novel multi-part and multi-scale cross-attention (MPMSCA) module. Before feeding to the MPMSCA module, the part navigator is developed to address the scale confusion problems and accurately identify the local distinctive regions. Furthermore, we propose a generic multi-level semantic quality evaluation module (MLSQE) to progressively supervise and enhance hierarchical semantics from different levels of the backbone network. Finally, context-aware features from MPMSCA and semantically enhanced features from MLSQE are fed into the corresponding quality probing classifiers to evaluate their quality in real-time, thus boosting the discriminability of feature representations. Comprehensive experiments on four popular and highly competitive FGVC datasets demonstrate the superiority of the proposed CSQA-Net in comparison with the state-of-the-art methods.
Authors: Junjin Xiao, Qing Zhang, Zhan Xu, Wei-Shi Zheng
Abstract: Human avatar has become a novel type of 3D asset with various applications. Ideally, a human avatar should be fully customizable to accommodate different settings and environments. In this work, we introduce NECA, an approach capable of learning versatile human representation from monocular or sparse-view videos, enabling granular customization across aspects such as pose, shadow, shape, lighting and texture. The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering. Extensive experiments demonstrate the advantage of our method over the state-of-the-art methods in photorealistic rendering, as well as various editing tasks such as novel pose synthesis and relighting. The code is available at https://github.com/iSEE-Laboratory/NECA.
Authors: Cong Wang, Jinshan Pan, Yeying Jin, Liyan Wang, Wei Wang, Gang Fu, Wenqi Ren, Xiaochun Cao
Abstract: Transformers have demonstrated their effectiveness in image restoration tasks. Existing Transformer architectures typically comprise two essential components: multi-head self-attention and feed-forward network (FFN). The former captures long-range pixel dependencies, while the latter enables the model to learn complex patterns and relationships in the data. Previous studies have demonstrated that FFNs are key-value memories \cite{geva2020transformer}, which are vital in modern Transformer architectures. In this paper, we conduct an empirical study to explore the potential of attention mechanisms without using FFN and provide novel structures to demonstrate that removing FFN is flexible for image restoration. Specifically, we propose Continuous Scaling Attention (\textbf{CSAttn}), a method that computes attention continuously in three stages without using FFN. To achieve competitive performance, we propose a series of key components within the attention. Our designs provide a closer look at the attention mechanism and reveal that some simple operations can significantly affect the model performance. We apply our \textbf{CSAttn} to several image restoration tasks and show that our model can outperform CNN-based and Transformer-based image restoration approaches.
Authors: Tianxiang Ye, Qi Wu, Junyuan Deng, Guoqing Liu, Liu Liu, Songpengcheng Xia, Liang Pang, Wenxian Yu, Ling Pei
Abstract: In recent years, Neural Radiance Fields (NeRFs) have demonstrated significant potential in encoding highly-detailed 3D geometry and environmental appearance, positioning themselves as a promising alternative to traditional explicit representation for 3D scene reconstruction. However, the predominant reliance on RGB imaging presupposes ideal lighting conditions: a premise frequently unmet in robotic applications plagued by poor lighting or visual obstructions. This limitation overlooks the capabilities of infrared (IR) cameras, which excel in low-light detection and present a robust alternative under such adverse scenarios. To tackle these issues, we introduce Thermal-NeRF, the first method that estimates a volumetric scene representation in the form of a NeRF solely from IR imaging. By leveraging a thermal mapping and structural thermal constraint derived from the thermal characteristics of IR imaging, our method showcasing unparalleled proficiency in recovering NeRFs in visually degraded scenes where RGB-based methods fall short. We conduct extensive experiments to demonstrate that Thermal-NeRF can achieve superior quality compared to existing methods. Furthermore, we contribute a dataset for IR-based NeRF applications, paving the way for future research in IR NeRF reconstruction.
Authors: Hala Djeghim, Nathan Piasco, Moussab Bennehar, Luis Rold\~ao, Dzmitry Tsishkou, D\'esir\'e Sidib\'e
Abstract: Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct urban outdoor scenes due to their large, unbounded, and highly detailed nature. Hence, to achieve accurate reconstructions, additional supervision data such as LiDAR, strong geometric priors, and long training times are required. To tackle such issues, we present SCILLA, a new hybrid implicit surface learning method to reconstruct large driving scenes from 2D images. SCILLA's hybrid architecture models two separate implicit fields: one for the volumetric density and another for the signed distance to the surface. To accurately represent urban outdoor scenarios, we introduce a novel volume-rendering strategy that relies on self-supervised probabilistic density estimation to sample points near the surface and transition progressively from volumetric to surface representation. Our solution permits a proper and fast initialization of the signed distance field without relying on any geometric prior on the scene, compared to concurrent methods. By conducting extensive experiments on four outdoor driving datasets, we show that SCILLA can learn an accurate and detailed 3D surface scene representation in various urban scenarios while being two times faster to train compared to previous state-of-the-art solutions.
Authors: Jin-Young Kim, Hyojun Go, Soonwoo Kwon, Hyun-Gyoon Kim
Abstract: Diffusion-based generative models have emerged as powerful tools in the realm of generative modeling. Despite extensive research on denoising across various timesteps and noise levels, a conflict persists regarding the relative difficulties of the denoising tasks. While various studies argue that lower timesteps present more challenging tasks, others contend that higher timesteps are more difficult. To address this conflict, our study undertakes a comprehensive examination of task difficulties, focusing on convergence behavior and changes in relative entropy between consecutive probability distributions across timesteps. Our observational study reveals that denoising at earlier timesteps poses challenges characterized by slower convergence and higher relative entropy, indicating increased task difficulty at these lower timesteps. Building on these observations, we introduce an easy-to-hard learning scheme, drawing from curriculum learning, to enhance the training process of diffusion models. By organizing timesteps or noise levels into clusters and training models with descending orders of difficulty, we facilitate an order-aware training regime, progressing from easier to harder denoising tasks, thereby deviating from the conventional approach of training diffusion models simultaneously across all timesteps. Our approach leads to improved performance and faster convergence by leveraging the benefits of curriculum learning, while maintaining orthogonality with existing improvements in diffusion training techniques. We validate these advantages through comprehensive experiments in image generation tasks, including unconditional, class-conditional, and text-to-image generation.
Authors: Qijian Zhang, Junhui Hou, Ying He
Abstract: Surface parameterization is a fundamental geometry processing problem with rich downstream applications. Traditional approaches are designed to operate on well-behaved mesh models with high-quality triangulations that are laboriously produced by specialized 3D modelers, and thus unable to meet the processing demand for the current explosion of ordinary 3D data. In this paper, we seek to perform UV unwrapping on unstructured 3D point clouds. Technically, we propose ParaPoint, an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization by building point-wise mappings between given 3D points and 2D UV coordinates with adaptively deformed boundaries. We ingeniously construct several geometrically meaningful sub-networks with specific functionalities, and assemble them into a bi-directional cycle mapping framework. We also design effective loss functions and auxiliary differential geometric constraints for the optimization of the neural mapping process. To the best of our knowledge, this work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries. Experiments demonstrate the effectiveness and inspiring potential of our proposed learning paradigm. The code will be publicly available.
Authors: Yingqi Tang, Zhaotie Meng, Guoliang Chen, Erkang Cheng
Abstract: The field of autonomous driving has attracted considerable interest in approaches that directly infer 3D objects in the Bird's Eye View (BEV) from multiple cameras. Some attempts have also explored utilizing 2D detectors from single images to enhance the performance of 3D detection. However, these approaches rely on a two-stage process with separate detectors, where the 2D detection results are utilized only once for token selection or query initialization. In this paper, we present a single model termed SimPB, which simultaneously detects 2D objects in the perspective view and 3D objects in the BEV space from multiple cameras. To achieve this, we introduce a hybrid decoder consisting of several multi-view 2D decoder layers and several 3D decoder layers, specifically designed for their respective detection tasks. A Dynamic Query Allocation module and an Adaptive Query Aggregation module are proposed to continuously update and refine the interaction between 2D and 3D results, in a cyclic 3D-2D-3D manner. Additionally, Query-group Attention is utilized to strengthen the interaction among 2D queries within each camera group. In the experiments, we evaluate our method on the nuScenes dataset and demonstrate promising results for both 2D and 3D detection tasks. Our code is available at: https://github.com/nullmax-vision/SimPB.
Authors: Marco Pesavento, Yuanlu Xu, Nikolaos Sarafianos, Robert Maier, Ziyan Wang, Chun-Han Yao, Marco Volino, Edmond Boyer, Adrian Hilton, Tony Tung
Abstract: Recent progress in human shape learning, shows that neural implicit models are effective in generating 3D human surfaces from limited number of views, and even from a single RGB image. However, existing monocular approaches still struggle to recover fine geometric details such as face, hands or cloth wrinkles. They are also easily prone to depth ambiguities that result in distorted geometries along the camera optical axis. In this paper, we explore the benefits of incorporating depth observations in the reconstruction process by introducing ANIM, a novel method that reconstructs arbitrary 3D human shapes from single-view RGB-D images with an unprecedented level of accuracy. Our model learns geometric details from both multi-resolution pixel-aligned and voxel-aligned features to leverage depth information and enable spatial relationships, mitigating depth ambiguities. We further enhance the quality of the reconstructed shape by introducing a depth-supervision strategy, which improves the accuracy of the signed distance field estimation of points that lie on the reconstructed surface. Experiments demonstrate that ANIM outperforms state-of-the-art works that use RGB, surface normals, point cloud or RGB-D data as input. In addition, we introduce ANIM-Real, a new multi-modal dataset comprising high-quality scans paired with consumer-grade RGB-D camera, and our protocol to fine-tune ANIM, enabling high-quality reconstruction from real-world human capture.
Authors: Anna Kuznetsova, Vadim Kimmelman
Abstract: Advances in Deep Learning have made possible reliable landmark tracking of human bodies and faces that can be used for a variety of tasks. We test a recent Computer Vision solution, MediaPipe Holistic (MPH), to find out if its tracking of the facial features is reliable enough for a linguistic analysis of data from sign languages, and compare it to an older solution (OpenFace, OF). We use an existing data set of sentences in Kazakh-Russian Sign Language and a newly created small data set of videos with head tilts and eyebrow movements. We find that MPH does not perform well enough for linguistic analysis of eyebrow movement -- but in a different way from OF, which is also performing poorly without correction. We reiterate a previous proposal to train additional correction models to overcome these limitations.
Authors: Sara Antiles, Sachin S. Talathi
Abstract: We present the Open Stamped Parts Dataset (OSPD), featuring synthetic and real images of stamped metal sheets for auto manufacturing. The real part images, captured from 7 cameras, consist of 7,980 unlabeled images and 1,680 labeled images. In addition, we have compiled a defect dataset by overlaying synthetically generated masks on 10% of the holes. The synthetic dataset replicates the real manufacturing environment in terms of lighting and part placement relative to the cameras. The synthetic data includes 7,980 training images, 1,680 validation images and 1,680 test images, each with bounding box and segmentation mask annotations around all holes. 10% of the holes in the synthetic data mimic defects generated in the real image dataset. We trained a hole-detection model on the synthetic-OSPD, achieving a modified recall score of 67.2% and a precision of 94.4% . We anticipate researchers in the auto manufacturing and broader machine learning and computer vision communities using OSPD to advance the state of the art in defect detection of stamped holes in the metalsheet stamping process. The dataset is available for download at: https://tinyurl.com/hm6xatd7
Authors: Xiaoning Liu, Ao Li, Zongwei Wu, Yapeng Du, Le Zhang, Yulun Zhang, Radu Timofte, Ce Zhu
Abstract: Leveraging Transformer attention has led to great advancements in HDR deghosting. However, the intricate nature of self-attention introduces practical challenges, as existing state-of-the-art methods often demand high-end GPUs or exhibit slow inference speeds, especially for high-resolution images like 2K. Striking an optimal balance between performance and latency remains a critical concern. In response, this work presents PASTA, a novel Progressively Aggregated Spatio-Temporal Alignment framework for HDR deghosting. Our approach achieves effectiveness and efficiency by harnessing hierarchical representation during feature distanglement. Through the utilization of diverse granularities within the hierarchical structure, our method substantially boosts computational speed and optimizes the HDR imaging workflow. In addition, we explore within-scale feature modeling with local and global attention, gradually merging and refining them in a coarse-to-fine fashion. Experimental results showcase PASTA's superiority over current SOTA methods in both visual quality and performance metrics, accompanied by a substantial 3-fold (x3) increase in inference speed.
Authors: Alexander Hepburn, Raul Santos-Rodriguez, Javier Portilla
Abstract: The two-alternative forced choice (2AFC) experimental setup is popular in the visual perception literature, where practitioners aim to understand how human observers perceive distances within triplets that consist of a reference image and two distorted versions of that image. In the past, this had been conducted in controlled environments, with a tournament-style algorithm dictating which images are shown to each participant to rank the distorted images. Recently, crowd-sourced perceptual datasets have emerged, with no images shared between triplets, making ranking impossible. Evaluating perceptual distances using this data is non-trivial, relying on reducing the collection of judgements on a triplet to a binary decision -- which is suboptimal and prone to misleading conclusions. Instead, we statistically model the underlying decision-making process during 2AFC experiments using a binomial distribution. We use maximum likelihood estimation to fit a distribution to the perceptual judgements, conditioned on the perceptual distance to test and impose consistency and smoothness between our empirical estimates of the density. This way, we can evaluate a different number of judgements per triplet, and can calculate metrics such as likelihoods of judgements according to a set of distances -- key ingredients that neural network counterparts lack.
Authors: Hyuck Lee, Heeyoung Kim
Abstract: Pseudo-label-based semi-supervised learning (SSL) algorithms trained on a class-imbalanced set face two cascading challenges: 1) Classifiers tend to be biased towards majority classes, and 2) Biased pseudo-labels are used for training. It is difficult to appropriately re-balance the classifiers in SSL because the class distribution of an unlabeled set is often unknown and could be mismatched with that of a labeled set. We propose a novel class-imbalanced SSL algorithm called class-distribution-mismatch-aware debiasing (CDMAD). For each iteration of training, CDMAD first assesses the classifier's biased degree towards each class by calculating the logits on an image without any patterns (e.g., solid color image), which can be considered irrelevant to the training set. CDMAD then refines biased pseudo-labels of the base SSL algorithm by ensuring the classifier's neutrality. CDMAD uses these refined pseudo-labels during the training of the base SSL algorithm to improve the quality of the representations. In the test phase, CDMAD similarly refines biased class predictions on test samples. CDMAD can be seen as an extension of post-hoc logit adjustment to address a challenge of incorporating the unknown class distribution of the unlabeled set for re-balancing the biased classifier under class distribution mismatch. CDMAD ensures Fisher consistency for the balanced error. Extensive experiments verify the effectiveness of CDMAD.
Authors: Pengkun Liu, Yikai Wang, Fuchun Sun, Jiafang Li, Hang Xiao, Hongxiang Xue, Xinzhou Wang
Abstract: Encouraged by the growing availability of pre-trained 2D diffusion models, image-to-3D generation by leveraging Score Distillation Sampling (SDS) is making remarkable progress. Most existing methods combine novel-view lifting from 2D diffusion models which usually take the reference image as a condition while applying hard L2 image supervision at the reference view. Yet heavily adhering to the image is prone to corrupting the inductive knowledge of the 2D diffusion model leading to flat or distorted 3D generation frequently. In this work, we reexamine image-to-3D in a novel perspective and present Isotropic3D, an image-to-3D generation pipeline that takes only an image CLIP embedding as input. Isotropic3D allows the optimization to be isotropic w.r.t. the azimuth angle by solely resting on the SDS loss. The core of our framework lies in a two-stage diffusion model fine-tuning. Firstly, we fine-tune a text-to-3D diffusion model by substituting its text encoder with an image encoder, by which the model preliminarily acquires image-to-image capabilities. Secondly, we perform fine-tuning using our Explicit Multi-view Attention (EMA) which combines noisy multi-view images with the noise-free reference image as an explicit condition. CLIP embedding is sent to the diffusion model throughout the whole process while reference images are discarded once after fine-tuning. As a result, with a single image CLIP embedding, Isotropic3D is capable of generating multi-view mutually consistent images and also a 3D model with more symmetrical and neat content, well-proportioned geometry, rich colored texture, and less distortion compared with existing image-to-3D methods while still preserving the similarity to the reference image to a large extent. The project page is available at https://isotropic3d.github.io/. The code and models are available at https://github.com/pkunliu/Isotropic3D.
URLs: https://isotropic3d.github.io/., https://github.com/pkunliu/Isotropic3D.
Authors: Marc Lafon, Cl\'ement Rambour, Nicolas Thome
Abstract: In this work, we study the out-of-distribution (OOD) detection problem through the use of the feature space of a pre-trained deep classifier. We show that learning the density of in-distribution (ID) features with an energy-based models (EBM) leads to competitive detection results. However, we found that the non-mixing of MCMC sampling during the EBM's training undermines its detection performance. To overcome this an energy-based correction of a mixture of class-conditional Gaussian distributions. We obtains favorable results when compared to a strong baseline like the KNN detector on the CIFAR-10/CIFAR-100 OOD detection benchmarks.
Authors: Hongyuan Yu, Cheng Wan, Mengchen Liu, Dongdong Chen, Bin Xiao, Xiyang Dai
Abstract: Image segmentation is one of the most fundamental problems in computer vision and has drawn a lot of attentions due to its vast applications in image understanding and autonomous driving. However, designing effective and efficient segmentation neural architectures is a labor-intensive process that may require lots of trials by human experts. In this paper, we address the challenge of integrating multi-head self-attention into high resolution representation CNNs efficiently, by leveraging architecture search. Manually replacing convolution layers with multi-head self-attention is non-trivial due to the costly overhead in memory to maintain high resolution. By contrast, we develop a multi-target multi-branch supernet method, which not only fully utilizes the advantages of high-resolution features, but also finds the proper location for placing multi-head self-attention module. Our search algorithm is optimized towards multiple objective s (e.g., latency and mIoU) and capable of finding architectures on Pareto frontier with arbitrary number of branches in a single search. We further present a series of model via Hybrid Convolutional-Transformer Architecture Search (HyCTAS) method that searched for the best hybrid combination of light-weight convolution layers and memory-efficient self-attention layers between branches from different resolutions and fuse to high resolution for both efficiency and effectiveness. Extensive experiments demonstrate that HyCTAS outperforms previous methods on semantic segmentation task. Code and models are available at \url{https://github.com/MarvinYu1995/HyCTAS}.
Authors: Zhiyong Zhang, Huaizu Jiang, Hanumant Singh
Abstract: Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based optical flow methods have achieved high accuracy, they often come with heavy computation costs. In this paper, we propose a highly efficient optical flow architecture, called NeuFlow, that addresses both high accuracy and computational cost concerns. The architecture follows a global-to-local scheme. Given the features of the input images extracted at different spatial resolutions, global matching is employed to estimate an initial optical flow on the 1/16 resolution, capturing large displacement, which is then refined on the 1/8 resolution with lightweight CNN layers for better accuracy. We evaluate our approach on Jetson Orin Nano and RTX 2080 to demonstrate efficiency improvements across different computing platforms. We achieve a notable 10x-80x speedup compared to several state-of-the-art methods, while maintaining comparable accuracy. Our approach achieves around 30 FPS on edge computing platforms, which represents a significant breakthrough in deploying complex computer vision tasks such as SLAM on small robots like drones. The full training and evaluation code is available at https://github.com/neufieldrobotics/NeuFlow.
Authors: Hiba Dahmani, Moussab Bennehar, Nathan Piasco, Luis Roldao, Dzmitry Tsishkou
Abstract: Implicit neural representation methods have shown impressive advancements in learning 3D scenes from unstructured in-the-wild photo collections but are still limited by the large computational cost of volumetric rendering. More recently, 3D Gaussian Splatting emerged as a much faster alternative with superior rendering quality and training efficiency, especially for small-scale and object-centric scenarios. Nevertheless, this technique suffers from poor performance on unstructured in-the-wild data. To tackle this, we extend over 3D Gaussian Splatting to handle unstructured image collections. We achieve this by modeling appearance to seize photometric variations in the rendered images. Additionally, we introduce a new mechanism to train transient Gaussians to handle the presence of scene occluders in an unsupervised manner. Experiments on diverse photo collection scenes and multi-pass acquisition of outdoor landmarks show the effectiveness of our method over prior works achieving state-of-the-art results with improved efficiency.
Authors: Ozge Mercanoglu Sincan, Necati Cihan Camgoz, Richard Bowden
Abstract: Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos. In this paper, we introduce a hybrid SLT approach, Spotter+GPT, that utilizes a sign spotter and a pretrained large language model to improve SLT performance. Our method builds upon the strengths of both components. The videos are first processed by the spotter, which is trained on a linguistic sign language dataset, to identify individual signs. These spotted signs are then passed to the powerful language model, which transforms them into coherent and contextually appropriate spoken language sentences.
Authors: Florian Kluger, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn
Abstract: Humans perceive and construct the world as an arrangement of simple parametric models. In particular, we can often describe man-made environments using volumetric primitives such as cuboids or cylinders. Inferring these primitives is important for attaining high-level, abstract scene descriptions. Previous approaches for primitive-based abstraction estimate shape parameters directly and are only able to reproduce simple objects. In contrast, we propose a robust estimator for primitive fitting, which meaningfully abstracts complex real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to a depth map. We condition the network on previously detected parts of the scene, parsing it one-by-one. To obtain cuboids from single RGB images, we additionally optimise a depth estimation CNN end-to-end. Naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene. We thus propose an improved occlusion-aware distance metric correctly handling opaque scenes. Furthermore, we present a neural network based cuboid solver which provides more parsimonious scene abstractions while also reducing inference time. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.
Authors: Haoyang Liu, Aditya Singh, Yijiang Li, Haohan Wang
Abstract: Enhancing the robustness of deep learning models, particularly in the realm of vision transformers (ViTs), is crucial for their real-world deployment. In this work, we provide a finetuning approach to enhance the robustness of vision transformers inspired by the concept of nullspace from linear algebra. Our investigation centers on whether a vision transformer can exhibit resilience to input variations akin to the nullspace property in linear mappings, implying that perturbations sampled from this nullspace do not influence the model's output when added to the input. Firstly, we show that for many pretrained ViTs, a non-trivial nullspace exists due to the presence of the patch embedding layer. Secondly, as nullspace is a concept associated with linear algebra, we demonstrate that it is possible to synthesize approximate nullspace elements for the non-linear blocks of ViTs employing an optimisation strategy. Finally, we propose a fine-tuning strategy for ViTs wherein we augment the training data with synthesized approximate nullspace noise. After finetuning, we find that the model demonstrates robustness to adversarial and natural image perbutations alike.
Authors: Paul Waligora, Osama Zeeshan, Haseeb Aslam, Soufiane Belharbi, Alessandro Lameiras Koerich, Marco Pedersoli, Simon Bacon, Eric Granger
Abstract: Audiovisual emotion recognition (ER) in videos has immense potential over unimodal performance. It effectively leverages the inter- and intra-modal dependencies between visual and auditory modalities. This work proposes a novel audio-visual emotion recognition system utilizing a joint multimodal transformer architecture with key-based cross-attention. This framework aims to exploit the complementary nature of audio and visual cues (facial expressions and vocal patterns) in videos, leading to superior performance compared to solely relying on a single modality. The proposed model leverages separate backbones for capturing intra-modal temporal dependencies within each modality (audio and visual). Subsequently, a joint multimodal transformer architecture integrates the individual modality embeddings, enabling the model to effectively capture inter-modal (between audio and visual) and intra-modal (within each modality) relationships. Extensive evaluations on the challenging Affwild2 dataset demonstrate that the proposed model significantly outperforms baseline and state-of-the-art methods in ER tasks.
Authors: Dongmin Park, Zhaofang Qian, Guangxing Han, Ser-Nam Lim
Abstract: Mitigating hallucinations of Large Multi-modal Models(LMMs) is crucial to enhance their reliability for general-purpose assistants. This paper shows that such hallucinations of LMMs can be significantly exacerbated by preceding user-system dialogues. To precisely measure this, we first present an evaluation benchmark by extending popular multi-modal benchmark datasets with prepended hallucinatory dialogues generated by our novel Adversarial Question Generator, which can automatically generate image-related yet adversarial dialogues by adopting adversarial attacks on LMMs. On our benchmark, the zero-shot performance of state-of-the-art LMMs dropped significantly for both the VQA and Captioning tasks. Next, we further reveal this hallucination is mainly due to the prediction bias toward preceding dialogues rather than visual content. To reduce this bias, we propose Adversarial Instruction Tuning that robustly fine-tunes LMMs on augmented multi-modal instruction-following datasets with hallucinatory dialogues. Extensive experiments show that our proposed approach successfully reduces dialogue hallucination while maintaining or even improving performance.
Authors: Anshul Gupta, Samy Tafasca, Arya Farkhondeh, Pierre Vuillecard, Jean-Marc Odobez
Abstract: Gaze following and social gaze prediction are fundamental tasks providing insights into human communication behaviors, intent, and social interactions. Most previous approaches addressed these tasks separately, either by designing highly specialized social gaze models that do not generalize to other social gaze tasks or by considering social gaze inference as an ad-hoc post-processing of the gaze following task. Furthermore, the vast majority of gaze following approaches have proposed static models that can handle only one person at a time, therefore failing to take advantage of social interactions and temporal dynamics. In this paper, we address these limitations and introduce a novel framework to jointly predict the gaze target and social gaze label for all people in the scene. The framework comprises of: (i) a temporal, transformer-based architecture that, in addition to image tokens, handles person-specific tokens capturing the gaze information related to each individual; (ii) a new dataset, VSGaze, that unifies annotation types across multiple gaze following and social gaze datasets. We show that our model trained on VSGaze can address all tasks jointly, and achieves state-of-the-art results for multi-person gaze following and social gaze prediction.
Authors: Stephanie Fu, Mark Hamilton, Laura Brandt, Axel Feldman, Zhoutong Zhang, William T. Freeman
Abstract: Deep features are a cornerstone of computer vision research, capturing image semantics and enabling the community to solve downstream tasks even in the zero- or few-shot regime. However, these features often lack the spatial resolution to directly perform dense prediction tasks like segmentation and depth prediction because models aggressively pool information over large areas. In this work, we introduce FeatUp, a task- and model-agnostic framework to restore lost spatial information in deep features. We introduce two variants of FeatUp: one that guides features with high-resolution signal in a single forward pass, and one that fits an implicit model to a single image to reconstruct features at any resolution. Both approaches use a multi-view consistency loss with deep analogies to NeRFs. Our features retain their original semantics and can be swapped into existing applications to yield resolution and performance gains even without re-training. We show that FeatUp significantly outperforms other feature upsampling and image super-resolution approaches in class activation map generation, transfer learning for segmentation and depth prediction, and end-to-end training for semantic segmentation.
Authors: Xiaohan Wang, Yuhui Zhang, Orr Zohar, Serena Yeung-Levy
Abstract: Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, VideoAgent, that employs a large language model as a central agent to iteratively identify and compile crucial information to answer a question, with vision-language foundation models serving as tools to translate and retrieve visual information. Evaluated on the challenging EgoSchema and NExT-QA benchmarks, VideoAgent achieves 54.1% and 71.3% zero-shot accuracy with only 8.4 and 8.2 frames used on average. These results demonstrate superior effectiveness and efficiency of our method over the current state-of-the-art methods, highlighting the potential of agent-based approaches in advancing long-form video understanding.
Authors: Ronghui Li, YuXiang Zhang, Yachao Zhang, Hongwen Zhang, Jie Guo, Yan Zhang, Yebin Liu, Xiu Li
Abstract: We propose Lodge, a network capable of generating extremely long dance sequences conditioned on given music. We design Lodge as a two-stage coarse to fine diffusion architecture, and propose the characteristic dance primitives that possess significant expressiveness as intermediate representations between two diffusion models. The first stage is global diffusion, which focuses on comprehending the coarse-level music-dance correlation and production characteristic dance primitives. In contrast, the second-stage is the local diffusion, which parallelly generates detailed motion sequences under the guidance of the dance primitives and choreographic rules. In addition, we propose a Foot Refine Block to optimize the contact between the feet and the ground, enhancing the physical realism of the motion. Our approach can parallelly generate dance sequences of extremely long length, striking a balance between global choreographic patterns and local motion quality and expressiveness. Extensive experiments validate the efficacy of our method.
Authors: Andreas B\"ar, Neil Houlsby, Mostafa Dehghani, Manoj Kumar
Abstract: Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks. Currently, frozen features are not modified during training. On the other hand, when networks are trained directly on images, data augmentation is a standard recipe that improves performance with no substantial overhead. In this paper, we conduct an extensive pilot study on few-shot image classification that explores applying data augmentations in the frozen feature space, dubbed 'frozen feature augmentation (FroFA)', covering twenty augmentations in total. Our study demonstrates that adopting a deceptively simple pointwise FroFA, such as brightness, can improve few-shot performance consistently across three network architectures, three large pretraining datasets, and eight transfer datasets.
Authors: Zeyu Zhang, Junlin Han, Chenhui Gou, Hongdong Li, Liang Zheng
Abstract: Blind image decomposition aims to decompose all components present in an image, typically used to restore a multi-degraded input image. While fully recovering the clean image is appealing, in some scenarios, users might want to retain certain degradations, such as watermarks, for copyright protection. To address this need, we add controllability to the blind image decomposition process, allowing users to enter which types of degradation to remove or retain. We design an architecture named controllable blind image decomposition network. Inserted in the middle of U-Net structure, our method first decomposes the input feature maps and then recombines them according to user instructions. Advantageously, this functionality is implemented at minimal computational cost: decomposition and recombination are all parameter-free. Experimentally, our system excels in blind image decomposition tasks and can outputs partially or fully restored images that well reflect user intentions. Furthermore, we evaluate and configure different options for the network structure and loss functions. This, combined with the proposed decomposition-and-recombination method, yields an efficient and competitive system for blind image decomposition, compared with current state-of-the-art methods.
Authors: Zhou Jiang, Zhenxin Zhu, Pengfei Li, Huan-ang Gao, Tianyuan Yuan, Yongliang Shi, Hang Zhao, Hao Zhao
Abstract: Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepping into regions without this expensive digital infrastructure. This fact drives many researchers to study online HDMap generation algorithms, but the performance of these algorithms at far regions is still unsatisfying. We present P-MapNet, in which the letter P highlights the fact that we focus on incorporating map priors to improve model performance. Specifically, we exploit priors in both SDMap and HDMap. On one hand, we extract weakly aligned SDMap from OpenStreetMap, and encode it as an additional conditioning branch. Despite the misalignment challenge, our attention-based architecture adaptively attends to relevant SDMap skeletons and significantly improves performance. On the other hand, we exploit a masked autoencoder to capture the prior distribution of HDMap, which can serve as a refinement module to mitigate occlusions and artifacts. We benchmark on the nuScenes and Argoverse2 datasets. Through comprehensive experiments, we show that: (1) our SDMap prior can improve online map generation performance, using both rasterized (by up to $+18.73$ $\rm mIoU$) and vectorized (by up to $+8.50$ $\rm mAP$) output representations. (2) our HDMap prior can improve map perceptual metrics by up to $6.34\%$. (3) P-MapNet can be switched into different inference modes that covers different regions of the accuracy-efficiency trade-off landscape. (4) P-MapNet is a far-seeing solution that brings larger improvements on longer ranges. Codes and models are publicly available at https://jike5.github.io/P-MapNet.
Authors: Yiqing Shen, Jingxing Li, Xinyuan Shao, Blanca Inigo Romillo, Ankush Jindal, David Dreizin, Mathias Unberath
Abstract: Segment anything models (SAMs) are gaining attention for their zero-shot generalization capability in segmenting objects of unseen classes and in unseen domains when properly prompted. Interactivity is a key strength of SAMs, allowing users to iteratively provide prompts that specify objects of interest to refine outputs. However, to realize the interactive use of SAMs for 3D medical imaging tasks, rapid inference times are necessary. High memory requirements and long processing delays remain constraints that hinder the adoption of SAMs for this purpose. Specifically, while 2D SAMs applied to 3D volumes contend with repetitive computation to process all slices independently, 3D SAMs suffer from an exponential increase in model parameters and FLOPS. To address these challenges, we present FastSAM3D which accelerates SAM inference to 8 milliseconds per 128*128*128 3D volumetric image on an NVIDIA A100 GPU. This speedup is accomplished through 1) a novel layer-wise progressive distillation scheme that enables knowledge transfer from a complex 12-layer ViT-B to a lightweight 6-layer ViT-Tiny variant encoder without training from scratch; and 2) a novel 3D sparse flash attention to replace vanilla attention operators, substantially reducing memory needs and improving parallelization. Experiments on three diverse datasets reveal that FastSAM3D achieves a remarkable speedup of 527.38x compared to 2D SAMs and 8.75x compared to 3D SAMs on the same volumes without significant performance decline. Thus, FastSAM3D opens the door for low-cost truly interactive SAM-based 3D medical imaging segmentation with commonly used GPU hardware. Code is available at https://github.com/arcadelab/FastSAM3D.
Authors: Adam Tupper, Christian Gagn\'e
Abstract: Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability in medical image analysis, it is frequently underutilized. This appears to be due to a gap in our collective understanding of the efficacy of different augmentation techniques across medical imaging tasks and modalities. One domain where this is especially true is breast ultrasound images. This work addresses this issue by analyzing the effectiveness of different augmentation techniques for the classification of breast lesions in ultrasound images. We assess the generalizability of our findings across several datasets, demonstrate that certain augmentations are far more effective than others, and show that their usage leads to significant performance gains.
Authors: Al Amin, Kamrul Hasan, Saleh Zein-Sabatto, Deo Chimba, Liang Hong, Imtiaz Ahmed, Tariqul Islam
Abstract: In the healthcare domain, Magnetic Resonance Imaging (MRI) assumes a pivotal role, as it employs Artificial Intelligence (AI) and Machine Learning (ML) methodologies to extract invaluable insights from imaging data. Nonetheless, the imperative need for patient privacy poses significant challenges when collecting data from diverse healthcare sources. Consequently, the Deep Learning (DL) communities occasionally face difficulties detecting rare features. In this research endeavor, we introduce the Ensemble-Based Federated Learning (EBFL) Framework, an innovative solution tailored to address this challenge. The EBFL framework deviates from the conventional approach by emphasizing model features over sharing sensitive patient data. This unique methodology fosters a collaborative and privacy-conscious environment for healthcare institutions, empowering them to harness the capabilities of a centralized server for model refinement while upholding the utmost data privacy standards.Conversely, a robust ensemble architecture boasts potent feature extraction capabilities, distinguishing itself from a single DL model. This quality makes it remarkably dependable for MRI analysis. By harnessing our groundbreaking EBFL methodology, we have achieved remarkable precision in the classification of brain tumors, including glioma, meningioma, pituitary, and non-tumor instances, attaining a precision rate of 94% for the Global model and an impressive 96% for the Ensemble model. Our models underwent rigorous evaluation using conventional performance metrics such as Accuracy, Precision, Recall, and F1 Score. Integrating DL within the Federated Learning (FL) framework has yielded a methodology that offers precise and dependable diagnostics for detecting brain tumors.
Authors: Chenxi Liu, Zhenyi Wang, Tianyi Xiong, Ruibo Chen, Yihan Wu, Junfeng Guo, Heng Huang
Abstract: Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading to overfitting and hindering the potential to learn new classes. On the other hand, recent prompt-based CIL approaches alleviate forgetting by training prompts with sufficient data in each task. In this work, we propose a novel framework named Attention-aware Self-adaptive Prompt (ASP). ASP encourages task-invariant prompts to capture shared knowledge by reducing specific information from the attention aspect. Additionally, self-adaptive task-specific prompts in ASP provide specific information and transfer knowledge from old classes to new classes with an Information Bottleneck learning objective. In summary, ASP prevents overfitting on base task and does not require enormous data in few-shot incremental tasks. Extensive experiments on three benchmark datasets validate that ASP consistently outperforms state-of-the-art FSCIL and prompt-based CIL methods in terms of both learning new classes and mitigating forgetting.
Authors: Aiden Swann, Matthew Strong, Won Kyung Do, Gadiel Sznaier Camps, Mac Schwager, Monroe Kennedy III
Abstract: In this work, we propose a novel method to supervise 3D Gaussian Splatting (3DGS) scenes using optical tactile sensors. Optical tactile sensors have become widespread in their use in robotics for manipulation and object representation; however, raw optical tactile sensor data is unsuitable to directly supervise a 3DGS scene. Our representation leverages a Gaussian Process Implicit Surface to implicitly represent the object, combining many touches into a unified representation with uncertainty. We merge this model with a monocular depth estimation network, which is aligned in a two stage process, coarsely aligning with a depth camera and then finely adjusting to match our touch data. For every training image, our method produces a corresponding fused depth and uncertainty map. Utilizing this additional information, we propose a new loss function, variance weighted depth supervised loss, for training the 3DGS scene model. We leverage the DenseTact optical tactile sensor and RealSense RGB-D camera to show that combining touch and vision in this manner leads to quantitatively and qualitatively better results than vision or touch alone in a few-view scene syntheses on opaque as well as on reflective and transparent objects. Please see our project page at http://armlabstanford.github.io/touch-gs
Authors: Vishnu Sashank Dorbala, Bhrij Patel, Amrit Singh Bedi, Dinesh Manocha
Abstract: We present a novel approach to tackle the ObjectNav task for non-stationary and potentially occluded targets in an indoor environment. We refer to this task Portable ObjectNav (or P-ObjectNav), and in this work, present its formulation, feasibility, and a navigation benchmark using a novel memory-enhanced LLM-based policy. In contrast to ObjNav where target object locations are fixed for each episode, P-ObjectNav tackles the challenging case where the target objects move during the episode. This adds a layer of time-sensitivity to navigation, and is particularly relevant in scenarios where the agent needs to find portable targets (e.g. misplaced wallets) in human-centric environments. The agent needs to estimate not just the correct location of the target, but also the time at which the target is at that location for visual grounding -- raising the question about the feasibility of the task. We address this concern by inferring results on two cases for object placement: one where the objects placed follow a routine or a path, and the other where they are placed at random. We dynamize Matterport3D for these experiments, and modify PPO and LLM-based navigation policies for evaluation. Using PPO, we observe that agent performance in the random case stagnates, while the agent in the routine-following environment continues to improve, allowing us to infer that P-ObjectNav is solvable in environments with routine-following object placement. Using memory-enhancement on an LLM-based policy, we set a benchmark for P-ObjectNav. Our memory-enhanced agent significantly outperforms their non-memory-based counterparts across object placement scenarios by 71.76% and 74.68% on average when measured by Success Rate (SR) and Success Rate weighted by Path Length (SRPL), showing the influence of memory on improving P-ObjectNav performance. Our code and dataset will be made publicly available.
Authors: Ziya Ata Yaz{\i}c{\i}, \.Ilkay \"Oks\"uz, Haz{\i}m Kemal Ekenel
Abstract: Glioblastoma is a highly aggressive and malignant brain tumor type that requires early diagnosis and prompt intervention. Due to its heterogeneity in appearance, developing automated detection approaches is challenging. To address this challenge, Artificial Intelligence (AI)-driven approaches in healthcare have generated interest in efficiently diagnosing and evaluating brain tumors. The Brain Tumor Segmentation Challenge (BraTS) is a platform for developing and assessing automated techniques for tumor analysis using high-quality, clinically acquired MRI data. In our approach, we utilized a multi-scale, attention-guided and hybrid U-Net-shaped model -- GLIMS -- to perform 3D brain tumor segmentation in three regions: Enhancing Tumor (ET), Tumor Core (TC), and Whole Tumor (WT). The multi-scale feature extraction provides better contextual feature aggregation in high resolutions and the Swin Transformer blocks improve the global feature extraction at deeper levels of the model. The segmentation mask generation in the decoder branch is guided by the attention-refined features gathered from the encoder branch to enhance the important attributes. Moreover, hierarchical supervision is used to train the model efficiently. Our model's performance on the validation set resulted in 92.19, 87.75, and 83.18 Dice Scores and 89.09, 84.67, and 82.15 Lesion-wise Dice Scores in WT, TC, and ET, respectively. The code is publicly available at https://github.com/yaziciz/GLIMS.
Authors: Zixin Yang, Richard Simon, Kelly Merrell, Cristian. A. Linte
Abstract: In image-guided liver surgery, 3D-3D non-rigid registration methods play a crucial role in estimating the mapping between the preoperative model and the intraoperative surface represented as point clouds, addressing the challenge of tissue deformation. Typically, these methods incorporate a biomechanical model, represented as a finite element model (FEM), used to regularize a surface matching term. This paper introduces a novel 3D-3D non-rigid registration method. In contrast to the preceding techniques, our method uniquely incorporates the FEM within the surface matching term itself, ensuring that the estimated deformation maintains geometric consistency throughout the registration process. Additionally, we eliminate the need to determine zero-boundary conditions and applied force locations in the FEM. We achieve this by integrating soft springs into the stiffness matrix and allowing forces to be distributed across the entire liver surface. To further improve robustness, we introduce a regularization technique focused on the gradient of the force magnitudes. This regularization imposes spatial smoothness and helps prevent the overfitting of irregular noise in intraoperative data. Optimization is achieved through an accelerated proximal gradient algorithm, further enhanced by our proposed method for determining the optimal step size. Our method is evaluated and compared to both a learning-based method and a traditional method that features FEM regularization using data collected on our custom-developed phantom, as well as two publicly available datasets. Our method consistently outperforms or is comparable to the baseline techniques. Both the code and dataset will be made publicly available.
Authors: Yucen Wang, Shenghua Wan, Le Gan, Shuai Feng, De-Chuan Zhan
Abstract: Model-based methods have significantly contributed to distinguishing task-irrelevant distractors for visual control. However, prior research has primarily focused on heterogeneous distractors like noisy background videos, leaving homogeneous distractors that closely resemble controllable agents largely unexplored, which poses significant challenges to existing methods. To tackle this problem, we propose Implicit Action Generator (IAG) to learn the implicit actions of visual distractors, and present a new algorithm named implicit Action-informed Diverse visual Distractors Distinguisher (AD3), that leverages the action inferred by IAG to train separated world models. Implicit actions effectively capture the behavior of background distractors, aiding in distinguishing the task-irrelevant components, and the agent can optimize the policy within the task-relevant state space. Our method achieves superior performance on various visual control tasks featuring both heterogeneous and homogeneous distractors. The indispensable role of implicit actions learned by IAG is also empirically validated.
Authors: Zhennong Chen, Sekeun Kim, Hui Ren, Quanzheng Li, Xiang Li
Abstract: Accurate 2D+T myocardium segmentation in cine cardiac magnetic resonance (CMR) scans is essential to analyze LV motion throughout the cardiac cycle comprehensively. The Segment Anything Model (SAM), known for its accurate segmentation and zero-shot generalization, has not yet been tailored for CMR 2D+T segmentation. We therefore introduce CMR2D+T-SAM, a novel approach to adapt SAM for CMR 2D+T segmentation using spatio-temporal adaption. This approach also incorporates a U-Net framework for multi-scale feature extraction, as well as text prompts for accurate segmentation on both short-axis (SAX) and long-axis (LAX) views using a single model. CMR2D+T-SAM outperforms existing deep learning methods on the STACOM2011 dataset, achieving a myocardium Dice score of 0.885 and a Hausdorff distance (HD) of 2.900 pixels. It also demonstrates superior zero-shot generalization on the ACDC dataset with a Dice score of 0.840 and a HD of 4.076 pixels.
Authors: Zhikang Wang, Yumeng Zhang, Yingxue Xu, Seiya Imoto, Hao Chen, Jiangning Song
Abstract: Histo-genomic multi-modal methods have recently emerged as a powerful paradigm, demonstrating significant potential for improving cancer prognosis. However, genome sequencing, unlike histopathology imaging, is still not widely accessible in underdeveloped regions, limiting the application of these multi-modal approaches in clinical settings. To address this, we propose a novel Genome-informed Hyper-Attention Network, termed G-HANet, which is capable of effectively distilling the histo-genomic knowledge during training to elevate uni-modal whole slide image (WSI)-based inference for the first time. Compared with traditional knowledge distillation methods (i.e., teacher-student architecture) in other tasks, our end-to-end model is superior in terms of training efficiency and learning cross-modal interactions. Specifically, the network comprises the cross-modal associating branch (CAB) and hyper-attention survival branch (HSB). Through the genomic data reconstruction from WSIs, CAB effectively distills the associations between functional genotypes and morphological phenotypes and offers insights into the gene expression profiles in the feature space. Subsequently, HSB leverages the distilled histo-genomic associations as well as the generated morphology-based weights to achieve the hyper-attention modeling of the patients from both histopathology and genomic perspectives to improve cancer prognosis. Extensive experiments are conducted on five TCGA benchmarking datasets and the results demonstrate that G-HANet significantly outperforms the state-of-the-art WSI-based methods and achieves competitive performance with genome-based and multi-modal methods. G-HANet is expected to be explored as a useful tool by the research community to address the current bottleneck of insufficient histo-genomic data pairing in the context of cancer prognosis and precision oncology.
Authors: Eric Xue, Yijiang Li, Haoyang Liu, Yifan Shen, Haohan Wang
Abstract: Dataset distillation (DD) allows datasets to be distilled to fractions of their original size while preserving the rich distributional information so that models trained on the distilled datasets can achieve a comparable accuracy while saving significant computational loads. Recent research in this area has been focusing on improving the accuracy of models trained on distilled datasets. In this paper, we aim to explore a new perspective of DD. We study how to embed adversarial robustness in distilled datasets, so that models trained on these datasets maintain the high accuracy and meanwhile acquire better adversarial robustness. We propose a new method that achieves this goal by incorporating curvature regularization into the distillation process with much less computational overhead than standard adversarial training. Extensive empirical experiments suggest that our method not only outperforms standard adversarial training on both accuracy and robustness with less computation overhead but is also capable of generating robust distilled datasets that can withstand various adversarial attacks.
Authors: Chong Wang, Lanqing Guo, Yufei Wang, Hao Cheng, Yi Yu, Bihan Wen
Abstract: Deep unfolding networks (DUN) have emerged as a popular iterative framework for accelerated magnetic resonance imaging (MRI) reconstruction. However, conventional DUN aims to reconstruct all the missing information within the entire null space in each iteration. Thus it could be challenging when dealing with highly ill-posed degradation, usually leading to unsatisfactory reconstruction. In this work, we propose a Progressive Divide-And-Conquer (PDAC) strategy, aiming to break down the subsampling process in the actual severe degradation and thus perform reconstruction sequentially. Starting from decomposing the original maximum-a-posteriori problem of accelerated MRI, we present a rigorous derivation of the proposed PDAC framework, which could be further unfolded into an end-to-end trainable network. Specifically, each iterative stage in PDAC focuses on recovering a distinct moderate degradation according to the decomposition. Furthermore, as part of the PDAC iteration, such decomposition is adaptively learned as an auxiliary task through a degradation predictor which provides an estimation of the decomposed sampling mask. Following this prediction, the sampling mask is further integrated via a severity conditioning module to ensure awareness of the degradation severity at each stage. Extensive experiments demonstrate that our proposed method achieves superior performance on the publicly available fastMRI and Stanford2D FSE datasets in both multi-coil and single-coil settings.
Authors: Shuai Hu, Feng Gao, Xiaowei Zhou, Junyu Dong, Qian Du
Abstract: Hyperspectral image (HSI) denoising is critical for the effective analysis and interpretation of hyperspectral data. However, simultaneously modeling global and local features is rarely explored to enhance HSI denoising. In this letter, we propose a hybrid convolution and attention network (HCANet), which leverages both the strengths of convolution neural networks (CNNs) and Transformers. To enhance the modeling of both global and local features, we have devised a convolution and attention fusion module aimed at capturing long-range dependencies and neighborhood spectral correlations. Furthermore, to improve multi-scale information aggregation, we design a multi-scale feed-forward network to enhance denoising performance by extracting features at different scales. Experimental results on mainstream HSI datasets demonstrate the rationality and effectiveness of the proposed HCANet. The proposed model is effective in removing various types of complex noise. Our codes are available at \url{https://github.com/summitgao/HCANet}.
Authors: Frank Nielsen
Abstract: The Fisher-Rao distance between two probability distributions of a statistical model is defined as the Riemannian geodesic distance induced by the Fisher information metric. In order to calculate the Fisher-Rao distance in closed-form, we need (1) to elicit a formula for the Fisher-Rao geodesics, and (2) to integrate the Fisher length element along those geodesics. We consider several numerically robust approximation and bounding techniques for the Fisher-Rao distances: First, we report generic upper bounds on Fisher-Rao distances based on closed-form 1D Fisher-Rao distances of submodels. Second, we describe several generic approximation schemes depending on whether the Fisher-Rao geodesics or pregeodesics are available in closed-form or not. In particular, we obtain a generic method to guarantee an arbitrarily small additive error on the approximation provided that Fisher-Rao pregeodesics and tight lower and upper bounds are available. Third, we consider the case of Fisher metrics being Hessian metrics, and report generic tight upper bounds on the Fisher-Rao distances using techniques of information geometry. Uniparametric and biparametric statistical models always have Fisher Hessian metrics, and in general a simple test allows to check whether the Fisher information matrix yields a Hessian metric or not. Fourth, we consider elliptical distribution families and show how to apply the above techniques to these models. We also propose two new distances based either on the Fisher-Rao lengths of curves serving as proxies of Fisher-Rao geodesics, or based on the Birkhoff/Hilbert projective cone distance. Last, we consider an alternative group-theoretic approach for statistical transformation models based on the notion of maximal invariant which yields insights on the structures of the Fisher-Rao distance formula which may be used fruitfully in applications.
Authors: Masakazu Yoshimura, Junji Otsuka, Takeshi Ohashi
Abstract: Full DNN-based image signal processors (ISPs) have been actively studied and have achieved superior image quality compared to conventional ISPs. In contrast to this trend, we propose a lightweight ISP that consists of simple conventional ISP functions but achieves high image quality by increasing expressiveness. Specifically, instead of tuning the parameters of the ISP, we propose to control them dynamically for each environment and even locally. As a result, state-of-the-art accuracy is achieved on various datasets, including other tasks like tone mapping and image enhancement, even though ours is lighter than DNN-based ISPs. Additionally, our method can process different image sensors with a single ISP through dynamic control, whereas conventional methods require training for each sensor.
Authors: Shin'ya Yamaguchi, Sekitoshi Kanai, Kazuki Adachi, Daiki Chijiwa
Abstract: While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source datasets or introducing regularization terms such as contrastive loss. However, these methods require auxiliary source information (e.g., source labels or datasets) or heavy additional computations. In this paper, we propose a simple method called adaptive random feature regularization (AdaRand). AdaRand helps the feature extractors of training models to adaptively change the distribution of feature vectors for downstream classification tasks without auxiliary source information and with reasonable computation costs. To this end, AdaRand minimizes the gap between feature vectors and random reference vectors that are sampled from class conditional Gaussian distributions. Furthermore, AdaRand dynamically updates the conditional distribution to follow the currently updated feature extractors and balance the distance between classes in feature spaces. Our experiments show that AdaRand outperforms the other fine-tuning regularization, which requires auxiliary source information and heavy computation costs.
Authors: Benjamin Strandli Fermann, John Nyberg, Espen W. Remme, Jahn Frederik Grue, Hel\'en Grue, Roger H{\aa}land, Lasse Lovstakken, H{\aa}vard Dalen, Bj{\o}rnar Grenne, Svein Arne Aase, Sten Roar Snar, Andreas {\O}stvik
Abstract: Cardiac valve event timing plays a crucial role when conducting clinical measurements using echocardiography. However, established automated approaches are limited by the need of external electrocardiogram sensors, and manual measurements often rely on timing from different cardiac cycles. Recent methods have applied deep learning to cardiac timing, but they have mainly been restricted to only detecting two key time points, namely end-diastole (ED) and end-systole (ES). In this work, we propose a deep learning approach that leverages triplane recordings to enhance detection of valve events in echocardiography. Our method demonstrates improved performance detecting six different events, including valve events conventionally associated with ED and ES. Of all events, we achieve an average absolute frame difference (aFD) of maximum 1.4 frames (29 ms) for start of diastasis, down to 0.6 frames (12 ms) for mitral valve opening when performing a ten-fold cross-validation with test splits on triplane data from 240 patients. On an external independent test consisting of apical long-axis data from 180 other patients, the worst performing event detection had an aFD of 1.8 (30 ms). The proposed approach has the potential to significantly impact clinical practice by enabling more accurate, rapid and comprehensive event detection, leading to improved clinical measurements.
Authors: Arkajit Datta, Tushar Verma, Rajat Chawla
Abstract: In recent advancements within the domain of Large Language Models (LLMs), there has been a notable emergence of agents capable of addressing Robotic Process Automation (RPA) challenges through enhanced cognitive capabilities and sophisticated reasoning. This development heralds a new era of scalability and human-like adaptability in goal attainment. In this context, we introduce AUTONODE (Autonomous User-interface Transformation through Online Neuro-graphic Operations and Deep Exploration). AUTONODE employs advanced neuro-graphical techniques to facilitate autonomous navigation and task execution on web interfaces, thereby obviating the necessity for predefined scripts or manual intervention. Our engine empowers agents to comprehend and implement complex workflows, adapting to dynamic web environments with unparalleled efficiency. Our methodology synergizes cognitive functionalities with robotic automation, endowing AUTONODE with the ability to learn from experience. We have integrated an exploratory module, DoRA (Discovery and mapping Operation for graph Retrieval Agent), which is instrumental in constructing a knowledge graph that the engine utilizes to optimize its actions and achieve objectives with minimal supervision. The versatility and efficacy of AUTONODE are demonstrated through a series of experiments, highlighting its proficiency in managing a diverse array of web-based tasks, ranging from data extraction to transaction processing.
Authors: Ahcen Aliouat, Elsa Dupraz
Abstract: In goal-oriented communications, the objective of the receiver is often to apply a Deep-Learning model, rather than reconstructing the original data. In this context, direct learning over compressed data, without any prior decoding, holds promise for enhancing the time-efficient execution of inference models at the receiver. However, conventional entropic-coding methods like Huffman and Arithmetic break data structure, rendering them unsuitable for learning without decoding. In this paper, we propose an alternative approach in which entropic coding is realized with Low-Density Parity Check (LDPC) codes. We hypothesize that Deep Learning models can more effectively exploit the internal code structure of LDPC codes. At the receiver, we leverage a specific class of Recurrent Neural Networks (RNNs), specifically Gated Recurrent Unit (GRU), trained for image classification. Our numerical results indicate that classification based on LDPC-coded bit-planes surpasses Huffman and Arithmetic coding, while necessitating a significantly smaller learning model. This demonstrates the efficiency of classification directly from LDPC-coded data, eliminating the need for any form of decompression, even partial, prior to applying the learning model.
Authors: Peng Jia, Chao Lv, Yushan Li, Yongyang Sun, Shu Niu, Zhuoxiao Wang
Abstract: In recent years, there has been a gradual increase in the performance of Complementary Metal Oxide Semiconductor (CMOS) cameras. These cameras have gained popularity as a viable alternative to charge-coupled device (CCD) cameras in a wide range of applications. One particular application is the CMOS camera installed in small space telescopes. However, the limited power and spatial resources available on satellites present challenges in maintaining ideal observation conditions, including temperature and radiation environment. Consequently, images captured by CMOS cameras are susceptible to issues such as dark current noise and defective pixels. In this paper, we introduce a data-driven framework for mitigating dark current noise and bad pixels for CMOS cameras. Our approach involves two key steps: pixel clustering and function fitting. During pixel clustering step, we identify and group pixels exhibiting similar dark current noise properties. Subsequently, in the function fitting step, we formulate functions that capture the relationship between dark current and temperature, as dictated by the Arrhenius law. Our framework leverages ground-based test data to establish distinct temperature-dark current relations for pixels within different clusters. The cluster results could then be utilized to estimate the dark current noise level and detect bad pixels from real observational data. To assess the effectiveness of our approach, we have conducted tests using real observation data obtained from the Yangwang-1 satellite, equipped with a near-ultraviolet telescope and an optical telescope. The results show a considerable improvement in the detection efficiency of space-based telescopes.
Authors: Hengxing Cai, Xiaochen Cai, Shuwen Yang, Jiankun Wang, Lin Yao, Zhifeng Gao, Junhan Chang, Sihang Li, Mingjun Xu, Changxin Wang, Hongshuai Wang, Yongge Li, Mujie Lin, Yaqi Li, Yuqi Yin, Linfeng Zhang, Guolin Ke
Abstract: In scientific research and its application, scientific literature analysis is crucial as it allows researchers to build on the work of others. However, the fast growth of scientific knowledge has led to a massive increase in scholarly articles, making in-depth literature analysis increasingly challenging and time-consuming. The emergence of Large Language Models (LLMs) has offered a new way to address this challenge. Known for their strong abilities in summarizing texts, LLMs are seen as a potential tool to improve the analysis of scientific literature. However, existing LLMs have their own limits. Scientific literature often includes a wide range of multimodal elements, such as molecular structure, tables, and charts, which are hard for text-focused LLMs to understand and analyze. This issue points to the urgent need for new solutions that can fully understand and analyze multimodal content in scientific literature. To answer this demand, we present Uni-SMART (Universal Science Multimodal Analysis and Research Transformer), an innovative model designed for in-depth understanding of multimodal scientific literature. Through rigorous quantitative evaluation across several domains, Uni-SMART demonstrates superior performance over leading text-focused LLMs. Furthermore, our exploration extends to practical applications, including patent infringement detection and nuanced analysis of charts. These applications not only highlight Uni-SMART's adaptability but also its potential to revolutionize how we interact with scientific literature.
Authors: George Yiasemis, Jan-Jakob Sonke, Jonas Teuwen
Abstract: Accelerating dynamic MRI is essential for enhancing clinical applications, such as adaptive radiotherapy, and improving patient comfort. Traditional deep learning (DL) approaches for accelerated dynamic MRI reconstruction typically rely on predefined or random subsampling patterns, applied uniformly across all temporal phases. This standard practice overlooks the potential benefits of leveraging temporal correlations and lacks the adaptability required for case-specific subsampling optimization, which holds the potential for maximizing reconstruction quality. Addressing this gap, we present a novel end-to-end framework for adaptive dynamic MRI subsampling and reconstruction. Our pipeline integrates a DL-based adaptive sampler, generating case-specific dynamic subsampling patterns, trained end-to-end with a state-of-the-art 2D dynamic reconstruction network, namely vSHARP, which effectively reconstructs the adaptive dynamic subsampled data into a moving image. Our method is assessed using dynamic cine cardiac MRI data, comparing its performance against vSHARP models that employ common subsampling trajectories, and pipelines trained to optimize dataset-specific sampling schemes alongside vSHARP reconstruction. Our results indicate superior reconstruction quality, particularly at high accelerations.
Authors: Qiang Zhu, Jinhua Hao, Yukang Ding, Yu Liu, Qiao Mo, Ming Sun, Chao Zhou, Shuyuan Zhu
Abstract: Recently, numerous approaches have achieved notable success in compressed video quality enhancement (VQE). However, these methods usually ignore the utilization of valuable coding priors inherently embedded in compressed videos, such as motion vectors and residual frames, which carry abundant temporal and spatial information. To remedy this problem, we propose the Coding Priors-Guided Aggregation (CPGA) network to utilize temporal and spatial information from coding priors. The CPGA mainly consists of an inter-frame temporal aggregation (ITA) module and a multi-scale non-local aggregation (MNA) module. Specifically, the ITA module aggregates temporal information from consecutive frames and coding priors, while the MNA module globally captures spatial information guided by residual frames. In addition, to facilitate research in VQE task, we newly construct the Video Coding Priors (VCP) dataset, comprising 300 videos with various coding priors extracted from corresponding bitstreams. It remedies the shortage of previous datasets on the lack of coding information. Experimental results demonstrate the superiority of our method compared to existing state-of-the-art methods. The code and dataset will be released at https://github.com/CPGA/CPGA.git.
Authors: Edward P. Chandler, Shirin Shoushtari, Jiaming Liu, M. Salman Asif, Ulugbek S. Kamilov
Abstract: Plug-and-Play Priors (PnP) is a well-known class of methods for solving inverse problems in computational imaging. PnP methods combine physical forward models with learned prior models specified as image denoisers. A common issue with the learned models is that of a performance drop when there is a distribution shift between the training and testing data. Test-time training (TTT) was recently proposed as a general strategy for improving the performance of learned models when training and testing data come from different distributions. In this paper, we propose PnP-TTT as a new method for overcoming distribution shifts in PnP. PnP-TTT uses deep equilibrium learning (DEQ) for optimizing a self-supervised loss at the fixed points of PnP iterations. PnP-TTT can be directly applied on a single test sample to improve the generalization of PnP. We show through simulations that given a sufficient number of measurements, PnP-TTT enables the use of image priors trained on natural images for image reconstruction in magnetic resonance imaging (MRI).
Authors: Rocktim Jyoti Das, Simeon Emilov Hristov, Haonan Li, Dimitar Iliyanov Dimitrov, Ivan Koychev, Preslav Nakov
Abstract: We introduce EXAMS-V, a new challenging multi-discipline multimodal multilingual exam benchmark for evaluating vision language models. It consists of 20,932 multiple-choice questions across 20 school disciplines covering natural science, social science, and other miscellaneous studies, e.g., religion, fine arts, business, etc. EXAMS-V includes a variety of multimodal features such as text, images, tables, figures, diagrams, maps, scientific symbols, and equations. The questions come in 11 languages from 7 language families. Unlike existing benchmarks, EXAMS-V is uniquely curated by gathering school exam questions from various countries, with a variety of education systems. This distinctive approach calls for intricate reasoning across diverse languages and relies on region-specific knowledge. Solving the problems in the dataset requires advanced perception and joint reasoning over the text and the visual content of the image. Our evaluation results demonstrate that this is a challenging dataset, which is difficult even for advanced vision-text models such as GPT-4V and Gemini; this underscores the inherent complexity of the dataset and its significance as a future benchmark.
Authors: Tom F. Hansen, Georg H. Erharter, Zhongqiang Liu, Jim Torresen
Abstract: Current rock engineering design in drill and blast tunnelling primarily relies on engineers' observational assessments. Measure While Drilling (MWD) data, a high-resolution sensor dataset collected during tunnel excavation, is underutilised, mainly serving for geological visualisation. This study aims to automate the translation of MWD data into actionable metrics for rock engineering. It seeks to link data to specific engineering actions, thus providing critical decision support for geological challenges ahead of the tunnel face. Leveraging a large and geologically diverse dataset of 500,000 drillholes from 15 tunnels, the research introduces models for accurate rock mass quality classification in a real-world tunnelling context. Both conventional machine learning and image-based deep learning are explored to classify MWD data into Q-classes and Q-values, examples of metrics describing the stability of the rock mass, using both tabular and image data. The results indicate that the K-nearest neighbours algorithm in an ensemble with tree-based models using tabular data, effectively classifies rock mass quality. It achieves a cross-validated balanced accuracy of 0.86 in classifying rock mass into the Q-classes A, B, C, D, E1, E2, and 0.95 for a binary classification with E versus the rest. Classification using a CNN with MWD-images for each blasting round resulted in a balanced accuracy of 0.82 for binary classification. Regressing the Q-value from tabular MWD-data achieved cross-validated R2 and MSE scores of 0.80 and 0.18 for a similar ensemble model as in classification. High performance in regression and classification boosts confidence in automated rock mass assessment. Applying advanced modelling on a unique dataset demonstrates MWD data's value in improving rock mass classification accuracy and advancing data-driven rock engineering design, reducing manual intervention.
Authors: Marc Lafon, Alexandre Thomas
Abstract: Combining empirical risk minimization with capacity control is a classical strategy in machine learning when trying to control the generalization gap and avoid overfitting, as the model class capacity gets larger. Yet, in modern deep learning practice, very large over-parameterized models (e.g. neural networks) are optimized to fit perfectly the training data and still obtain great generalization performance. Past the interpolation point, increasing model complexity seems to actually lower the test error. In this tutorial, we explain the concept of double descent and its mechanisms. The first section sets the classical statistical learning framework and introduces the double descent phenomenon. By looking at a number of examples, section 2 introduces inductive biases that appear to have a key role in double descent by selecting, among the multiple interpolating solutions, a smooth empirical risk minimizer. Finally, section 3 explores the double descent with two linear models, and gives other points of view from recent related works.
Authors: Chenguang Wang, Ruoxi Jia, Xin Liu, Dawn Song
Abstract: Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP, produce state-of-the-art zero-shot results that often reach competitiveness with fully supervised methods without the need for task-specific training. Besides the encouraging performance on classification accuracy, it is reported that these models close the robustness gap by matching the performance of supervised models trained on ImageNet under natural distribution shift. Because robustness is critical to real-world applications, especially safety-critical ones, in this paper, we present a comprehensive evaluation based on a large-scale robustness benchmark covering 7 natural, 3 synthetic distribution shifts, and 11 adversarial attacks. We use CLIP as a pilot study. We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark, especially under synthetic distribution shift and adversarial attacks. Furthermore, data overlap analysis suggests that the observed robustness under natural distribution shifts could be attributed, at least in part, to data overlap. In summary, our evaluation shows a comprehensive evaluation of robustness is necessary; and there is a significant need to improve the robustness of zero-shot multimodal models.
Authors: Wen Wen, Mu Li, Yiru Yao, Xiangjie Sui, Yabin Zhang, Long Lan, Yuming Fang, Kede Ma
Abstract: Investigating how people perceive virtual reality (VR) videos in the wild (i.e., those captured by everyday users) is a crucial and challenging task in VR-related applications due to complex authentic distortions localized in space and time. Existing panoramic video databases only consider synthetic distortions, assume fixed viewing conditions, and are limited in size. To overcome these shortcomings, we construct the VR Video Quality in the Wild (VRVQW) database, containing $502$ user-generated videos with diverse content and distortion characteristics. Based on VRVQW, we conduct a formal psychophysical experiment to record the scanpaths and perceived quality scores from $139$ participants under two different viewing conditions. We provide a thorough statistical analysis of the recorded data, observing significant impact of viewing conditions on both human scanpaths and perceived quality. Moreover, we develop an objective quality assessment model for VR videos based on pseudocylindrical representation and convolution. Results on the proposed VRVQW show that our method is superior to existing video quality assessment models. We have made the database and code available at https://github.com/limuhit/VR-Video-Quality-in-the-Wild.
URLs: https://github.com/limuhit/VR-Video-Quality-in-the-Wild.
Authors: Jiachen Lu, Junge Zhang, Xiatian Zhu, Jianfeng Feng, Tao Xiang, Li Zhang
Abstract: Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory usage. This motivates the development of approximating the self-attention at linear complexity. However, an in-depth analysis in this work reveals that existing methods are either theoretically flawed or empirically ineffective for visual recognition. We identify that their limitations are rooted in the inheritance of softmax-based self-attention during approximations, that is, normalizing the scaled dot-product between token feature vectors using the softmax function. As preserving the softmax operation challenges any subsequent linearization efforts. By this insight, a family of Softmax-Free Transformers (SOFT) are proposed. Specifically, a Gaussian kernel function is adopted to replace the dot-product similarity, enabling a full self-attention matrix to be approximated under low-rank matrix decomposition. For computational robustness, we estimate the Moore-Penrose inverse using an iterative Newton-Raphson method in the forward process only, while calculating its theoretical gradients only once in the backward process. To further expand applicability (e.g., dense prediction tasks), an efficient symmetric normalization technique is introduced. Extensive experiments on ImageNet, COCO, and ADE20K show that our SOFT significantly improves the computational efficiency of existing ViT variants. With linear complexity, much longer token sequences are permitted by SOFT, resulting in superior trade-off between accuracy and complexity. Code and models are available at https://github.com/fudan-zvg/SOFT.
Authors: Oren Shrout, Yizhak Ben-Shabat, Ayellet Tal
Abstract: 3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to add ground-truth objects from other scenes. Differently, we propose to modify the scenes by removing elements (voxels), rather than adding ones. Our approach selects the "meaningful" voxels, in a manner that addresses both types of dataset imbalance. The approach is general and can be applied to any voxel-based detector, yet the meaningfulness of a voxel is network-dependent. Our voxel selection is shown to improve the performance of several prominent 3D detection methods.
Authors: Dongchan Min, Minyoung Song, Eunji Ko, Sung Ju Hwang
Abstract: We propose StyleTalker, a novel audio-driven talking head generation model that can synthesize a video of a talking person from a single reference image with accurately audio-synced lip shapes, realistic head poses, and eye blinks. Specifically, by leveraging a pretrained image generator and an image encoder, we estimate the latent codes of the talking head video that faithfully reflects the given audio. This is made possible with several newly devised components: 1) A contrastive lip-sync discriminator for accurate lip synchronization, 2) A conditional sequential variational autoencoder that learns the latent motion space disentangled from the lip movements, such that we can independently manipulate the motions and lip movements while preserving the identity. 3) An auto-regressive prior augmented with normalizing flow to learn a complex audio-to-motion multi-modal latent space. Equipped with these components, StyleTalker can generate talking head videos not only in a motion-controllable way when another motion source video is given but also in a completely audio-driven manner by inferring realistic motions from the input audio. Through extensive experiments and user studies, we show that our model is able to synthesize talking head videos with impressive perceptual quality which are accurately lip-synced with the input audios, largely outperforming state-of-the-art baselines.
Authors: Byeongjun Park, Hyojun Go, Changick Kim
Abstract: Creating novel views from a single image has achieved tremendous strides with advanced autoregressive models, as unseen regions have to be inferred from the visible scene contents. Although recent methods generate high-quality novel views, synthesizing with only one explicit or implicit 3D geometry has a trade-off between two objectives that we call the "seesaw" problem: 1) preserving reprojected contents and 2) completing realistic out-of-view regions. Also, autoregressive models require a considerable computational cost. In this paper, we propose a single-image view synthesis framework for mitigating the seesaw problem while utilizing an efficient non-autoregressive model. Motivated by the characteristics that explicit methods well preserve reprojected pixels and implicit methods complete realistic out-of-view regions, we introduce a loss function to complement two renderers. Our loss function promotes that explicit features improve the reprojected area of implicit features and implicit features improve the out-of-view area of explicit features. With the proposed architecture and loss function, we can alleviate the seesaw problem, outperforming autoregressive-based state-of-the-art methods and generating an image $\approx$100 times faster. We validate the efficiency and effectiveness of our method with experiments on RealEstate10K and ACID datasets.
Authors: Cong Wang, Jinshan Pan, Wanyu Lin, Jiangxin Dong, Xiao-Ming Wu
Abstract: This work presents an effective depth-consistency self-prompt Transformer for image dehazing. It is motivated by an observation that the estimated depths of an image with haze residuals and its clear counterpart vary. Enforcing the depth consistency of dehazed images with clear ones, therefore, is essential for dehazing. For this purpose, we develop a prompt based on the features of depth differences between the hazy input images and corresponding clear counterparts that can guide dehazing models for better restoration. Specifically, we first apply deep features extracted from the input images to the depth difference features for generating the prompt that contains the haze residual information in the input. Then we propose a prompt embedding module that is designed to perceive the haze residuals, by linearly adding the prompt to the deep features. Further, we develop an effective prompt attention module to pay more attention to haze residuals for better removal. By incorporating the prompt, prompt embedding, and prompt attention into an encoder-decoder network based on VQGAN, we can achieve better perception quality. As the depths of clear images are not available at inference, and the dehazed images with one-time feed-forward execution may still contain a portion of haze residuals, we propose a new continuous self-prompt inference that can iteratively correct the dehazing model towards better haze-free image generation. Extensive experiments show that our method performs favorably against the state-of-the-art approaches on both synthetic and real-world datasets in terms of perception metrics including NIQE, PI, and PIQE.
Authors: Yining Jiao, Carlton Zdanski, Julia Kimbell, Andrew Prince, Cameron Worden, Samuel Kirse, Christopher Rutter, Benjamin Shields, William Dunn, Jisan Mahmud, Marc Niethammer
Abstract: Deep implicit functions (DIFs) have emerged as a powerful paradigm for many computer vision tasks such as 3D shape reconstruction, generation, registration, completion, editing, and understanding. However, given a set of 3D shapes with associated covariates there is at present no shape representation method which allows to precisely represent the shapes while capturing the individual dependencies on each covariate. Such a method would be of high utility to researchers to discover knowledge hidden in a population of shapes. For scientific shape discovery, we propose a 3D Neural Additive Model for Interpretable Shape Representation ($\texttt{NAISR}$) which describes individual shapes by deforming a shape atlas in accordance to the effect of disentangled covariates. Our approach captures shape population trends and allows for patient-specific predictions through shape transfer. $\texttt{NAISR}$ is the first approach to combine the benefits of deep implicit shape representations with an atlas deforming according to specified covariates. We evaluate $\texttt{NAISR}$ with respect to shape reconstruction, shape disentanglement, shape evolution, and shape transfer on three datasets: 1) $\textit{Starman}$, a simulated 2D shape dataset; 2) the ADNI hippocampus 3D shape dataset; and 3) a pediatric airway 3D shape dataset. Our experiments demonstrate that $\textit{Starman}$ achieves excellent shape reconstruction performance while retaining interpretability. Our code is available at $\href{https://github.com/uncbiag/NAISR}{https://github.com/uncbiag/NAISR}$.
URLs: https://github.com/uncbiag/NAISR, https://github.com/uncbiag/NAISR
Authors: Jiahao Zhang, Anoop Cherian, Yanbin Liu, Yizhak Ben-Shabat, Cristian Rodriguez, Stephen Gould
Abstract: Multimodal alignment facilitates the retrieval of instances from one modality when queried using another. In this paper, we consider a novel setting where such an alignment is between (i) instruction steps that are depicted as assembly diagrams (commonly seen in Ikea assembly manuals) and (ii) video segments from in-the-wild videos; these videos comprising an enactment of the assembly actions in the real world. To learn this alignment, we introduce a novel supervised contrastive learning method that learns to align videos with the subtle details in the assembly diagrams, guided by a set of novel losses. To study this problem and demonstrate the effectiveness of our method, we introduce a novel dataset: IAW for Ikea assembly in the wild consisting of 183 hours of videos from diverse furniture assembly collections and nearly 8,300 illustrations from their associated instruction manuals and annotated for their ground truth alignments. We define two tasks on this dataset: First, nearest neighbor retrieval between video segments and illustrations, and, second, alignment of instruction steps and the segments for each video. Extensive experiments on IAW demonstrate superior performances of our approach against alternatives.
Authors: Zhaoyang Zhang, Yantao Shen, Kunyu Shi, Zhaowei Cai, Jun Fang, Siqi Deng, Hao Yang, Davide Modolo, Zhuowen Tu, Stefano Soatto
Abstract: We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks which may interfere with each other, resulting in a single model which we named Musketeer. The integration of knowledge across heterogeneous tasks is enabled by a novel feature called Task Explanation Prompt (TEP). With rich and structured information such as task input/output format, TEP reduces interference among tasks, allowing the model to focus on their shared structure. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.
Authors: Sourav Das, Guglielmo Camporese, Shaokang Cheng, Lamberto Ballan
Abstract: Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics. One fundamental difficulty stands in the evolution of the trajectory that becomes more and more uncertain and unpredictable as the time horizon grows, subsequently increasing the complexity of the problem. To overcome this issue, in this paper, we propose Di-Long, a new method that employs the distillation of a short-term trajectory model forecaster that guides a student network for long-term trajectory prediction during the training process. Given a total sequence length that comprehends the allowed observation for the student network and the complementary target sequence, we let the student and the teacher solve two different related tasks defined over the same full trajectory: the student observes a short sequence and predicts a long trajectory, whereas the teacher observes a longer sequence and predicts the remaining short target trajectory. The teacher's task is less uncertain, and we use its accurate predictions to guide the student through our knowledge distillation framework, reducing long-term future uncertainty. Our experiments show that our proposed Di-Long method is effective for long-term forecasting and achieves state-of-the-art performance on the Intersection Drone Dataset (inD) and the Stanford Drone Dataset (SDD).
Authors: Jin-Young Kim, Soonwoo Kwon, Hyojun Go, Yunsung Lee, Seungtaek Choi
Abstract: Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing that of negative ones. Recently, it has been verified that the model learns better representation with diversely augmented positive pairs because they enable the model to be more view-invariant. However, only a few studies on CL have considered the difference between augmented views, and have not gone beyond the hand-crafted findings. In this paper, we first observe that the score-matching function can measure how much data has changed from the original through augmentation. With the observed property, every pair in CL can be weighted adaptively by the difference of score values, resulting in boosting the performance of the existing CL method. We show the generality of our method, referred to as ScoreCL, by consistently improving various CL methods, SimCLR, SimSiam, W-MSE, and VICReg, up to 3%p in k-NN evaluation on CIFAR-10, CIFAR-100, and ImageNet-100. Moreover, we have conducted exhaustive experiments and ablations, including results on diverse downstream tasks, comparison with possible baselines, and improvement when used with other proposed augmentation methods. We hope our exploration will inspire more research in exploiting the score matching for CL.
Authors: Wufei Ma, Qihao Liu, Jiahao Wang, Angtian Wang, Xiaoding Yuan, Yi Zhang, Zihao Xiao, Guofeng Zhang, Beijia Lu, Ruxiao Duan, Yongrui Qi, Adam Kortylewski, Yaoyao Liu, Alan Yuille
Abstract: Diffusion models have emerged as a powerful generative method, capable of producing stunning photo-realistic images from natural language descriptions. However, these models lack explicit control over the 3D structure in the generated images. Consequently, this hinders our ability to obtain detailed 3D annotations for the generated images or to craft instances with specific poses and distances. In this paper, we propose 3D Diffusion Style Transfer (3D-DST), which incorporates 3D geometry control into diffusion models. Our method exploits ControlNet, which extends diffusion models by using visual prompts in addition to text prompts. We generate images of the 3D objects taken from 3D shape repositories~(e.g., ShapeNet and Objaverse), render them from a variety of poses and viewing directions, compute the edge maps of the rendered images, and use these edge maps as visual prompts to generate realistic images. With explicit 3D geometry control, we can easily change the 3D structures of the objects in the generated images and obtain ground-truth 3D annotations automatically. This allows us to improve a wide range of vision tasks, e.g., classification and 3D pose estimation, in both in-distribution (ID) and out-of-distribution (OOD) settings. We demonstrate the effectiveness of our method through extensive experiments on ImageNet-100/200, ImageNet-R, PASCAL3D+, ObjectNet3D, and OOD-CV. The results show that our method significantly outperforms existing methods, e.g., 3.8 percentage points on ImageNet-100 using DeiT-B.
Authors: Peng Xu, Zhiyu Xiang, Chenyu Qiao, Jingyun Fu, Tianyu Pu
Abstract: Despite the great success of deep learning in stereo matching, recovering accurate disparity maps is still challenging. Currently, L1 and cross-entropy are the two most widely used losses for stereo network training. Compared with the former, the latter usually performs better thanks to its probability modeling and direct supervision to the cost volume. However, how to accurately model the stereo ground-truth for cross-entropy loss remains largely under-explored. Existing works simply assume that the ground-truth distributions are uni-modal, which ignores the fact that most of the edge pixels can be multi-modal. In this paper, a novel adaptive multi-modal cross-entropy loss (ADL) is proposed to guide the networks to learn different distribution patterns for each pixel. Moreover, we optimize the disparity estimator to further alleviate the bleeding or misalignment artifacts in inference. Extensive experimental results show that our method is generic and can help classic stereo networks regain state-of-the-art performance. In particular, GANet with our method ranks $1^{st}$ on both the KITTI 2015 and 2012 benchmarks among the published methods. Meanwhile, excellent synthetic-to-realistic generalization performance can be achieved by simply replacing the traditional loss with ours.
Authors: Francesco Ballerin, Erlend Grong
Abstract: Equipping the rototranslation group $SE(2)$ with a sub-Riemannian structure inspired by the visual cortex V1, we propose algorithms for image inpainting and enhancement based on hypoelliptic diffusion. We innovate on previous implementations of the methods by Citti, Sarti, and Boscain et al., by proposing an alternative that prevents fading and is capable of producing sharper results in a procedure that we call WaxOn-WaxOff. We also exploit the sub-Riemannian structure to define a completely new unsharp filter using $SE(2)$, analogous to the classical unsharp filter for 2D image processing. We demonstrate our method on blood vessels enhancement in retinal scans.
Authors: Xiaoting Wu, Xiaoyi Feng, Constantino \'Alvarez Casado, Lili Liu, Miguel Bordallo L\'opez
Abstract: Facial Kinship Verification (FKV) aims at automatically determining whether two subjects have a kinship relation based on human faces. It has potential applications in finding missing children and social media analysis. Traditional FKV faces challenges as it is vulnerable to spoof attacks and raises privacy issues. In this paper, we explore for the first time the FKV with vital bio-signals, focusing on remote Photoplethysmography (rPPG). rPPG signals are extracted from facial videos, resulting in a one-dimensional signal that measures the changes in visible light reflection emitted to and detected from the skin caused by the heartbeat. Specifically, in this paper, we employed a straightforward one-dimensional Convolutional Neural Network (1DCNN) with a 1DCNN-Attention module and kinship contrastive loss to learn the kin similarity from rPPGs. The network takes multiple rPPG signals extracted from various facial Regions of Interest (ROIs) as inputs. Additionally, the 1DCNN attention module is designed to learn and capture the discriminative kin features from feature embeddings. Finally, we demonstrate the feasibility of rPPG to detect kinship with the experiment evaluation on the UvANEMO Smile Database from different kin relations.
Authors: Runkai Zhao, Yuwen Heng, Heng Wang, Yuanda Gao, Shilei Liu, Changhao Yao, Jiawen Chen, Weidong Cai
Abstract: Advanced Driver-Assistance Systems (ADAS) have successfully integrated learning-based techniques into vehicle perception and decision-making. However, their application in 3D lane detection for effective driving environment perception is hindered by the lack of comprehensive LiDAR datasets. The sparse nature of LiDAR point cloud data prevents an efficient manual annotation process. To solve this problem, we present LiSV-3DLane, a large-scale 3D lane dataset that comprises 20k frames of surround-view LiDAR point clouds with enriched semantic annotation. Unlike existing datasets confined to a frontal perspective, LiSV-3DLane provides a full 360-degree spatial panorama around the ego vehicle, capturing complex lane patterns in both urban and highway environments. We leverage the geometric traits of lane lines and the intrinsic spatial attributes of LiDAR data to design a simple yet effective automatic annotation pipeline for generating finer lane labels. To propel future research, we propose a novel LiDAR-based 3D lane detection model, LiLaDet, incorporating the spatial geometry learning of the LiDAR point cloud into Bird's Eye View (BEV) based lane identification. Experimental results indicate that LiLaDet outperforms existing camera- and LiDAR-based approaches in the 3D lane detection task on the K-Lane dataset and our LiSV-3DLane.
Authors: Xichen Pan, Li Dong, Shaohan Huang, Zhiliang Peng, Wenhu Chen, Furu Wei
Abstract: Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and text input. These limitations keep them far from the ultimate goal of "image as a foreign language in image generation." This paper presents Kosmos-G, a model that leverages the advanced multimodal perception capabilities of Multimodal Large Language Models (MLLMs) to tackle the aforementioned challenge. Our approach aligns the output space of MLLM with CLIP using the textual modality as an anchor and performs compositional instruction tuning on curated data. Kosmos-G demonstrates an impressive capability of zero-shot subject-driven generation with interleaved multi-image and text input. Notably, the score distillation instruction tuning requires no modifications to the image decoder. This allows for a seamless substitution of CLIP and effortless integration with a myriad of U-Net techniques ranging from fine-grained controls to personalized image decoder variants. We posit Kosmos-G as an initial attempt towards the goal of "image as a foreign language in image generation." The code can be found at https://aka.ms/Kosmos-G
URLs: https://aka.ms/Kosmos-G
Authors: Jianglong Ye, Peng Wang, Kejie Li, Yichun Shi, Heng Wang
Abstract: Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild inputs, they still struggle to maintain 3D consistency across different views. In this paper, we present Consistent-1-to-3, which is a generative framework that significantly mitigates this issue. Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We design a scene representation transformer and view-conditioned diffusion model for performing these two stages respectively. Inside the models, to enforce 3D consistency, we propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information. Finally, we design a hierarchy generation paradigm to generate long sequences of consistent views, allowing a full 360-degree observation of the provided object image. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed mechanisms against state-of-the-art approaches. Our project page is at https://jianglongye.com/consistent123/
Authors: Duy-Kien Nguyen, Martin R. Oswald, Cees G. M. Snoek
Abstract: The ability to detect objects in images at varying scales has played a pivotal role in the design of modern object detectors. Despite considerable progress in removing hand-crafted components and simplifying the architecture with transformers, multi-scale feature maps and/or pyramid design remain a key factor for their empirical success. In this paper, we show that this reliance on either feature pyramids or an hierarchical backbone is unnecessary and a transformer-based detector with scale-aware attention enables the plain detector `SimPLR' whose backbone and detection head are both non-hierarchical and operate on single-scale features. We find through our experiments that SimPLR with scale-aware attention is plain and simple, yet competitive with multi-scale vision transformer alternatives. Compared to the multi-scale and single-scale state-of-the-art, our model scales much better with bigger capacity (self-supervised) models and more pre-training data, allowing us to report a consistently better accuracy and faster runtime for object detection, instance segmentation as well as panoptic segmentation. Code will be released.
Authors: Maximilian Seitzer, Sjoerd van Steenkiste, Thomas Kipf, Klaus Greff, Mehdi S. M. Sajjadi
Abstract: Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene Transformer (DyST) model leverages recent work in neural scene representation to learn a latent decomposition of monocular real-world videos into scene content, per-view scene dynamics, and camera pose. This separation is achieved through a novel co-training scheme on monocular videos and our new synthetic dataset DySO. DyST learns tangible latent representations for dynamic scenes that enable view generation with separate control over the camera and the content of the scene.
Authors: Xian Liu, Jian Ren, Aliaksandr Siarohin, Ivan Skorokhodov, Yanyu Li, Dahua Lin, Xihui Liu, Ziwei Liu, Sergey Tulyakov
Abstract: Despite significant advances in large-scale text-to-image models, achieving hyper-realistic human image generation remains a desirable yet unsolved task. Existing models like Stable Diffusion and DALL-E 2 tend to generate human images with incoherent parts or unnatural poses. To tackle these challenges, our key insight is that human image is inherently structural over multiple granularities, from the coarse-level body skeleton to fine-grained spatial geometry. Therefore, capturing such correlations between the explicit appearance and latent structure in one model is essential to generate coherent and natural human images. To this end, we propose a unified framework, HyperHuman, that generates in-the-wild human images of high realism and diverse layouts. Specifically, 1) we first build a large-scale human-centric dataset, named HumanVerse, which consists of 340M images with comprehensive annotations like human pose, depth, and surface normal. 2) Next, we propose a Latent Structural Diffusion Model that simultaneously denoises the depth and surface normal along with the synthesized RGB image. Our model enforces the joint learning of image appearance, spatial relationship, and geometry in a unified network, where each branch in the model complements to each other with both structural awareness and textural richness. 3) Finally, to further boost the visual quality, we propose a Structure-Guided Refiner to compose the predicted conditions for more detailed generation of higher resolution. Extensive experiments demonstrate that our framework yields the state-of-the-art performance, generating hyper-realistic human images under diverse scenarios. Project Page: https://snap-research.github.io/HyperHuman/
Authors: Prasanna Mayilvahanan, Thadd\"aus Wiedemer, Evgenia Rusak, Matthias Bethge, Wieland Brendel
Abstract: Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few-shot capabilities on a wide range of out-of-distribution (OOD) benchmarks, which prior works attribute mainly to today's large and comprehensive training dataset (like LAION). However, it is questionable how meaningful terms like out-of-distribution generalization are for CLIP as it seems likely that web-scale datasets like LAION simply contain many samples that are similar to common OOD benchmarks originally designed for ImageNet. To test this hypothesis, we retrain CLIP on pruned LAION splits that replicate ImageNet's train-test similarity with respect to common OOD benchmarks. While we observe a performance drop on some benchmarks, surprisingly, CLIP's overall performance remains high. This shows that high train-test similarity is insufficient to explain CLIP's OOD performance, and other properties of the training data must drive CLIP to learn more generalizable representations. Additionally, by pruning data points that are dissimilar to the OOD benchmarks, we uncover a 100M split of LAION ($\frac{1}{4}$th of its original size) on which CLIP can be trained to match its original OOD performance.
Authors: Yangyang Guo, Fangkai Jiao, Zhiqi Shen, Liqiang Nie, Mohan Kankanhalli
Abstract: Teaching Visual Question Answering (VQA) models to refrain from answering unanswerable questions is necessary for building a trustworthy AI system. Existing studies, though have explored various aspects of VQA but somewhat ignored this particular attribute. This paper aims to bridge the research gap by contributing a comprehensive dataset, called UNK-VQA. The dataset is specifically designed to address the challenge of questions that models do not know. To this end, we first augment the existing data via deliberate perturbations on either the image or question. In specific, we carefully ensure that the question-image semantics remain close to the original unperturbed distribution. By this means, the identification of unanswerable questions becomes challenging, setting our dataset apart from others that involve mere image replacement. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models and discover their significant limitations when applied to our dataset. Additionally, we also propose a straightforward method to tackle these unanswerable questions. This dataset, we believe, will serve as a valuable benchmark for enhancing the abstention capability of VQA models, thereby leading to increased trustworthiness of AI systems. We have made the dataset (https://github.com/guoyang9/UNK-VQA) available to facilitate further exploration in this area.
Authors: Songyan Zhang, Xinyu Sun, Hao Chen, Bo Li, Chunhua Shen
Abstract: Finding corresponding pixels within a pair of images is a fundamental computer vision task with various applications. Due to the specific requirements of different tasks like optical flow estimation and local feature matching, previous works are primarily categorized into dense matching and sparse feature matching focusing on specialized architectures along with task-specific datasets, which may somewhat hinder the generalization performance of specialized models. In this paper, we propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching). In particular, we elaborately design a cascaded GRU module for refinement by exploring the geometric similarity iteratively at multiple scales following an additional uncertainty estimation module for sparsification. To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth by generating optical flow supervision with greater intervals. As such, we are able to mix up various dense and sparse matching datasets, significantly improving the training diversity. The generalization capacity of our proposed RGM is greatly improved by learning the matching and uncertainty estimation in a two-stage manner on the large, mixed data. Superior performance is achieved for zero-shot matching and downstream geometry estimation across multiple datasets, outperforming the previous methods by a large margin.
Authors: Yue Cao, Tianlin Li, Xiaofeng Cao, Ivor Tsang, Yang Liu, Qing Guo
Abstract: We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical transformation. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks. To validate this concept, we present a comprehensive study on leveraging image resampling to defend against adversarial attacks. We have developed basic resampling methods that employ interpolation strategies and coordinate shifting magnitudes. Our analysis reveals that these basic methods can partially mitigate adversarial attacks. However, they come with apparent limitations: the accuracy of clean images noticeably decreases, while the improvement in accuracy on adversarial examples is not substantial. We propose implicit representation-driven image resampling (IRAD) to overcome these limitations. First, we construct an implicit continuous representation that enables us to represent any input image within a continuous coordinate space. Second, we introduce SampleNet, which automatically generates pixel-wise shifts for resampling in response to different inputs. Furthermore, we can extend our approach to the state-of-the-art diffusion-based method, accelerating it with fewer time steps while preserving its defense capability. Extensive experiments demonstrate that our method significantly enhances the adversarial robustness of diverse deep models against various attacks while maintaining high accuracy on clean images.
Authors: Ryosuke Furuta, Yoichi Sato
Abstract: Object detectors do not work well when domains largely differ between training and testing data. To overcome this domain gap in object detection without requiring expensive annotations, we consider two problem settings: semi-supervised domain generalizable object detection (SS-DGOD) and weakly-supervised DGOD (WS-DGOD). In contrast to the conventional domain generalization for object detection that requires labeled data from multiple domains, SS-DGOD and WS-DGOD require labeled data only from one domain and unlabeled or weakly-labeled data from multiple domains for training. In this paper, we show that object detectors can be effectively trained on the two settings with the same Mean Teacher learning framework, where a student network is trained with pseudo-labels output from a teacher on the unlabeled or weakly-labeled data. We provide novel interpretations of why the Mean Teacher learning framework works well on the two settings in terms of the relationships between the generalization gap and flat minima in parameter space. On the basis of the interpretations, we also propose incorporating a simple regularization method into the Mean Teacher learning framework to find flatter minima. The experimental results demonstrate that the regularization leads to flatter minima and boosts the performance of the detectors trained with the Mean Teacher learning framework on the two settings. They also indicate that those detectors significantly outperform the state-of-the-art methods.
Authors: Tianyi Wang, Mengxiao Huang, Harry Cheng, Bin Ma, Yinglong Wang
Abstract: Notwithstanding offering convenience and entertainment to society, Deepfake face swapping has caused critical privacy issues with the rapid development of deep generative models. Due to imperceptible artifacts in high-quality synthetic images, passive detection models against face swapping in recent years usually suffer performance damping regarding the generalizability issue. Therefore, several studies have been attempted to proactively protect the original images against malicious manipulations by inserting invisible signals in advance. However, the existing proactive defense approaches demonstrate unsatisfactory results with respect to visual quality, detection accuracy, and source tracing ability. In this study, to fulfill the research gap, we propose the first robust identity perceptual watermarking framework that concurrently performs detection and source tracing against Deepfake face swapping proactively. We assign identity semantics regarding the image contents to the watermarks and devise an unpredictable and nonreversible chaotic encryption system to ensure watermark confidentiality. The watermarks are encoded and recovered by jointly training an encoder-decoder framework along with adversarial image manipulations. Falsification and source tracing are accomplished by justifying the consistency between the content-matched identity perceptual watermark and the recovered robust watermark from the image. Extensive experiments demonstrate state-of-the-art detection performance on Deepfake face swapping under both cross-dataset and cross-manipulation settings.
Authors: Mikolaj Czerkawski, Christos Tachtatzis
Abstract: The letter investigates the utility of text-to-image inpainting models for satellite image data. Two technical challenges of injecting structural guiding signals into the generative process as well as translating the inpainted RGB pixels to a wider set of MSI bands are addressed by introducing a novel inpainting framework based on StableDiffusion and ControlNet as well as a novel method for RGB-to-MSI translation. The results on a wider set of data suggest that the inpainting synthesized via StableDiffusion suffers from undesired artifacts and that a simple alternative of self-supervised internal inpainting achieves a higher quality of synthesis.
Authors: Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin
Abstract: Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which involves an irreconcilable training imbalance. Precisely, to generate realistic persons, they need to sufficiently tune the pre-trained model, which inevitably causes the model to forget the rich semantic scene prior and makes scene generation over-fit to the training data. Moreover, even with sufficient fine-tuning, these methods can still not generate high-fidelity persons since joint learning of the scene and person generation also lead to quality compromise. In this paper, we propose Face-diffuser, an effective collaborative generation pipeline to eliminate the above training imbalance and quality compromise. Specifically, we first develop two specialized pre-trained diffusion models, i.e., Text-driven Diffusion Model (TDM) and Subject-augmented Diffusion Model (SDM), for scene and person generation, respectively. The sampling process is divided into three sequential stages, i.e., semantic scene construction, subject-scene fusion, and subject enhancement. The first and last stages are performed by TDM and SDM respectively. The subject-scene fusion stage, that is the collaboration achieved through a novel and highly effective mechanism, Saliency-adaptive Noise Fusion (SNF). Specifically, it is based on our key observation that there exists a robust link between classifier-free guidance responses and the saliency of generated images. In each time step, SNF leverages the unique strengths of each model and allows for the spatial blending of predicted noises from both models automatically in a saliency-aware manner. Extensive experiments confirm the impressive effectiveness and robustness of the Face-diffuser.
Authors: Tony Lindeberg
Abstract: 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: Aleksis Pirinen, Nosheen Abid, Nuria Agues Paszkowsky, Thomas Ohlson Timoudas, Ronald Scheirer, Chiara Ceccobello, Gy\"orgy Kov\'acs, Anders Persson
Abstract: Cloud formations often obscure optical satellite-based monitoring of the Earth's surface, thus limiting Earth observation (EO) activities such as land cover mapping, ocean color analysis, and cropland monitoring. The integration of machine learning (ML) methods within the remote sensing domain has significantly improved performance on a wide range of EO tasks, including cloud detection and filtering, but there is still much room for improvement. A key bottleneck is that ML methods typically depend on large amounts of annotated data for training, which is often difficult to come by in EO contexts. This is especially true when it comes to cloud optical thickness (COT) estimation. A reliable estimation of COT enables more fine-grained and application-dependent control compared to using pre-specified cloud categories, as is commonly done in practice. To alleviate the COT data scarcity problem, in this work we propose a novel synthetic dataset for COT estimation, that we subsequently leverage for obtaining reliable and versatile cloud masks on real data. In our dataset, top-of-atmosphere radiances have been simulated for 12 of the spectral bands of the Multispectral Imagery (MSI) sensor onboard Sentinel-2 platforms. These data points have been simulated under consideration of different cloud types, COTs, and ground surface and atmospheric profiles. Extensive experimentation of training several ML models to predict COT from the measured reflectivity of the spectral bands demonstrates the usefulness of our proposed dataset. In particular, by thresholding COT estimates from our ML models, we show on two satellite image datasets (one that is publicly available, and one which we have collected and annotated) that reliable cloud masks can be obtained. The synthetic data, the collected real dataset, code and models have been made publicly available at https://github.com/aleksispi/ml-cloud-opt-thick.
Authors: Van Nguyen Nguyen, Thibault Groueix, Mathieu Salzmann, Vincent Lepetit
Abstract: We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative "templates", rendered images of the CAD models, to recover the out-of-plane rotation and then uses patch correspondences to estimate the four remaining parameters. Our approach samples templates in only a two-degrees-of-freedom space instead of the usual three and matches the input image to the templates using fast nearest-neighbor search in feature space, results in a speedup factor of 35x compared to the state of the art. Moreover, GigaPose is significantly more robust to segmentation errors. Our extensive evaluation on the seven core datasets of the BOP challenge demonstrates that it achieves state-of-the-art accuracy and can be seamlessly integrated with existing refinement methods. Additionally, we show the potential of GigaPose with 3D models predicted by recent work on 3D reconstruction from a single image, relaxing the need for CAD models and making 6D pose object estimation much more convenient. Our source code and trained models are publicly available at https://github.com/nv-nguyen/gigaPose
Authors: Hoang-Quan Nguyen, Thanh-Dat Truong, Xuan Bac Nguyen, Ashley Dowling, Xin Li, Khoa Luu
Abstract: In precision agriculture, the detection and recognition of insects play an essential role in the ability of crops to grow healthy and produce a high-quality yield. The current machine vision model requires a large volume of data to achieve high performance. However, there are approximately 5.5 million different insect species in the world. None of the existing insect datasets can cover even a fraction of them due to varying geographic locations and acquisition costs. In this paper, we introduce a novel "Insect-1M" dataset, a game-changing resource poised to revolutionize insect-related foundation model training. Covering a vast spectrum of insect species, our dataset, including 1 million images with dense identification labels of taxonomy hierarchy and insect descriptions, offers a panoramic view of entomology, enabling foundation models to comprehend visual and semantic information about insects like never before. Then, to efficiently establish an Insect Foundation Model, we develop a micro-feature self-supervised learning method with a Patch-wise Relevant Attention mechanism capable of discerning the subtle differences among insect images. In addition, we introduce Description Consistency loss to improve micro-feature modeling via insect descriptions. Through our experiments, we illustrate the effectiveness of our proposed approach in insect modeling and achieve State-of-the-Art performance on standard benchmarks of insect-related tasks. Our Insect Foundation Model and Dataset promise to empower the next generation of insect-related vision models, bringing them closer to the ultimate goal of precision agriculture.
Authors: Zhe Li, Zerong Zheng, Lizhen Wang, Yebin Liu
Abstract: Modeling animatable human avatars from RGB videos is a long-standing and challenging problem. Recent works usually adopt MLP-based neural radiance fields (NeRF) to represent 3D humans, but it remains difficult for pure MLPs to regress pose-dependent garment details. To this end, we introduce Animatable Gaussians, a new avatar representation that leverages powerful 2D CNNs and 3D Gaussian splatting to create high-fidelity avatars. To associate 3D Gaussians with the animatable avatar, we learn a parametric template from the input videos, and then parameterize the template on two front \& back canonical Gaussian maps where each pixel represents a 3D Gaussian. The learned template is adaptive to the wearing garments for modeling looser clothes like dresses. Such template-guided 2D parameterization enables us to employ a powerful StyleGAN-based CNN to learn the pose-dependent Gaussian maps for modeling detailed dynamic appearances. Furthermore, we introduce a pose projection strategy for better generalization given novel poses. Overall, our method can create lifelike avatars with dynamic, realistic and generalized appearances. Experiments show that our method outperforms other state-of-the-art approaches. Code: https://github.com/lizhe00/AnimatableGaussians
Authors: Alexander Becker, Rodrigo Caye Daudt, Nando Metzger, Jan Dirk Wegner, Konrad Schindler
Abstract: Recent approaches for arbitrary-scale single image super-resolution (ASSR) have used local neural fields to represent continuous signals that can be sampled at arbitrary rates. However, the point-wise query of the neural field does not naturally match the point spread function (PSF) of a given pixel, which may cause aliasing in the super-resolved image. We present a novel way to design neural fields such that points can be queried with an adaptive Gaussian PSF, so as to guarantee correct anti-aliasing at any desired output resolution. We achieve this with a novel activation function derived from Fourier theory. Querying points with a Gaussian PSF, compliant with sampling theory, does not incur any additional computational cost in our framework, unlike filtering in the image domain. With its theoretically guaranteed anti-aliasing, our method sets a new state of the art for ASSR, while being more parameter-efficient than previous methods. Notably, even a minimal version of our model still outperforms previous methods in most cases, while adding 2-4 orders of magnitude fewer parameters. Code and pretrained models are available at https://github.com/prs-eth/thera.
Authors: Tengjin Weng, Yang Shen, Zhidong Zhao, Zhiming Cheng, Shuai Wang
Abstract: Optic disc and cup segmentation plays a crucial role in automating the screening and diagnosis of optic glaucoma. While data-driven convolutional neural networks (CNNs) show promise in this area, the inherent ambiguity of segmenting objects and background boundaries in the task of optic disc and cup segmentation leads to noisy annotations that impact model performance. To address this, we propose an innovative label-denoising method of Multiple Pseudo-labels Noise-aware Network (MPNN) for accurate optic disc and cup segmentation. Specifically, the Multiple Pseudo-labels Generation and Guided Denoising (MPGGD) module generates pseudo-labels by multiple different initialization networks trained on true labels, and the pixel-level consensus information extracted from these pseudo-labels guides to differentiate clean pixels from noisy pixels. The training framework of the MPNN is constructed by a teacher-student architecture to learn segmentation from clean pixels and noisy pixels. Particularly, such a framework adeptly leverages (i) reliable and fundamental insight from clean pixels and (ii) the supplementary knowledge within noisy pixels via multiple perturbation-based unsupervised consistency. Compared to other label-denoising methods, comprehensive experimental results on the RIGA dataset demonstrate our method's excellent performance. The code is available at https://github.com/wwwtttjjj/MPNN
Authors: Saurav Sengupta, Donald E. Brown
Abstract: Deep learning for histopathology has been successfully used for disease classification, image segmentation and more. However, combining image and text modalities using current state-of-the-art (SOTA) methods has been a challenge due to the high resolution of histopathology images. Automatic report generation for histopathology images is one such challenge. In this work, we show that using an existing pre-trained Vision Transformer (ViT) to encode 4096x4096 sized patches of the Whole Slide Image (WSI) and a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model for language modeling-based decoder for report generation, we can build a performant and portable report generation mechanism that takes into account the whole high resolution image. Our method allows us to not only generate and evaluate captions that describe the image, but also helps us classify the image into tissue types and the gender of the patient as well. Our best performing model achieves a 89.52% accuracy in Tissue Type classification with a BLEU-4 score of 0.12 in our caption generation task.
Authors: Ruochen Chen, Liming Chen, Shaifali Parashar
Abstract: Recent neural, physics-based modeling of garment deformations allows faster and visually aesthetic results as opposed to the existing methods. Material-specific parameters are used by the formulation to control the garment inextensibility. This delivers unrealistic results with physically implausible stretching. Oftentimes, the draped garment is pushed inside the body which is either corrected by an expensive post-processing, thus adding to further inconsistent stretching; or by deploying a separate training regime for each body type, restricting its scalability. Additionally, the flawed skinning process deployed by existing methods produces incorrect results on loose garments. In this paper, we introduce a geometrical constraint to the existing formulation that is collision-aware and imposes garment inextensibility wherever possible. Thus, we obtain realistic results where draped clothes stretch only while covering bigger body regions. Furthermore, we propose a geometry-aware garment skinning method by defining a body-garment closeness measure which works for all garment types, especially the loose ones.
Authors: Wenyang Zhou, Zhiyang Dou, Zeyu Cao, Zhouyingcheng Liao, Jingbo Wang, Wenjia Wang, Yuan Liu, Taku Komura, Wenping Wang, Lingjie Liu
Abstract: We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. On the one hand, previous works, like motion latent diffusion, conduct diffusion within a latent space for efficiency, but learning such a latent space can be a non-trivial effort. On the other hand, accelerating generation by naively increasing the sampling step size, e.g., DDIM, often leads to quality degradation as it fails to approximate the complex denoising distribution. To address these issues, we propose EMDM, which captures the complex distribution during multiple sampling steps in the diffusion model, allowing for much fewer sampling steps and significant acceleration in generation. This is achieved by a conditional denoising diffusion GAN to capture multimodal data distributions among arbitrary (and potentially larger) step sizes conditioned on control signals, enabling fewer-step motion sampling with high fidelity and diversity. To minimize undesired motion artifacts, geometric losses are imposed during network learning. As a result, EMDM achieves real-time motion generation and significantly improves the efficiency of motion diffusion models compared to existing methods while achieving high-quality motion generation. Our code will be publicly available upon publication.
Authors: Haoran Tang, Xin Zhou, Jieren Deng, Zhihong Pan, Hao Tian, Pratik Chaudhari
Abstract: Newly developed diffusion-based techniques have showcased phenomenal abilities in producing a wide range of high-quality images, sparking considerable interest in various applications. A prevalent scenario is to generate new images based on a subject from reference images. This subject could be face identity for styled avatars, body and clothing for virtual try-on and so on. Satisfying this requirement is evolving into a field called Subject-Driven Generation. In this paper, we consider Subject-Driven Generation as a unified retrieval problem with diffusion models. We introduce a novel diffusion model architecture, named RetriNet, designed to address and solve these problems by retrieving subject attributes from reference images precisely, and filter out irrelevant information. RetriNet demonstrates impressive performance when compared to existing state-of-the-art approaches in face generation. We further propose a research and iteration friendly dataset, RetriBooru, to study a more difficult problem, concept composition. Finally, to better evaluate alignment between similarity and diversity or measure diversity that have been previously unaccounted for, we introduce a novel class of metrics named Similarity Weighted Diversity (SWD).
Authors: Trong-Thuan Nguyen, Pha Nguyen, Khoa Luu
Abstract: Visual interactivity understanding within visual scenes presents a significant challenge in computer vision. Existing methods focus on complex interactivities while leveraging a simple relationship model. These methods, however, struggle with a diversity of appearance, situation, position, interaction, and relation in videos. This limitation hinders the ability to fully comprehend the interplay within the complex visual dynamics of subjects. In this paper, we delve into interactivities understanding within visual content by deriving scene graph representations from dense interactivities among humans and objects. To achieve this goal, we first present a new dataset containing Appearance-Situation-Position-Interaction-Relation predicates, named ASPIRe, offering an extensive collection of videos marked by a wide range of interactivities. Then, we propose a new approach named Hierarchical Interlacement Graph (HIG), which leverages a unified layer and graph within a hierarchical structure to provide deep insights into scene changes across five distinct tasks. Our approach demonstrates superior performance to other methods through extensive experiments conducted in various scenarios.
Authors: Xiaogang Peng, Yiming Xie, Zizhao Wu, Varun Jampani, Deqing Sun, Huaizu Jiang
Abstract: We address the problem of generating realistic 3D human-object interactions (HOIs) driven by textual prompts. To this end, we take a modular design and decompose the complex task into simpler sub-tasks. We first develop a dual-branch diffusion model (HOI-DM) to generate both human and object motions conditioned on the input text, and encourage coherent motions by a cross-attention communication module between the human and object motion generation branches. We also develop an affordance prediction diffusion model (APDM) to predict the contacting area between the human and object during the interactions driven by the textual prompt. The APDM is independent of the results by the HOI-DM and thus can correct potential errors by the latter. Moreover, it stochastically generates the contacting points to diversify the generated motions. Finally, we incorporate the estimated contacting points into the classifier-guidance to achieve accurate and close contact between humans and objects. To train and evaluate our approach, we annotate BEHAVE dataset with text descriptions. Experimental results on BEHAVE and OMOMO demonstrate that our approach produces realistic HOIs with various interactions and different types of objects.
Authors: Dan Kondratyuk, Lijun Yu, Xiuye Gu, Jos\'e Lezama, Jonathan Huang, Rachel Hornung, Hartwig Adam, Hassan Akbari, Yair Alon, Vighnesh Birodkar, Yong Cheng, Ming-Chang Chiu, Josh Dillon, Irfan Essa, Agrim Gupta, Meera Hahn, Anja Hauth, David Hendon, Alonso Martinez, David Minnen, David Ross, Grant Schindler, Mikhail Sirotenko, Kihyuk Sohn, Krishna Somandepalli, Huisheng Wang, Jimmy Yan, Ming-Hsuan Yang, Xuan Yang, Bryan Seybold, Lu Jiang
Abstract: We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
Authors: Hengjia Li, Yang Liu, Yuqi Lin, Zhanwei Zhang, Yibo Zhao, weihang Pan, Tu Zheng, Zheng Yang, Yuchun Jiang, Boxi Wu, Deng Cai
Abstract: Recently, generative domain adaptation has achieved remarkable progress, enabling us to adapt a pre-trained generator to a new target domain. However, existing methods simply adapt the generator to a single target domain and are limited to a single modality, either text-driven or image-driven. Moreover, they cannot maintain well consistency with the source domain, which impedes the inheritance of the diversity. In this paper, we propose UniHDA, a \textbf{unified} and \textbf{versatile} framework for generative hybrid domain adaptation with multi-modal references from multiple domains. We use CLIP encoder to project multi-modal references into a unified embedding space and then linearly interpolate the direction vectors from multiple target domains to achieve hybrid domain adaptation. To ensure \textbf{consistency} with the source domain, we propose a novel cross-domain spatial structure (CSS) loss that maintains detailed spatial structure information between source and target generator. Experiments show that the adapted generator can synthesise realistic images with various attribute compositions. Additionally, our framework is generator-agnostic and versatile to multiple generators, e.g., StyleGAN, EG3D, and Diffusion Models.
Authors: Guang Lin, Chao Li, Jianhai Zhang, Toshihisa Tanaka, Qibin Zhao
Abstract: The deep neural networks are known to be vulnerable to well-designed adversarial attacks. The most successful defense technique based on adversarial training (AT) can achieve optimal robustness against particular attacks but cannot generalize well to unseen attacks. Another effective defense technique based on adversarial purification (AP) can enhance generalization but cannot achieve optimal robustness. Meanwhile, both methods share one common limitation on the degraded standard accuracy. To mitigate these issues, we propose a novel pipeline to acquire the robust purifier model, named Adversarial Training on Purification (AToP), which comprises two components: perturbation destruction by random transforms (RT) and purifier model fine-tuned (FT) by adversarial loss. RT is essential to avoid overlearning to known attacks, resulting in the robustness generalization to unseen attacks, and FT is essential for the improvement of robustness. To evaluate our method in an efficient and scalable way, we conduct extensive experiments on CIFAR-10, CIFAR-100, and ImageNette to demonstrate that our method achieves optimal robustness and exhibits generalization ability against unseen attacks.
Authors: Li Ren, Chen Chen, Liqiang Wang, Kien Hua
Abstract: Deep Metric Learning (DML) has long attracted the attention of the machine learning community as a key objective. Existing solutions concentrate on fine-tuning the pre-trained models on conventional image datasets. As a result of the success of recent pre-trained models trained from larger-scale datasets, it is challenging to adapt the model to the DML tasks in the local data domain while retaining the previously gained knowledge. In this paper, we investigate parameter-efficient methods for fine-tuning the pre-trained model for DML tasks. In particular, we propose a novel and effective framework based on learning Visual Prompts (VPT) in the pre-trained Vision Transformers (ViT). Based on the conventional proxy-based DML paradigm, we augment the proxy by incorporating the semantic information from the input image and the ViT, in which we optimize the visual prompts for each class. We demonstrate that our new approximations with semantic information are superior to representative capabilities, thereby improving metric learning performance. We conduct extensive experiments to demonstrate that our proposed framework is effective and efficient by evaluating popular DML benchmarks. In particular, we demonstrate that our fine-tuning method achieves comparable or even better performance than recent state-of-the-art full fine-tuning works of DML while tuning only a small percentage of total parameters.
Authors: Zi Ye, Tianxiang Chen, Fangyijie Wang, Hanwei Zhang, Guanxi Li, Lijun Zhang
Abstract: In pediatric cardiology, the accurate and immediate assessment of cardiac function through echocardiography is important since it can determine whether urgent intervention is required in many emergencies. However, echocardiography is characterized by ambiguity and heavy background noise interference, bringing more difficulty to accurate segmentation. Present methods lack efficiency and are also prone to mistakenly segmenting some background noise areas as the left ventricular area due to noise disturbance. To relieve the two issues, we introduce P-Mamba for efficient pediatric echocardiographic left ventricular segmentation. Specifically, we turn to the recently proposed vision mamba layers in our vision mamba encoder branch to improve the computing and memory efficiency of our model while modeling global dependencies. In the other DWT-based PMD encoder branch, we devise DWT-based Perona-Malik Diffusion (PMD) Blocks that utilize PMD for noise suppression, while simultaneously preserving the local shape cues of the left ventricle. Leveraging the strengths of both the two encoder branches, P-Mamba achieves superior accuracy and efficiency to established models, such as vision transformers with quadratic and linear computational complexity. This innovative approach promises significant advancements in pediatric cardiac imaging and beyond.
Authors: Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu
Abstract: Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of their capabilities has grown increasingly important. However, most existing benchmarks fail to consider that, in certain situations, images need to be interpreted within a broader context. In this work, we introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. Further analysis confirms that these models struggle to effectively extract and utilize contextual information to improve their understanding of images. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner. View our project website at https://thunlp-mt.github.io/CODIS.
Authors: Alexander Black, Jing Shi, Yifei Fan, Tu Bui, John Collomosse
Abstract: We present VIXEN - a technique that succinctly summarizes in text the visual differences between a pair of images in order to highlight any content manipulation present. Our proposed network linearly maps image features in a pairwise manner, constructing a soft prompt for a pretrained large language model. We address the challenge of low volume of training data and lack of manipulation variety in existing image difference captioning (IDC) datasets by training on synthetically manipulated images from the recent InstructPix2Pix dataset generated via prompt-to-prompt editing framework. We augment this dataset with change summaries produced via GPT-3. We show that VIXEN produces state-of-the-art, comprehensible difference captions for diverse image contents and edit types, offering a potential mitigation against misinformation disseminated via manipulated image content. Code and data are available at http://github.com/alexblck/vixen
Authors: Qingyao Tian, Huai Liao, Xinyan Huang, Jian Chen, Zihui Zhang, Bingyu Yang, Sebastien Ourselin, Hongbin Liu
Abstract: Real-time 6 DOF localization of bronchoscopes is crucial for enhancing intervention quality. However, current vision-based technologies struggle to balance between generalization to unseen data and computational speed. In this study, we propose a Depth-based Dual-Loop framework for real-time Visually Navigated Bronchoscopy (DD-VNB) that can generalize across patient cases without the need of re-training. The DD-VNB framework integrates two key modules: depth estimation and dual-loop localization. To address the domain gap among patients, we propose a knowledge-embedded depth estimation network that maps endoscope frames to depth, ensuring generalization by eliminating patient-specific textures. The network embeds view synthesis knowledge into a cycle adversarial architecture for scale-constrained monocular depth estimation. For real-time performance, our localization module embeds a fast ego-motion estimation network into the loop of depth registration. The ego-motion inference network estimates the pose change of the bronchoscope in high frequency while depth registration against the pre-operative 3D model provides absolute pose periodically. Specifically, the relative pose changes are fed into the registration process as the initial guess to boost its accuracy and speed. Experiments on phantom and in-vivo data from patients demonstrate the effectiveness of our framework: 1) monocular depth estimation outperforms SOTA, 2) localization achieves an accuracy of Absolute Tracking Error (ATE) of 4.7 $\pm$ 3.17 mm in phantom and 6.49 $\pm$ 3.88 mm in patient data, 3) with a frame-rate approaching video capture speed, 4) without the necessity of case-wise network retraining. The framework's superior speed and accuracy demonstrate its promising clinical potential for real-time bronchoscopic navigation.
Authors: Zhengqi Xu, Ke Yuan, Huiqiong Wang, Yong Wang, Mingli Song, Jie Song
Abstract: Recently, model merging techniques have surfaced as a solution to combine multiple single-talent models into a single multi-talent model. However, previous endeavors in this field have either necessitated additional training or fine-tuning processes, or require that the models possess the same pre-trained initialization. In this work, we identify a common drawback in prior works w.r.t. the inconsistency of unit similarity in the weight space and the activation space. To address this inconsistency, we propose an innovative model merging framework, coined as merging under dual-space constraints (MuDSC). Specifically, instead of solely maximizing the objective of a single space, we advocate for the exploration of permutation matrices situated in a region with a unified high similarity in the dual space, achieved through the linear combination of activation and weight similarity matrices. In order to enhance usability, we have also incorporated adaptations for group structure, including Multi-Head Attention and Group Normalization. Comprehensive experimental comparisons demonstrate that MuDSC can significantly boost the performance of merged models with various task combinations and architectures. Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task. Our code is publicly available at https://github.com/zju-vipa/training_free_model_merging.
URLs: https://github.com/zju-vipa/training_free_model_merging.
Authors: Yichen Yao, Zimo Jiang, Yujing Sun, Zhencai Zhu, Xinge Zhu, Runnan Chen, Yuexin Ma
Abstract: Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics. However, human-centric real-life scenarios are extremely diverse and complicated, and humans have intricate motions and interactions. With limited labeled data, supervised methods are difficult to generalize to general scenarios, hindering real-life applications. Mimicking human intelligence, we propose an unsupervised 3D detection method for human-centric scenarios by transferring the knowledge from synthetic human instances to real scenes. To bridge the gap between the distinct data representations and feature distributions of synthetic models and real point clouds, we introduce novel modules for effective instance-to-scene representation transfer and synthetic-to-real feature alignment. Remarkably, our method exhibits superior performance compared to current state-of-the-art techniques, achieving 87.8% improvement in mAP and closely approaching the performance of fully supervised methods (62.15 mAP vs. 69.02 mAP) on HuCenLife Dataset.
Authors: Sagi Eppel, Jolina Li, Manuel Drehwald, Alan Aspuru-Guzik
Abstract: Visual understanding and segmentation of materials and their states is fundamental for understanding the physical world. The infinite textures, shapes, and often blurry boundaries formed by materials make this task particularly hard to generalize. Whether it's identifying wet regions of a surface, minerals in rocks, infected regions in plants, or pollution in water, each material state has its own unique form. For neural nets to learn general class-agnostic materials segmentation it is necessary to first collect and annotate data that capture this complexity. Collecting and manually annotating real-world images is limited by the cost and precision of manual labor. In contrast, synthetic CGI data is highly accurate and almost cost-free but fails to replicate the vast diversity of the material world. This work offers a method to bridge this crucial gap, by implanting patterns extracted from real-world images, in synthetic data. Hence, patterns automatically collected from natural images are used to map materials into synthetic scenes. This unsupervised approach allows the generated data to capture the vast complexity of the real world while maintaining the precision and scale of synthetic data. We also present the first general benchmark for class-agnostic material state segmentation. The benchmark contains a wide range of real-world images of material states, from cooking, food, rocks, construction, plants, and liquids each in various states (wet/dry/stained/cooked/burned/worn/rusted/sediment/foam...). The annotation includes both partial similarity between regions with similar but not identical materials, and hard segmentation of only points of the exact same material state. We show that net trains on MatSeg significantly outperform existing state-of-the-art methods on this task. The dataset, code, and trained model are available.
Authors: Yuliang Liu, Biao Yang, Qiang Liu, Zhang Li, Zhiyin Ma, Shuo Zhang, Xiang Bai
Abstract: We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9\% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at https://github.com/Yuliang-Liu/Monkey.
Authors: Hashmat Shadab Malik, Muhammad Huzaifa, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan
Abstract: Given the large-scale multi-modal training of recent vision-based models and their generalization capabilities, understanding the extent of their robustness is critical for their real-world deployment. In this work, we evaluate the resilience of current vision-based models against diverse object-to-background context variations. The majority of robustness evaluation methods have introduced synthetic datasets to induce changes to object characteristics (viewpoints, scale, color) or utilized image transformation techniques (adversarial changes, common corruptions) on real images to simulate shifts in distributions. Recent works have explored leveraging large language models and diffusion models to generate changes in the background. However, these methods either lack in offering control over the changes to be made or distort the object semantics, making them unsuitable for the task. Our method, on the other hand, can induce diverse object-to-background changes while preserving the original semantics and appearance of the object. To achieve this goal, we harness the generative capabilities of text-to-image, image-to-text, and image-to-segment models to automatically generate a broad spectrum of object-to-background changes. We induce both natural and adversarial background changes by either modifying the textual prompts or optimizing the latents and textual embedding of text-to-image models. This allows us to quantify the role of background context in understanding the robustness and generalization of deep neural networks. We produce various versions of standard vision datasets (ImageNet, COCO), incorporating either diverse and realistic backgrounds into the images or introducing color, texture, and adversarial changes in the background. We conduct extensive experiment to analyze the robustness of vision-based models against object-to-background context variations across diverse tasks.
Authors: Xiang Huang, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Wangmeng Xiang, Baigui Sun, Xiao Wu
Abstract: The quest for real-time, accurate environmental perception is pivotal in the evolution of autonomous driving technologies. In response to this challenge, we present DyRoNet, a Dynamic Router Network that innovates by incorporating low-rank dynamic routing to enhance streaming perception. DyRoNet distinguishes itself by seamlessly integrating a diverse array of specialized pre-trained branch networks, each meticulously fine-tuned for specific environmental contingencies, thus facilitating an optimal balance between response latency and detection precision. Central to DyRoNet's architecture is the Speed Router module, which employs an intelligent routing mechanism to dynamically allocate input data to the most suitable branch network, thereby ensuring enhanced performance adaptability in real-time scenarios. Through comprehensive evaluations, DyRoNet demonstrates superior adaptability and significantly improved performance over existing methods, efficiently catering to a wide variety of environmental conditions and setting new benchmarks in streaming perception accuracy and efficiency. Beyond establishing a paradigm in autonomous driving perception, DyRoNet also offers engineering insights and lays a foundational framework for future advancements in streaming perception. For further information and updates on the project, visit https://tastevision.github.io/DyRoNet/.
Authors: Anindya Mondal, Sauradip Nag, Xiatian Zhu, Anjan Dutta
Abstract: Object counting is pivotal for understanding the composition of scenes. Previously, this task was dominated by class-specific methods, which have gradually evolved into more adaptable class-agnostic strategies. However, these strategies come with their own set of limitations, such as the need for manual exemplar input and multiple passes for multiple categories, resulting in significant inefficiencies. This paper introduces a new, more practical approach enabling simultaneous counting of multiple object categories using an open vocabulary framework. Our solution, OmniCount, stands out by using semantic and geometric insights from pre-trained models to count multiple categories of objects as specified by users, all without additional training. OmniCount distinguishes itself by generating precise object masks and leveraging point prompts via the Segment Anything Model for efficient counting. To evaluate OmniCount, we created the OmniCount-191 benchmark, a first-of-its-kind dataset with multi-label object counts, including points, bounding boxes, and VQA annotations. Our comprehensive evaluation in OmniCount-191, alongside other leading benchmarks, demonstrates OmniCount's exceptional performance, significantly outpacing existing solutions and heralding a new era in object counting technology.
Authors: Guangkai Xu, Yongtao Ge, Mingyu Liu, Chengxiang Fan, Kangyang Xie, Zhiyue Zhao, Hao Chen, Chunhua Shen
Abstract: We show that, simply initializing image understanding models using a pre-trained UNet (or transformer) of diffusion models, it is possible to achieve remarkable transferable performance on fundamental vision perception tasks using a moderate amount of target data (even synthetic data only), including monocular depth, surface normal, image segmentation, matting, human pose estimation, among virtually many others. Previous works have adapted diffusion models for various perception tasks, often reformulating these tasks as generation processes to align with the diffusion process. In sharp contrast, we demonstrate that fine-tuning these models with minimal adjustments can be a more effective alternative, offering the advantages of being embarrassingly simple and significantly faster. As the backbone network of Stable Diffusion models is trained on giant datasets comprising billions of images, we observe very robust generalization capabilities of the diffusion backbone. Experimental results showcase the remarkable transferability of the backbone of diffusion models across diverse tasks and real-world datasets.
Authors: Minjie Zhu, Yichen Zhu, Xin Liu, Ning Liu, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Zhicai Ou, Feifei Feng, Jian Tang
Abstract: Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models, and optimization strategies. We show that without increasing the volume of training data, our Mipha-3B outperforms the state-of-the-art large MLLMs, especially LLaVA-1.5-13B, on multiple benchmarks. Through detailed discussion, we provide insights and guidelines for developing strong MSLMs that rival the capabilities of MLLMs. Our code is available at https://github.com/zhuyiche/Mipha.
Authors: Haozhi Cao, Yuecong Xu, Jianfei Yang, Pengyu Yin, Xingyu Ji, Shenghai Yuan, Lihua Xie
Abstract: Multi-modal test-time adaptation (MM-TTA) is proposed to adapt models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. Previous MM-TTA methods rely on predictions of cross-modal information in each input frame, while they ignore the fact that predictions of geometric neighborhoods within consecutive frames are highly correlated, leading to unstable predictions across time. To fulfill this gap, we propose ReLiable Spatial-temporal Voxels (Latte), an MM-TTA method that leverages reliable cross-modal spatial-temporal correspondences for multi-modal 3D segmentation. Motivated by the fact that reliable predictions should be consistent with their spatial-temporal correspondences, Latte aggregates consecutive frames in a slide window manner and constructs ST voxel to capture temporally local prediction consistency for each modality. After filtering out ST voxels with high ST entropy, Latte conducts cross-modal learning for each point and pixel by attending to those with reliable and consistent predictions among both spatial and temporal neighborhoods. Experimental results show that Latte achieves state-of-the-art performance on three different MM-TTA benchmarks compared to previous MM-TTA or TTA methods.
Authors: Chunlong Xia, Xinliang Wang, Feng Lv, Xin Hao, Yifeng Shi
Abstract: Although Vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information interaction and the limited diversity of feature scale. Most existing studies are devoted to designing vision-specific transformers to solve the above problems, which introduce additional pre-training costs. Therefore, we present a plain, pre-training-free, and feature-enhanced ViT backbone with Convolutional Multi-scale feature interaction, named ViT-CoMer, which facilitates bidirectional interaction between CNN and transformer. Compared to the state-of-the-art, ViT-CoMer has the following advantages: (1) We inject spatial pyramid multi-receptive field convolutional features into the ViT architecture, which effectively alleviates the problems of limited local information interaction and single-feature representation in ViT. (2) We propose a simple and efficient CNN-Transformer bidirectional fusion interaction module that performs multi-scale fusion across hierarchical features, which is beneficial for handling dense prediction tasks. (3) We evaluate the performance of ViT-CoMer across various dense prediction tasks, different frameworks, and multiple advanced pre-training. Notably, our ViT-CoMer-L achieves 64.3% AP on COCO val2017 without extra training data, and 62.1% mIoU on ADE20K val, both of which are comparable to state-of-the-art methods. We hope ViT-CoMer can serve as a new backbone for dense prediction tasks to facilitate future research. The code will be released at https://github.com/Traffic-X/ViT-CoMer.
Authors: Weijia Wu, Zhuang Li, Yuchao Gu, Rui Zhao, Yefei He, David Junhao Zhang, Mike Zheng Shou, Yan Li, Tingting Gao, Di Zhang
Abstract: We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation. Comparison to existing motion control methods, DragAnything offers several advantages. Firstly, trajectory-based is more userfriendly for interaction, when acquiring other guidance signals (e.g., masks, depth maps) is labor-intensive. Users only need to draw a line (trajectory) during interaction. Secondly, our entity representation serves as an open-domain embedding capable of representing any object, enabling the control of motion for diverse entities, including background. Lastly, our entity representation allows simultaneous and distinct motion control for multiple objects. Extensive experiments demonstrate that our DragAnything achieves state-of-the-art performance for FVD, FID, and User Study, particularly in terms of object motion control, where our method surpasses the previous methods (e.g., DragNUWA) by 26% in human voting.
Authors: Anastasios Arsenos, Dimitrios Kollias, Evangelos Petrongonas, Christos Skliros, Stefanos Kollias
Abstract: In the context of single domain generalisation, the objective is for models that have been exclusively trained on data from a single domain to demonstrate strong performance when confronted with various unfamiliar domains. In this paper, we introduce a novel model referred to as Contrastive Uncertainty Domain Generalisation Network (CUDGNet). The key idea is to augment the source capacity in both input and label spaces through the fictitious domain generator and jointly learn the domain invariant representation of each class through contrastive learning. Extensive experiments on two Single Source Domain Generalisation (SSDG) datasets demonstrate the effectiveness of our approach, which surpasses the state-of-the-art single-DG methods by up to $7.08\%$. Our method also provides efficient uncertainty estimation at inference time from a single forward pass through the generator subnetwork.
Authors: Han Qiu, Jiaxing Huang, Peng Gao, Lewei Lu, Xiaoqin Zhang, Shijian Lu
Abstract: Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional attention to capture sequential dependencies and generate task sequences recursively. However, such autoregressive Transformers may not fit vision tasks well, as vision task sequences usually lack the sequential dependencies typically observed in natural languages. In this work, we design Masked AutoDecoder~(MAD), an effective multi-task vision generalist. MAD consists of two core designs. First, we develop a parallel decoding framework that introduces bi-directional attention to capture contextual dependencies comprehensively and decode vision task sequences in parallel. Second, we design a masked sequence modeling approach that learns rich task contexts by masking and reconstructing task sequences. In this way, MAD handles all the tasks by a single network branch and a simple cross-entropy loss with minimal task-specific designs. Extensive experiments demonstrate the great potential of MAD as a new paradigm for unifying various vision tasks. MAD achieves superior performance and inference efficiency compared to autoregressive counterparts while obtaining competitive accuracy with task-specific models. Code will be released.
Authors: Meir Yossef Levi, Guy Gilboa
Abstract: We propose a fast and simple explainable AI (XAI) method for point cloud data. It computes pointwise importance with respect to a trained network downstream task. This allows better understanding of the network properties, which is imperative for safety-critical applications. In addition to debugging and visualization, our low computational complexity facilitates online feedback to the network at inference. This can be used to reduce uncertainty and to increase robustness. In this work, we introduce \emph{Feature Based Interpretability} (FBI), where we compute the features' norm, per point, before the bottleneck. We analyze the use of gradients and post- and pre-bottleneck strategies, showing pre-bottleneck is preferred, in terms of smoothness and ranking. We obtain at least three orders of magnitude speedup, compared to current XAI methods, thus, scalable for big point clouds or large-scale architectures. Our approach achieves SOTA results, in terms of classification explainability. We demonstrate how the proposed measure is helpful in analyzing and characterizing various aspects of 3D learning, such as rotation invariance, robustness to out-of-distribution (OOD) outliers or domain shift and dataset bias.
Authors: Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew, Agata M. Wijata, Jakub Nalepa, Nicolas Long\'ep\'e, Przemyslaw Biecek
Abstract: Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for identifying and exposing potential flaws and biases. Since both fields advance independently, there is a notable gap in integrating red teaming strategies into RS. This paper introduces a methodology for examining ML models operating on hyperspectral images within the HYPERVIEW challenge, focusing on soil parameters' estimation. We use post-hoc explanation methods from the Explainable AI (XAI) domain to critically assess the best performing model that won the HYPERVIEW challenge and served as an inspiration for the model deployed on board the INTUITION-1 hyperspectral mission. Our approach effectively red teams the model by pinpointing and validating key shortcomings, constructing a model that achieves comparable performance using just 1% of the input features and a mere up to 5% performance loss. Additionally, we propose a novel way of visualizing explanations that integrate domain-specific information about hyperspectral bands (wavelengths) and data transformations to better suit interpreting models for hyperspectral image analysis.
Authors: Yuelong Li, Yafei Mao, Raja Bala, Sunil Hadap
Abstract: We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3D object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class. Connecting the two stages is a novel multi-scale residual correlation (MRC) layer that captures high-and-low level correspondences between the input image and rendering from first stage. MRC-Net employs a Siamese network with shared weights between both stages to learn embeddings for input and rendered images. To mitigate ambiguity when predicting discrete pose class labels on symmetric objects, we use soft probabilistic labels to define pose class in the first stage. We demonstrate state-of-the-art accuracy, outperforming all competing RGB-based methods on four challenging BOP benchmark datasets: T-LESS, LM-O, YCB-V, and ITODD. Our method is non-iterative and requires no complex post-processing.
Authors: Hao Shi, Song Wang, Jiaming Zhang, Xiaoting Yin, Zhongdao Wang, Zhijian Zhao, Guangming Wang, Jianke Zhu, Kailun Yang, Kaiwei Wang
Abstract: Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation, continuity across varying viewpoints, and single-view occlusion. Our paper introduces OccFiner, a novel offboard framework designed to enhance the accuracy of vision-based occupancy predictions. OccFiner operates in two hybrid phases: 1) a multi-to-multi local propagation network that implicitly aligns and processes multiple local frames for correcting onboard model errors and consistently enhancing occupancy accuracy across all distances. 2) the region-centric global propagation, focuses on refining labels using explicit multi-view geometry and integrating sensor bias, especially to increase the accuracy of distant occupied voxels. Extensive experiments demonstrate that OccFiner improves both geometric and semantic accuracy across various types of coarse occupancy, setting a new state-of-the-art performance on the SemanticKITTI dataset. Notably, OccFiner elevates vision-based SSC models to a level even surpassing that of LiDAR-based onboard SSC models.
Authors: Zhihao Chen, Yiyuan Ge
Abstract: Cloth-changing person re-identification aims to retrieve and identify spe-cific pedestrians by using cloth-unrelated features in person cloth-changing scenarios. However, pedestrian images captured by surveillance probes usually contain occlusions in real-world scenarios. The perfor-mance of existing cloth-changing person re-identification methods is sig-nificantly degraded due to the reduction of discriminative cloth-unrelated features caused by occlusion. We define cloth-changing person re-identification in occlusion scenarios as occluded cloth-changing person re-identification (Occ-CC-ReID), and to the best of our knowledge, we are the first to propose occluded cloth-changing person re-identification as a new task. We constructed two occluded cloth-changing person re-identification datasets: Occluded-PRCC and Occluded-LTCC. The da-tasets can be obtained from the following link: https://github.com/1024AILab/Occluded-Cloth-Changing-Person-Re-Identification.
URLs: https://github.com/1024AILab/Occluded-Cloth-Changing-Person-Re-Identification.
Authors: Yuki Kondo, Riku Miyata, Fuma Yasue, Taito Naruki, Norimichi Ukita
Abstract: In this paper, we analyze and discuss ShadowFormer in preparation for the NTIRE2023 Shadow Removal Challenge [1], implementing five key improvements: image alignment, the introduction of a perceptual quality loss function, the semi-automatic annotation for shadow detection, joint learning of shadow detection and removal, and the introduction of new data augmentation technique "CutShadow" for shadow removal. Our method achieved scores of 0.196 (3rd out of 19) in LPIPS and 7.44 (4th out of 19) in the Mean Opinion Score (MOS).
Authors: Hyunkyung Han, Jihyeon Seong, Jaesik Choi
Abstract: Capsule Neural Networks (CapsNets) is a novel architecture that utilizes vector-wise representations formed by multiple neurons. Specifically, the Dynamic Routing CapsNets (DR-CapsNets) employ an affine matrix and dynamic routing mechanism to train capsules and acquire translation-equivariance properties, enhancing its robustness compared to traditional Convolutional Neural Networks (CNNs). Echocardiograms, which capture moving images of the heart, present unique challenges for traditional image classification methods. In this paper, we explore the potential of DR-CapsNets and propose CardioCaps, a novel attention-based DR-CapsNet architecture for class-imbalanced echocardiogram classification. CardioCaps comprises two key components: a weighted margin loss incorporating a regression auxiliary loss and an attention mechanism. First, the weighted margin loss prioritizes positive cases, supplemented by an auxiliary loss function based on the Ejection Fraction (EF) regression task, a crucial measure of cardiac function. This approach enhances the model's resilience in the face of class imbalance. Second, recognizing the quadratic complexity of dynamic routing leading to training inefficiencies, we adopt the attention mechanism as a more computationally efficient alternative. Our results demonstrate that CardioCaps surpasses traditional machine learning baseline methods, including Logistic Regression, Random Forest, and XGBoost with sampling methods and a class weight matrix. Furthermore, CardioCaps outperforms other deep learning baseline methods such as CNNs, ResNets, U-Nets, and ViTs, as well as advanced CapsNets methods such as EM-CapsNets and Efficient-CapsNets. Notably, our model demonstrates robustness to class imbalance, achieving high precision even in datasets with a substantial proportion of negative cases.
Authors: Tianshuo Xu, Lijiang Li, Peng Mi, Xiawu Zheng, Fei Chao, Rongrong Ji, Yonghong Tian, Qiang Shen
Abstract: PSNR-oriented models are a critical class of super-resolution models with applications across various fields. However, these models tend to generate over-smoothed images, a problem that has been analyzed previously from the perspectives of models or loss functions, but without taking into account the impact of data properties. In this paper, we present a novel phenomenon that we term the center-oriented optimization (COO) problem, where a model's output converges towards the center point of similar high-resolution images, rather than towards the ground truth. We demonstrate that the strength of this problem is related to the uncertainty of data, which we quantify using entropy. We prove that as the entropy of high-resolution images increases, their center point will move further away from the clean image distribution, and the model will generate over-smoothed images. Implicitly optimizing the COO problem, perceptual-driven approaches such as perceptual loss, model structure optimization, or GAN-based methods can be viewed. We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss). DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution and thereby decrease the entropy. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models. Moreover, when applied to GAN-based methods, such as RaGAN, DECLoss helps to achieve state-of-the-art performance, such as 0.093 LPIPS with 24.51 PSNR on 4x downsampled Urban100, validating the effectiveness and generalization of our approach.
Authors: Zihao Huang, Yue Wang, Weixing Xin, Xingtong Lin, Huizhen Li, Haowen Chen, Yizhen Lao, Xia Chen
Abstract: Medical image recognition often faces the problem of insufficient data in practical applications. Image recognition and processing under few-shot conditions will produce overfitting, low recognition accuracy, low reliability and insufficient robustness. It is often the case that the difference of characteristics is subtle, and the recognition is affected by perspectives, background, occlusion and other factors, which increases the difficulty of recognition. Furthermore, in fine-grained images, the few-shot problem leads to insufficient useful feature information in the images. Considering the characteristics of few-shot and fine-grained image recognition, this study has established a recognition model based on attention and Siamese neural network. Aiming at the problem of few-shot samples, a Siamese neural network suitable for classification model is proposed. The Attention-Based neural network is used as the main network to improve the classification effect. Covid- 19 lung samples have been selected for testing the model. The results show that the less the number of image samples are, the more obvious the advantage shows than the ordinary neural network.
Authors: Levente Juh\'asz, Peter Mooney, Hartwig H. Hochmair, Boyuan Guan
Abstract: This paper explores the concept of leveraging generative AI as a mapping assistant for enhancing the efficiency of collaborative mapping. We present results of an experiment that combines multiple sources of volunteered geographic information (VGI) and large language models (LLMs). Three analysts described the content of crowdsourced Mapillary street-level photographs taken along roads in a small test area in Miami, Florida. GPT-3.5-turbo was instructed to suggest the most appropriate tagging for each road in OpenStreetMap (OSM). The study also explores the utilization of BLIP-2, a state-of-the-art multimodal pre-training method as an artificial analyst of street-level photographs in addition to human analysts. Results demonstrate two ways to effectively increase the accuracy of mapping suggestions without modifying the underlying AI models: by (1) providing a more detailed description of source photographs, and (2) combining prompt engineering with additional context (e.g. location and objects detected along a road). The first approach increases the suggestion accuracy by up to 29%, and the second one by up to 20%.
Authors: Lana Touma, Mohammad Al Horani, Manar Tailouni, Anas Dahabiah, Khloud Al Jallad
Abstract: Automatic Deception Detection has been a hot research topic for a long time, using machine learning and deep learning to automatically detect deception, brings new light to this old field. In this paper, we proposed a voting-based method for automatic deception detection from videos using audio, visual and lexical features. Experiments were done on two datasets, the Real-life trial dataset by Michigan University and the Miami University deception detection dataset. Video samples were split into frames of images, audio, and manuscripts. Our Voting-based Multimodal proposed solution consists of three models. The first model is CNN for detecting deception from images, the second model is Support Vector Machine (SVM) on Mel spectrograms for detecting deception from audio and the third model is Word2Vec on Support Vector Machine (SVM) for detecting deception from manuscripts. Our proposed solution outperforms state of the art. Best results achieved on images, audio and text were 97%, 96%, 92% respectively on Real-Life Trial Dataset, and 97%, 82%, 73% on video, audio and text respectively on Miami University Deception Detection.
Authors: Shashidhar Reddy Javaji, Sovesh Mohapatra, Advait Gosai, Gottfried Schlaug
Abstract: Brain tumors remain a critical global health challenge, necessitating advancements in diagnostic techniques and treatment methodologies. A tumor or its recurrence often needs to be identified in imaging studies and differentiated from normal brain tissue. In response to the growing need for age-specific segmentation models, particularly for pediatric patients, this study explores the deployment of deep learning techniques using magnetic resonance imaging (MRI) modalities. By introducing a novel ensemble approach using ONet and modified versions of UNet, coupled with innovative loss functions, this study achieves a precise segmentation model for the BraTS-PEDs 2023 Challenge. Data augmentation, including both single and composite transformations, ensures model robustness and accuracy across different scanning protocols. The ensemble strategy, integrating the ONet and UNet models, shows greater effectiveness in capturing specific features and modeling diverse aspects of the MRI images which result in lesion wise Dice scores of 0.52, 0.72 and 0.78 on unseen validation data and scores of 0.55, 0.70, 0.79 on final testing data for the "enhancing tumor", "tumor core" and "whole tumor" labels respectively. Visual comparisons further confirm the superiority of the ensemble method in accurate tumor region coverage. The results indicate that this advanced ensemble approach, building upon the unique strengths of individual models, offers promising prospects for enhanced diagnostic accuracy and effective treatment planning and monitoring for brain tumors in pediatric brains.
Authors: Roshan Prakash Rane, JiHoon Kim, Arjun Umesha, Didem Stark, Marc-Andr\'e Schulz, Kerstin Ritter
Abstract: Deep Learning (DL) models have gained popularity in neuroimaging studies for predicting psychological behaviors, cognitive traits, and brain pathologies. However, these models can be biased by confounders such as age, sex, or imaging artifacts from the acquisition process. To address this, we introduce 'DeepRepViz', a two-part framework designed to identify confounders in DL model predictions. The first component is a visualization tool that can be used to qualitatively examine the final latent representation of the DL model. The second component is a metric called 'Con-score' that quantifies the confounder risk associated with a variable, using the final latent representation of the DL model. We demonstrate the effectiveness of the Con-score using a simple simulated setup by iteratively altering the strength of a simulated confounder and observing the corresponding change in the Con-score. Next, we validate the DeepRepViz framework on a large-scale neuroimaging dataset (n=12000) by performing three MRI-phenotype prediction tasks that include (a) predicting chronic alcohol users, (b) classifying participant sex, and (c) predicting performance speed on a cognitive task called 'trail making'. DeepRepViz identifies sex as a significant confounder in the DL model predicting chronic alcohol users (Con-score=0.35) and age as a confounder in the model predicting cognitive task performance (Con-score=0.3). In conclusion, the DeepRepViz framework provides a systematic approach to test for potential confounders such as age, sex, and imaging artifacts and improves the transparency of DL models for neuroimaging studies.
Authors: Xiaosen Zheng, Tianyu Pang, Chao Du, Jing Jiang, Min Lin
Abstract: Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training samples, ensuring that data contributors are fairly compensated or credited. Several theoretically motivated methods have been proposed to implement data attribution, in an effort to improve the trade-off between computational scalability and effectiveness. In this work, we conduct extensive experiments and ablation studies on attributing diffusion models, specifically focusing on DDPMs trained on CIFAR-10 and CelebA, as well as a Stable Diffusion model LoRA-finetuned on ArtBench. Intriguingly, we report counter-intuitive observations that theoretically unjustified design choices for attribution empirically outperform previous baselines by a large margin, in terms of both linear datamodeling score and counterfactual evaluation. Our work presents a significantly more efficient approach for attributing diffusion models, while the unexpected findings suggest that at least in non-convex settings, constructions guided by theoretical assumptions may lead to inferior attribution performance. The code is available at https://github.com/sail-sg/D-TRAK.
Authors: Reza Esfandiarpoor, Stephen H. Bach
Abstract: A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related attributes, e.g., using brown sparrow instead of sparrow. However, current zero-shot methods select a subset of attributes regardless of commonalities between the target classes, potentially providing no useful information that would have helped to distinguish between them. For instance, they may use color instead of bill shape to distinguish between sparrows and wrens, which are both brown. We propose Follow-up Differential Descriptions (FuDD), a zero-shot approach that tailors the class descriptions to each dataset and leads to additional attributes that better differentiate the target classes. FuDD first identifies the ambiguous classes for each image, and then uses a Large Language Model (LLM) to generate new class descriptions that differentiate between them. The new class descriptions resolve the initial ambiguity and help predict the correct label. In our experiments, FuDD consistently outperforms generic description ensembles and naive LLM-generated descriptions on 12 datasets. We show that differential descriptions are an effective tool to resolve class ambiguities, which otherwise significantly degrade the performance. We also show that high quality natural language class descriptions produced by FuDD result in comparable performance to few-shot adaptation methods.
Authors: Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli
Abstract: The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed worldview and restrict opportunities for minority groups. In this work, we frame fairness as a distributional alignment problem. Our solution consists of two main technical contributions: (1) a distributional alignment loss that steers specific characteristics of the generated images towards a user-defined target distribution, and (2) adjusted direct finetuning of diffusion model's sampling process (adjusted DFT), which leverages an adjusted gradient to directly optimize losses defined on the generated images. Empirically, our method markedly reduces gender, racial, and their intersectional biases for occupational prompts. Gender bias is significantly reduced even when finetuning just five soft tokens. Crucially, our method supports diverse perspectives of fairness beyond absolute equality, which is demonstrated by controlling age to a $75\%$ young and $25\%$ old distribution while simultaneously debiasing gender and race. Finally, our method is scalable: it can debias multiple concepts at once by simply including these prompts in the finetuning data. We share code and various fair diffusion model adaptors at https://sail-sg.github.io/finetune-fair-diffusion/.
Authors: Shuning Xu, Binbin Song, Xiangyu Chen, Xina Liu, Jiantao Zhou
Abstract: Moire patterns frequently appear when capturing screens with smartphones or cameras, potentially compromising image quality. Previous studies suggest that moire pattern elimination in the RAW domain offers greater effectiveness compared to demoireing in the sRGB domain. Nevertheless, relying solely on RAW data for image demoireing is insufficient in mitigating the color cast due to the absence of essential information required for the color correction by the image signal processor (ISP). In this paper, we propose to jointly utilize both RAW and sRGB data for image demoireing (RRID), which are readily accessible in modern smartphones and DSLR cameras. We develop Skip-Connection-based Demoireing Module (SCDM) with Gated Feedback Module (GFM) and Frequency Selection Module (FSM) embedded in skip-connections for the efficient and effective demoireing of RAW and sRGB features, respectively. Subsequently, we design a RGB Guided ISP (RGISP) to learn a device-dependent ISP, assisting the process of color recovery. Extensive experiments demonstrate that our RRID outperforms state-of-the-art approaches, in terms of the performance in moire pattern removal and color cast correction by 0.62dB in PSNR and 0.003 in SSIM.
Authors: Nisar Ahmed, Luke Burks, Kailah Cabral, Alyssa Bekai Rose
Abstract: We consider the problem of evaluating dynamic consistency in discrete time probabilistic filters that approximate stochastic system state densities with Gaussian mixtures. Dynamic consistency means that the estimated probability distributions correctly describe the actual uncertainties. As such, the problem of consistency testing naturally arises in applications with regards to estimator tuning and validation. However, due to the general complexity of the density functions involved, straightforward approaches for consistency testing of mixture-based estimators have remained challenging to define and implement. This paper derives a new exact result for Gaussian mixture consistency testing within the framework of normalized deviation squared (NDS) statistics. It is shown that NDS test statistics for generic multivariate Gaussian mixture models exactly follow mixtures of generalized chi-square distributions, for which efficient computational tools are available. The accuracy and utility of the resulting consistency tests are numerically demonstrated on static and dynamic mixture estimation examples.
Authors: Ru Peng, Heming Zou, Haobo Wang, Yawen Zeng, Zenan Huang, Junbo Zhao
Abstract: The conventional evaluation protocols on machine learning models rely heavily on a labeled, i.i.d-assumed testing dataset, which is not often present in real world applications. The Automated Model Evaluation (AutoEval) shows an alternative to this traditional workflow, by forming a proximal prediction pipeline of the testing performance without the presence of ground-truth labels. Despite its recent successes, the AutoEval frameworks still suffer from an overconfidence issue, substantial storage and computational cost. In that regard, we propose a novel measure -- Meta-Distribution Energy (MDE) -- that allows the AutoEval framework to be both more efficient and effective. The core of the MDE is to establish a meta-distribution statistic, on the information (energy) associated with individual samples, then offer a smoother representation enabled by energy-based learning. We further provide our theoretical insights by connecting the MDE with the classification loss. We provide extensive experiments across modalities, datasets and different architectural backbones to validate MDE's validity, together with its superiority compared with prior approaches. We also prove MDE's versatility by showing its seamless integration with large-scale models, and easy adaption to learning scenarios with noisy- or imbalanced- labels. Code and data are available: https://github.com/pengr/Energy_AutoEval
Authors: Antonio Curci, Andrea Esposito
Abstract: Tumors can manifest in various forms and in different areas of the human body. Brain tumors are specifically hard to diagnose and treat because of the complexity of the organ in which they develop. Detecting them in time can lower the chances of death and facilitate the therapy process for patients. The use of Artificial Intelligence (AI) and, more specifically, deep learning, has the potential to significantly reduce costs in terms of time and resources for the discovery and identification of tumors from images obtained through imaging techniques. This research work aims to assess the performance of a multimodal model for the classification of Magnetic Resonance Imaging (MRI) scans processed as grayscale images. The results are promising, and in line with similar works, as the model reaches an accuracy of around 98\%. We also highlight the need for explainability and transparency to ensure human control and safety.
Authors: Minheng Chen, Zhirun Zhang, Shuheng Gu, Zhangyang Ge, Youyong Kong
Abstract: Image-based rigid 2D/3D registration is a critical technique for fluoroscopic guided surgical interventions. In recent years, some learning-based fully differentiable methods have produced beneficial outcomes while the process of feature extraction and gradient flow transmission still lack controllability and interpretability. To alleviate these problems, in this work, we propose a novel fully differentiable correlation-driven network using a dual-branch CNN-transformer encoder which enables the network to extract and separate low-frequency global features from high-frequency local features. A correlation-driven loss is further proposed for low-frequency feature and high-frequency feature decomposition based on embedded information. Besides, a training strategy that learns to approximate a convex-shape similarity function is applied in our work. We test our approach on a in-house datasetand show that it outperforms both existing fully differentiable learning-based registration approaches and the conventional optimization-based baseline.
Authors: Arash Harirpoush, Amirhossein Rasoulian, Marta Kersten-Oertel, Yiming Xiao
Abstract: Recent rising interests in patient-specific thoracic surgical planning and simulation require efficient and robust creation of digital anatomical models from automatic medical image segmentation algorithms. Deep learning (DL) is now state-of-the-art in various radiological tasks, and U-shaped DL models have particularly excelled in medical image segmentation since the inception of the 2D UNet. To date, many variants of U-shaped models have been proposed by the integration of different attention mechanisms and network configurations. Systematic benchmark studies which analyze the architecture of these models by leveraging the recent development of the multi-label databases, can provide valuable insights for clinical deployment and future model designs, but such studies are still rare. We conduct the first systematic benchmark study for variants of 3D U-shaped models (3DUNet, STUNet, AttentionUNet, SwinUNETR, FocalSegNet, and a novel 3D SwinUnet with four variants) with a focus on CT-based anatomical segmentation for thoracic surgery. Our study systematically examines the impact of different attention mechanisms, the number of resolution stages, and network configurations on segmentation accuracy and computational complexity. To allow cross-reference with other recent benchmarking studies, we also included a performance assessment of the BTCV abdominal structural segmentation. With the STUNet ranking at the top, our study demonstrated the value of CNN-based U-shaped models for the investigated tasks and the benefit of residual blocks in network configuration designs to boost segmentation performance.
Authors: Yan Wang, Yi Liu, Shijie Zhao, Junlin Li, Li Zhang
Abstract: To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR), prevailing methods follow two independent tracks: 1) accelerate existing networks by content-aware routing, and 2) design better super-resolution networks via token mixer refining. Despite directness, they encounter unavoidable defects (e.g., inflexible route or non-discriminative processing) limiting further improvements of quality-complexity trade-off. To erase the drawbacks, we integrate these schemes by proposing a content-aware mixer (CAMixer), which assigns convolution for simple contexts and additional deformable window-attention for sparse textures. Specifically, the CAMixer uses a learnable predictor to generate multiple bootstraps, including offsets for windows warping, a mask for classifying windows, and convolutional attentions for endowing convolution with the dynamic property, which modulates attention to include more useful textures self-adaptively and improves the representation capability of convolution. We further introduce a global classification loss to improve the accuracy of predictors. By simply stacking CAMixers, we obtain CAMixerSR which achieves superior performance on large-image SR, lightweight SR, and omnidirectional-image SR.
Authors: Fei Zhu, Shijie Ma, Zhen Cheng, Xu-Yao Zhang, Zhaoxiang Zhang, Cheng-Lin Liu
Abstract: Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed once deployed. In many real-world applications, this fundamental and rather naive assumption may not hold because an open environment is complex, dynamic, and full of unknowns. In such cases, rejecting unknowns, discovering novelties, and then incrementally learning them, could enable models to be safe and evolve continually as biological systems do. This paper provides a holistic view of open-world machine learning by investigating unknown rejection, novel class discovery, and class-incremental learning in a unified paradigm. The challenges, principles, and limitations of current methodologies are discussed in detail. Finally, we discuss several potential directions for future research. This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm, to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
Authors: Sotirios Panagiotis Chytas, Vishnu Suresh Lokhande, Peiran Li, Vikas Singh
Abstract: Small sample sizes are common in many disciplines, which necessitates pooling roughly similar datasets across multiple institutions to study weak but relevant associations between images and disease outcomes. Such data often manifest shift/imbalance in covariates (i.e., secondary non-imaging data). Controlling for such nuisance variables is common within standard statistical analysis, but the ideas do not directly apply to overparameterized models. Consequently, recent work has shown how strategies from invariant representation learning provides a meaningful starting point, but the current repertoire of methods is limited to accounting for shifts/imbalances in just a couple of covariates at a time. In this paper, we show how viewing this problem from the perspective of Category theory provides a simple and effective solution that completely avoids elaborate multi-stage training pipelines that would otherwise be needed. We show the effectiveness of this approach via extensive experiments on real datasets. Further, we discuss how this style of formulation offers a unified perspective on at least 5+ distinct problem settings, from self-supervised learning to matching problems in 3D reconstruction.
Authors: Ronald B. Liu, Zhe Liu, Max G. A. Wolf, Krishna P. Purohit, Gregor Fritz, Yi Feng, Carsten G. Hansen, Pierre O. Bagnaninchi, Xavier Casadevall i Solvas, Yunjie Yang
Abstract: Advancements in high-throughput biomedical applications necessitate real-time, large field-of-view (FOV) imaging capabilities. Conventional lens-free imaging (LFI) systems, while addressing the limitations of physical lenses, have been constrained by dynamic, hard-to-model optical fields, resulting in a limited one-shot FOV of approximately 20 $mm^2$. This restriction has been a major bottleneck in applications like live-cell imaging and automation of microfluidic systems for biomedical research. Here, we present a deep-learning(DL)-based imaging framework - GenLFI - leveraging generative artificial intelligence (AI) for holographic image reconstruction. We demonstrate that GenLFI can achieve a real-time FOV over 550 $mm^2$, surpassing the current LFI system by more than 20-fold, and even larger than the world's largest confocal microscope by 1.76 times. The resolution is at the sub-pixel level of 5.52 $\mu m$, without the need for a shifting light source. The unsupervised learning-based reconstruction does not require optical field modeling, making imaging dynamic 3D samples (e.g., droplet-based microfluidics and 3D cell models) in complex optical fields possible. This GenLFI framework unlocks the potential of LFI systems, offering a robust tool to tackle new frontiers in high-throughput biomedical applications such as drug discovery.
Authors: Hongyang Zhu, Xin Lu, Yanwei Qin, Xinran Yu, Tianjiao Sun, Yunsong Zhao
Abstract: Ring artifacts in computed tomography images, arising from the undesirable responses of detector units, significantly degrade image quality and diagnostic reliability. To address this challenge, we propose a dual-domain regularization model to effectively remove ring artifacts, while maintaining the integrity of the original CT image. The proposed model corrects the vertical stripe artifacts on the sinogram by innovatively updating the response inconsistency compensation coefficients of detector units, which is achieved by employing the group sparse constraint and the projection-view direction sparse constraint on the stripe artifacts. Simultaneously, we apply the sparse constraint on the reconstructed image to further rectified ring artifacts in the image domain. The key advantage of the proposed method lies in considering the relationship between the response inconsistency compensation coefficients of the detector units and the projection views, which enables a more accurate correction of the response of the detector units. An alternating minimization method is designed to solve the model. Comparative experiments on real photon counting detector data demonstrate that the proposed method not only surpasses existing methods in removing ring artifacts but also excels in preserving structural details and image fidelity.
Authors: Li Lin, Yamini Sri Krubha, Zhenhuan Yang, Cheng Ren, Thuc Duy Le, Irene Amerini, Xin Wang, Shu Hu
Abstract: In the realm of medical imaging, particularly for COVID-19 detection, deep learning models face substantial challenges such as the necessity for extensive computational resources, the paucity of well-annotated datasets, and a significant amount of unlabeled data. In this work, we introduce the first lightweight detector designed to overcome these obstacles, leveraging a frozen CLIP image encoder and a trainable multilayer perception (MLP). Enhanced with Conditional Value at Risk (CVaR) for robustness and a loss landscape flattening strategy for improved generalization, our model is tailored for high efficacy in COVID-19 detection. Furthermore, we integrate a teacher-student framework to capitalize on the vast amounts of unlabeled data, enabling our model to achieve superior performance despite the inherent data limitations. Experimental results on the COV19-CT-DB dataset demonstrate the effectiveness of our approach, surpassing baseline by up to 10.6% in `macro' F1 score in supervised learning. The code is available at https://github.com/Purdue-M2/COVID-19_Detection_M2_PURDUE.
URLs: https://github.com/Purdue-M2/COVID-19_Detection_M2_PURDUE.
Authors: Yu Cai, Hao Chen, Kwang-Ting Cheng
Abstract: Medical anomaly detection aims to identify abnormal findings using only normal training data, playing a crucial role in health screening and recognizing rare diseases. Reconstruction-based methods, particularly those utilizing autoencoders (AEs), are dominant in this field. They work under the assumption that AEs trained on only normal data cannot reconstruct unseen abnormal regions well, thereby enabling the anomaly detection based on reconstruction errors. However, this assumption does not always hold due to the mismatch between the reconstruction training objective and the anomaly detection task objective, rendering these methods theoretically unsound. This study focuses on providing a theoretical foundation for AE-based reconstruction methods in anomaly detection. By leveraging information theory, we elucidate the principles of these methods and reveal that the key to improving AE in anomaly detection lies in minimizing the information entropy of latent vectors. Experiments on four datasets with two image modalities validate the effectiveness of our theory. To the best of our knowledge, this is the first effort to theoretically clarify the principles and design philosophy of AE for anomaly detection. Code will be available upon acceptance.