Authors: Zhi Qin Tan, Olga Isupova, Gustavo Carneiro, Xiatian Zhu, Yunpeng Li
Abstract: Acquiring fine-grained object detection annotations in unconstrained images is time-consuming, expensive, and prone to noise, especially in crowdsourcing scenarios. Most prior object detection methods assume accurate annotations; A few recent works have studied object detection with noisy crowdsourced annotations, with evaluation on distinct synthetic crowdsourced datasets of varying setups under artificial assumptions. To address these algorithmic limitations and evaluation inconsistency, we first propose a novel Bayesian Detector Combination (BDC) framework to more effectively train object detectors with noisy crowdsourced annotations, with the unique ability of automatically inferring the annotators' label qualities. Unlike previous approaches, BDC is model-agnostic, requires no prior knowledge of the annotators' skill level, and seamlessly integrates with existing object detection models. Due to the scarcity of real-world crowdsourced datasets, we introduce large synthetic datasets by simulating varying crowdsourcing scenarios. This allows consistent evaluation of different models at scale. Extensive experiments on both real and synthetic crowdsourced datasets show that BDC outperforms existing state-of-the-art methods, demonstrating its superiority in leveraging crowdsourced data for object detection. Our code and data are available at https://github.com/zhiqin1998/bdc.
Authors: Jaeyeul Kim, Jungwan Woo, Ukcheol Shin, Jean Oh, Sunghoon Im
Abstract: Understanding the motion states of the surrounding environment is critical for safe autonomous driving. These motion states can be accurately derived from scene flow, which captures the three-dimensional motion field of points. Existing LiDAR scene flow methods extract spatial features from each point cloud and then fuse them channel-wise, resulting in the implicit extraction of spatio-temporal features. Furthermore, they utilize 2D Bird's Eye View and process only two frames, missing crucial spatial information along the Z-axis and the broader temporal context, leading to suboptimal performance. To address these limitations, we propose Flow4D, which temporally fuses multiple point clouds after the 3D intra-voxel feature encoder, enabling more explicit extraction of spatio-temporal features through a 4D voxel network. However, while using 4D convolution improves performance, it significantly increases the computational load. For further efficiency, we introduce the Spatio-Temporal Decomposition Block (STDB), which combines 3D and 1D convolutions instead of using heavy 4D convolution. In addition, Flow4D further improves performance by using five frames to take advantage of richer temporal information. As a result, the proposed method achieves a 45.9% higher performance compared to the state-of-the-art while running in real-time, and won 1st place in the 2024 Argoverse 2 Scene Flow Challenge. The code is available at https://github.com/dgist-cvlab/Flow4D.
Authors: Mingchen Xu, Jing Wu, Yukun Lai, Ze Ji
Abstract: Techniques for detecting mirrors from static images have witnessed rapid growth in recent years. However, these methods detect mirrors from single input images. Detecting mirrors from video requires further consideration of temporal consistency between frames. We observe that humans can recognize mirror candidates, from just one or two frames, based on their appearance (e.g. shape, color). However, to ensure that the candidate is indeed a mirror (not a picture or a window), we often need to observe more frames for a global view. This observation motivates us to detect mirrors by fusing appearance features extracted from a short-term attention module and context information extracted from a long-term attention module. To evaluate the performance, we build a challenging benchmark dataset of 19,255 frames from 281 videos. Experimental results demonstrate that our method achieves state-of-the-art performance on the benchmark dataset.
Authors: Lingzhi Pan, Tong Zhang, Bingyuan Chen, Qi Zhou, Wei Ke, Sabine S\"usstrunk, Mathieu Salzmann
Abstract: With the advancements in denoising diffusion probabilistic models (DDPMs), image inpainting has significantly evolved from merely filling information based on nearby regions to generating content conditioned on various prompts such as text, exemplar images, and sketches. However, existing methods, such as model fine-tuning and simple concatenation of latent vectors, often result in generation failures due to overfitting and inconsistency between the inpainted region and the background. In this paper, we argue that the current large diffusion models are sufficiently powerful to generate realistic images without further tuning. Hence, we introduce PILOT (in\textbf{P}ainting v\textbf{I}a \textbf{L}atent \textbf{O}p\textbf{T}imization), an optimization approach grounded on a novel \textit{semantic centralization} and \textit{background preservation loss}. Our method searches latent spaces capable of generating inpainted regions that exhibit high fidelity to user-provided prompts while maintaining coherence with the background. Furthermore, we propose a strategy to balance optimization expense and image quality, significantly enhancing generation efficiency. Our method seamlessly integrates with any pre-trained model, including ControlNet and DreamBooth, making it suitable for deployment in multi-modal editing tools. Our qualitative and quantitative evaluations demonstrate that PILOT outperforms existing approaches by generating more coherent, diverse, and faithful inpainted regions in response to provided prompts.
Authors: Hao Li, Baris Oguz, Gabriel Arenas, Xing Yao, Jiacheng Wang, Alison Pouch, Brett Byram, Nadav Schwartz, Ipek Oguz
Abstract: Placenta volume measurement from 3D ultrasound images is critical for predicting pregnancy outcomes, and manual annotation is the gold standard. However, such manual annotation is expensive and time-consuming. Automated segmentation algorithms can often successfully segment the placenta, but these methods may not consistently produce robust segmentations suitable for practical use. Recently, inspired by the Segment Anything Model (SAM), deep learning-based interactive segmentation models have been widely applied in the medical imaging domain. These models produce a segmentation from visual prompts provided to indicate the target region, which may offer a feasible solution for practical use. However, none of these models are specifically designed for interactively segmenting 3D ultrasound images, which remain challenging due to the inherent noise of this modality. In this paper, we evaluate publicly available state-of-the-art 3D interactive segmentation models in contrast to a human-in-the-loop approach for the placenta segmentation task. The Dice score, normalized surface Dice, averaged symmetric surface distance, and 95-percent Hausdorff distance are used as evaluation metrics. We consider a Dice score of 0.95 a successful segmentation. Our results indicate that the human-in-the-loop segmentation model reaches this standard. Moreover, we assess the efficiency of the human-in-the-loop model as a function of the amount of prompts. Our results demonstrate that the human-in-the-loop model is both effective and efficient for interactive placenta segmentation. The code is available at \url{https://github.com/MedICL-VU/PRISM-placenta}.
Authors: Jinjie Mai, Abdullah Hamdi, Silvio Giancola, Chen Zhao, Bernard Ghanem
Abstract: We built our pipeline EgoLoc-v1, mainly inspired by EgoLoc. We propose a model ensemble strategy to improve the camera pose estimation part of the VQ3D task, which has been proven to be essential in previous work. The core idea is not only to do SfM for egocentric videos but also to do 2D-3D matching between existing 3D scans and 2D video frames. In this way, we have a hybrid SfM and camera relocalization pipeline, which can provide us with more camera poses, leading to higher QwP and overall success rate. Our method achieves the best performance regarding the most important metric, the overall success rate. We surpass previous state-of-the-art, the competitive EgoLoc, by $1.5\%$. The code is available at \url{https://github.com/Wayne-Mai/egoloc_v1}.
Authors: Kazi Sajeed Mehrab, M. Maruf, Arka Daw, Harish Babu Manogaran, Abhilash Neog, Mridul Khurana, Bahadir Altintas, Yasin Bakis, Elizabeth G Campolongo, Matthew J Thompson, Xiaojun Wang, Hilmar Lapp, Wei-Lun Chao, Paula M. Mabee, Henry L. Bart Jr., Wasila Dahdul, Anuj Karpatne
Abstract: Fishes are integral to both ecological systems and economic sectors, and studying fish traits is crucial for understanding biodiversity patterns and macro-evolution trends. To enable the analysis of visual traits from fish images, we introduce the Fish-Visual Trait Analysis (Fish-Vista) dataset - a large, annotated collection of about 60K fish images spanning 1900 different species, supporting several challenging and biologically relevant tasks including species classification, trait identification, and trait segmentation. These images have been curated through a sophisticated data processing pipeline applied to a cumulative set of images obtained from various museum collections. Fish-Vista provides fine-grained labels of various visual traits present in each image. It also offers pixel-level annotations of 9 different traits for 2427 fish images, facilitating additional trait segmentation and localization tasks. The ultimate goal of Fish-Vista is to provide a clean, carefully curated, high-resolution dataset that can serve as a foundation for accelerating biological discoveries using advances in AI. Finally, we provide a comprehensive analysis of state-of-the-art deep learning techniques on Fish-Vista.
Authors: Jayateja Kalla, Rohit Kumar, Soma Biswas
Abstract: We propose a novel TACLE (TAsk and CLass-awarE) framework to address the relatively unexplored and challenging problem of exemplar-free semi-supervised class incremental learning. In this scenario, at each new task, the model has to learn new classes from both (few) labeled and unlabeled data without access to exemplars from previous classes. In addition to leveraging the capabilities of pre-trained models, TACLE proposes a novel task-adaptive threshold, thereby maximizing the utilization of the available unlabeled data as incremental learning progresses. Additionally, to enhance the performance of the under-represented classes within each task, we propose a class-aware weighted cross-entropy loss. We also exploit the unlabeled data for classifier alignment, which further enhances the model performance. Extensive experiments on benchmark datasets, namely CIFAR10, CIFAR100, and ImageNet-Subset100 demonstrate the effectiveness of the proposed TACLE framework. We further showcase its effectiveness when the unlabeled data is imbalanced and also for the extreme case of one labeled example per class.
Authors: Lei Cheng, Arindam Sengupta, Siyang Cao
Abstract: Autonomous driving holds great promise in addressing traffic safety concerns by leveraging artificial intelligence and sensor technology. Multi-Object Tracking plays a critical role in ensuring safer and more efficient navigation through complex traffic scenarios. This paper presents a novel deep learning-based method that integrates radar and camera data to enhance the accuracy and robustness of Multi-Object Tracking in autonomous driving systems. The proposed method leverages a Bi-directional Long Short-Term Memory network to incorporate long-term temporal information and improve motion prediction. An appearance feature model inspired by FaceNet is used to establish associations between objects across different frames, ensuring consistent tracking. A tri-output mechanism is employed, consisting of individual outputs for radar and camera sensors and a fusion output, to provide robustness against sensor failures and produce accurate tracking results. Through extensive evaluations of real-world datasets, our approach demonstrates remarkable improvements in tracking accuracy, ensuring reliable performance even in low-visibility scenarios.
Authors: Ningli Xu, Rongjun Qin
Abstract: Predicting realistic ground views from satellite imagery in urban scenes is a challenging task due to the significant view gaps between satellite and ground-view images. We propose a novel pipeline to tackle this challenge, by generating geospecifc views that maximally respect the weak geometry and texture from multi-view satellite images. Different from existing approaches that hallucinate images from cues such as partial semantics or geometry from overhead satellite images, our method directly predicts ground-view images at geolocation by using a comprehensive set of information from the satellite image, resulting in ground-level images with a resolution boost at a factor of ten or more. We leverage a novel building refinement method to reduce geometric distortions in satellite data at ground level, which ensures the creation of accurate conditions for view synthesis using diffusion networks. Moreover, we proposed a novel geospecific prior, which prompts distribution learning of diffusion models to respect image samples that are closer to the geolocation of the predicted images. We demonstrate our pipeline is the first to generate close-to-real and geospecific ground views merely based on satellite images.
Authors: Ali Hatamizadeh, Jan Kautz
Abstract: We propose a novel hybrid Mamba-Transformer backbone, denoted as MambaVision, which is specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. In addition, we conduct a comprehensive ablation study on the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results demonstrate that equipping the Mamba architecture with several self-attention blocks at the final layers greatly improves the modeling capacity to capture long-range spatial dependencies. Based on our findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria. For Image classification on ImageNet-1K dataset, MambaVision model variants achieve a new State-of-the-Art (SOTA) performance in terms of Top-1 accuracy and image throughput. In downstream tasks such as object detection, instance segmentation and semantic segmentation on MS COCO and ADE20K datasets, MambaVision outperforms comparably-sized backbones and demonstrates more favorable performance. Code: https://github.com/NVlabs/MambaVision.
Authors: Sunny Panchal, Apratim Bhattacharyya, Guillaume Berger, Antoine Mercier, Cornelius Bohm, Florian Dietrichkeit, Reza Pourreza, Xuanlin Li, Pulkit Madan, Mingu Lee, Mark Todorovich, Ingo Bax, Roland Memisevic
Abstract: Tasks at the intersection of vision and language have had a profound impact in advancing the capabilities of vision-language models such as dialog-based assistants. However, models trained on existing tasks are largely limited to turn-based interactions, where each turn must be stepped (i.e., prompted) by the user. Open-ended, asynchronous interactions where an AI model may proactively deliver timely responses or feedback based on the unfolding situation in real-time are an open challenge. In this work, we present the QEVD benchmark and dataset which explores human-AI interaction in the challenging, yet controlled, real-world domain of fitness coaching - a task which intrinsically requires monitoring live user activity and providing timely feedback. It is the first benchmark that requires assistive vision-language models to recognize complex human actions, identify mistakes grounded in those actions, and provide appropriate feedback. Our experiments reveal the limitations of existing state of the art vision-language models for such asynchronous situated interactions. Motivated by this, we propose a simple end-to-end streaming baseline that can respond asynchronously to human actions with appropriate feedbacks at the appropriate time.
Authors: Suqi Song, Chenxu Zhang, Peng Zhang, Pengkun Li, Fenglong Song, Lei Zhang
Abstract: Urban waterlogging poses a major risk to public safety and infrastructure. Conventional methods using water-level sensors need high-maintenance to hardly achieve full coverage. Recent advances employ surveillance camera imagery and deep learning for detection, yet these struggle amidst scarce data and adverse environmental conditions. In this paper, we establish a challenging Urban Waterlogging Benchmark (UW-Bench) under diverse adverse conditions to advance real-world applications. We propose a Large-Small Model co-adapter paradigm (LSM-adapter), which harnesses the substantial generic segmentation potential of large model and the specific task-directed guidance of small model. Specifically, a Triple-S Prompt Adapter module alongside a Dynamic Prompt Combiner are proposed to generate then merge multiple prompts for mask decoder adaptation. Meanwhile, a Histogram Equalization Adap-ter module is designed to infuse the image specific information for image encoder adaptation. Results and analysis show the challenge and superiority of our developed benchmark and algorithm. Project page: \url{https://github.com/zhang-chenxu/LSM-Adapter}
Authors: Byunggwan Son, Youngmin Oh, Donghyeon Baek, Bumsub Ham
Abstract: Dataset distillation synthesizes a small set of images from a large-scale real dataset such that synthetic and real images share similar behavioral properties (e.g, distributions of gradients or features) during a training process. Through extensive analyses on current methods and real datasets, together with empirical observations, we provide in this paper two important things to share for dataset distillation. First, object parts that appear on one side of a real image are highly likely to appear on the opposite side of another image within a dataset, which we call the bilateral equivalence. Second, the bilateral equivalence enforces synthetic images to duplicate discriminative parts of objects on both the left and right sides of the images, limiting the recognition of subtle differences between objects. To address this problem, we introduce a surprisingly simple yet effective technique for dataset distillation, dubbed FYI, that enables distilling rich semantics of real images into synthetic ones. To this end, FYI embeds a horizontal flipping technique into distillation processes, mitigating the influence of the bilateral equivalence, while capturing more details of objects. Experiments on CIFAR-10/100, Tiny-ImageNet, and ImageNet demonstrate that FYI can be seamlessly integrated into several state-of-the-art methods, without modifying training objectives and network architectures, and it improves the performance remarkably.
Authors: Shahriar Rezaie, Neda Saberitabar, Elnaz Salehi
Abstract: Deep learning has emerged as a transformative tool in healthcare, offering significant advancements in dental diagnostics by analyzing complex imaging data. This paper presents an enhanced ResNet50 architecture, integrated with the SimAM attention module, to address the challenge of limited contrast in dental images and optimize deep learning performance while mitigating computational demands. The SimAM module, incorporated after the second ResNet block, refines feature extraction by capturing spatial dependencies and enhancing significant features. Our model demonstrates superior performance across various feature extraction techniques, achieving an F1 score of 0.676 and outperforming traditional architectures such as VGG, EfficientNet, DenseNet, and AlexNet. This study highlights the effectiveness of our approach in improving classification accuracy and robustness in dental image analysis, underscoring the potential of deep learning to enhance diagnostic accuracy and efficiency in dental care. The integration of advanced AI models like ours is poised to revolutionize dental diagnostics, contributing to better patient outcomes and the broader adoption of AI in dentistry.
Authors: Yufan Liu, Wanqian Zhang, Dayan Wu, Zheng Lin, Jingzi Gu, Weiping Wang
Abstract: Model inversion (MI) attack reconstructs the private training data of a target model given its output, posing a significant threat to deep learning models and data privacy. On one hand, most of existing MI methods focus on searching for latent codes to represent the target identity, yet this iterative optimization-based scheme consumes a huge number of queries to the target model, making it unrealistic especially in black-box scenario. On the other hand, some training-based methods launch an attack through a single forward inference, whereas failing to directly learn high-level mappings from prediction vectors to images. Addressing these limitations, we propose a novel Prediction-to-Image (P2I) method for black-box MI attack. Specifically, we introduce the Prediction Alignment Encoder to map the target model's output prediction into the latent code of StyleGAN. In this way, prediction vector space can be well aligned with the more disentangled latent space, thus establishing a connection between prediction vectors and the semantic facial features. During the attack phase, we further design the Aligned Ensemble Attack scheme to integrate complementary facial attributes of target identity for better reconstruction. Experimental results show that our method outperforms other SOTAs, e.g.,compared with RLB-MI, our method improves attack accuracy by 8.5% and reduces query numbers by 99% on dataset CelebA.
Authors: Minghang Zhou, Tianyu Li, Chaofan Qiao, Dongyu Xie, Guoqing Wang, Ningjuan Ruan, Lin Mei, Yang Yang
Abstract: Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However, the quadratic computational complexity of transformers limits their performance. Inspired by the efficiency and lower complexity of Mamba in long sequence tasks, we propose Disparity-guided Multispectral Mamba (DMM), a multispectral oriented object detection framework comprised of a Disparity-guided Cross-modal Fusion Mamba (DCFM) module, a Multi-scale Target-aware Attention (MTA) module, and a Target-Prior Aware (TPA) auxiliary task. The DCFM module leverages disparity information between modalities to adaptively merge features from RGB and IR images, mitigating inter-modal conflicts. The MTA module aims to enhance feature representation by focusing on relevant target regions within the RGB modality, addressing intra-modal variations. The TPA auxiliary task utilizes single-modal labels to guide the optimization of the MTA module, ensuring it focuses on targets and their local context. Extensive experiments on the DroneVehicle and VEDAI datasets demonstrate the effectiveness of our method, which outperforms state-of-the-art methods while maintaining computational efficiency. Code will be available at https://github.com/Another-0/DMM.
Authors: Jianan Wei, Tianfei Zhou, Yi Yang, Wenguan Wang
Abstract: This work addresses a new challenge of understanding human nonverbal interaction in social contexts. Nonverbal signals pervade virtually every communicative act. Our gestures, facial expressions, postures, gaze, even physical appearance all convey messages, without anything being said. Despite their critical role in social life, nonverbal signals receive very limited attention as compared to the linguistic counterparts, and existing solutions typically examine nonverbal cues in isolation. Our study marks the first systematic effort to enhance the interpretation of multifaceted nonverbal signals. First, we contribute a novel large-scale dataset, called NVI, which is meticulously annotated to include bounding boxes for humans and corresponding social groups, along with 22 atomic-level nonverbal behaviors under five broad interaction types. Second, we establish a new task NVI-DET for nonverbal interaction detection, which is formalized as identifying triplets in the form
Authors: A. Noorizadegan, Y. C. Hon, D. L. Young, C. S. Chen
Abstract: Surface reconstruction from point clouds is a fundamental challenge in computer graphics and medical imaging. In this paper, we explore the application of advanced neural network architectures for the accurate and efficient reconstruction of surfaces from data points. We introduce a novel variant of the Highway network (Hw) called Square-Highway (SqrHw) within the context of multilayer perceptrons and investigate its performance alongside plain neural networks and a simplified Hw in various numerical examples. These examples include the reconstruction of simple and complex surfaces, such as spheres, human hands, and intricate models like the Stanford Bunny. We analyze the impact of factors such as the number of hidden layers, interior and exterior points, and data distribution on surface reconstruction quality. Our results show that the proposed SqrHw architecture outperforms other neural network configurations, achieving faster convergence and higher-quality surface reconstructions. Additionally, we demonstrate the SqrHw's ability to predict surfaces over missing data, a valuable feature for challenging applications like medical imaging. Furthermore, our study delves into further details, demonstrating that the proposed method based on highway networks yields more stable weight norms and backpropagation gradients compared to the Plain Network architecture. This research not only advances the field of computer graphics but also holds utility for other purposes such as function interpolation and physics-informed neural networks, which integrate multilayer perceptrons into their algorithms.
Authors: Zhiyuan Chen, Jiajiong Cao, Zhiquan Chen, Yuming Li, Chenguang Ma
Abstract: The area of portrait image animation, propelled by audio input, has witnessed notable progress in the generation of lifelike and dynamic portraits. Conventional methods are limited to utilizing either audios or facial key points to drive images into videos, while they can yield satisfactory results, certain issues exist. For instance, methods driven solely by audios can be unstable at times due to the relatively weaker audio signal, while methods driven exclusively by facial key points, although more stable in driving, can result in unnatural outcomes due to the excessive control of key point information. In addressing the previously mentioned challenges, in this paper, we introduce a novel approach which we named EchoMimic. EchoMimic is concurrently trained using both audios and facial landmarks. Through the implementation of a novel training strategy, EchoMimic is capable of generating portrait videos not only by audios and facial landmarks individually, but also by a combination of both audios and selected facial landmarks. EchoMimic has been comprehensively compared with alternative algorithms across various public datasets and our collected dataset, showcasing superior performance in both quantitative and qualitative evaluations. Additional visualization and access to the source code can be located on the EchoMimic project page.
Authors: Yonge Bai, LikHang Wong, TszYin Twan
Abstract: This survey aims to investigate fundamental deep learning (DL) based 3D reconstruction techniques that produce photo-realistic 3D models and scenes, highlighting Neural Radiance Fields (NeRFs), Latent Diffusion Models (LDM), and 3D Gaussian Splatting. We dissect the underlying algorithms, evaluate their strengths and tradeoffs, and project future research trajectories in this rapidly evolving field. We provide a comprehensive overview of the fundamental in DL-driven 3D scene reconstruction, offering insights into their potential applications and limitations.
Authors: Runmin Zhang, Jun Ma, Si-Yuan Cao, Lun Luo, Beinan Yu, Shu-Jie Chen, Junwei Li, Hui-Liang Shen
Abstract: We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal self-supervised learning is first presented to facilitate the unsupervised cross-modal homography estimation. The correlation-based homography estimation network and the consistent feature map projection are combined to form the learnable architecture of SCPNet, boosting the unsupervised learning framework. SCPNet is the first to achieve effective unsupervised homography estimation on the satellite-map image pair cross-modal dataset, GoogleMap, under [-32,+32] offset on a 128x128 image, leading the supervised approach MHN by 14.0% of mean average corner error (MACE). We further conduct extensive experiments on several cross-modal/spectral and manually-made inconsistent datasets, on which SCPNet achieves the state-of-the-art (SOTA) performance among unsupervised approaches, and owns 49.0%, 25.2%, 36.4%, and 10.7% lower MACEs than the supervised approach MHN. Source code is available at https://github.com/RM-Zhang/SCPNet.
Authors: Chenhao Li, Trung Thanh Ngo, Hajime Nagahara
Abstract: In this work, we propose a novel learning-based method to jointly estimate the shape and subsurface scattering (SSS) parameters of translucent objects by utilizing polarization cues. Although polarization cues have been used in various applications, such as shape from polarization (SfP), BRDF estimation, and reflection removal, their application in SSS estimation has not yet been explored. Our observations indicate that the SSS affects not only the light intensity but also the polarization signal. Hence, the polarization signal can provide additional cues for SSS estimation. We also introduce the first large-scale synthetic dataset of polarized translucent objects for training our model. Our method outperforms several baselines from the SfP and inverse rendering realms on both synthetic and real data, as demonstrated by qualitative and quantitative results.
Authors: Minghui Wu, Chenxu Zhao, Anyang Su, Donglin Di, Tianyu Fu, Da An, Min He, Ya Gao, Meng Ma, Kun Yan, Ping Wang
Abstract: Understanding of video creativity and content often varies among individuals, with differences in focal points and cognitive levels across different ages, experiences, and genders. There is currently a lack of research in this area, and most existing benchmarks suffer from several drawbacks: 1) a limited number of modalities and answers with restrictive length; 2) the content and scenarios within the videos are excessively monotonous, transmitting allegories and emotions that are overly simplistic. To bridge the gap to real-world applications, we introduce a large-scale \textbf{S}ubjective \textbf{R}esponse \textbf{I}ndicators for \textbf{A}dvertisement \textbf{V}ideos dataset, namely SRI-ADV. Specifically, we collected real changes in Electroencephalographic (EEG) and eye-tracking regions from different demographics while they viewed identical video content. Utilizing this multi-modal dataset, we developed tasks and protocols to analyze and evaluate the extent of cognitive understanding of video content among different users. Along with the dataset, we designed a \textbf{H}ypergraph \textbf{M}ulti-modal \textbf{L}arge \textbf{L}anguage \textbf{M}odel (HMLLM) to explore the associations among different demographics, video elements, EEG and eye-tracking indicators. HMLLM could bridge semantic gaps across rich modalities and integrate information beyond different modalities to perform logical reasoning. Extensive experimental evaluations on SRI-ADV and other additional video-based generative performance benchmarks demonstrate the effectiveness of our method. The codes and dataset will be released at \url{https://github.com/suay1113/HMLLM}.
Authors: Qiushi Guo
Abstract: Data augmentation remains a widely utilized technique in deep learning, particularly in tasks such as image classification, semantic segmentation, and object detection. Among them, Copy-Paste is a simple yet effective method and gain great attention recently. However, existing Copy-Paste often overlook contextual relevance between source and target images, resulting in inconsistencies in generated outputs. To address this challenge, we propose a context-aware approach that integrates Bidirectional Latent Information Propagation (BLIP) for content extraction from source images. By matching extracted content information with category information, our method ensures cohesive integration of target objects using Segment Anything Model (SAM) and You Only Look Once (YOLO). This approach eliminates the need for manual annotation, offering an automated and user-friendly solution. Experimental evaluations across diverse datasets demonstrate the effectiveness of our method in enhancing data diversity and generating high-quality pseudo-images across various computer vision tasks.
Authors: Xinyu Zhu, Zhiguo Jiang, Kun Wu, Jun Shi, Yushan Zheng
Abstract: Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database. However, in clinical practice, the continuously expanding size of WSI databases limits the practical application of the current CBHIR methods. In this paper, we propose a Lifelong Whole Slide Retrieval (LWSR) framework to address the challenges of catastrophic forgetting by progressive model updating on continuously growing retrieval database. Our framework aims to achieve the balance between stability and plasticity during continuous learning. To preserve system plasticity, we utilize local memory bank with reservoir sampling method to save instances, which can comprehensively encompass the feature spaces of both old and new tasks. Furthermore, A distance consistency rehearsal (DCR) module is designed to ensure the retrieval queue's consistency for previous tasks, which is regarded as stability within a lifelong CBHIR system. We evaluated the proposed method on four public WSI datasets from TCGA projects. The experimental results have demonstrated the proposed method is effective and is superior to the state-of-the-art methods.
Authors: Shixiong Xu, Chenghao Zhang, Lubin Fan, Gaofeng Meng, Shiming Xiang, Jieping Ye
Abstract: In this study, we introduce a new problem raised by social media and photojournalism, named Image Address Localization (IAL), which aims to predict the readable textual address where an image was taken. Existing two-stage approaches involve predicting geographical coordinates and converting them into human-readable addresses, which can lead to ambiguity and be resource-intensive. In contrast, we propose an end-to-end framework named AddressCLIP to solve the problem with more semantics, consisting of two key ingredients: i) image-text alignment to align images with addresses and scene captions by contrastive learning, and ii) image-geography matching to constrain image features with the spatial distance in terms of manifold learning. Additionally, we have built three datasets from Pittsburgh and San Francisco on different scales specifically for the IAL problem. Experiments demonstrate that our approach achieves compelling performance on the proposed datasets and outperforms representative transfer learning methods for vision-language models. Furthermore, extensive ablations and visualizations exhibit the effectiveness of the proposed method. The datasets and source code are available at https://github.com/xsx1001/AddressCLIP.
Authors: Owen Claxton, Connor Malone, Helen Carson, Jason Ford, Gabe Bolton, Iman Shames, Michael Milford
Abstract: Visual Place Recognition (VPR) systems often have imperfect performance, which affects robot navigation decisions. This research introduces a novel Multi-Layer Perceptron (MLP) integrity monitor for VPR which demonstrates improved performance and generalizability over the previous state-of-the-art SVM approach, removing per-environment training and reducing manual tuning requirements. We test our proposed system in extensive real-world experiments, where we also present two real-time integrity-based VPR verification methods: an instantaneous rejection method for a robot navigating to a goal zone (Experiment 1); and a historical method that takes a best, verified, match from its recent trajectory and uses an odometer to extrapolate forwards to a current position estimate (Experiment 2). Noteworthy results for Experiment 1 include a decrease in aggregate mean along-track goal error from ~9.8m to ~3.1m in missions the robot pursued to completion, and an increase in the aggregate rate of successful mission completion from ~41% to ~55%. Experiment 2 showed a decrease in aggregate mean along-track localization error from ~2.0m to ~0.5m, and an increase in the aggregate precision of localization attempts from ~97% to ~99%. Overall, our results demonstrate the practical usefulness of a VPR integrity monitor in real-world robotics to improve VPR localization and consequent navigation performance.
Authors: Ruijie Zhu, Chuxin Wang, Ziyang Song, Li Liu, Tianzhu Zhang, Yongdong Zhang
Abstract: Estimating depth from a single image is a challenging visual task. Compared to relative depth estimation, metric depth estimation attracts more attention due to its practical physical significance and critical applications in real-life scenarios. However, existing metric depth estimation methods are typically trained on specific datasets with similar scenes, facing challenges in generalizing across scenes with significant scale variations. To address this challenge, we propose a novel monocular depth estimation method called ScaleDepth. Our method decomposes metric depth into scene scale and relative depth, and predicts them through a semantic-aware scale prediction (SASP) module and an adaptive relative depth estimation (ARDE) module, respectively. The proposed ScaleDepth enjoys several merits. First, the SASP module can implicitly combine structural and semantic features of the images to predict precise scene scales. Second, the ARDE module can adaptively estimate the relative depth distribution of each image within a normalized depth space. Third, our method achieves metric depth estimation for both indoor and outdoor scenes in a unified framework, without the need for setting the depth range or fine-tuning model. Extensive experiments demonstrate that our method attains state-of-the-art performance across indoor, outdoor, unconstrained, and unseen scenes. Project page: https://ruijiezhu94.github.io/ScaleDepth
Authors: Rui Yin, Yulun Zhang, Zherong Pan, Jianjun Zhu, Cheng Wang, Biao Jia
Abstract: Two-view pose estimation is essential for map-free visual relocalization and object pose tracking tasks. However, traditional matching methods suffer from time-consuming robust estimators, while deep learning-based pose regressors only cater to camera-to-world pose estimation, lacking generalizability to different image sizes and camera intrinsics. In this paper, we propose SRPose, a sparse keypoint-based framework for two-view relative pose estimation in camera-to-world and object-to-camera scenarios. SRPose consists of a sparse keypoint detector, an intrinsic-calibration position encoder, and promptable prior knowledge-guided attention layers. Given two RGB images of a fixed scene or a moving object, SRPose estimates the relative camera or 6D object pose transformation. Extensive experiments demonstrate that SRPose achieves competitive or superior performance compared to state-of-the-art methods in terms of accuracy and speed, showing generalizability to both scenarios. It is robust to different image sizes and camera intrinsics, and can be deployed with low computing resources.
Authors: Shikun Xu, Yandong Zhu, Gen Li, Changhu Wang
Abstract: Soccer is one of the most popular sport worldwide, with live broadcasts frequently available for major matches. However, extracting detailed, frame-by-frame information on player actions from these videos remains a challenge. Utilizing state-of-the-art computer vision technologies, our system can detect key objects such as soccer balls, players and referees. It also tracks the movements of players and the ball, recognizes player numbers, classifies scenes, and identifies highlights such as goal kicks. By analyzing live TV streams of soccer matches, our system can generate highlight GIFs, tactical illustrations, and diverse summary graphs of ongoing games. Through these visual recognition techniques, we deliver a comprehensive understanding of soccer game videos, enriching the viewer's experience with detailed and insightful analysis.
Authors: Qin Lei, Jiang Zhong, Qizhu Dai
Abstract: Curvilinear object segmentation plays a crucial role across various applications, yet datasets in this domain often suffer from small scale due to the high costs associated with data acquisition and annotation. To address these challenges, this paper introduces a novel approach for expanding curvilinear object segmentation datasets, focusing on enhancing the informativeness of generated data and the consistency between semantic maps and generated images. Our method enriches synthetic data informativeness by generating curvilinear objects through their multiple textual features. By combining textual features from each sample in original dataset, we obtain synthetic images that beyond the original dataset's distribution. This initiative necessitated the creation of the Curvilinear Object Segmentation based on Text Generation (COSTG) dataset. Designed to surpass the limitations of conventional datasets, COSTG incorporates not only standard semantic maps but also some textual descriptions of curvilinear object features. To ensure consistency between synthetic semantic maps and images, we introduce the Semantic Consistency Preserving ControlNet (SCP ControlNet). This involves an adaptation of ControlNet with Spatially-Adaptive Normalization (SPADE), allowing it to preserve semantic information that would typically be washed away in normalization layers. This modification facilitates more accurate semantic image synthesis. Experimental results demonstrate the efficacy of our approach across three types of curvilinear objects (angiography, crack and retina) and six public datasets (CHUAC, XCAD, DCA1, DRIVE, CHASEDB1 and Crack500). The synthetic data generated by our method not only expand the dataset, but also effectively improves the performance of other curvilinear object segmentation models. Source code and dataset are available at \url{https://github.com/tanlei0/COSTG}.
Authors: Vinayak Gupta, Rongali Simhachala Venkata Girish, Mukund Varma T, Ayush Tewari, Kaushik Mitra
Abstract: Neural rendering methods can achieve near-photorealistic image synthesis of scenes from posed input images. However, when the images are imperfect, e.g., captured in very low-light conditions, state-of-the-art methods fail to reconstruct high-quality 3D scenes. Recent approaches have tried to address this limitation by modeling various degradation processes in the image formation model; however, this limits them to specific image degradations. In this paper, we propose a generalizable neural rendering method that can perform high-fidelity novel view synthesis under several degradations. Our method, GAURA, is learning-based and does not require any test-time scene-specific optimization. It is trained on a synthetic dataset that includes several degradation types. GAURA outperforms state-of-the-art methods on several benchmarks for low-light enhancement, dehazing, deraining, and on-par for motion deblurring. Further, our model can be efficiently fine-tuned to any new incoming degradation using minimal data. We thus demonstrate adaptation results on two unseen degradations, desnowing and removing defocus blur. Code and video results are available at vinayak-vg.github.io/GAURA.
Authors: Jinxiu Liang, Bohan Yu, Yixin Yang, Yiming Han, Boxin Shi
Abstract: Event cameras, mimicking the human retina, capture brightness changes with unparalleled temporal resolution and dynamic range. Integrating events into intensities poses a highly ill-posed challenge, marred by initial condition ambiguities. Traditional regression-based deep learning methods fall short in perceptual quality, offering deterministic and often unrealistic reconstructions. In this paper, we introduce diffusion models to events-to-video reconstruction, achieving colorful, realistic, and perceptually superior video generation from achromatic events. Powered by the image generation ability and knowledge of pretrained diffusion models, the proposed method can achieve a better trade-off between the perception and distortion of the reconstructed frame compared to previous solutions. Extensive experiments on benchmark datasets demonstrate that our approach can produce diverse, realistic frames with faithfulness to the given events.
Authors: Jingyi Yang, Zitong Yu, Xiuming Ni, Jia He, Hui Li
Abstract: Face anti-spoofing techniques based on domain generalization have recently been studied widely. Adversarial learning and meta-learning techniques have been adopted to learn domain-invariant representations. However, prior approaches often consider the dataset gap as the primary factor behind domain shifts. This perspective is not fine-grained enough to reflect the intrinsic gap among the data accurately. In our work, we redefine domains based on identities rather than datasets, aiming to disentangle liveness and identity attributes. We emphasize ignoring the adverse effect of identity shift, focusing on learning identity-invariant liveness representations through orthogonalizing liveness and identity features. To cope with style shifts, we propose Style Cross module to expand the stylistic diversity and Channel-wise Style Attention module to weaken the sensitivity to style shifts, aiming to learn robust liveness representations. Furthermore, acknowledging the asymmetry between live and spoof samples, we introduce a novel contrastive loss, Asymmetric Augmented Instance Contrast. Extensive experiments on four public datasets demonstrate that our method achieves state-of-the-art performance under cross-dataset and limited source dataset scenarios. Additionally, our method has good scalability when expanding diversity of identities. The codes will be released soon.
Authors: Dongliang Cao, Zorah Laehner, Florian Bernard
Abstract: Most recent unsupervised non-rigid 3D shape matching methods are based on the functional map framework due to its efficiency and superior performance. Nevertheless, respective methods struggle to obtain spatially smooth pointwise correspondences due to the lack of proper regularisation. In this work, inspired by the success of message passing on graphs, we propose a synchronous diffusion process which we use as regularisation to achieve smoothness in non-rigid 3D shape matching problems. The intuition of synchronous diffusion is that diffusing the same input function on two different shapes results in consistent outputs. Using different challenging datasets, we demonstrate that our novel regularisation can substantially improve the state-of-the-art in shape matching, especially in the presence of topological noise.
Authors: Aitao Yang, Min Li, Yao Ding, Leyuan Fang, Yaoming Cai, Yujie He
Abstract: Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification. In terms of spectral sequence feature capture, RNN and Transformer have become mainstream classification frameworks due to their long-range feature capture capabilities. In terms of spatial information aggregation, CNN enhances the receptive field to retain integrated spatial information as much as possible. However, the spectral feature-capturing architectures exhibit low computational efficiency, and CNNs lack the flexibility to perceive spatial contextual information. To address these issues, this paper proposes GraphMamba--an efficient graph structure learning vision Mamba classification framework that fully considers HSI characteristics to achieve deep spatial-spectral information mining. Specifically, we propose a novel hyperspectral visual GraphMamba processing paradigm (HVGM) that preserves spatial-spectral features by constructing spatial-spectral cubes and utilizes linear spectral encoding to enhance the operability of subsequent tasks. The core components of GraphMamba include the HyperMamba module for improving computational efficiency and the SpectralGCN module for adaptive spatial context awareness. The HyperMamba mitigates clutter interference by employing the global mask (GM) and introduces a parallel training inference architecture to alleviate computational bottlenecks. The SpatialGCN incorporates weighted multi-hop aggregation (WMA) spatial encoding to focus on highly correlated spatial structural features, thus flexibly aggregating contextual information while mitigating spatial noise interference. Extensive experiments were conducted on three different scales of real HSI datasets, and compared with the state-of-the-art classification frameworks, GraphMamba achieved optimal performance.
Authors: Seonwhee Jin
Abstract: Models based on convolutional neural networks (CNN) and transformers have steadily been improved. They also have been applied in various computer vision downstream tasks. However, in object detection tasks, accurately localizing and classifying almost infinite categories of foods in images remains challenging. To address these problems, we first segmented the food as the region-of-interest (ROI) by using the segment-anything model (SAM) and masked the rest of the region except ROI as black pixels. This process simplified the problems into a single classification for which annotation and training were much simpler than object detection. The images in which only the ROI was preserved were fed as inputs to fine-tune various off-the-shelf models that encoded their own inductive biases. Among them, Data-efficient image Transformers (DeiTs) had the best classification performance. Nonetheless, when foods' shapes and textures were similar, the contextual features of the ROI-only images were not enough for accurate classification. Therefore, we introduced a novel type of combined architecture, RveRNet, which consisted of ROI, extra-ROI, and integration modules that allowed it to account for both the ROI's and global contexts. The RveRNet's F1 score was 10% better than other individual models when classifying ambiguous food images. If the RveRNet's modules were DeiT with the knowledge distillation from the CNN, performed the best. We investigated how architectures can be made robust against input noise caused by permutation and translocation. The results indicated that there was a trade-off between how much the CNN teacher's knowledge could be distilled to DeiT and DeiT's innate strength. Code is publicly available at: https://github.com/Seonwhee-Genome/RveRNet.
Authors: Raktim Gautam Goswami, Naman Patel, Prashanth Krishnamurthy, Farshad Khorrami
Abstract: Large-scale LiDAR mappings and localization leverage place recognition techniques to mitigate odometry drifts, ensuring accurate mapping. These techniques utilize scene representations from LiDAR point clouds to identify previously visited sites within a database. Local descriptors, assigned to each point within a point cloud, are aggregated to form a scene representation for the point cloud. These descriptors are also used to re-rank the retrieved point clouds based on geometric fitness scores. We propose SALSA, a novel, lightweight, and efficient framework for LiDAR place recognition. It consists of a Sphereformer backbone that uses radial window attention to enable information aggregation for sparse distant points, an adaptive self-attention layer to pool local descriptors into tokens, and a multi-layer-perceptron Mixer layer for aggregating the tokens to generate a scene descriptor. The proposed framework outperforms existing methods on various LiDAR place recognition datasets in terms of both retrieval and metric localization while operating in real-time.
Authors: Miao Yan, Ping Zhang, Haofei Zhang, Ruqian Hao, Juanxiu Liu, Xiaoyang Wang, Lin Liu
Abstract: Thermal infrared tracking is an essential topic in computer vision tasks because of its advantage of all-weather imaging. However, most conventional methods utilize only hand-crafted features, while deep learning-based correlation filtering methods are limited by simple correlation operations. Transformer-based methods ignore temporal and coordinate information, which is critical for TIR tracking that lacks texture and color information. In this paper, to address these issues, we apply natural language modeling to TIR tracking and propose a novel model called NLMTrack, which enhances the utilization of coordinate and temporal information. NLMTrack applies an encoder that unifies feature extraction and feature fusion, which simplifies the TIR tracking pipeline. To address the challenge of low detail and low contrast in TIR images, on the one hand, we design a multi-level progressive fusion module that enhances the semantic representation and incorporates multi-scale features. On the other hand, the decoder combines the TIR features and the coordinate sequence features using a causal transformer to generate the target sequence step by step. Moreover, we explore an adaptive loss aimed at elevating tracking accuracy and a simple template update strategy to accommodate the target's appearance variations. Experiments show that NLMTrack achieves state-of-the-art performance on multiple benchmarks. The Code is publicly available at \url{https://github.com/ELOESZHANG/NLMTrack}.
Authors: Tong Shao, Zhuotao Tian, Hang Zhao, Jingyong Su
Abstract: CLIP, as a vision-language model, has significantly advanced Open-Vocabulary Semantic Segmentation (OVSS) with its zero-shot capabilities. Despite its success, its application to OVSS faces challenges due to its initial image-level alignment training, which affects its performance in tasks requiring detailed local context. Our study delves into the impact of CLIP's [CLS] token on patch feature correlations, revealing a dominance of "global" patches that hinders local feature discrimination. To overcome this, we propose CLIPtrase, a novel training-free semantic segmentation strategy that enhances local feature awareness through recalibrated self-correlation among patches. This approach demonstrates notable improvements in segmentation accuracy and the ability to maintain semantic coherence across objects.Experiments show that we are 22.3% ahead of CLIP on average on 9 segmentation benchmarks, outperforming existing state-of-the-art training-free methods.The code are made publicly available at: https://github.com/leaves162/CLIPtrase.
Authors: Dominika Przewlocka-Rus, Tomasz Kryjak, Marek Gorgon
Abstract: The performance of object detection systems in automotive solutions must be as high as possible, with minimal response time and, due to the often battery-powered operation, low energy consumption. When designing such solutions, we therefore face challenges typical for embedded vision systems: the problem of fitting algorithms of high memory and computational complexity into small low-power devices. In this paper we propose PowerYOLO - a mixed precision solution, which targets three essential elements of such application. First, we propose a system based on a Dynamic Vision Sensor (DVS), a novel sensor, that offers low power requirements and operates well in conditions with variable illumination. It is these features that may make event cameras a preferential choice over frame cameras in some applications. Second, to ensure high accuracy and low memory and computational complexity, we propose to use 4-bit width Powers-of-Two (PoT) quantisation for convolution weights of the YOLO detector, with all other parameters quantised linearly. Finally, we embrace from PoT scheme and replace multiplication with bit-shifting to increase the efficiency of hardware acceleration of such solution, with a special convolution-batch normalisation fusion scheme. The use of specific sensor with PoT quantisation and special batch normalisation fusion leads to a unique system with almost 8x reduction in memory complexity and vast computational simplifications, with relation to a standard approach. This efficient system achieves high accuracy of mAP 0.301 on the GEN1 DVS dataset, marking the new state-of-the-art for such compressed model.
Authors: Marcel Vosshans, Omar Ait-Aider, Youcef Mezouar, Markus Enzweiler
Abstract: In this work, we present a novel approach for general object segmentation from a monocular image, eliminating the need for manually labeled training data and enabling rapid, straightforward training and adaptation with minimal data. Our model initially learns from LiDAR during the training process, which is subsequently removed from the system, allowing it to function solely on monocular imagery. This study leverages the concept of the Stixel-World to recognize a medium level representation of its surroundings. Our network directly predicts a 2D multi-layer Stixel-World and is capable of recognizing and locating multiple, superimposed objects within an image. Due to the scarcity of comparable works, we have divided the capabilities into modules and present a free space detection in our experiments section. Furthermore, we introduce an improved method for generating Stixels from LiDAR data, which we use as ground truth for our network.
Authors: Jannik Z\"urn, Paul Gladkov, Sof\'ia Dudas, Fergal Cotter, Sofi Toteva, Jamie Shotton, Vasiliki Simaiaki, Nikhil Mohan
Abstract: We present WayveScenes101, a dataset designed to help the community advance the state of the art in novel view synthesis that focuses on challenging driving scenes containing many dynamic and deformable elements with changing geometry and texture. The dataset comprises 101 driving scenes across a wide range of environmental conditions and driving scenarios. The dataset is designed for benchmarking reconstructions on in-the-wild driving scenes, with many inherent challenges for scene reconstruction methods including image glare, rapid exposure changes, and highly dynamic scenes with significant occlusion. Along with the raw images, we include COLMAP-derived camera poses in standard data formats. We propose an evaluation protocol for evaluating models on held-out camera views that are off-axis from the training views, specifically testing the generalisation capabilities of methods. Finally, we provide detailed metadata for all scenes, including weather, time of day, and traffic conditions, to allow for a detailed model performance breakdown across scene characteristics. Dataset and code are available at https://github.com/wayveai/wayve_scenes.
Authors: Yu Feng, Yiming Xu, Yan Xia, Claus Brenner, Monika Sester
Abstract: Recent advances in mobile mapping systems have greatly enhanced the efficiency and convenience of acquiring urban 3D data. These systems utilize LiDAR sensors mounted on vehicles to capture vast cityscapes. However, a significant challenge arises due to occlusions caused by roadside parked vehicles, leading to the loss of scene information, particularly on the roads, sidewalks, curbs, and the lower sections of buildings. In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion. We have developed an innovative technique where we place virtual vehicle models along road boundaries in the gap-free scene and utilize a ray-casting algorithm to create a new scene with occluded gaps. This allows us to generate diverse and realistic urban point cloud scenes with and without vehicle occlusion, surpassing the limitations of real-world training data collection and annotation. Furthermore, we introduce the Scene Gap Completion Network (SGC-Net), an end-to-end model that can generate well-defined shape boundaries and smooth surfaces within occluded gaps. The experiment results reveal that 97.66% of the filled points fall within a range of 5 centimeters relative to the high-density ground truth point cloud scene. These findings underscore the efficacy of our proposed model in gap completion and reconstructing urban scenes affected by vehicle occlusions.
Authors: Hiba Najjar, Francisco Mena, Marlon Nuske, Andreas Dengel
Abstract: Vegetation indices allow to efficiently monitor vegetation growth and agricultural activities. Previous generations of satellites were capturing a limited number of spectral bands, and a few expert-designed vegetation indices were sufficient to harness their potential. New generations of multi- and hyperspectral satellites can however capture additional bands, but are not yet efficiently exploited. In this work, we propose an explainable-AI-based method to select and design suitable vegetation indices. We first train a deep neural network using multispectral satellite data, then extract feature importance to identify the most influential bands. We subsequently select suitable existing vegetation indices or modify them to incorporate the identified bands and retrain our model. We validate our approach on a crop classification task. Our results indicate that models trained on individual indices achieve comparable results to the baseline model trained on all bands, while the combination of two indices surpasses the baseline in certain cases.
Authors: Xiaotong Li, Fan Zhang, Haiwen Diao, Yueze Wang, Xinlong Wang, Ling-Yu Duan
Abstract: Existing Multimodal Large Language Models (MLLMs) increasingly emphasize complex understanding of various visual elements, including multiple objects, text information, and spatial relations. Their development for comprehensive visual perception hinges on the availability of high-quality image-text datasets that offer diverse visual elements and throughout image descriptions. However, the scarcity of such hyper-detailed datasets currently hinders progress within the MLLM community. The bottleneck stems from the limited perceptual capabilities of current caption engines, which fall short in providing complete and accurate annotations. To facilitate the cutting-edge research of MLLMs on comprehensive vision perception, we thereby propose Perceptual Fusion, using a low-budget but highly effective caption engine for complete and accurate image descriptions. Specifically, Perceptual Fusion integrates diverse perception experts as image priors to provide explicit information on visual elements and adopts an efficient MLLM as a centric pivot to mimic advanced MLLMs' perception abilities. We carefully select 1M highly representative images from uncurated LAION dataset and generate dense descriptions using our engine, dubbed DenseFusion-1M. Extensive experiments validate that our engine outperforms its counterparts, where the resulting dataset significantly improves the perception and cognition abilities of existing MLLMs across diverse vision-language benchmarks, especially with high-resolution images as inputs. The dataset and code are publicly available at https://github.com/baaivision/DenseFusion.
Authors: Rui Cao, Jiangliu Wang, Yun-Hui Liu
Abstract: Surgical phase recognition is crucial for enhancing the efficiency and safety of computer-assisted interventions. One of the fundamental challenges involves modeling the long-distance temporal relationships present in surgical videos. Inspired by the recent success of Mamba, a state space model with linear scalability in sequence length, this paper presents SR-Mamba, a novel attention-free model specifically tailored to meet the challenges of surgical phase recognition. In SR-Mamba, we leverage a bidirectional Mamba decoder to effectively model the temporal context in overlong sequences. Moreover, the efficient optimization of the proposed Mamba decoder facilitates single-step neural network training, eliminating the need for separate training steps as in previous works. This single-step training approach not only simplifies the training process but also ensures higher accuracy, even with a lighter spatial feature extractor. Our SR-Mamba establishes a new benchmark in surgical video analysis by demonstrating state-of-the-art performance on the Cholec80 and CATARACTS Challenge datasets. The code is accessible at https://github.com/rcao-hk/SR-Mamba.
Authors: Yuho Shoji, Yuka Ogino, Takahiro Toizumi, Atsushi Ito
Abstract: This paper proposes a deep feature extractor for iris recognition at arbitrary resolutions. Resolution degradation reduces the recognition performance of deep learning models trained by high-resolution images. Using various-resolution images for training can improve the model's robustness while sacrificing recognition performance for high-resolution images. To achieve higher recognition performance at various resolutions, we propose a method of resolution-adaptive feature extraction with automatically switching networks. Our framework includes resolution expert modules specialized for different resolution degradations, including down-sampling and out-of-focus blurring. The framework automatically switches them depending on the degradation condition of an input image. Lower-resolution experts are trained by knowledge-distillation from the high-resolution expert in such a manner that both experts can extract common identity features. We applied our framework to three conventional neural network models. The experimental results show that our method enhances the recognition performance at low-resolution in the conventional methods and also maintains their performance at high-resolution.
Authors: Yashwanth Rao, Gaurisankar S, Durga R, Aparna Purayath, Vivek Maik, Manojkumar Lakshmanan, Mohanasankar Sivaprakasm
Abstract: In this paper, we propose an innovative Graphical User Interface (GUI) aimed at improving preoperative planning and intra-operative guidance for precise spinal screw placement through vertebrae segmentation. The methodology encompasses both front-end and back-end computations. The front end comprises a GUI that allows surgeons to precisely adjust the placement of screws on X-Ray images, thereby improving the simulation of surgical screw insertion in the patient's spine. On the other hand, the back-end processing involves several steps, including acquiring spinal X-ray images, performing pre-processing techniques to reduce noise, and training a neural network model to achieve real-time segmentation of the vertebrae. The integration of vertebral segmentation in the GUI ensures precise screw placement, reducing complications like nerve injury and ultimately improving surgical outcomes. The Spine-Vision provides a comprehensive solution with innovative features like synchronous AP-LP planning, accurate screw positioning via vertebrae segmentation, effective screw visualization, and dynamic position adjustments. This X-ray image-based GUI workflow emerges as a valuable tool, enhancing precision and safety in spinal screw placement and planning procedures.
Authors: Tomasz Kryjak
Abstract: In recent years there has been a growing interest in event cameras, i.e. vision sensors that record changes in illumination independently for each pixel. This type of operation ensures that acquisition is possible in very adverse lighting conditions, both in low light and high dynamic range, and reduces average power consumption. In addition, the independent operation of each pixel results in low latency, which is desirable for robotic solutions. Nowadays, Field Programmable Gate Arrays (FPGAs), along with general-purpose processors (GPPs/CPUs) and programmable graphics processing units (GPUs), are popular architectures for implementing and accelerating computing tasks. In particular, their usefulness in the embedded vision domain has been repeatedly demonstrated over the past 30 years, where they have enabled fast data processing (even in real-time) and energy efficiency. Hence, the combination of event cameras and reconfigurable devices seems to be a good solution, especially in the context of energy-efficient real-time embedded systems. This paper gives an overview of the most important works, where FPGAs have been used in different contexts to process event data. It covers applications in the following areas: filtering, stereovision, optical flow, acceleration of AI-based algorithms (including spiking neural networks) for object classification, detection and tracking, and applications in robotics and inspection systems. Current trends and challenges for such systems are also discussed.
Authors: Ilya Trofimov, Daria Voronkova, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov
Abstract: We propose a new topological tool for computer vision - Scalar Function Topology Divergence (SFTD), which measures the dissimilarity of multi-scale topology between sublevel sets of two functions having a common domain. Functions can be defined on an undirected graph or Euclidean space of any dimensionality. Most of the existing methods for comparing topology are based on Wasserstein distance between persistence barcodes and they don't take into account the localization of topological features. On the other hand, the minimization of SFTD ensures that the corresponding topological features of scalar functions are located in the same places. The proposed tool provides useful visualizations depicting areas where functions have topological dissimilarities. We provide applications of the proposed method to 3D computer vision. In particular, experiments demonstrate that SFTD improves the reconstruction of cellular 3D shapes from 2D fluorescence microscopy images, and helps to identify topological errors in 3D segmentation.
Authors: Jinlong Li, Zequn Jie, Elisa Ricci, Lin Ma, Nicu Sebe
Abstract: Efficient finetuning of vision-language models (VLMs) like CLIP for specific downstream tasks is gaining significant attention. Previous works primarily focus on prompt learning to adapt the CLIP into a variety of downstream tasks, however, suffering from task overfitting when finetuned on a small data set. In this paper, we introduce an orthogonal finetuning method for efficiently updating pretrained weights which enhances robustness and generalization, while a cross-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed \textbf{\textit{OrthCR}}. Specifically, trainable orthogonal matrices are injected seamlessly into the transformer architecture and enforced with orthogonality constraint using Cayley parameterization, benefiting from the norm-preserving property and thus leading to stable and faster convergence. To alleviate deviation from orthogonal constraint during training, a cross-regularization strategy is further employed with initial pretrained weights within a bypass manner. In addition, to enrich the sample diversity for downstream tasks, we first explore Cutout data augmentation to boost the efficient finetuning and comprehend how our approach improves the specific downstream performance and maintains the generalizability in the perspective of Orthogonality Learning. Beyond existing prompt learning techniques, we conduct extensive experiments to demonstrate that our method explicitly steers pretrained weight space to represent the task-specific knowledge and presents competitive generalizability under \textit{base-to-base/base-to-new}, \textit{cross-dataset transfer} and \textit{domain generalization} evaluations.
Authors: Shengqi Xu, Run Sun, Yi Chang, Shuning Cao, Xueyao Xiao, Luxin Yan
Abstract: Long-range imaging inevitably suffers from atmospheric turbulence with severe geometric distortions due to random refraction of light. The further the distance, the more severe the disturbance. Despite existing research has achieved great progress in tackling short-range turbulence, there is less attention paid to long-range turbulence with significant distortions. To address this dilemma and advance the field, we construct a large-scale real long-range atmospheric turbulence dataset (RLR-AT), including 1500 turbulence sequences spanning distances from 1 Km to 13 Km. The advantages of RLR-AT compared to existing ones: turbulence with longer-distances and higher-diversity, scenes with greater-variety and larger-scale. Moreover, most existing work adopts either registration-based or decomposition-based methods to address distortions through one-step mitigation. However, they fail to effectively handle long-range turbulence due to its significant pixel displacements. In this work, we propose a coarse-to-fine framework to handle severe distortions, which cooperates dynamic turbulence and static background priors (CDSP). On the one hand, we discover the pixel motion statistical prior of turbulence, and propose a frequency-aware reference frame for better large-scale distortion registration, greatly reducing the burden of refinement. On the other hand, we take advantage of the static prior of background, and propose a subspace-based low-rank tensor refinement model to eliminate the misalignments inevitably left by registration while well preserving details. The dynamic and static priors complement to each other, facilitating us to progressively mitigate long-range turbulence with severe distortions. Extensive experiments demonstrate that the proposed method outperforms SOTA methods on different datasets.
Authors: Antonio Hern\'andez Mart\'inez, Iv\'an Garc\'ia Daza, Carlos Fern\'andez L\'opez, David Fern\'andez Llorca
Abstract: Accurate vision-based speed estimation is much more cost-effective than traditional methods based on radar or LiDAR. However, it is also challenging due to the limitations of perspective projection on a discrete sensor, as well as the high sensitivity to calibration, lighting and weather conditions. Interestingly, deep learning approaches (which dominate the field of computer vision) are very limited in this context due to the lack of available data. Indeed, obtaining video sequences of real road traffic with accurate speed values associated with each vehicle is very complex and costly, and the number of available datasets is very limited. Recently, some approaches are focusing on the use of synthetic data. However, it is still unclear how models trained on synthetic data can be effectively applied to real world conditions. In this work, we propose the use of digital-twins using CARLA simulator to generate a large dataset representative of a specific real-world camera. The synthetic dataset contains a large variability of vehicle types, colours, speeds, lighting and weather conditions. A 3D CNN model is trained on the digital twin and tested on the real sequences. Unlike previous approaches that generate multi-camera sequences, we found that the gap between the the real and the virtual conditions is a key factor in obtaining low speed estimation errors. Even with a preliminary approach, the mean absolute error obtained remains below 3km/h.
Authors: Zhengbo Zhang, Li Xu, Duo Peng, Hossein Rahmani, Jun Liu
Abstract: We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained diffusion model, such as the understanding of image semantics and structural information, to address unsupervised visual tracking. To this end, we design an initial prompt learner to enable the diffusion model to recognize the tracking target by learning a prompt representing the target. Furthermore, to facilitate dynamic adaptation of the prompt to the target's movements, we propose an online prompt updater. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our proposed method, which also achieves state-of-the-art performance.
Authors: Sarah Rockstrok, Patrick Frenzel, Daniel Matthes, Kay Schubert, David Wollburg, Mirco Fuchs
Abstract: Assessing an athlete's performance in canoe sprint is often established by measuring a variety of kinematic parameters during training sessions. Many of these parameters are related to single or multiple paddle stroke cycles. Determining on- and offset of these cycles in force sensor signals is usually not straightforward and requires human interaction. This paper explores convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in terms of their ability to automatically predict these events. In addition, our work proposes an extension to the recently published SoftED metric for event detection in order to properly assess the model performance on time windows. In our results, an RNN based on bidirectional gated recurrent units (BGRUs) turned out to be the most suitable model for paddle stroke detection.
Authors: Shishir Muralidhara, Saqib Bukhari, Georg Schneider, Didier Stricker, Ren\'e Schuster
Abstract: Continual learning (CL) addresses the problem of catastrophic forgetting in neural networks, which occurs when a trained model tends to overwrite previously learned information, when presented with a new task. CL aims to instill the lifelong learning characteristic of humans in intelligent systems, making them capable of learning continuously while retaining what was already learned. Current CL problems involve either learning new domains (domain-incremental) or new and previously unseen classes (class-incremental). However, general learning processes are not just limited to learning information, but also refinement of existing information. In this paper, we define CLEO - Continual Learning of Evolving Ontologies, as a new incremental learning setting under CL to tackle evolving classes. CLEO is motivated by the need for intelligent systems to adapt to real-world ontologies that change over time, such as those in autonomous driving. We use Cityscapes, PASCAL VOC, and Mapillary Vistas to define the task settings and demonstrate the applicability of CLEO. We highlight the shortcomings of existing CIL methods in adapting to CLEO and propose a baseline solution, called Modelling Ontologies (MoOn). CLEO is a promising new approach to CL that addresses the challenge of evolving ontologies in real-world applications. MoOn surpasses previous CL approaches in the context of CLEO.
Authors: Yushuo Chen, Zerong Zheng, Zhe Li, Chao Xu, Yebin Liu
Abstract: We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos. Recent methods for avatar learning are typically based on neural radiance fields (NeRF), which is not compatible with traditional graphics pipeline and poses great challenges for operations like editing or synthesizing under different environments. To overcome these limitations, our method represents the avatar with an explicit triangular mesh extracted from an implicit SDF field, complemented by an implicit material field conditioned on given poses. Leveraging this triangular avatar representation, we incorporate physics-based rendering to accurately decompose geometry and texture. To enhance both the geometric and appearance details, we further employ a 2D UNet as the network backbone and introduce pseudo normal ground-truth as additional supervision. Experiments show that our method can learn triangular avatars with high-quality geometry reconstruction and plausible material decomposition, inherently supporting editing, manipulation or relighting operations.
Authors: Wentao Lei, Jinting Wang, Fengji Ma, Guanjie Huang, Li Liu
Abstract: Human video generation is a dynamic and rapidly evolving task that aims to synthesize 2D human body video sequences with generative models given control conditions such as text, audio, and pose. With the potential for wide-ranging applications in film, gaming, and virtual communication, the ability to generate natural and realistic human video is critical. Recent advancements in generative models have laid a solid foundation for the growing interest in this area. Despite the significant progress, the task of human video generation remains challenging due to the consistency of characters, the complexity of human motion, and difficulties in their relationship with the environment. This survey provides a comprehensive review of the current state of human video generation, marking, to the best of our knowledge, the first extensive literature review in this domain. We start with an introduction to the fundamentals of human video generation and the evolution of generative models that have facilitated the field's growth. We then examine the main methods employed for three key sub-tasks within human video generation: text-driven, audio-driven, and pose-driven motion generation. These areas are explored concerning the conditions that guide the generation process. Furthermore, we offer a collection of the most commonly utilized datasets and the evaluation metrics that are crucial in assessing the quality and realism of generated videos. The survey concludes with a discussion of the current challenges in the field and suggests possible directions for future research. The goal of this survey is to offer the research community a clear and holistic view of the advancements in human video generation, highlighting the milestones achieved and the challenges that lie ahead.
Authors: Mengtian Li, Chengshuo Zhai, Shengxiang Yao, Zhifeng Xie, Keyu Chen Yu-Gang Jiang
Abstract: In the realm of motion generation, the creation of long-duration, high-quality motion sequences remains a significant challenge. This paper presents our groundbreaking work on "Infinite Motion", a novel approach that leverages long text to extended motion generation, effectively bridging the gap between short and long-duration motion synthesis. Our core insight is the strategic extension and reassembly of existing high-quality text-motion datasets, which has led to the creation of a novel benchmark dataset to facilitate the training of models for extended motion sequences. A key innovation of our model is its ability to accept arbitrary lengths of text as input, enabling the generation of motion sequences tailored to specific narratives or scenarios. Furthermore, we incorporate the timestamp design for text which allows precise editing of local segments within the generated sequences, offering unparalleled control and flexibility in motion synthesis. We further demonstrate the versatility and practical utility of "Infinite Motion" through three specific applications: natural language interactive editing, motion sequence editing within long sequences and splicing of independent motion sequences. Each application highlights the adaptability of our approach and broadens the spectrum of possibilities for research and development in motion generation. Through extensive experiments, we demonstrate the superior performance of our model in generating long sequence motions compared to existing methods.Project page: https://shuochengzhai.github.io/Infinite-motion.github.io/
URLs: https://shuochengzhai.github.io/Infinite-motion.github.io/
Authors: Jonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys, Torsten Sattler
Abstract: While the field of 3D scene reconstruction is dominated by NeRFs due to their photorealistic quality, 3D Gaussian Splatting (3DGS) has recently emerged, offering similar quality with real-time rendering speeds. However, both methods primarily excel with well-controlled 3D scenes, while in-the-wild data - characterized by occlusions, dynamic objects, and varying illumination - remains challenging. NeRFs can adapt to such conditions easily through per-image embedding vectors, but 3DGS struggles due to its explicit representation and lack of shared parameters. To address this, we introduce WildGaussians, a novel approach to handle occlusions and appearance changes with 3DGS. By leveraging robust DINO features and integrating an appearance modeling module within 3DGS, our method achieves state-of-the-art results. We demonstrate that WildGaussians matches the real-time rendering speed of 3DGS while surpassing both 3DGS and NeRF baselines in handling in-the-wild data, all within a simple architectural framework.
Authors: Delong Wu, Hao Zhu, Qi Zhang, You Li, Zhan Ma, Xun Cao
Abstract: Implicit Neural Representation (INR) has become a popular method for representing visual signals (e.g., 2D images and 3D scenes), demonstrating promising results in various downstream applications. Given its potential as a medium for visual signals, exploring the development of a neural blending method that utilizes INRs is a natural progression. Neural blending involves merging two INRs to create a new INR that encapsulates information from both original representations. A direct approach involves applying traditional image editing methods to the INR rendering process. However, this method often results in blending distortions, artifacts, and color shifts, primarily due to the discretization of the underlying pixel grid and the introduction of boundary conditions for solving variational problems. To tackle this issue, we introduce the Neural Poisson Solver, a plug-and-play and universally applicable framework across different signal dimensions for blending visual signals represented by INRs. Our Neural Poisson Solver offers a variational problem-solving approach based on the continuous Poisson equation, demonstrating exceptional performance across various domains. Specifically, we propose a gradient-guided neural solver to represent the solution process of the variational problem, refining the target signal to achieve natural blending results. We also develop a Poisson equation-based loss and optimization scheme to train our solver, ensuring it effectively blends the input INR scenes while preserving their inherent structure and semantic content. The lack of dependence on additional prior knowledge makes our method easily adaptable to various task categories, highlighting its versatility. Comprehensive experimental results validate the robustness of our approach across multiple dimensions and blending tasks.
Authors: Tahira Shehzadi, Ifza, Didier Stricker, Muhammad Zeshan Afzal
Abstract: The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision. Semi-Supervised Object Detection (SSOD) leverages a combination of a small labeled dataset and a larger, unlabeled dataset. This approach effectively reduces the dependence on large labeled datasets, which are often expensive and time-consuming to obtain. Initially, SSOD models encountered challenges in effectively leveraging unlabeled data and managing noise in generated pseudo-labels for unlabeled data. However, numerous recent advancements have addressed these issues, resulting in substantial improvements in SSOD performance. This paper presents a comprehensive review of 27 cutting-edge developments in SSOD methodologies, from Convolutional Neural Networks (CNNs) to Transformers. We delve into the core components of semi-supervised learning and its integration into object detection frameworks, covering data augmentation techniques, pseudo-labeling strategies, consistency regularization, and adversarial training methods. Furthermore, we conduct a comparative analysis of various SSOD models, evaluating their performance and architectural differences. We aim to ignite further research interest in overcoming existing challenges and exploring new directions in semi-supervised learning for object detection.
Authors: Thien-Qua T. Nguyen, Hieu-Nghia Nguyen, Thanh-Hieu Bui, Thien B. Nguyen-Tat, Vuong M. Ngo
Abstract: This research presents an enhanced approach for precise segmentation of brain tumor masses in magnetic resonance imaging (MRI) using an advanced 3D-UNet model combined with a Context Transformer (CoT). By architectural expansion CoT, the proposed model extends its architecture to a 3D format, integrates it smoothly with the base model to utilize the complex contextual information found in MRI scans, emphasizing how elements rely on each other across an extended spatial range. The proposed model synchronizes tumor mass characteristics from CoT, mutually reinforcing feature extraction, facilitating the precise capture of detailed tumor mass structures, including location, size, and boundaries. Several experimental results present the outstanding segmentation performance of the proposed method in comparison to current state-of-the-art approaches, achieving Dice score of 82.0%, 81.5%, 89.0% for Enhancing Tumor, Tumor Core and Whole Tumor, respectively, on BraTS2019.
Authors: Jinyoung Park, Hee-Seon Kim, Kangwook Ko, Minbeom Kim, Changick Kim
Abstract: We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms leading to high computational costs by quadratic complexity, VideoMamba leverages Mamba's linear complexity and selective SSM mechanism for more efficient processing. The proposed Spatio-Temporal Forward and Backward SSM allows the model to effectively capture the complex relationship between non-sequential spatial and sequential temporal information in video. Consequently, VideoMamba is not only resource-efficient but also effective in capturing long-range dependency in videos, demonstrated by competitive performance and outstanding efficiency on a variety of video understanding benchmarks. Our work highlights the potential of VideoMamba as a powerful tool for video understanding, offering a simple yet effective baseline for future research in video analysis.
Authors: Stefan Novakovi\'c, Vladimir Risojevi\'c
Abstract: Contemporary approaches to solving various problems that require analyzing three-dimensional (3D) meshes and point clouds have adopted the use of deep learning algorithms that directly process 3D data such as point coordinates, normal vectors and vertex connectivity information. Our work proposes one such solution to the problem of positioning body and finger animation skeleton joints within 3D models of human bodies. Due to scarcity of annotated real human scans, we resort to generating synthetic samples while varying their shape and pose parameters. Similarly to the state-of-the-art approach, our method computes each joint location as a convex combination of input points. Given only a list of point coordinates and normal vector estimates as input, a dynamic graph convolutional neural network is used to predict the coefficients of the convex combinations. By comparing our method with the state-of-the-art, we show that it is possible to achieve significantly better results with a simpler architecture, especially for finger joints. Since our solution requires fewer precomputed features, it also allows for shorter processing times.
Authors: Zeyang Zhao, Qilong Xue, Yuhang He, Yifan Bai, Xing Wei, Yihong Gong
Abstract: This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks.
Authors: Wenjing Lu, Liang Wu, Liming Tang, Zhuang Fang
Abstract: The Retinex theory models the image as a product of illumination and reflection components, which has received extensive attention and is widely used in image enhancement, segmentation and color restoration. However, it has been rarely used in additive noise removal due to the inclusion of both multiplication and addition operations in the Retinex noisy image modeling. In this paper, we propose an exponential Retinex decomposition model based on hybrid non-convex regularization and weak space oscillation-modeling for image denoising. The proposed model utilizes non-convex first-order total variation (TV) and non-convex second-order TV to regularize the reflection component and the illumination component, respectively, and employs weak $H^{-1}$ norm to measure the residual component. By utilizing different regularizers, the proposed model effectively decomposes the image into reflection, illumination, and noise components. An alternating direction multipliers method (ADMM) combined with the Majorize-Minimization (MM) algorithm is developed to solve the proposed model. Furthermore, we provide a detailed proof of the convergence property of the algorithm. Numerical experiments validate both the proposed model and algorithm. Compared with several state-of-the-art denoising models, the proposed model exhibits superior performance in terms of peak signal-to-noise ratio (PSNR) and mean structural similarity (MSSIM).
Authors: Zijie Yue, Miaojing Shi, Hanli Wang, Shuai Ding, Qijun Chen, Shanlin Yang
Abstract: Facial video-based remote physiological measurement is a promising research area for detecting human vital signs (e.g., heart rate, respiration frequency) in a non-contact way. Conventional approaches are mostly supervised learning, requiring extensive collections of facial videos and synchronously recorded photoplethysmography (PPG) signals. To tackle it, self-supervised learning has recently gained attentions; due to the lack of ground truth PPG signals, its performance is however limited. In this paper, we propose a novel self-supervised framework that successfully integrates the popular vision-language models (VLMs) into the remote physiological measurement task. Given a facial video, we first augment its positive and negative video samples with varying rPPG signal frequencies. Next, we introduce a frequency-oriented vision-text pair generation method by carefully creating contrastive spatio-temporal maps from positive and negative samples and designing proper text prompts to describe their relative ratios of signal frequencies. A pre-trained VLM is employed to extract features for these formed vision-text pairs and estimate rPPG signals thereafter. We develop a series of generative and contrastive learning mechanisms to optimize the VLM, including the text-guided visual map reconstruction task, the vision-text contrastive learning task, and the frequency contrastive and ranking task. Overall, our method for the first time adapts VLMs to digest and align the frequency-related knowledge in vision and text modalities. Extensive experiments on four benchmark datasets demonstrate that it significantly outperforms state of the art self-supervised methods.
Authors: Youssef Sultan, Jiangqin Ma, Yu-Ying Liao
Abstract: In this paper, we show different fine-tuning methods for Stable Diffusion XL; this includes inference steps, and caption customization for each image to align with generating images in the style of a commercial 2D icon training set. We also show how important it is to properly define what "high-quality" really is especially for a commercial-use environment. As generative AI models continue to gain widespread acceptance and usage, there emerge many different ways to optimize and evaluate them for various applications. Specifically text-to-image models, such as Stable Diffusion XL and DALL-E 3 require distinct evaluation practices to effectively generate high-quality icons according to a specific style. Although some images that are generated based on a certain style may have a lower FID score (better), we show how this is not absolute in and of itself even for rasterized icons. While FID scores reflect the similarity of generated images to the overall training set, CLIP scores measure the alignment between generated images and their textual descriptions. We show how FID scores miss significant aspects, such as the minority of pixel differences that matter most in an icon, while CLIP scores result in misjudging the quality of icons. The CLIP model's understanding of "similarity" is shaped by its own training data; which does not account for feature variation in our style of choice. Our findings highlight the need for specialized evaluation metrics and fine-tuning approaches when generating high-quality commercial icons, potentially leading to more effective and tailored applications of text-to-image models in professional design contexts.
Authors: Yuxin Cao, Yumeng Zhu, Derui Wang, Sheng Wen, Minhui Xue, Jin Lu, Hao Ge
Abstract: Face recognition pipelines have been widely deployed in various mission-critical systems in trust, equitable and responsible AI applications. However, the emergence of adversarial attacks has threatened the security of the entire recognition pipeline. Despite the sheer number of attack methods proposed for crafting adversarial examples in both digital and physical forms, it is never an easy task to assess the real threat level of different attacks and obtain useful insight into the key risks confronted by face recognition systems. Traditional attacks view imperceptibility as the most important measurement to keep perturbations stealthy, while we suspect that industry professionals may possess a different opinion. In this paper, we delve into measuring the threat brought about by adversarial attacks from the perspectives of the industry and the applications of face recognition. In contrast to widely studied sophisticated attacks in the field, we propose an effective yet easy-to-launch physical adversarial attack, named AdvColor, against black-box face recognition pipelines in the physical world. AdvColor fools models in the recognition pipeline via directly supplying printed photos of human faces to the system under adversarial illuminations. Experimental results show that physical AdvColor examples can achieve a fooling rate of more than 96% against the anti-spoofing model and an overall attack success rate of 88% against the face recognition pipeline. We also conduct a survey on the threats of prevailing adversarial attacks, including AdvColor, to understand the gap between the machine-measured and human-assessed threat levels of different forms of adversarial attacks. The survey results surprisingly indicate that, compared to deliberately launched imperceptible attacks, perceptible but accessible attacks pose more lethal threats to real-world commercial systems of face recognition.
Authors: Dawei Dai, YuTang Li, YingGe Liu, Mingming Jia, Zhang YuanHui, Guoyin Wang
Abstract: Currently, image-text-driven multi-modal deep learning models have demonstrated their outstanding potential in many fields. In practice, tasks centered around facial images have broad application prospects. This paper presents \textbf{FaceCaption-15M}, a large-scale, diverse, and high-quality dataset of facial images accompanied by their natural language descriptions (facial image-to-text). This dataset aims to facilitate a study on face-centered tasks. FaceCaption-15M comprises over 15 million pairs of facial images and their corresponding natural language descriptions of facial features, making it the largest facial image-caption dataset to date. We conducted a comprehensive analysis of image quality, text naturalness, text complexity, and text-image relevance to demonstrate the superiority of FaceCaption-15M. To validate the effectiveness of FaceCaption-15M, we first trained a facial language-image pre-training model (FLIP, similar to CLIP) to align facial image with its corresponding captions in feature space. Subsequently, using both image and text encoders and fine-tuning only the linear layer, our FLIP-based models achieved state-of-the-art results on two challenging face-centered tasks. The purpose is to promote research in the field of face-related tasks through the availability of the proposed FaceCaption-15M dataset. All data, codes, and models are publicly available. https://huggingface.co/datasets/OpenFace-CQUPT/FaceCaption-15M
URLs: https://huggingface.co/datasets/OpenFace-CQUPT/FaceCaption-15M
Authors: Wenjing Lu, Zhuang Fang, Liang Wu, Liming Tang, Hanxin Liu
Abstract: The low-rank matrix completion (LRMC) technology has achieved remarkable results in low-level visual tasks. There is an underlying assumption that the real-world matrix data is low-rank in LRMC. However, the real matrix data does not satisfy the strict low-rank property, which undoubtedly present serious challenges for the above-mentioned matrix recovery methods. Fortunately, there are feasible schemes that devise appropriate and effective priori representations for describing the intrinsic information of real data. In this paper, we firstly model the matrix data ${\bf{Y}}$ as the sum of a low-rank approximation component $\bf{X}$ and an approximation error component $\cal{E}$. This finer-grained data decomposition architecture enables each component of information to be portrayed more precisely. Further, we design an overlapping group error representation (OGER) function to characterize the above error structure and propose a generalized low-rank matrix completion model based on OGER. Specifically, the low-rank component describes the global structure information of matrix data, while the OGER component not only compensates for the approximation error between the low-rank component and the real data but also better captures the local block sparsity information of matrix data. Finally, we develop an alternating direction method of multipliers (ADMM) that integrates the majorization-minimization (MM) algorithm, which enables the efficient solution of the proposed model. And we analyze the convergence of the algorithm in detail both theoretically and experimentally. In addition, the results of numerical experiments demonstrate that the proposed model outperforms existing competing models in performance.
Authors: Morris Alper, Hadar Averbuch-Elor
Abstract: While recent vision-and-language models (VLMs) like CLIP are a powerful tool for analyzing text and images in a shared semantic space, they do not explicitly model the hierarchical nature of the set of texts which may describe an image. Conversely, existing multimodal hierarchical representation learning methods require costly training from scratch, failing to leverage the knowledge encoded by state-of-the-art multimodal foundation models. In this work, we study the knowledge of existing foundation models, finding that they exhibit emergent understanding of visual-semantic hierarchies despite not being directly trained for this purpose. We propose the Radial Embedding (RE) framework for probing and optimizing hierarchical understanding, and contribute the HierarCaps dataset, a benchmark facilitating the study of hierarchical knowledge in image--text representations, constructed automatically via large language models. Our results show that foundation VLMs exhibit zero-shot hierarchical understanding, surpassing the performance of prior models explicitly designed for this purpose. Furthermore, we show that foundation models may be better aligned to hierarchical reasoning via a text-only fine-tuning phase, while retaining pretraining knowledge.
Authors: Hang Wu, Zhenghao Zhang, Siyuan Lin, Tong Qin, Jin Pan, Qiang Zhao, Chunjing Xu, Ming Yang
Abstract: Bird's-eye-view (BEV) representation is crucial for the perception function in autonomous driving tasks. It is difficult to balance the accuracy, efficiency and range of BEV representation. The existing works are restricted to a limited perception range within 50 meters. Extending the BEV representation range can greatly benefit downstream tasks such as topology reasoning, scene understanding, and planning by offering more comprehensive information and reaction time. The Standard-Definition (SD) navigation maps can provide a lightweight representation of road structure topology, characterized by ease of acquisition and low maintenance costs. An intuitive idea is to combine the close-range visual information from onboard cameras with the beyond line-of-sight (BLOS) environmental priors from SD maps to realize expanded perceptual capabilities. In this paper, we propose BLOS-BEV, a novel BEV segmentation model that incorporates SD maps for accurate beyond line-of-sight perception, up to 200m. Our approach is applicable to common BEV architectures and can achieve excellent results by incorporating information derived from SD maps. We explore various feature fusion schemes to effectively integrate the visual BEV representations and semantic features from the SD map, aiming to leverage the complementary information from both sources optimally. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in BEV segmentation on nuScenes and Argoverse benchmark. Through multi-modal inputs, BEV segmentation is significantly enhanced at close ranges below 50m, while also demonstrating superior performance in long-range scenarios, surpassing other methods by over 20% mIoU at distances ranging from 50-200m.
Authors: Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov, Bartlomiej Twardowski, Joost van de Weijer
Abstract: Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small first task presents a significant challenge for continual representation learning. Prototype-based approaches, when continually updated, face the critical issue of semantic drift due to which the old class prototypes drift to different positions in the new feature space. Through an analysis of prototype-based continual learning, we show that forgetting is not due to diminished discriminative power of the feature extractor, and can potentially be corrected by drift compensation. To address this, we propose Learnable Drift Compensation (LDC), which can effectively mitigate drift in any moving backbone, whether supervised or unsupervised. LDC is fast and straightforward to integrate on top of existing continual learning approaches. Furthermore, we showcase how LDC can be applied in combination with self-supervised CL methods, resulting in the first exemplar-free semi-supervised continual learning approach. We achieve state-of-the-art performance in both supervised and semi-supervised settings across multiple datasets. Code is available at \url{https://github.com/alviur/ldc}.
Authors: Yihan Zhang, Xuanshuo Zhang, Wei Wu, Haohan Wang
Abstract: Saliency maps have been widely used to interpret deep learning classifiers for Alzheimer's disease (AD). However, since AD is heterogeneous and has multiple subtypes, the pathological mechanism of AD remains not fully understood and may vary from patient to patient. Due to the lack of such understanding, it is difficult to comprehensively and effectively assess the saliency map of AD classifier. In this paper, we utilize the anatomical segmentation to allocate saliency values into different brain regions. By plotting the distributions of saliency maps corresponding to AD and NC (Normal Control), we can gain a comprehensive view of the model's decisions process. In order to leverage the fact that the brain volume shrinkage happens in AD patients during disease progression, we define a new evaluation metric, brain volume change score (VCS), by computing the average Pearson correlation of the brain volume changes and the saliency values of a model in different brain regions for each patient. Thus, the VCS metric can help us gain some knowledge of how saliency maps resulting from different models relate to the changes of the volumes across different regions in the whole brain. We trained candidate models on the ADNI dataset and tested on three different datasets. Our results indicate: (i) models with higher VCSs tend to demonstrate saliency maps with more details relevant to the AD pathology, (ii) using gradient-based adversarial training strategies such as FGSM and stochastic masking can improve the VCSs of the models.
Authors: Hang Wu, Zhenghao Zhang, Siyuan Lin, Xiangru Mu, Qiang Zhao, Ming Yang, Tong Qin
Abstract: Robust localization is the cornerstone of autonomous driving, especially in challenging urban environments where GPS signals suffer from multipath errors. Traditional localization approaches rely on high-definition (HD) maps, which consist of precisely annotated landmarks. However, building HD map is expensive and challenging to scale up. Given these limitations, leveraging navigation maps has emerged as a promising low-cost alternative for localization. Current approaches based on navigation maps can achieve highly accurate localization, but their complex matching strategies lead to unacceptable inference latency that fails to meet the real-time demands. To address these limitations, we propose a novel transformer-based neural re-localization method. Inspired by image registration, our approach performs a coarse-to-fine neural feature registration between navigation map and visual bird's-eye view features. Our method significantly outperforms the current state-of-the-art OrienterNet on both the nuScenes and Argoverse datasets, which is nearly 10%/20% localization accuracy and 30/16 FPS improvement on single-view and surround-view input settings, separately. We highlight that our research presents an HD-map-free localization method for autonomous driving, offering cost-effective, reliable, and scalable performance in challenging driving environments.
Authors: Konstantinos Panagiotis Alexandridis, Jiankang Deng, Anh Nguyen, Shan Luo
Abstract: The activation function plays a crucial role in model optimisation, yet the optimal choice remains unclear. For example, the Sigmoid activation is the de-facto activation in balanced classification tasks, however, in imbalanced classification, it proves inappropriate due to bias towards frequent classes. In this work, we delve deeper in this phenomenon by performing a comprehensive statistical analysis in the classification and intermediate layers of both balanced and imbalanced networks and we empirically show that aligning the activation function with the data distribution, enhances the performance in both balanced and imbalanced tasks. To this end, we propose the Adaptive Parametric Activation (APA) function, a novel and versatile activation function that unifies most common activation functions under a single formula. APA can be applied in both intermediate layers and attention layers, significantly outperforming the state-of-the-art on several imbalanced benchmarks such as ImageNet-LT, iNaturalist2018, Places-LT, CIFAR100-LT and LVIS and balanced benchmarks such as ImageNet1K, COCO and V3DET. The code is available at https://github.com/kostas1515/AGLU.
Authors: Ruiyang Zhang, Hu Zhang, Hang Yu, Zhedong Zheng
Abstract: The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting distant or small objects due to the inherent sparsity and limited spatial resolution. In this paper, we are among the early attempts to integrate LiDAR data with 2D images for unsupervised 3D detection and introduce a new method, dubbed LiDAR-2D Self-paced Learning (LiSe). We argue that RGB images serve as a valuable complement to LiDAR data, offering precise 2D localization cues, particularly when scarce LiDAR points are available for certain objects. Considering the unique characteristics of both modalities, our framework devises a self-paced learning pipeline that incorporates adaptive sampling and weak model aggregation strategies. The adaptive sampling strategy dynamically tunes the distribution of pseudo labels during training, countering the tendency of models to overfit easily detected samples, such as nearby and large-sized objects. By doing so, it ensures a balanced learning trajectory across varying object scales and distances. The weak model aggregation component consolidates the strengths of models trained under different pseudo label distributions, culminating in a robust and powerful final model. Experimental evaluations validate the efficacy of our proposed LiSe method, manifesting significant improvements of +7.1% AP$_{BEV}$ and +3.4% AP$_{3D}$ on nuScenes, and +8.3% AP$_{BEV}$ and +7.4% AP$_{3D}$ on Lyft compared to existing techniques.
Authors: Yunfeng Diao, Baiqi Wu, Ruixuan Zhang, Xun Yang, Meng Wang, He Wang
Abstract: Skeletal motion plays a pivotal role in human activity recognition (HAR). Recently, attack methods have been proposed to identify the universal vulnerability of skeleton-based HAR(S-HAR). However, the research of adversarial transferability on S-HAR is largely missing. More importantly, existing attacks all struggle in transfer across unknown S-HAR models. We observed that the key reason is that the loss landscape of the action recognizers is rugged and sharp. Given the established correlation in prior studies~\cite{qin2022boosting,wu2020towards} between loss landscape and adversarial transferability, we assume and empirically validate that smoothing the loss landscape could potentially improve adversarial transferability on S-HAR. This is achieved by proposing a new post-train Dual Bayesian strategy, which can effectively explore the model posterior space for a collection of surrogates without the need for re-training. Furthermore, to craft adversarial examples along the motion manifold, we incorporate the attack gradient with information of the motion dynamics in a Bayesian manner. Evaluated on benchmark datasets, e.g. HDM05 and NTU 60, the average transfer success rate can reach as high as 35.9\% and 45.5\% respectively. In comparison, current state-of-the-art skeletal attacks achieve only 3.6\% and 9.8\%. The high adversarial transferability remains consistent across various surrogate, victim, and even defense models. Through a comprehensive analysis of the results, we provide insights on what surrogates are more likely to exhibit transferability, to shed light on future research.
Authors: Tao Jiang, Xinchen Xie, Yining Li
Abstract: Whole-body pose estimation is a challenging task that requires simultaneous prediction of keypoints for the body, hands, face, and feet. Whole-body pose estimation aims to predict fine-grained pose information for the human body, including the face, torso, hands, and feet, which plays an important role in the study of human-centric perception and generation and in various applications. In this work, we present RTMW (Real-Time Multi-person Whole-body pose estimation models), a series of high-performance models for 2D/3D whole-body pose estimation. We incorporate RTMPose model architecture with FPN and HEM (Hierarchical Encoding Module) to better capture pose information from different body parts with various scales. The model is trained with a rich collection of open-source human keypoint datasets with manually aligned annotations and further enhanced via a two-stage distillation strategy. RTMW demonstrates strong performance on multiple whole-body pose estimation benchmarks while maintaining high inference efficiency and deployment friendliness. We release three sizes: m/l/x, with RTMW-l achieving a 70.2 mAP on the COCO-Wholebody benchmark, making it the first open-source model to exceed 70 mAP on this benchmark. Meanwhile, we explored the performance of RTMW in the task of 3D whole-body pose estimation, conducting image-based monocular 3D whole-body pose estimation in a coordinate classification manner. We hope this work can benefit both academic research and industrial applications. The code and models have been made publicly available at: https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose
URLs: https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose
Authors: Anjith George, Sebastien Marcel
Abstract: Heterogeneous Face Recognition (HFR) systems aim to enhance the capability of face recognition in challenging cross-modal authentication scenarios. However, the significant domain gap between the source and target modalities poses a considerable challenge for cross-domain matching. Existing literature primarily focuses on developing HFR approaches for specific pairs of face modalities, necessitating the explicit training of models for each source-target combination. In this work, we introduce a novel framework designed to train a modality-agnostic HFR method capable of handling multiple modalities during inference, all without explicit knowledge of the target modality labels. We achieve this by implementing a computationally efficient automatic routing mechanism called Switch Style Modulation Blocks (SSMB) that trains various domain expert modulators which transform the feature maps adaptively reducing the domain gap. Our proposed SSMB can be trained end-to-end and seamlessly integrated into pre-trained face recognition models, transforming them into modality-agnostic HFR models. We have performed extensive evaluations on HFR benchmark datasets to demonstrate its effectiveness. The source code and protocols will be made publicly available.
Authors: Pranav Poudel, Prashant Shrestha, Sanskar Amgain, Yash Raj Shrestha, Prashnna Gyawali, Binod Bhattarai
Abstract: Multimodal AI has demonstrated superior performance over unimodal approaches by leveraging diverse data sources for more comprehensive analysis. However, applying this effectiveness in healthcare is challenging due to the limited availability of public datasets. Federated learning presents an exciting solution, allowing the use of extensive databases from hospitals and health centers without centralizing sensitive data, thus maintaining privacy and security. Yet, research in multimodal federated learning, particularly in scenarios with missing modalities a common issue in healthcare datasets remains scarce, highlighting a critical area for future exploration. Toward this, we propose a novel method for multimodal federated learning with missing modalities. Our contribution lies in a novel cross-modal data augmentation by retrieval, leveraging the small publicly available dataset to fill the missing modalities in the clients. Our method learns the parameters in a federated manner, ensuring privacy protection and improving performance in multiple challenging multimodal benchmarks in the medical domain, surpassing several competitive baselines. Code Available: https://github.com/bhattarailab/CAR-MFL
Authors: Lucrezia Tosato, Hichem Boussaid, Flora Weissgerber, Camille Kurtz, Laurent Wendling, Sylvain Lobry
Abstract: Visual Question Answering for Remote Sensing (RSVQA) is a task that aims at answering natural language questions about the content of a remote sensing image. The visual features extraction is therefore an essential step in a VQA pipeline. By incorporating attention mechanisms into this process, models gain the ability to focus selectively on salient regions of the image, prioritizing the most relevant visual information for a given question. In this work, we propose to embed an attention mechanism guided by segmentation into a RSVQA pipeline. We argue that segmentation plays a crucial role in guiding attention by providing a contextual understanding of the visual information, underlying specific objects or areas of interest. To evaluate this methodology, we provide a new VQA dataset that exploits very high-resolution RGB orthophotos annotated with 16 segmentation classes and question/answer pairs. Our study shows promising results of our new methodology, gaining almost 10% of overall accuracy compared to a classical method on the proposed dataset.
Authors: Yi Zhang, Chun-Wun Cheng, Ke Yu, Zhihai He, Carola-Bibiane Sch\"onlieb, Angelica I. Aviles-Rivero
Abstract: In this paper, we consider the problem of prototype-based vision-language reasoning problem. We observe that existing methods encounter three major challenges: 1) escalating resource demands and prolonging training times, 2) contending with excessive learnable parameters, and 3) fine-tuning based only on a single modality. These challenges will hinder their capability to adapt Vision-Language Models (VLMs) to downstream tasks. Motivated by this critical observation, we propose a novel method called NODE-Adapter, which utilizes Neural Ordinary Differential Equations for better vision-language reasoning. To fully leverage both visual and textual modalities and estimate class prototypes more effectively and accurately, we divide our method into two stages: cross-modal prototype construction and cross-modal prototype optimization using neural ordinary differential equations. Specifically, we exploit VLM to encode hand-crafted prompts into textual features and few-shot support images into visual features. Then, we estimate the textual prototype and visual prototype by averaging the textual features and visual features, respectively, and adaptively combine the textual prototype and visual prototype to construct the cross-modal prototype. To alleviate the prototype bias, we then model the prototype optimization process as an initial value problem with Neural ODEs to estimate the continuous gradient flow. Our extensive experimental results, which cover few-shot classification, domain generalization, and visual reasoning on human-object interaction, demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches.
Authors: Hila Chefer, Shiran Zada, Roni Paiss, Ariel Ephrat, Omer Tov, Michael Rubinstein, Lior Wolf, Tali Dekel, Tomer Michaeli, Inbar Mosseri
Abstract: Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight $\textit{Spatial Adapters}$ that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on $\textit{"frozen videos"}$ (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel $\textit{Motion Adapter}$ module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.
Authors: Zujin Guo, Wei Li, Chen Change Loy
Abstract: Motion modeling is critical in flow-based Video Frame Interpolation (VFI). Existing paradigms either consider linear combinations of bidirectional flows or directly predict bilateral flows for given timestamps without exploring favorable motion priors, thus lacking the capability of effectively modeling spatiotemporal dynamics in real-world videos. To address this limitation, in this study, we introduce Generalizable Implicit Motion Modeling (GIMM), a novel and effective approach to motion modeling for VFI. Specifically, to enable GIMM as an effective motion modeling paradigm, we design a motion encoding pipeline to model spatiotemporal motion latent from bidirectional flows extracted from pre-trained flow estimators, effectively representing input-specific motion priors. Then, we implicitly predict arbitrary-timestep optical flows within two adjacent input frames via an adaptive coordinate-based neural network, with spatiotemporal coordinates and motion latent as inputs. Our GIMM can be smoothly integrated with existing flow-based VFI works without further modifications. We show that GIMM performs better than the current state of the art on the VFI benchmarks.
Authors: Shuai Yang, Yuying Ge, Yang Li, Yukang Chen, Yixiao Ge, Ying Shan, Yingcong Chen
Abstract: With the remarkable advancements in image generation and open-form text generation, the creation of interleaved image-text content has become an increasingly intriguing field. Multimodal story generation, characterized by producing narrative texts and vivid images in an interleaved manner, has emerged as a valuable and practical task with broad applications. However, this task poses significant challenges, as it necessitates the comprehension of the complex interplay between texts and images, and the ability to generate long sequences of coherent, contextually relevant texts and visuals. In this work, we propose SEED-Story, a novel method that leverages a Multimodal Large Language Model (MLLM) to generate extended multimodal stories. Our model, built upon the powerful comprehension capability of MLLM, predicts text tokens as well as visual tokens, which are subsequently processed with an adapted visual de-tokenizer to produce images with consistent characters and styles. We further propose multimodal attention sink mechanism to enable the generation of stories with up to 25 sequences (only 10 for training) in a highly efficient autoregressive manner. Additionally, we present a large-scale and high-resolution dataset named StoryStream for training our model and quantitatively evaluating the task of multimodal story generation in various aspects.
Authors: Zhening Xing, Gereon Fox, Yanhong Zeng, Xingang Pan, Mohamed Elgharib, Christian Theobalt, Kai Chen
Abstract: Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous tokens. However, video streaming remains much less explored, despite a growing need for live video processing. State-of-the-art video diffusion models leverage bi-directional temporal attention to model the correlations between the current frame and all the surrounding (i.e. including future) frames, which hinders them from processing streaming videos. To address this problem, we present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation. Compared to previous works, our approach ensures temporal consistency and smoothness by correlating the current frame with its predecessors and a few initial warmup frames, without any future frames. Additionally, we use a highly efficient denoising scheme featuring a KV-cache mechanism and pipelining, to facilitate streaming video translation at interactive framerates. Extensive experiments demonstrate the effectiveness of the proposed attention mechanism and pipeline, outperforming previous methods in terms of temporal smoothness and/or efficiency.
Authors: Runhui Huang, Xinpeng Ding, Chunwei Wang, Jianhua Han, Yulong Liu, Hengshuang Zhao, Hang Xu, Lu Hou, Wei Zhang, Xiaodan Liang
Abstract: High-resolution inputs enable Large Vision-Language Models (LVLMs) to discern finer visual details, enhancing their comprehension capabilities. To reduce the training and computation costs caused by high-resolution input, one promising direction is to use sliding windows to slice the input into uniform patches, each matching the input size of the well-trained vision encoder. Although efficient, this slicing strategy leads to the fragmentation of original input, i.e., the continuity of contextual information and spatial geometry is lost across patches, adversely affecting performance in cross-patch context perception and position-specific tasks. To overcome these shortcomings, we introduce HiRes-LLaVA, a novel framework designed to efficiently process any size of high-resolution input without altering the original contextual and geometric information. HiRes-LLaVA comprises two innovative components: (i) a SliceRestore adapter that reconstructs sliced patches into their original form, efficiently extracting both global and local features via down-up-sampling and convolution layers, and (ii) a Self-Mining Sampler to compresses the vision tokens based on themselves, preserving the original context and positional information while reducing training overhead. To assess the ability of handling context fragmentation, we construct a new benchmark, EntityGrid-QA, consisting of edge-related and position-related tasks. Our comprehensive experiments demonstrate the superiority of HiRes-LLaVA on both existing public benchmarks and on EntityGrid-QA, particularly on document-oriented tasks, establishing new standards for handling high-resolution inputs.
Authors: Francesco Pinto, Nathalie Rauschmayr, Florian Tram\`er, Philip Torr, Federico Tombari
Abstract: Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can memorize responses for training samples and regurgitate them even when the relevant visual information has been removed. This includes Personal Identifiable Information (PII) repeated once in the training set, indicating these models could divulge memorised sensitive information and therefore pose a privacy risk. We quantitatively measure the extractability of information in controlled experiments and differentiate between cases where it arises from generalization capabilities or from memorization. We further investigate the factors that influence memorization across multiple state-of-the-art models and propose an effective heuristic countermeasure that empirically prevents the extractability of PII.
Authors: Akshay Krishnan, Abhijit Kundu, Kevis-Kokitsi Maninis, James Hays, Matthew Brown
Abstract: We propose OmniNOCS, a large-scale monocular dataset with 3D Normalized Object Coordinate Space (NOCS) maps, object masks, and 3D bounding box annotations for indoor and outdoor scenes. OmniNOCS has 20 times more object classes and 200 times more instances than existing NOCS datasets (NOCS-Real275, Wild6D). We use OmniNOCS to train a novel, transformer-based monocular NOCS prediction model (NOCSformer) that can predict accurate NOCS, instance masks and poses from 2D object detections across diverse classes. It is the first NOCS model that can generalize to a broad range of classes when prompted with 2D boxes. We evaluate our model on the task of 3D oriented bounding box prediction, where it achieves comparable results to state-of-the-art 3D detection methods such as Cube R-CNN. Unlike other 3D detection methods, our model also provides detailed and accurate 3D object shape and segmentation. We propose a novel benchmark for the task of NOCS prediction based on OmniNOCS, which we hope will serve as a useful baseline for future work in this area. Our dataset and code will be at the project website: https://omninocs.github.io.
Authors: Abdollah Zakeri, Hamid Hassanpour, Mohammad Hossein Khosravi, Amir Masoud Nourollah
Abstract: Lip-based biometric authentication (LBBA) has attracted many researchers during the last decade. The lip is specifically interesting for biometric researchers because it is a twin biometric with the potential to function both as a physiological and a behavioral trait. Although much valuable research was conducted on LBBA, none of them considered the different emotions of the client during the video acquisition step of LBBA, which can potentially affect the client's facial expressions and speech tempo. We proposed a novel network structure called WhisperNetV2, which extends our previously proposed network called WhisperNet. Our proposed network leverages a deep Siamese structure with triplet loss having three identical SlowFast networks as embedding networks. The SlowFast network is an excellent candidate for our task since the fast pathway extracts motion-related features (behavioral lip movements) with a high frame rate and low channel capacity. The slow pathway extracts visual features (physiological lip appearance) with a low frame rate and high channel capacity. Using an open-set protocol, we trained our network using the CREMA-D dataset and acquired an Equal Error Rate (EER) of 0.005 on the test set. Considering that the acquired EER is less than most similar LBBA methods, our method can be considered as a state-of-the-art LBBA method.
Authors: Wayne Wu, Honglin He, Yiran Wang, Chenda Duan, Jack He, Zhizheng Liu, Quanyi Li, Bolei Zhou
Abstract: Public urban spaces like streetscapes and plazas serve residents and accommodate social life in all its vibrant variations. Recent advances in Robotics and Embodied AI make public urban spaces no longer exclusive to humans. Food delivery bots and electric wheelchairs have started sharing sidewalks with pedestrians, while diverse robot dogs and humanoids have recently emerged in the street. Ensuring the generalizability and safety of these forthcoming mobile machines is crucial when navigating through the bustling streets in urban spaces. In this work, we present MetaUrban, a compositional simulation platform for Embodied AI research in urban spaces. MetaUrban can construct an infinite number of interactive urban scenes from compositional elements, covering a vast array of ground plans, object placements, pedestrians, vulnerable road users, and other mobile agents' appearances and dynamics. We design point navigation and social navigation tasks as the pilot study using MetaUrban for embodied AI research and establish various baselines of Reinforcement Learning and Imitation Learning. Experiments demonstrate that the compositional nature of the simulated environments can substantially improve the generalizability and safety of the trained mobile agents. MetaUrban will be made publicly available to provide more research opportunities and foster safe and trustworthy embodied AI in urban spaces.
Authors: Cherie Ho, Jiaye Zou, Omar Alama, Sai Mitheran Jagadesh Kumar, Benjamin Chiang, Taneesh Gupta, Chen Wang, Nikhil Keetha, Katia Sycara, Sebastian Scherer
Abstract: Top-down Bird's Eye View (BEV) maps are a popular representation for ground robot navigation due to their richness and flexibility for downstream tasks. While recent methods have shown promise for predicting BEV maps from First-Person View (FPV) images, their generalizability is limited to small regions captured by current autonomous vehicle-based datasets. In this context, we show that a more scalable approach towards generalizable map prediction can be enabled by using two large-scale crowd-sourced mapping platforms, Mapillary for FPV images and OpenStreetMap for BEV semantic maps. We introduce Map It Anywhere (MIA), a data engine that enables seamless curation and modeling of labeled map prediction data from existing open-source map platforms. Using our MIA data engine, we display the ease of automatically collecting a dataset of 1.2 million pairs of FPV images & BEV maps encompassing diverse geographies, landscapes, environmental factors, camera models & capture scenarios. We further train a simple camera model-agnostic model on this data for BEV map prediction. Extensive evaluations using established benchmarks and our dataset show that the data curated by MIA enables effective pretraining for generalizable BEV map prediction, with zero-shot performance far exceeding baselines trained on existing datasets by 35%. Our analysis highlights the promise of using large-scale public maps for developing & testing generalizable BEV perception, paving the way for more robust autonomous navigation.
Authors: Stefanos Pertigkiozoglou, Evangelos Chatzipantazis, Kostas Daniilidis
Abstract: The goal of this paper is to address the problem of \textit{global} point cloud registration (PCR) i.e., finding the optimal alignment between point clouds irrespective of the initial poses of the scans. This problem is notoriously challenging for classical optimization methods due to computational constraints. First, we show that state-of-the-art deep learning methods suffer from huge performance degradation when the point clouds are arbitrarily placed in space. We propose that \textit{equivariant deep learning} should be utilized for solving this task and we characterize the specific type of bi-equivariance of PCR. Then, we design BiEquiformer a novel and scalable \textit{bi-equivariant} pipeline i.e. equivariant to the independent transformations of the input point clouds. While a naive approach would process the point clouds independently we design expressive bi-equivariant layers that fuse the information from both point clouds. This allows us to extract high-quality superpoint correspondences and in turn, robust point-cloud registration. Extensive comparisons against state-of-the-art methods show that our method achieves comparable performance in the canonical setting and superior performance in the robust setting in both the 3DMatch and the challenging low-overlap 3DLoMatch dataset.
Authors: Mihir Prabhudesai, Russell Mendonca, Zheyang Qin, Katerina Fragkiadaki, Deepak Pathak
Abstract: We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting these models via supervised fine-tuning requires collecting target datasets of videos, which is challenging and tedious. In this work, we utilize pre-trained reward models that are learned via preferences on top of powerful vision discriminative models to adapt video diffusion models. These models contain dense gradient information with respect to generated RGB pixels, which is critical to efficient learning in complex search spaces, such as videos. We show that backpropagating gradients from these reward models to a video diffusion model can allow for compute and sample efficient alignment of the video diffusion model. We show results across a variety of reward models and video diffusion models, demonstrating that our approach can learn much more efficiently in terms of reward queries and computation than prior gradient-free approaches. Our code, model weights,and more visualization are available at https://vader-vid.github.io.
Authors: Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Yichi Zhang, Ziyu Guo, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, Shanghang Zhang, Peng Gao, Hongsheng Li
Abstract: Multi-modal Large Language Models (MLLMs) have recently emerged as a significant focus in academia and industry. Despite their proficiency in general multi-modal scenarios, the mathematical problem-solving capabilities in visual contexts remain insufficiently explored. We identify three key areas within MLLMs that need to be improved: visual encoding of math diagrams, diagram-language alignment, and mathematical reasoning skills. This draws forth an urgent demand for large-scale, high-quality data and training pipelines in visual mathematics. In this paper, we propose MAVIS, the first MAthematical VISual instruction tuning paradigm for MLLMs, involving a series of mathematical visual datasets and specialized MLLMs. Targeting the three issues, MAVIS contains three progressive training stages from scratch. First, we curate MAVIS-Caption, consisting of 558K diagram-caption pairs, to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we utilize MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we introduce MAVIS-Instruct, including 900K meticulously collected and annotated visual math problems, which is adopted to finally instruct-tune the MLLM for robust mathematical reasoning skills. In MAVIS-Instruct, we incorporate complete chain-of-thought (CoT) rationales for each problem, and minimize textual redundancy, thereby concentrating the model towards the visual elements. Data and Models are released at https://github.com/ZrrSkywalker/MAVIS
Authors: Tuan Nguyen, Dung Thuy Nguyen, Khoa D Doan, Kok-Seng Wong
Abstract: Despite the promise of Federated Learning (FL) for privacy-preserving model training on distributed data, it remains susceptible to backdoor attacks. These attacks manipulate models by embedding triggers (specific input patterns) in the training data, forcing misclassification as predefined classes during deployment. Traditional single-trigger attacks and recent work on cooperative multiple-trigger attacks, where clients collaborate, highlight limitations in attack realism due to coordination requirements. We investigate a more alarming scenario: non-cooperative multiple-trigger attacks. Here, independent adversaries introduce distinct triggers targeting unique classes. These parallel attacks exploit FL's decentralized nature, making detection difficult. Our experiments demonstrate the alarming vulnerability of FL to such attacks, where individual backdoors can be successfully learned without impacting the main task. This research emphasizes the critical need for robust defenses against diverse backdoor attacks in the evolving FL landscape. While our focus is on empirical analysis, we believe it can guide backdoor research toward more realistic settings, highlighting the crucial role of FL in building robust defenses against diverse backdoor threats. The code is available at \url{https://anonymous.4open.science/r/nba-980F/}.
Authors: Hang Zhang, Xiang Chen, Renjiu Hu, Dongdong Liu, Gaolei Li, Rongguang Wang
Abstract: Many existing learning-based deformable image registration methods impose constraints on deformation fields to ensure they are globally smooth and continuous. However, this assumption does not hold in cardiac image registration, where different anatomical regions exhibit asymmetric motions during respiration and movements due to sliding organs within the chest. Consequently, such global constraints fail to accommodate local discontinuities across organ boundaries, potentially resulting in erroneous and unrealistic displacement fields. In this paper, we address this issue with MemWarp, a learning framework that leverages a memory network to store prototypical information tailored to different anatomical regions. MemWarp is different from earlier approaches in two main aspects: firstly, by decoupling feature extraction from similarity matching in moving and fixed images, it facilitates more effective utilization of feature maps; secondly, despite its capability to preserve discontinuities, it eliminates the need for segmentation masks during model inference. In experiments on a publicly available cardiac dataset, our method achieves considerable improvements in registration accuracy and producing realistic deformations, outperforming state-of-the-art methods with a remarkable 7.1\% Dice score improvement over the runner-up semi-supervised method. Source code will be available at https://github.com/tinymilky/Mem-Warp.
Authors: Jinxing Zhou, Dan Guo, Yuxin Mao, Yiran Zhong, Xiaojun Chang, Meng Wang
Abstract: Audio-Visual Video Parsing (AVVP) task aims to detect and temporally locate events within audio and visual modalities. Multiple events can overlap in the timeline, making identification challenging. While traditional methods usually focus on improving the early audio-visual encoders to embed more effective features, the decoding phase -- crucial for final event classification, often receives less attention. We aim to advance the decoding phase and improve its interpretability. Specifically, we introduce a new decoding paradigm, \underline{l}abel s\underline{e}m\underline{a}ntic-based \underline{p}rojection (LEAP), that employs labels texts of event categories, each bearing distinct and explicit semantics, for parsing potentially overlapping events.LEAP works by iteratively projecting encoded latent features of audio/visual segments onto semantically independent label embeddings. This process, enriched by modeling cross-modal (audio/visual-label) interactions, gradually disentangles event semantics within video segments to refine relevant label embeddings, guaranteeing a more discriminative and interpretable decoding process. To facilitate the LEAP paradigm, we propose a semantic-aware optimization strategy, which includes a novel audio-visual semantic similarity loss function. This function leverages the Intersection over Union of audio and visual events (EIoU) as a novel metric to calibrate audio-visual similarities at the feature level, accommodating the varied event densities across modalities. Extensive experiments demonstrate the superiority of our method, achieving new state-of-the-art performance for AVVP and also enhancing the relevant audio-visual event localization task.
Authors: Wenrui Li, Penghong Wang, Ruiqin Xiong, Xiaopeng Fan
Abstract: The spiking neural networks (SNNs) that efficiently encode temporal sequences have shown great potential in extracting audio-visual joint feature representations. However, coupling SNNs (binary spike sequences) with transformers (float-point sequences) to jointly explore the temporal-semantic information still facing challenges. In this paper, we introduce a novel Spiking Tucker Fusion Transformer (STFT) for audio-visual zero-shot learning (ZSL). The STFT leverage the temporal and semantic information from different time steps to generate robust representations. The time-step factor (TSF) is introduced to dynamically synthesis the subsequent inference information. To guide the formation of input membrane potentials and reduce the spike noise, we propose a global-local pooling (GLP) which combines the max and average pooling operations. Furthermore, the thresholds of the spiking neurons are dynamically adjusted based on semantic and temporal cues. Integrating the temporal and semantic information extracted by SNNs and Transformers are difficult due to the increased number of parameters in a straightforward bilinear model. To address this, we introduce a temporal-semantic Tucker fusion module, which achieves multi-scale fusion of SNN and Transformer outputs while maintaining full second-order interactions. Our experimental results demonstrate the effectiveness of the proposed approach in achieving state-of-the-art performance in three benchmark datasets. The harmonic mean (HM) improvement of VGGSound, UCF101 and ActivityNet are around 15.4\%, 3.9\%, and 14.9\%, respectively.
Authors: Yuke Xing, Qi Yang, Kaifa Yang, Yilin Xu, Zhu Li
Abstract: In recent years, Neural Radiance Fields (NeRF) have demonstrated significant advantages in representing and synthesizing 3D scenes. Explicit NeRF models facilitate the practical NeRF applications with faster rendering speed, and also attract considerable attention in NeRF compression due to its huge storage cost. To address the challenge of the NeRF compression study, in this paper, we construct a new dataset, called Explicit_NeRF_QA. We use 22 3D objects with diverse geometries, textures, and material complexities to train four typical explicit NeRF models across five parameter levels. Lossy compression is introduced during the model generation, pivoting the selection of key parameters such as hash table size for InstantNGP and voxel grid resolution for Plenoxels. By rendering NeRF samples to processed video sequences (PVS), a large scale subjective experiment with lab environment is conducted to collect subjective scores from 21 viewers. The diversity of content, accuracy of mean opinion scores (MOS), and characteristics of NeRF distortion are comprehensively presented, establishing the heterogeneity of the proposed dataset. The state-of-the-art objective metrics are tested in the new dataset. Best Person correlation, which is around 0.85, is collected from the full-reference objective metric. All tested no-reference metrics report very poor results with 0.4 to 0.6 correlations, demonstrating the need for further development of more robust no-reference metrics. The dataset, including NeRF samples, source 3D objects, multiview images for NeRF generation, PVSs, MOS, is made publicly available at the following location: https://github.com/LittlericeChloe/Explicit_NeRF_QA.
Authors: Yuan Zhang, Yaolei Qi, Xiaoming Qi, Yongyue Wei, Guanyu Yang
Abstract: The precise subtype classification of myeloproliferative neoplasms (MPNs) based on multimodal information, which assists clinicians in diagnosis and long-term treatment plans, is of great clinical significance. However, it remains a great challenging task due to the lack of diagnostic representativeness for local patches and the absence of diagnostic-relevant features from a single modality. In this paper, we propose a Dynamic Screening and Clinical-Enhanced Network (DSCENet) for the subtype classification of MPNs on the multimodal fusion of whole slide images (WSIs) and clinical information. (1) A dynamic screening module is proposed to flexibly adapt the feature learning of local patches, reducing the interference of irrelevant features and enhancing their diagnostic representativeness. (2) A clinical-enhanced fusion module is proposed to integrate clinical indicators to explore complementary features across modalities, providing comprehensive diagnostic information. Our approach has been validated on the real clinical data, achieving an increase of 7.91% AUC and 16.89% accuracy compared with the previous state-of-the-art (SOTA) methods. The code is available at https://github.com/yuanzhang7/DSCENet.
Authors: Wenwen Min, Zhiceng Shi, Jun Zhang, Jun Wan, Changmiao Wang
Abstract: In recent years, the advent of spatial transcriptomics (ST) technology has unlocked unprecedented opportunities for delving into the complexities of gene expression patterns within intricate biological systems. Despite its transformative potential, the prohibitive cost of ST technology remains a significant barrier to its widespread adoption in large-scale studies. An alternative, more cost-effective strategy involves employing artificial intelligence to predict gene expression levels using readily accessible whole-slide images (WSIs) stained with Hematoxylin and Eosin (H\&E). However, existing methods have yet to fully capitalize on multimodal information provided by H&E images and ST data with spatial location. In this paper, we propose \textbf{mclSTExp}, a multimodal contrastive learning with Transformer and Densenet-121 encoder for Spatial Transcriptomics Expression prediction. We conceptualize each spot as a "word", integrating its intrinsic features with spatial context through the self-attention mechanism of a Transformer encoder. This integration is further enriched by incorporating image features via contrastive learning, thereby enhancing the predictive capability of our model. Our extensive evaluation of \textbf{mclSTExp} on two breast cancer datasets and a skin squamous cell carcinoma dataset demonstrates its superior performance in predicting spatial gene expression. Moreover, mclSTExp has shown promise in interpreting cancer-specific overexpressed genes, elucidating immune-related genes, and identifying specialized spatial domains annotated by pathologists. Our source code is available at https://github.com/shizhiceng/mclSTExp.
Authors: Seunghan Yang, Seokeon Choi, Hyunsin Park, Sungha Choi, Simyung Chang, Sungrack Yun
Abstract: Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their limited domains, leading to a `domain shift' across clients. Privacy concerns limit each client's learning to its own domain data, which increase the risk of overfitting. Moreover, the process of aggregating models trained on own limited domain can be potentially lead to a significant degradation in the global model performance. To deal with these challenges, we introduce the concept of federated feature diversification. Each client diversifies the own limited domain data by leveraging global feature statistics, i.e., the aggregated average statistics over all participating clients, shared through the global model's parameters. This data diversification helps local models to learn client-invariant representations while preserving privacy. Our resultant global model shows robust performance on unseen test domain data. To enhance performance further, we develop an instance-adaptive inference approach tailored for test domain data. Our proposed instance feature adapter dynamically adjusts feature statistics to align with the test input, thereby reducing the domain gap between the test and training domains. We show that our method achieves state-of-the-art performance on several domain generalization benchmarks within a federated learning setting.
Authors: Shaojie Guo, Haofei Song, Qingli Li, Yan Wang
Abstract: This paper focuses on the dataset-free Blind Image Super-Resolution (BISR). Unlike existing dataset-free BISR methods that focus on obtaining a degradation kernel for the entire image, we are the first to explicitly design a spatially-variant degradation model for each pixel. Our method also benefits from having a significantly smaller number of learnable parameters compared to data-driven spatially-variant BISR methods. Concretely, each pixel's degradation kernel is expressed as a linear combination of a learnable dictionary composed of a small number of spatially-variant atom kernels. The coefficient matrices of the atom degradation kernels are derived using membership functions of fuzzy set theory. We construct a novel Probabilistic BISR model with tailored likelihood function and prior terms. Subsequently, we employ the Monte Carlo EM algorithm to infer the degradation kernels for each pixel. Our method achieves a significant improvement over other state-of-the-art BISR methods, with an average improvement of 1 dB (2x).Code will be released at https://github.com/shaojieguoECNU/SVDSR.
Authors: Noam Elata, Tomer Michaeli, Michael Elad
Abstract: Compressed Sensing (CS) facilitates rapid image acquisition by selecting a small subset of measurements sufficient for high-fidelity reconstruction. Adaptive CS seeks to further enhance this process by dynamically choosing future measurements based on information gleaned from data that is already acquired. However, many existing frameworks are often tailored to specific tasks and require intricate training procedures. We propose AdaSense, a novel Adaptive CS approach that leverages zero-shot posterior sampling with pre-trained diffusion models. By sequentially sampling from the posterior distribution, we can quantify the uncertainty of each possible future linear measurement throughout the acquisition process. AdaSense eliminates the need for additional training and boasts seamless adaptation to diverse domains with minimal tuning requirements. Our experiments demonstrate the effectiveness of AdaSense in reconstructing facial images from a small number of measurements. Furthermore, we apply AdaSense for active acquisition of medical images in the domains of magnetic resonance imaging (MRI) and computed tomography (CT), highlighting its potential for tangible real-world acceleration.
Authors: Vivek Maik, Aparna Purayath, Durga R, Manojkumar Lakshmanan, Mohanasankar Sivaprakasm
Abstract: The proposed work establishes a novel Graphical User Interface (GUI) framework, primarily designed for intraoperative pedicle screw planning. Current planning workflow in Image Guided Surgeries primarily relies on pre-operative CT planning. Intraoperative CT planning can be time-consuming and expensive and thus is not a common practice. In situations where efficiency and cost-effectiveness are paramount, planning to utilize fluoroscopic images acquired for image registration emerges as the optimal choice. The methodology proposed in this study employs a simulated 3D pedicle screw to calculate its coronal and sagittal projections for pedicle screw planning using anterior-posterior (AP) and lateral (LP) images. The initialization and placement of pedicle screw is computed by utilizing the bounding box of vertebral segmentation, which is obtained by the application of enhanced YOLOv5. The GUI front end includes functionality that allows surgeons or medical practitioners to efficiently choose, set up, and dynamically maneuver the pedicle screw on AP and LP images. This is based on a novel feature called synchronous planning, which involves correlating pedicle screws from the coronal and sagittal planes. This correlation utilizes projective correspondence to ensure that any movement of the pedicle screw in either the AP or LP image will be reflected in the other image. The proposed GUI framework is a time-efficient and cost-effective tool for synchronizing and planning the movement of pedicle screws during intraoperative surgical procedures.
Authors: Xiao-Ming Wu, Jia-Feng Cai, Jian-Jian Jiang, Dian Zheng, Yi-Lin Wei, Wei-Shi Zheng
Abstract: Robotic grasping in clutters is a fundamental task in robotic manipulation. In this work, we propose an economic framework for 6-DoF grasp detection, aiming to economize the resource cost in training and meanwhile maintain effective grasp performance. To begin with, we discover that the dense supervision is the bottleneck of current SOTA methods that severely encumbers the entire training overload, meanwhile making the training difficult to converge. To solve the above problem, we first propose an economic supervision paradigm for efficient and effective grasping. This paradigm includes a well-designed supervision selection strategy, selecting key labels basically without ambiguity, and an economic pipeline to enable the training after selection. Furthermore, benefit from the economic supervision, we can focus on a specific grasp, and thus we devise a focal representation module, which comprises an interactive grasp head and a composite score estimation to generate the specific grasp more accurately. Combining all together, the EconomicGrasp framework is proposed. Our extensive experiments show that EconomicGrasp surpasses the SOTA grasp method by about 3AP on average, and with extremely low resource cost, for about 1/4 training time cost, 1/8 memory cost and 1/30 storage cost. Our code is available at https://github.com/iSEE-Laboratory/EconomicGrasp.
Authors: Yuze Jiang, Ehsan Javanmardi, Manabu Tsukada, Hiroshi Esaki
Abstract: Recent advancements in LiDAR technology have significantly lowered costs and improved both its precision and resolution, thereby solidifying its role as a critical component in autonomous vehicle localization. Using sophisticated 3D registration algorithms, LiDAR now facilitates vehicle localization with centimeter-level accuracy. However, these high-precision techniques often face reliability challenges in environments devoid of identifiable map features. To address this limitation, we propose a novel approach that utilizes road side units (RSU) with vehicle-to-infrastructure (V2I) communications to assist vehicle self-localization. By using RSUs as stationary reference points and processing real-time LiDAR data, our method enhances localization accuracy through a cooperative localization framework. By placing RSUs in critical areas, our proposed method can improve the reliability and precision of vehicle localization when the traditional vehicle self-localization technique falls short. Evaluation results in an end-to-end autonomous driving simulator AWSIM show that the proposed method can improve localization accuracy by up to 80% under vulnerable environments compared to traditional localization methods. Additionally, our method also demonstrates robust resistance to network delays and packet loss in heterogeneous network environments.
Authors: Muhammad Suhaib Shahid, Gleb E. Yakubov, Andrew P. French
Abstract: Forming oral models capable of understanding the complete dynamics of the oral cavity is vital across research areas such as speech correction, designing foods for the aging population, and dentistry. Magnetic resonance imaging (MRI) technologies, capable of capturing oral data essential for creating such detailed representations, offer a powerful tool for illustrating articulatory dynamics. However, its real-time application is hindered by expense and expertise requirements. Ever advancing generative AI approaches present themselves as a way to address this barrier by leveraging multi-modal approaches for generating pseudo-MRI views. Nonetheless, this immediately sparks ethical concerns regarding the utilisation of a technology with the capability to produce MRIs from facial observations. This paper explores the ethical implications of external-to-internal correlation modeling (E2ICM). E2ICM utilises facial movements to infer internal configurations and provides a cost-effective supporting technology for MRI. In this preliminary work, we employ Pix2PixGAN to generate pseudo-MRI views from external articulatory data, demonstrating the feasibility of this approach. Ethical considerations concerning privacy, consent, and potential misuse, which are fundamental to our examination of this innovative methodology, are discussed as a result of this experimentation.
Authors: ZiDong Wang, Zeyu Lu, Di Huang, Tong He, Xihui Liu, Wanli Ouyang, Lei Bai
Abstract: In this paper, we introduce PredBench, a benchmark tailored for the holistic evaluation of spatio-temporal prediction networks. Despite significant progress in this field, there remains a lack of a standardized framework for a detailed and comparative analysis of various prediction network architectures. PredBench addresses this gap by conducting large-scale experiments, upholding standardized and appropriate experimental settings, and implementing multi-dimensional evaluations. This benchmark integrates 12 widely adopted methods with 15 diverse datasets across multiple application domains, offering extensive evaluation of contemporary spatio-temporal prediction networks. Through meticulous calibration of prediction settings across various applications, PredBench ensures evaluations relevant to their intended use and enables fair comparisons. Moreover, its multi-dimensional evaluation framework broadens the analysis with a comprehensive set of metrics, providing deep insights into the capabilities of models. The findings from our research offer strategic directions for future developments in the field. Our codebase is available at https://github.com/WZDTHU/PredBench.
Authors: Iris Dumeur (CESBIO), Silvia Valero (CESBIO), Jordi Inglada (CESBIO)
Abstract: Although recently several foundation models for satellite remote sensing imagery have been proposed, they fail to address major challenges of real/operational applications. Indeed, embeddings that don't take into account the spectral, spatial and temporal dimensions of the data as well as the irregular or unaligned temporal sampling are of little use for most real world uses.As a consequence, we propose an ALIgned Sits Encoder (ALISE), a novel approach that leverages the spatial, spectral, and temporal dimensions of irregular and unaligned SITS while producing aligned latent representations. Unlike SSL models currently available for SITS, ALISE incorporates a flexible query mechanism to project the SITS into a common and learned temporal projection space. Additionally, thanks to a multi-view framework, we explore integration of instance discrimination along a masked autoencoding task to SITS. The quality of the produced representation is assessed through three downstream tasks: crop segmentation (PASTIS), land cover segmentation (MultiSenGE), and a novel crop change detection dataset. Furthermore, the change detection task is performed without supervision. The results suggest that the use of aligned representations is more effective than previous SSL methods for linear probing segmentation tasks.
Authors: Congrui Fu, Hui Yuan, Shiqi Jiang, Guanghui Zhang, Liquan Shen, Raouf Hamzaoui
Abstract: By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This presents a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.02 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectively), and visually.
Authors: Chao Fan, Hongyuan Yu, Luo Wang, Yan Huang, Liang Wang, Xibin Jia
Abstract: Despite the progress made in Mamba-based medical image segmentation models, current methods utilizing unidirectional or multi-directional feature scanning mechanisms fail to well model dependencies between neighboring positions in the image, hindering the effective modeling of local features. However, local features are crucial for medical image segmentation as they provide vital information about lesions and tissue structures. To address this limitation, we propose a simple yet effective method named SliceMamba, a locally sensitive pure Mamba medical image segmentation model. The proposed SliceMamba includes an efffcient Bidirectional Slice Scan module (BSS), which performs bidirectional feature segmentation while employing varied scanning mechanisms for distinct features. This ensures that spatially adjacent features maintain proximity in the scanning sequence, thereby enhancing segmentation performance. Extensive experiments on skin lesion and polyp segmentation datasets validate the effectiveness of our method.
Authors: Ju Cheon Lee, Keunho Byeon, Boram Song, Kyungeun Kim, Jin Tae Kwak
Abstract: In computational pathology, cancer grading has been mainly studied as a categorical classification problem, which does not utilize the ordering nature of cancer grades such as the higher the grade is, the worse the cancer is. To incorporate the ordering relationship among cancer grades, we introduce a differential ordinal learning problem in which we define and learn the degree of difference in the categorical class labels between pairs of samples by using their differences in the feature space. To this end, we propose a transformer-based neural network that simultaneously conducts both categorical classification and differential ordinal classification for cancer grading. We also propose a tailored loss function for differential ordinal learning. Evaluating the proposed method on three different types of cancer datasets, we demonstrate that the adoption of differential ordinal learning can improve the accuracy and reliability of cancer grading, outperforming conventional cancer grading approaches. The proposed approach should be applicable to other diseases and problems as they involve ordinal relationship among class labels.
Authors: Shuang Xu, Chang Yu, Jiangjun Peng, Xiangyong Cao
Abstract: Remote sensing image restoration aims to reconstruct missing or corrupted areas within images. To date, low-rank based models have garnered significant interest in this field. This paper proposes a novel low-rank regularization term, named the Haar nuclear norm (HNN), for efficient and effective remote sensing image restoration. It leverages the low-rank properties of wavelet coefficients derived from the 2-D frontal slice-wise Haar discrete wavelet transform, effectively modeling the low-rank prior for separated coarse-grained structure and fine-grained textures in the image. Experimental evaluations conducted on hyperspectral image inpainting, multi-temporal image cloud removal, and hyperspectral image denoising have revealed the HNN's potential. Typically, HNN achieves a performance improvement of 1-4 dB and a speedup of 10-28x compared to some state-of-the-art methods (e.g., tensor correlated total variation, and fully-connected tensor network) for inpainting tasks.
Authors: Chang Sun, Hui Yuan, Shuai Li, Xin Lu, Raouf Hamzaoui
Abstract: In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function. However, this approach has two main weaknesses. First, the differences between contexts of different nodes are not significant, making it difficult for the context model to accurately predict the probability distribution of node occupancy. Second, as the one-hot encoding is not the actual probability distribution of node occupancy, the cross-entropy loss function is inaccurate. To address these problems, we propose a general structure that can enhance existing context models. We introduce the context feature residuals into the context model to amplify the differences between contexts. We also add a multi-layer perception branch, that uses the mean squared error between its output and node occupancy as a loss function to provide accurate gradients in backpropagation. We validate our method by showing that it can improve the performance of an octree-based model (OctAttention) and a voxel-based model (VoxelDNN) on the object point cloud datasets MPEG 8i and MVUB, as well as the LiDAR point cloud dataset SemanticKITTI.
Authors: Chang Sun, Hui Yuan, Xiaolong Mao, Xin Lu, Raouf Hamzaoui
Abstract: In point cloud geometry compression, most octreebased context models use the cross-entropy between the onehot encoding of node occupancy and the probability distribution predicted by the context model as the loss. This approach converts the problem of predicting the number (a regression problem) and the position (a classification problem) of occupied child nodes into a 255-dimensional classification problem. As a result, it fails to accurately measure the difference between the one-hot encoding and the predicted probability distribution. We first analyze why the cross-entropy loss function fails to accurately measure the difference between the one-hot encoding and the predicted probability distribution. Then, we propose an attention-based child node number prediction (ACNP) module to enhance the context models. The proposed module can predict the number of occupied child nodes and map it into an 8- dimensional vector to assist the context model in predicting the probability distribution of the occupancy of the current node for efficient entropy coding. Experimental results demonstrate that the proposed module enhances the coding efficiency of octree-based context models.
Authors: Shiqi Jiang, Ting Ren, Congrui Fu, Shuai Li, Hui Yuan
Abstract: Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast. Aiming at addressing the inadequacies of current learned image compression (LIC) methods for SC, we propose an improved two-stage octave convolutional residual blocks (IToRB) for high and low-frequency feature extraction and a cascaded two-stage multi-scale residual blocks (CTMSRB) for improved multi-scale learning and nonlinearity in SC. Additionally, we employ a window-based attention module (WAM) to capture pixel correlations, especially for high contrast regions in the image. We also construct a diverse SC image compression dataset (SDU-SCICD2K) for training, including text, charts, graphics, animation, movie, game and mixture of SC images and NS images. Experimental results show our method, more suited for SC than NS data, outperforms existing LIC methods in rate-distortion performance on SC images. The code is publicly available at https://github.com/SunshineSki/OMR Net.git.
Authors: Xin You, Yixin Lou, Minghui Zhang, Chuyan Zhang, Jie Yang, Yun Gu
Abstract: Automatic and precise segmentation of vertebrae from CT images is crucial for various clinical applications. However, due to a lack of explicit and strict constraints, existing methods especially for single-stage methods, still suffer from the challenge of intra-vertebrae segmentation inconsistency, which refers to multiple label predictions inside a singular vertebra. For multi-stage methods, vertebrae detection serving as the first step, is affected by the pathology and mental implants. Thus, incorrect detections cause biased patches before segmentation, then lead to inconsistent labeling and segmentation. In our work, motivated by the perspective of instance segmentation, we try to label individual and complete binary masks to address this limitation. Specifically, a contour-based network is proposed based on Structural Low-Rank Descriptors for shape consistency, termed SLoRD. These contour descriptors are acquired in a data-driven manner in advance. For a more precise representation of contour descriptors, we adopt the spherical coordinate system and devise the spherical centroid. Besides, the contour loss is designed to impose explicit consistency constraints, facilitating regressed contour points close to vertebral boundaries. Quantitative and qualitative evaluations on VerSe 2019 demonstrate the superior performance of our framework over other single-stage and multi-stage state-of-the-art (SOTA) methods.
Authors: Zhen Qin, Daoyuan Chen, Wenhao Zhang, Liuyi Yao, Yilun Huang, Bolin Ding, Yaliang Li, Shuiguang Deng
Abstract: The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs, on the other hand, MLLMs can facilitate the development of data. The co-development of multi-modal data and MLLMs requires a clear view of 1) at which development stage of MLLMs can specific data-centric approaches be employed to enhance which capabilities, and 2) by utilizing which capabilities and acting as which roles can models contribute to multi-modal data. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective. A regularly maintained project associated with this survey is accessible at https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md.
URLs: https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md.
Authors: Nourhan Bayasi, Jamil Fayyad, Alceu Bissoto, Ghassan Hamarneh, Rafeef Garbi
Abstract: Continual Learning (CL) is crucial for enabling networks to dynamically adapt as they learn new tasks sequentially, accommodating new data and classes without catastrophic forgetting. Diverging from conventional perspectives on CL, our paper introduces a new perspective wherein forgetting could actually benefit the sequential learning paradigm. Specifically, we present BiasPruner, a CL framework that intentionally forgets spurious correlations in the training data that could lead to shortcut learning. Utilizing a new bias score that measures the contribution of each unit in the network to learning spurious features, BiasPruner prunes those units with the highest bias scores to form a debiased subnetwork preserved for a given task. As BiasPruner learns a new task, it constructs a new debiased subnetwork, potentially incorporating units from previous subnetworks, which improves adaptation and performance on the new task. During inference, BiasPruner employs a simple task-agnostic approach to select the best debiased subnetwork for predictions. We conduct experiments on three medical datasets for skin lesion classification and chest X-Ray classification and demonstrate that BiasPruner consistently outperforms SOTA CL methods in terms of classification performance and fairness. Our code is available here.
Authors: Andrey Ignatov, Josephine Yates, Valentina Boeva
Abstract: Histopathological images are widely used for the analysis of diseased (tumor) tissues and patient treatment selection. While the majority of microscopy image processing was previously done manually by pathologists, recent advances in computer vision allow for accurate recognition of lesion regions with deep learning-based solutions. Such models, however, usually require extensive annotated datasets for training, which is often not the case in the considered task, where the number of available patient data samples is very limited. To deal with this problem, we propose a novel DeepCMorph model pre-trained to learn cell morphology and identify a large number of different cancer types. The model consists of two modules: the first one performs cell nuclei segmentation and annotates each cell type, and is trained on a combination of 8 publicly available datasets to ensure its high generalizability and robustness. The second module combines the obtained segmentation map with the original microscopy image and is trained for the downstream task. We pre-trained this module on the Pan-Cancer TCGA dataset consisting of over 270K tissue patches extracted from 8736 diagnostic slides from 7175 patients. The proposed solution achieved a new state-of-the-art performance on the dataset under consideration, detecting 32 cancer types with over 82% accuracy and outperforming all previously proposed solutions by more than 4%. We demonstrate that the resulting pre-trained model can be easily fine-tuned on smaller microscopy datasets, yielding superior results compared to the current top solutions and models initialized with ImageNet weights. The codes and pre-trained models presented in this paper are available at: https://github.com/aiff22/DeepCMorph
Authors: Edward Wang, Ryan Au, Pencilla Lang, Sarah A. Mattonen
Abstract: Evidence is accumulating in favour of using stereotactic ablative body radiotherapy (SABR) to treat multiple cancer lesions in the lung. Multi-lesion lung SABR plans are complex and require significant resources to create. In this work, we propose a novel two-stage latent transformer framework (LDFormer) for dose prediction of lung SABR plans with varying numbers of lesions. In the first stage, patient anatomical information and the dose distribution are encoded into a latent space. In the second stage, a transformer learns to predict the dose latent from the anatomical latents. Causal attention is modified to adapt to different numbers of lesions. LDFormer outperforms a state-of-the-art generative adversarial network on dose conformality in and around lesions, and the performance gap widens when considering overlapping lesions. LDFormer generates predictions of 3-D dose distributions in under 30s on consumer hardware, and has the potential to assist physicians with clinical decision making, reduce resource costs, and accelerate treatment planning.
Authors: Shuangqi Li, Chen Liu, Tong Zhang, Hieu Le, Sabine S\"usstrunk, Mathieu Salzmann
Abstract: We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with either enhanced fidelity or increased diversity. Our approach involves manipulating the distribution of training and generated data through a novel metric for individual samples, named pseudo density, which is based on the nearest-neighbor information from real samples. Our approach offers three distinct techniques to adjust the fidelity and diversity of deep generative models: 1) Per-sample perturbation, enabling precise adjustments for individual samples towards either more common or more unique characteristics; 2) Importance sampling during model inference to enhance either fidelity or diversity in the generated data; 3) Fine-tuning with importance sampling, which guides the generative model to learn an adjusted distribution, thus controlling fidelity and diversity. Furthermore, our fine-tuning method demonstrates the ability to improve the Frechet Inception Distance (FID) for pre-trained generative models with minimal iterations.
Authors: James Seekings, Peyton Chandarana, Mahsa Ardakani, MohammadReza Mohammadi, Ramtin Zand
Abstract: This paper explores the synergistic potential of neuromorphic and edge computing to create a versatile machine learning (ML) system tailored for processing data captured by dynamic vision sensors. We construct and train hybrid models, blending spiking neural networks (SNNs) and artificial neural networks (ANNs) using PyTorch and Lava frameworks. Our hybrid architecture integrates an SNN for temporal feature extraction and an ANN for classification. We delve into the challenges of deploying such hybrid structures on hardware. Specifically, we deploy individual components on Intel's Neuromorphic Processor Loihi (for SNN) and Jetson Nano (for ANN). We also propose an accumulator circuit to transfer data from the spiking to the non-spiking domain. Furthermore, we conduct comprehensive performance analyses of hybrid SNN-ANN models on a heterogeneous system of neuromorphic and edge AI hardware, evaluating accuracy, latency, power, and energy consumption. Our findings demonstrate that the hybrid spiking networks surpass the baseline ANN model across all metrics and outperform the baseline SNN model in accuracy and latency.
Authors: Sizhe Lester Li, Annan Zhang, Boyuan Chen, Hanna Matusik, Chao Liu, Daniela Rus, Vincent Sitzmann
Abstract: Mirroring the complex structures and diverse functions of natural organisms is a long-standing challenge in robotics. Modern fabrication techniques have dramatically expanded feasible hardware, yet deploying these systems requires control software to translate desired motions into actuator commands. While conventional robots can easily be modeled as rigid links connected via joints, it remains an open challenge to model and control bio-inspired robots that are often multi-material or soft, lack sensing capabilities, and may change their material properties with use. Here, we introduce Neural Jacobian Fields, an architecture that autonomously learns to model and control robots from vision alone. Our approach makes no assumptions about the robot's materials, actuation, or sensing, requires only a single camera for control, and learns to control the robot without expert intervention by observing the execution of random commands. We demonstrate our method on a diverse set of robot manipulators, varying in actuation, materials, fabrication, and cost. Our approach achieves accurate closed-loop control and recovers the causal dynamic structure of each robot. By enabling robot control with a generic camera as the only sensor, we anticipate our work will dramatically broaden the design space of robotic systems and serve as a starting point for lowering the barrier to robotic automation.
Authors: Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Abstract: Vision Transformer (ViT) has recently gained significant attention in solving computer vision (CV) problems due to its capability of extracting informative features and modeling long-range dependencies through the attention mechanism. Whereas recent works have explored the trustworthiness of ViT, including its robustness and explainability, the issue of fairness has not yet been adequately addressed. We establish that the existing fairness-aware algorithms designed for CNNs do not perform well on ViT, which highlights the need to develop our novel framework via Debiased Self-Attention (DSA). DSA is a fairness-through-blindness approach that enforces ViT to eliminate spurious features correlated with the sensitive label for bias mitigation and simultaneously retain real features for target prediction. Notably, DSA leverages adversarial examples to locate and mask the spurious features in the input image patches with an additional attention weights alignment regularizer in the training objective to encourage learning real features for target prediction. Importantly, our DSA framework leads to improved fairness guarantees over prior works on multiple prediction tasks without compromising target prediction performance. Code is available at \href{https://github.com/qiangyao1988/DSA}{https://github.com/qiangyao1988/DSA}.
URLs: https://github.com/qiangyao1988/DSA, https://github.com/qiangyao1988/DSA
Authors: Conghao Xiong, Yi Lin, Hao Chen, Hao Zheng, Dong Wei, Yefeng Zheng, Joseph J. Y. Sung, Irwin King
Abstract: Transferring knowledge from a source domain to a target domain can be crucial for whole slide image classification, since the number of samples in a dataset is often limited due to high annotation costs. However, domain shift and task discrepancy between datasets can hinder effective knowledge transfer. In this paper, we propose a Target-Aware Knowledge Transfer framework, employing a teacher-student paradigm. Our framework enables the teacher model to learn common knowledge from the source and target domains by actively incorporating unlabelled target images into the training of the teacher model. The teacher bag features are subsequently adapted to supervise the training of the student model on the target domain. Despite incorporating the target features during training, the teacher model tends to overlook them under the inherent domain shift and task discrepancy. To alleviate this, we introduce a target-aware feature alignment module to establish a transferable latent relationship between the source and target features by solving the optimal transport problem. Experimental results show that models employing knowledge transfer outperform those trained from scratch, and our method achieves state-of-the-art performance among other knowledge transfer methods on various datasets, including TCGA-RCC, TCGA-NSCLC, and Camelyon16.
Authors: Sergey Sinitsa, Ohad Fried
Abstract: The generation of high-quality images has become widely accessible and is a rapidly evolving process. As a result, anyone can generate images that are indistinguishable from real ones. This leads to a wide range of applications, including malicious usage with deceptive intentions. Despite advances in detection techniques for generated images, a robust detection method still eludes us. Furthermore, model personalization techniques might affect the detection capabilities of existing methods. In this work, we utilize the architectural properties of convolutional neural networks (CNNs) to develop a new detection method. Our method can detect images from a known generative model and enable us to establish relationships between fine-tuned generative models. We tested the method on images produced by both Generative Adversarial Networks (GANs) and recent large text-to-image models (LTIMs) that rely on Diffusion Models. Our approach outperforms others trained under identical conditions and achieves comparable performance to state-of-the-art pre-trained detection methods on images generated by Stable Diffusion and MidJourney, with significantly fewer required train samples.
Authors: Yunfan LU, Guoqiang Liang, Yusheng Wang, Lin Wang, Hui Xiong
Abstract: Video frames captured by rolling shutter (RS) cameras during fast camera movement frequently exhibit RS distortion and blur simultaneously. Naturally, recovering high-frame-rate global shutter (GS) sharp frames from an RS blur frame must simultaneously consider RS correction, deblur, and frame interpolation. A naive way is to decompose the whole process into separate tasks and cascade existing methods; however, this results in cumulative errors and noticeable artifacts. Event cameras enjoy many advantages, e.g., high temporal resolution, making them potential for our problem. To this end, we propose the first and novel approach, named UniINR, to recover arbitrary frame-rate sharp GS frames from an RS blur frame and paired events. Our key idea is unifying spatial-temporal implicit neural representation (INR) to directly map the position and time coordinates to color values to address the interlocking degradations. Specifically, we introduce spatial-temporal implicit encoding (STE) to convert an RS blur image and events into a spatial-temporal representation (STR). To query a specific sharp frame (GS or RS), we embed the exposure time into STR and decode the embedded features pixel-by-pixel to recover a sharp frame. Our method features a lightweight model with only 0.38M parameters, and it also enjoys high inference efficiency, achieving 2.83ms/frame in 31 times frame interpolation of an RS blur frame. Extensive experiments show that our method significantly outperforms prior methods. Code is available at https://github.com/yunfanLu/UniINR.
Authors: Hanxi Li, Jingqi Wu, Lin Yuanbo Wu, Hao Chen, Deyin Liu, Mingwen Wang, Peng Wang
Abstract: Recent advancements in industrial Anomaly Detection (AD) have shown that incorporating a few anomalous samples during training can significantly boost accuracy. However, this performance improvement comes at a high cost: extensive annotation efforts, which are often impractical in real-world applications. In this work, we propose a novel framework called "Weakly-supervised RESidual Transformer" (WeakREST), which aims to achieve high AD accuracy while minimizing the need for extensive annotations. First, we reformulate the pixel-wise anomaly localization task into a block-wise classification problem. By shifting the focus to block-wise level, we can drastically reduce the amount of required annotations without compromising on the accuracy of anomaly detection Secondly, we design a residual-based transformer model, termed "Positional Fast Anomaly Residuals" (PosFAR), to classify the image blocks in real time. We further propose to label the anomalous regions using only bounding boxes or image tags as weaker labels, leading to a semi-supervised learning setting. On the benchmark dataset MVTec-AD, our proposed WeakREST framework achieves a remarkable Average Precision (AP) of 83.0%, significantly outperforming the previous best result of 75.8% in the unsupervised setting. In the supervised AD setting, WeakREST further improves performance, attaining an AP of 87.6% compared to the previous best of 78.6%. Notably, even when utilizing weaker labels based on bounding boxes, WeakREST surpasses recent leading methods that rely on pixel-wise supervision, achieving an AP of 87.1% against the prior best of 78.6% on MVTec-AD. This precision advantage is also consistently observed on other well-known AD datasets, such as BTAD and KSDD2.
Authors: Mu Cai, Zeyi Huang, Yuheng Li, Utkarsh Ojha, Haohan Wang, Yong Jae Lee
Abstract: Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well? This work investigates this question. To enable the LLM to process images, we convert them into a representation given by Scalable Vector Graphics (SVG). To study what the LLM can do with this XML-based textual description of images, we test the LLM on three broad computer vision tasks: (i) visual reasoning and question answering, (ii) image classification under distribution shift, few-shot learning, and (iii) generating new images using visual prompting. Even though we do not naturally associate LLMs with any visual understanding capabilities, our results indicate that the LLM can often do a decent job in many of these tasks, potentially opening new avenues for research into LLMs' ability to understand image data. Our code, data, and models can be found here https://github.com/mu-cai/svg-llm.
Authors: Yuhuan Yang, Chaofan Ma, Chen Ju, Fei Zhang, Jiangchao Yao, Ya Zhang, Yanfeng Wang
Abstract: In semantic segmentation, generalizing a visual system to both seen categories and novel categories at inference time has always been practically valuable yet challenging. To enable such functionality, existing methods mainly rely on either providing several support demonstrations from the visual aspect or characterizing the informative clues from the textual aspect (e.g., the class names). Nevertheless, both two lines neglect the complementary intrinsic of low-level visual and high-level language information, while the explorations that consider visual and textual modalities as a whole to promote predictions are still limited. To close this gap, we propose to encompass textual and visual clues as multi-modal prototypes to allow more comprehensive support for open-world semantic segmentation, and build a novel prototype-based segmentation framework to realize this promise. To be specific, unlike the straightforward combination of bi-modal clues, we decompose the high-level language information as multi-aspect prototypes and aggregate the low-level visual information as more semantic prototypes, on basis of which, a fine-grained complementary fusion makes the multi-modal prototypes more powerful and accurate to promote the prediction. Based on an elastic mask prediction module that permits any number and form of prototype inputs, we are able to solve the zero-shot, few-shot and generalized counterpart tasks in one architecture. Extensive experiments on both PASCAL-$5^i$ and COCO-$20^i$ datasets show the consistent superiority of the proposed method compared with the previous state-of-the-art approaches, and a range of ablation studies thoroughly dissects each component in our framework both quantitatively and qualitatively that verify their effectiveness.
Authors: Yuting Xiao, Jingwei Xu, Zehao Yu, Shenghua Gao
Abstract: In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in indoor scenes from multi-view images presents unique challenges. Indoor scenes typically contain large texture-less regions, making the photometric loss unreliable for optimizing the implicit surface. Previous work utilizes monocular geometry priors to improve the reconstruction in indoor scenes. However, monocular priors often contain substantial errors in thin structure regions due to domain gaps and the inherent inconsistencies when derived independently from different views. This paper presents \textbf{DebSDF} to address these challenges, focusing on the utilization of uncertainty in monocular priors and the bias in SDF-based volume rendering. We propose an uncertainty modeling technique that associates larger uncertainties with larger errors in the monocular priors. High-uncertainty priors are then excluded from optimization to prevent bias. This uncertainty measure also informs an importance-guided ray sampling and adaptive smoothness regularization, enhancing the learning of fine structures. We further introduce a bias-aware signed distance function to density transformation that takes into account the curvature and the angle between the view direction and the SDF normals to reconstruct fine details better. Our approach has been validated through extensive experiments on several challenging datasets, demonstrating improved qualitative and quantitative results in reconstructing thin structures in indoor scenes, thereby outperforming previous work.
Authors: Shengkun Tang, Yaqing Wang, Caiwen Ding, Yi Liang, Yao Li, Dongkuan Xu
Abstract: Diffusion models achieve great success in generating diverse and high-fidelity images, yet their widespread application, especially in real-time scenarios, is hampered by their inherently slow generation speed. The slow generation stems from the necessity of multi-step network inference. While some certain predictions benefit from the full computation of the model in each sampling iteration, not every iteration requires the same amount of computation, potentially leading to inefficient computation. Unlike typical adaptive computation challenges that deal with single-step generation problems, diffusion processes with a multi-step generation need to dynamically adjust their computational resource allocation based on the ongoing assessment of each step's importance to the final image output, presenting a unique set of challenges. In this work, we propose AdaDiff, an adaptive framework that dynamically allocates computation resources in each sampling step to improve the generation efficiency of diffusion models. To assess the effects of changes in computational effort on image quality, we present a timestep-aware uncertainty estimation module (UEM). Integrated at each intermediate layer, the UEM evaluates the predictive uncertainty. This uncertainty measurement serves as an indicator for determining whether to terminate the inference process. Additionally, we introduce an uncertainty-aware layer-wise loss aimed at bridging the performance gap between full models and their adaptive counterparts.
Authors: Xinhao Li, Yuhan Zhu, Limin Wang
Abstract: Adapting image models to the video domain has emerged as an efficient paradigm for solving video recognition tasks. Due to the huge number of parameters and effective transferability of image models, performing full fine-tuning is less efficient and even unnecessary. Thus, recent research is shifting its focus toward parameter-efficient image-to-video adaptation. However, these adaptation strategies inevitably introduce extra computational costs to deal with the domain gap and temporal modeling in videos. In this paper, we present a new adaptation paradigm (ZeroI2V) to transfer the image transformers to video recognition tasks (i.e., introduce zero extra cost to the original models during inference). To achieve this goal, we present two core designs. First, to capture the dynamics in videos and reduce the difficulty of image-to-video adaptation, we exploit the flexibility of self-attention and introduce spatial-temporal dual-headed attention (STDHA). This approach efficiently endows the image transformers with temporal modeling capability at zero extra parameters and computation. Second, to handle the domain gap between images and videos, we propose a linear adaption strategy that utilizes lightweight densely placed linear adapters to fully transfer the frozen image models to video recognition. Thanks to the customized linear design, all newly added adapters could be easily merged with the original modules through structural reparameterization after training, enabling zero extra cost during inference. Extensive experiments on representative fully-supervised and few-shot video recognition benchmarks showcase that ZeroI2V can match or even outperform previous state-of-the-art methods while enjoying superior parameter and inference efficiency.
Authors: Xinpeng Liu, Yong-Lu Li, Ailing Zeng, Zizheng Zhou, Yang You, Cewu Lu
Abstract: Motion understanding aims to establish a reliable mapping between motion and action semantics, while it is a challenging many-to-many problem. An abstract action semantic (i.e., walk forwards) could be conveyed by perceptually diverse motions (walking with arms up or swinging). In contrast, a motion could carry different semantics w.r.t. its context and intention. This makes an elegant mapping between them difficult. Previous attempts adopted direct-mapping paradigms with limited reliability. Also, current automatic metrics fail to provide reliable assessments of the consistency between motions and action semantics. We identify the source of these problems as the significant gap between the two modalities. To alleviate this gap, we propose Kinematic Phrases (KP) that take the objective kinematic facts of human motion with proper abstraction, interpretability, and generality. Based on KP, we can unify a motion knowledge base and build a motion understanding system. Meanwhile, KP can be automatically converted from motions to text descriptions with no subjective bias, inspiring Kinematic Prompt Generation (KPG) as a novel white-box motion generation benchmark. In extensive experiments, our approach shows superiority over other methods. Our project is available at https://foruck.github.io/KP/.
Authors: Oriane Sim\'eoni, \'Eloi Zablocki, Spyros Gidaris, Gilles Puy, Patrick P\'erez
Abstract: The recent enthusiasm for open-world vision systems show the high interest of the community to perform perception tasks outside of the closed-vocabulary benchmark setups which have been so popular until now. Being able to discover objects in images/videos without knowing in advance what objects populate the dataset is an exciting prospect. But how to find objects without knowing anything about them? Recent works show that it is possible to perform class-agnostic unsupervised object localization by exploiting self-supervised pre-trained features. We propose here a survey of unsupervised object localization methods that discover objects in images without requiring any manual annotation in the era of self-supervised ViTs. We gather links of discussed methods in the repository https://github.com/valeoai/Awesome-Unsupervised-Object-Localization.
URLs: https://github.com/valeoai/Awesome-Unsupervised-Object-Localization.
Authors: Shuai Yang, Zhifei Chen, Pengguang Chen, Xi Fang, Shu Liu, Yingcong Chen
Abstract: Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models.
Authors: Yichao Cai, Yuhang Liu, Zhen Zhang, Javen Qinfeng Shi
Abstract: Contrastive vision-language models, such as CLIP, have garnered considerable attention for various dowmsteam tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often blend content and style information, which somewhat limits their generalization capabilities under distribution shifts. To address this limitation, we adopt a causal generative perspective for multimodal data and propose contrastive learning with data augmentation to disentangle content features from the original representations. To achieve this, we begin with exploring image augmentation techniques and develop a method to seamlessly integrate them into pre-trained CLIP-like models to extract pure content features. Taking a step further, recognizing the inherent semantic richness and logical structure of text data, we explore the use of text augmentation to isolate latent content from style features. This enables CLIP-like model's encoders to concentrate on latent content information, refining the learned representations by pre-trained CLIP-like models. Our extensive experiments across diverse datasets demonstrate significant improvements in zero-shot and few-shot classification tasks, alongside enhanced robustness to various perturbations. These results underscore the effectiveness of our proposed methods in refining vision-language representations and advancing the state-of-the-art in multimodal learning.
Authors: Xiaobao Wei, Jiajun Cao, Yizhu Jin, Ming Lu, Guangyu Wang, Shanghang Zhang
Abstract: With the development of Deep Neural Networks (DNNs), many efforts have been made to handle medical image segmentation. Traditional methods such as nnUNet train specific segmentation models on the individual datasets. Plenty of recent methods have been proposed to adapt the foundational Segment Anything Model (SAM) to medical image segmentation. However, they still focus on discrete representations to generate pixel-wise predictions, which are spatially inflexible and scale poorly to higher resolution. In contrast, implicit methods learn continuous representations for segmentation, which is crucial for medical image segmentation. In this paper, we propose I-MedSAM, which leverages the benefits of both continuous representations and SAM, to obtain better cross-domain ability and accurate boundary delineation. Since medical image segmentation needs to predict detailed segmentation boundaries, we designed a novel adapter to enhance the SAM features with high-frequency information during Parameter-Efficient Fine-Tuning (PEFT). To convert the SAM features and coordinates into continuous segmentation output, we utilize Implicit Neural Representation (INR) to learn an implicit segmentation decoder. We also propose an uncertainty-guided sampling strategy for efficient learning of INR. Extensive evaluations on 2D medical image segmentation tasks have shown that our proposed method with only 1.6M trainable parameters outperforms existing methods including discrete and implicit methods. The code will be available at: https://github.com/ucwxb/I-MedSAM.
Authors: Or Hirschorn, Shai Avidan
Abstract: Traditional 2D pose estimation models are limited by their category-specific design, making them suitable only for predefined object categories. This restriction becomes particularly challenging when dealing with novel objects due to the lack of relevant training data. To address this limitation, category-agnostic pose estimation (CAPE) was introduced. CAPE aims to enable keypoint localization for arbitrary object categories using a few-shot single model, requiring minimal support images with annotated keypoints. We present a significant departure from conventional CAPE techniques, which treat keypoints as isolated entities, by treating the input pose data as a graph. We leverage the inherent geometrical relations between keypoints through a graph-based network to break symmetry, preserve structure, and better handle occlusions. We validate our approach on the MP-100 benchmark, a comprehensive dataset comprising over 20,000 images spanning over 100 categories. Our solution boosts performance by 0.98% under a 1-shot setting, achieving a new state-of-the-art for CAPE. Additionally, we enhance the dataset with skeleton annotations. Our code and data are publicly available.
Authors: Kyungho Bae, Geo Ahn, Youngrae Kim, Jinwoo Choi
Abstract: When watching a video, humans can naturally extract human actions from the surrounding scene context, even when action-scene combinations are unusual. However, unlike humans, video action recognition models often learn scene-biased action representations from the spurious correlation in training data, leading to poor performance in out-of-context scenarios. While scene-debiased models achieve improved performance in out-of-context scenarios, they often overlook valuable scene information in the data. Addressing this challenge, we propose Disentangled VIdeo representations of Action and Scene (DEVIAS), which aims to achieve holistic video understanding. Disentangled action and scene representations with our method could provide flexibility to adjust the emphasis on action or scene information depending on downstream task and dataset characteristics. Disentangled action and scene representations could be beneficial for both in-context and out-of-context video understanding. To this end, we employ slot attention to learn disentangled action and scene representations with a single model, along with auxiliary tasks that further guide slot attention. We validate the proposed method on both in-context datasets: UCF-101 and Kinetics-400, and out-of-context datasets: SCUBA and HAT. Our proposed method shows favorable performance across different datasets compared to the baselines, demonstrating its effectiveness in diverse video understanding scenarios.
Authors: Ming Nie, Renyuan Peng, Chunwei Wang, Xinyue Cai, Jianhua Han, Hang Xu, Li Zhang
Abstract: Large vision-language models (VLMs) have garnered increasing interest in autonomous driving areas, due to their advanced capabilities in complex reasoning tasks essential for highly autonomous vehicle behavior. Despite their potential, research in autonomous systems is hindered by the lack of datasets with annotated reasoning chains that explain the decision-making processes in driving. To bridge this gap, we present Reason2Drive, a benchmark dataset with over 600K video-text pairs, aimed at facilitating the study of interpretable reasoning in complex driving environments. We distinctly characterize the autonomous driving process as a sequential combination of perception, prediction, and reasoning steps, and the question-answer pairs are automatically collected from a diverse range of open-source outdoor driving datasets, including nuScenes, Waymo and ONCE. Moreover, we introduce a novel aggregated evaluation metric to assess chain-based reasoning performance in autonomous systems, addressing the semantic ambiguities of existing metrics such as BLEU and CIDEr. Based on the proposed benchmark, we conduct experiments to assess various existing VLMs, revealing insights into their reasoning capabilities. Additionally, we develop an efficient approach to empower VLMs to leverage object-level perceptual elements in both feature extraction and prediction, further enhancing their reasoning accuracy. The code and dataset will be released.
Authors: Shaofei Wang, Bo\v{z}idar Anti\'c, Andreas Geiger, Siyu Tang
Abstract: We present IntrinsicAvatar, a novel approach to recovering the intrinsic properties of clothed human avatars including geometry, albedo, material, and environment lighting from only monocular videos. Recent advancements in human-based neural rendering have enabled high-quality geometry and appearance reconstruction of clothed humans from just monocular videos. However, these methods bake intrinsic properties such as albedo, material, and environment lighting into a single entangled neural representation. On the other hand, only a handful of works tackle the problem of estimating geometry and disentangled appearance properties of clothed humans from monocular videos. They usually achieve limited quality and disentanglement due to approximations of secondary shading effects via learned MLPs. In this work, we propose to model secondary shading effects explicitly via Monte-Carlo ray tracing. We model the rendering process of clothed humans as a volumetric scattering process, and combine ray tracing with body articulation. Our approach can recover high-quality geometry, albedo, material, and lighting properties of clothed humans from a single monocular video, without requiring supervised pre-training using ground truth materials. Furthermore, since we explicitly model the volumetric scattering process and ray tracing, our model naturally generalizes to novel poses, enabling animation of the reconstructed avatar in novel lighting conditions.
Authors: Luchuan Song, Pinxin Liu, Lele Chen, Guojun Yin, Chenliang Xu
Abstract: Recent years have witnessed considerable achievements in facial avatar reconstruction with neural volume rendering. Despite notable advancements, the reconstruction of complex and dynamic head movements from monocular videos still suffers from capturing and restoring fine-grained details. In this work, we propose a novel approach, named Tri$^2$-plane, for monocular photo-realistic volumetric head avatar reconstructions. Distinct from the existing works that rely on a single tri-plane deformation field for dynamic facial modeling, the proposed Tri$^2$-plane leverages the principle of feature pyramids and three top-to-down lateral connections tri-planes for details improvement. It samples and renders facial details at multiple scales, transitioning from the entire face to specific local regions and then to even more refined sub-regions. Moreover, we incorporate a camera-based geometry-aware sliding window method as an augmentation in training, which improves the robustness beyond the canonical space, with a particular improvement in cross-identity generation capabilities. Experimental outcomes indicate that the Tri$^2$-plane not only surpasses existing methodologies but also achieves superior performance across quantitative and qualitative assessments. The project website is: \url{https://songluchuan.github.io/Tri2Plane.github.io/}.
Authors: Zixiang Zhao, Lilun Deng, Haowen Bai, Yukun Cui, Zhipeng Zhang, Yulun Zhang, Haotong Qin, Dongdong Chen, Jiangshe Zhang, Peng Wang, Luc Van Gool
Abstract: Image fusion integrates essential information from multiple images into a single composite, enhancing structures, textures, and refining imperfections. Existing methods predominantly focus on pixel-level and semantic visual features for recognition, but often overlook the deeper text-level semantic information beyond vision. Therefore, we introduce a novel fusion paradigm named image Fusion via vIsion-Language Model (FILM), for the first time, utilizing explicit textual information from source images to guide the fusion process. Specifically, FILM generates semantic prompts from images and inputs them into ChatGPT for comprehensive textual descriptions. These descriptions are fused within the textual domain and guide the visual information fusion, enhancing feature extraction and contextual understanding, directed by textual semantic information via cross-attention. FILM has shown promising results in four image fusion tasks: infrared-visible, medical, multi-exposure, and multi-focus image fusion. We also propose a vision-language dataset containing ChatGPT-generated paragraph descriptions for the eight image fusion datasets across four fusion tasks, facilitating future research in vision-language model-based image fusion. Code and dataset are available at https://github.com/Zhaozixiang1228/IF-FILM.
Authors: Yixuan Wu, Kaiyuan Hu, Danny Z. Chen, Jian Wu
Abstract: With the rapid advance of computer graphics and artificial intelligence technologies, the ways we interact with the world have undergone a transformative shift. Virtual Reality (VR) technology, aided by artificial intelligence (AI), has emerged as a dominant interaction media in multiple application areas, thanks to its advantage of providing users with immersive experiences. Among those applications, medicine is considered one of the most promising areas. In this paper, we present a comprehensive examination of the burgeoning field of AI-enhanced VR applications in medical care and services. By introducing a systematic taxonomy, we meticulously classify the pertinent techniques and applications into three well-defined categories based on different phases of medical diagnosis and treatment: Visualization Enhancement, VR-related Medical Data Processing, and VR-assisted Intervention. This categorization enables a structured exploration of the diverse roles that AI-powered VR plays in the medical domain, providing a framework for a more comprehensive understanding and evaluation of these technologies. To our best knowledge, this is the first systematic survey of AI-powered VR systems in medical settings, laying a foundation for future research in this interdisciplinary domain.
Authors: Xin Liu, Jiamin Wu, and Wenfei Yang, Xu Zhou, Tianzhu Zhang
Abstract: Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet overlooking multi-modal attribute characteristics. This limitation hinders the model's ability to perceive fine-grained visual details and restricts its generalization ability to a broader range of unseen classes. To address this issue, we propose a Multi-modal Attribute Prompting method (MAP) by jointly exploring textual attribute prompting, visual attribute prompting, and attribute-level alignment. The proposed MAP enjoys several merits. First, we introduce learnable visual attribute prompts enhanced by textual attribute semantics to adaptively capture visual attributes for images from unknown categories, boosting fine-grained visual perception capabilities for CLIP. Second, the proposed attribute-level alignment complements the global alignment to enhance the robustness of cross-modal alignment for open-vocabulary objects. To our knowledge, this is the first work to establish cross-modal attribute-level alignment for CLIP-based few-shot adaptation. Extensive experimental results on 11 datasets demonstrate that our method performs favorably against state-of-the-art approaches.
Authors: Tianyuan Yuan, Yucheng Mao, Jiawei Yang, Yicheng Liu, Yue Wang, Hang Zhao
Abstract: Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges persist under conditions like occlusion, extreme lighting, or in unfamiliar urban areas. Unlike these systems, humans do not solely depend on immediate observations to perceive the environment. In navigating new cities, humans gradually develop a preliminary mental map to supplement real-time perception during subsequent visits. Inspired by this human approach, we introduce a novel framework, PreSight, that leverages past traversals to construct static prior memories, enhancing online perception in later navigations. Our method involves optimizing a city-scale neural radiance field with data from previous journeys to generate neural priors. These priors, rich in semantic and geometric details, are derived without manual annotations and can seamlessly augment various state-of-the-art perception models, improving their efficacy with minimal additional computational cost. Experimental results on the nuScenes dataset demonstrate the framework's high compatibility with diverse online perception models. Specifically, it shows remarkable improvements in HD-map construction and occupancy prediction tasks, highlighting its potential as a new perception framework for autonomous driving systems. Our code will be released at https://github.com/yuantianyuan01/PreSight.
Authors: 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: Tianhe Wu, Kede Ma, Jie Liang, Yujiu Yang, Lei Zhang
Abstract: While Multimodal Large Language Models (MLLMs) have experienced significant advancement in visual understanding and reasoning, their potential to serve as powerful, flexible, interpretable, and text-driven models for Image Quality Assessment (IQA) remains largely unexplored. In this paper, we conduct a comprehensive and systematic study of prompting MLLMs for IQA. We first investigate nine prompting systems for MLLMs as the combinations of three standardized testing procedures in psychophysics (i.e., the single-stimulus, double-stimulus, and multiple-stimulus methods) and three popular prompting strategies in natural language processing (i.e., the standard, in-context, and chain-of-thought prompting). We then present a difficult sample selection procedure, taking into account sample diversity and uncertainty, to further challenge MLLMs equipped with the respective optimal prompting systems. We assess three open-source and one closed-source MLLMs on several visual attributes of image quality (e.g., structural and textural distortions, geometric transformations, and color differences) in both full-reference and no-reference scenarios. Experimental results show that only the closed-source GPT-4V provides a reasonable account for human perception of image quality, but is weak at discriminating fine-grained quality variations (e.g., color differences) and at comparing visual quality of multiple images, tasks humans can perform effortlessly.
Authors: Yeongtak Oh, Jonghyun Lee, Jooyoung Choi, Dahuin Jung, Uiwon Hwang, Sungroh Yoon
Abstract: Test-time adaptation (TTA) addresses the unforeseen distribution shifts occurring during test time. In TTA, performance, memory consumption, and time consumption are crucial considerations. A recent diffusion-based TTA approach for restoring corrupted images involves image-level updates. However, using pixel space diffusion significantly increases resource requirements compared to conventional model updating TTA approaches, revealing limitations as a TTA method. To address this, we propose a novel TTA method that leverages an image editing model based on a latent diffusion model (LDM) and fine-tunes it using our newly introduced corruption modeling scheme. This scheme enhances the robustness of the diffusion model against distribution shifts by creating (clean, corrupted) image pairs and fine-tuning the model to edit corrupted images into clean ones. Moreover, we introduce a distilled variant to accelerate the model for corruption editing using only 4 network function evaluations (NFEs). We extensively validated our method across various architectures and datasets including image and video domains. Our model achieves the best performance with a 100 times faster runtime than that of a diffusion-based baseline. Furthermore, it is three times faster than the previous model updating TTA method that utilizes data augmentation, making an image-level updating approach more feasible.
Authors: Yang Yang, Wen Wang, Liang Peng, Chaotian Song, Yao Chen, Hengjia Li, Xiaolong Yang, Qinglin Lu, Deng Cai, Boxi Wu, Wei Liu
Abstract: Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fusion matrix of multiple Low-Rank Adaptations (LoRAs) to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, where the model struggles to preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through concept injection constraints, enhancing concept visibility via an expanded cross-attention mechanism. To combat concept confusion, concept isolation constraints are introduced, refining the self-attention computation. Furthermore, latent re-initialization is proposed to effectively stimulate concept-specific latent within designated regions. Our extensive testing showcases a notable enhancement in LoRA-Composer's performance compared to standard baselines, especially when eliminating the image-based conditions like canny edge or pose estimations. Code is released at \url{https://github.com/Young98CN/LoRA_Composer}
Authors: Jingyu Lin, Jiaqi Gu, Bojian Wu, Lubin Fan, Renjie Chen, Ligang Liu, Jieping Ye
Abstract: We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose Regression (APR) architecture, together with an augmented NeRF module. This integration not only facilitates the generation of novel views to enrich the training dataset but also enables the learning of effective pose features. Additionally, we extend our architecture for self-supervised online alignment, allowing our method to be used and fine-tuned for unlabelled images within a unified framework. Experiments demonstrate that our method achieves 14.28% and 20.51% performance gain on average in indoor and outdoor benchmark scenes, outperforming existing APR methods with state-of-the-art accuracy.
Authors: Hanzhou Liu, Binghan Li, Chengkai Liu, Mi Lu
Abstract: Although prior state-of-the-art (SOTA) deblurring networks achieve high metric scores on synthetic datasets, there are two challenges which prevent them from perceptual image deblurring. First, a deblurring model overtrained on synthetic datasets may collapse in a broad range of unseen real-world scenarios. Second, the conventional metrics PSNR and SSIM may not correctly reflect the perceptual quality observed by human eyes. To this end, we propose DeblurDiNAT, a generalizable and efficient encoder-decoder Transformer which restores clean images visually close to the ground truth. We adopt an alternating dilation factor structure to capture local and global blur patterns. We propose a local cross-channel learner to assist self-attention layers to learn short-range cross-channel relationships. In addition, we present a linear feed-forward network and a non-linear dual-stage feature fusion module for faster feature propagation across the network. Compared to nearest competitors, our model demonstrates the strongest generalization ability and achieves the best perceptual quality on mainstream image deblurring datasets with 3%-68% fewer parameters.
Authors: Yu Deng, Duomin Wang, Baoyuan Wang
Abstract: In this paper, we propose a novel learning approach for feed-forward one-shot 4D head avatar synthesis. Different from existing methods that often learn from reconstructing monocular videos guided by 3DMM, we employ pseudo multi-view videos to learn a 4D head synthesizer in a data-driven manner, avoiding reliance on inaccurate 3DMM reconstruction that could be detrimental to the synthesis performance. The key idea is to first learn a 3D head synthesizer using synthetic multi-view images to convert monocular real videos into multi-view ones, and then utilize the pseudo multi-view videos to learn a 4D head synthesizer via cross-view self-reenactment. By leveraging a simple vision transformer backbone with motion-aware cross-attentions, our method exhibits superior performance compared to previous methods in terms of reconstruction fidelity, geometry consistency, and motion control accuracy. We hope our method offers novel insights into integrating 3D priors with 2D supervisions for improved 4D head avatar creation.
Authors: Florian Strohm, Mihai B\^ace, Andreas Bulling
Abstract: We present User-predictable Face Editing (UP-FacE) -- a novel method for predictable face shape editing. In stark contrast to existing methods for face editing using trial and error, edits with UP-FacE are predictable by the human user. That is, users can control the desired degree of change precisely and deterministically and know upfront the amount of change required to achieve a certain editing result. Our method leverages facial landmarks to precisely measure facial feature values, facilitating the training of UP-FacE without manually annotated attribute labels. At the core of UP-FacE is a transformer-based network that takes as input a latent vector from a pre-trained generative model and a facial feature embedding, and predicts a suitable manipulation vector. To enable user-predictable editing, a scaling layer adjusts the manipulation vector to achieve the precise desired degree of change. To ensure that the desired feature is manipulated towards the target value without altering uncorrelated features, we further introduce a novel semantic face feature loss. Qualitative and quantitative results demonstrate that UP-FacE enables precise and fine-grained control over 23 face shape features.
Authors: Narek Tumanyan, Assaf Singer, Shai Bagon, Tali Dekel
Abstract: We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT model. Specifically, our framework simultaneously adopts DINO's features to fit to the motion observations of the test video, while training a tracker that directly leverages the refined features. The entire framework is trained end-to-end using a combination of self-supervised losses, and regularization that allows us to retain and benefit from DINO's semantic prior. Extensive evaluation demonstrates that our method achieves state-of-the-art results on known benchmarks. DINO-tracker significantly outperforms self-supervised methods and is competitive with state-of-the-art supervised trackers, while outperforming them in challenging cases of tracking under long-term occlusions.
Authors: Adam Pardyl, Micha{\l} Wronka, Maciej Wo{\l}czyk, Kamil Adamczewski, Tomasz Trzci\'nski, Bartosz Zieli\'nski
Abstract: Active Visual Exploration (AVE) is a task that involves dynamically selecting observations (glimpses), which is critical to facilitate comprehension and navigation within an environment. While modern AVE methods have demonstrated impressive performance, they are constrained to fixed-scale glimpses from rigid grids. In contrast, existing mobile platforms equipped with optical zoom capabilities can capture glimpses of arbitrary positions and scales. To address this gap between software and hardware capabilities, we introduce AdaGlimpse. It uses Soft Actor-Critic, a reinforcement learning algorithm tailored for exploration tasks, to select glimpses of arbitrary position and scale. This approach enables our model to rapidly establish a general awareness of the environment before zooming in for detailed analysis. Experimental results demonstrate that AdaGlimpse surpasses previous methods across various visual tasks while maintaining greater applicability in realistic AVE scenarios.
Authors: Yingsen Zeng, Yujie Zhong, Chengjian Feng, Lin Ma
Abstract: Temporal Action Detection (TAD) focuses on detecting pre-defined actions, while Moment Retrieval (MR) aims to identify the events described by open-ended natural language within untrimmed videos. Despite that they focus on different events, we observe they have a significant connection. For instance, most descriptions in MR involve multiple actions from TAD. In this paper, we aim to investigate the potential synergy between TAD and MR. Firstly, we propose a unified architecture, termed Unified Moment Detection (UniMD), for both TAD and MR. It transforms the inputs of the two tasks, namely actions for TAD or events for MR, into a common embedding space, and utilizes two novel query-dependent decoders to generate a uniform output of classification score and temporal segments. Secondly, we explore the efficacy of two task fusion learning approaches, pre-training and co-training, in order to enhance the mutual benefits between TAD and MR. Extensive experiments demonstrate that the proposed task fusion learning scheme enables the two tasks to help each other and outperform the separately trained counterparts. Impressively, UniMD achieves state-of-the-art results on three paired datasets Ego4D, Charades-STA, and ActivityNet. Our code is available at https://github.com/yingsen1/UniMD.
Authors: Xiaoyi Bao, Siyang Sun, Shuailei Ma, Kecheng Zheng, Yuxin Guo, Guosheng Zhao, Yun Zheng, Xingang Wang
Abstract: The reasoning segmentation task, which demands a nuanced comprehension of intricate queries to accurately pinpoint object regions, is attracting increasing attention. However, Multi-modal Large Language Models (MLLM) often find it difficult to accurately localize the objects described in complex reasoning contexts. We believe that the act of reasoning segmentation should mirror the cognitive stages of human visual search, where each step is a progressive refinement of thought toward the final object. Thus we introduce the Chains of Reasoning and Segmenting (CoReS) and find this top-down visual hierarchy indeed enhances the visual search process. Specifically, we propose a dual-chain structure that generates multi-modal, chain-like outputs to aid the segmentation process. Furthermore, to steer the MLLM's outputs into this intended hierarchy, we incorporate in-context inputs as guidance. Extensive experiments demonstrate the superior performance of our CoReS, which surpasses the state-of-the-art method by 6.5\% on the ReasonSeg dataset. Project: https://chain-of-reasoning-and-segmentation.github.io/.
URLs: https://chain-of-reasoning-and-segmentation.github.io/.
Authors: Ahan Shabanov, Shrisudhan Govindarajan, Cody Reading, Lily Goli, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
Abstract: Largely due to their implicit nature, neural fields lack a direct mechanism for filtering, as Fourier analysis from discrete signal processing is not directly applicable to these representations. Effective filtering of neural fields is critical to enable level-of-detail processing in downstream applications, and support operations that involve sampling the field on regular grids (e.g. marching cubes). Existing methods that attempt to decompose neural fields in the frequency domain either resort to heuristics or require extensive modifications to the neural field architecture. We show that via a simple modification, one can obtain neural fields that are low-pass filtered, and in turn show how this can be exploited to obtain a frequency decomposition of the entire signal. We demonstrate the validity of our technique by investigating level-of-detail reconstruction, and showing how coarser representations can be computed effectively.
Authors: Jingxue Huang, Xilai Li, Tianshu Tan, Xiaosong Li, Tao Ye
Abstract: Multi-modal image fusion (MMIF) maps useful information from various modalities into the same representation space, thereby producing an informative fused image. However, the existing fusion algorithms tend to symmetrically fuse the multi-modal images, causing the loss of shallow information or bias towards a single modality in certain regions of the fusion results. In this study, we analyzed the spatial distribution differences of information in different modalities and proved that encoding features within the same network is not conducive to achieving simultaneous deep feature space alignment for multi-modal images. To overcome this issue, a Multi-Modal Asymmetric UNet (MMA-UNet) was proposed. We separately trained specialized feature encoders for different modal and implemented a cross-scale fusion strategy to maintain the features from different modalities within the same representation space, ensuring a balanced information fusion process. Furthermore, extensive fusion and downstream task experiments were conducted to demonstrate the efficiency of MMA-UNet in fusing infrared and visible image information, producing visually natural and semantically rich fusion results. Its performance surpasses that of the state-of-the-art comparison fusion methods.
Authors: Scott C. Lowe, Benjamin Misiuk, Isaac Xu, Shakhboz Abdulazizov, Amit R. Baroi, Alex C. Bastos, Merlin Best, Vicki Ferrini, Ariell Friedman, Deborah Hart, Ove Hoegh-Guldberg, Daniel Ierodiaconou, Julia Mackin-McLaughlin, Kathryn Markey, Pedro S. Menandro, Jacquomo Monk, Shreya Nemani, John O'Brien, Elizabeth Oh, Luba Y. Reshitnyk, Katleen Robert, Chris M. Roelfsema, Jessica A. Sameoto, Alexandre C. G. Schimel, Jordan A. Thomson, Brittany R. Wilson, Melisa C. Wong, Craig J. Brown, Thomas Trappenberg
Abstract: Advances in underwater imaging enable the collection of extensive seafloor image datasets that are necessary for monitoring important benthic ecosystems. The ability to collect seafloor imagery has outpaced our capacity to analyze it, hindering expedient mobilization of this crucial environmental information. Recent machine learning approaches provide opportunities to increase the efficiency with which seafloor image datasets are analyzed, yet large and consistent datasets necessary to support development of such approaches are scarce. Here we present BenthicNet: a global compilation of seafloor imagery designed to support the training and evaluation of large-scale image recognition models. An initial set of over 11.4 million images was collected and curated to represent a diversity of seafloor environments using a representative subset of 1.3 million images. These are accompanied by 2.6 million annotations translated to the CATAMI scheme, which span 190,000 of the images. A large deep learning model was trained on this compilation and preliminary results suggest it has utility for automating large and small-scale image analysis tasks. The compilation and model are made openly available for use by the scientific community at https://doi.org/10.20383/103.0614.
Authors: Qingtian Zhu, Zizhuang Wei, Zhongtian Zheng, Yifan Zhan, Zhuyu Yao, Jiawang Zhang, Kejian Wu, Yinqiang Zheng
Abstract: Point-based representations have recently gained popularity in novel view synthesis, for their unique advantages, e.g., intuitive geometric representation, simple manipulation, and faster convergence. However, based on our observation, these point-based neural re-rendering methods are only expected to perform well under ideal conditions and suffer from noisy, patchy points and unbounded scenes, which are challenging to handle but defacto common in real applications. To this end, we revisit one such influential method, known as Neural Point-based Graphics (NPBG), as our baseline, and propose Robust Point-based Graphics (RPBG). We in-depth analyze the factors that prevent NPBG from achieving satisfactory renderings on generic datasets, and accordingly reform the pipeline to make it more robust to varying datasets in-the-wild. Inspired by the practices in image restoration, we greatly enhance the neural renderer to enable the attention-based correction of point visibility and the inpainting of incomplete rasterization, with only acceptable overheads. We also seek for a simple and lightweight alternative for environment modeling and an iterative method to alleviate the problem of poor geometry. By thorough evaluation on a wide range of datasets with different shooting conditions and camera trajectories, RPBG stably outperforms the baseline by a large margin, and exhibits its great robustness over state-of-the-art NeRF-based variants. Code available at https://github.com/QT-Zhu/RPBG.
Authors: Jihwan Kwak, Sungmin Cha, Taesup Moon
Abstract: This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with different pixel labels, which is far from practical incremental learning scenarios. Moreover, we identified that this flawed scenario may lead to biased results for two commonly used techniques in CISS, pseudo-labeling and exemplar memory, resulting in unintended advantages or disadvantages for certain techniques. To mitigate this, a practical scenario called partitioned is proposed, in which the dataset is first divided into distinct subsets representing each class, and then the subsets are assigned to each corresponding task. This efficiently addresses the issue above while meeting the requirement of CISS scenario, such as capturing the background shifts. Furthermore, we identify and address the code implementation issues related to retrieving data from the exemplar memory, which was ignored in previous works. Lastly, we introduce a simple yet competitive memory-based baseline, MiB-AugM, that handles background shifts of current tasks in the exemplar memory. This baseline achieves state-of-the-art results across multiple tasks involving learning numerous new classes.
Authors: Bing Cao, Haiyu Yao, Pengfei Zhu, Qinghua Hu
Abstract: Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features of tiny objects. Existing methods usually perform generation-based feature enhancement, which is seriously affected by spurious textures and artifacts, making it difficult to make the tiny-object-specific features visible and clear for detection. To address this issue, we propose a self-reconstructed tiny object detection (SR-TOD) framework. We for the first time introduce a self-reconstruction mechanism in the detection model, and discover the strong correlation between it and the tiny objects. Specifically, we impose a reconstruction head in-between the neck of a detector, constructing a difference map of the reconstructed image and the input, which shows high sensitivity to tiny objects. This inspires us to enhance the weak representations of tiny objects under the guidance of the difference maps. Thus, improving the visibility of tiny objects for the detectors. Building on this, we further develop a Difference Map Guided Feature Enhancement (DGFE) module to make the tiny feature representation more clear. In addition, we further propose a new multi-instance anti-UAV dataset, which is called DroneSwarms dataset and contains a large number of tiny drones with the smallest average size to date. Extensive experiments on the DroneSwarms dataset and other datasets demonstrate the effectiveness of the proposed method. The code and dataset will be publicly available.
Authors: Jiawei Zhang, Jiahe Li, Xiaohan Yu, Lei Huang, Lin Gu, Jin Zheng, Xiao Bai
Abstract: 3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization perspective for improving sparse-view 3DGS. When training two 3D Gaussian radiance fields, we observe that the two radiance fields exhibit point disagreement and rendering disagreement that can unsupervisedly predict reconstruction quality, stemming from the randomness of densification implementation. We further quantify the two disagreements and demonstrate the negative correlation between them and accurate reconstruction, which allows us to identify inaccurate reconstruction without accessing ground-truth information. Based on the study, we propose CoR-GS, which identifies and suppresses inaccurate reconstruction based on the two disagreements: (1) Co-pruning considers Gaussians that exhibit high point disagreement in inaccurate positions and prunes them. (2) Pseudo-view co-regularization considers pixels that exhibit high rendering disagreement are inaccurate and suppress the disagreement. Results on LLFF, Mip-NeRF360, DTU, and Blender demonstrate that CoR-GS effectively regularizes the scene geometry, reconstructs the compact representations, and achieves state-of-the-art novel view synthesis quality under sparse training views.
Authors: Muyao Niu, Xiaodong Cun, Xintao Wang, Yong Zhang, Ying Shan, Yinqiang Zheng
Abstract: We present MOFA-Video, an advanced controllable image animation method that generates video from the given image using various additional controllable signals (such as human landmarks reference, manual trajectories, and another even provided video) or their combinations. This is different from previous methods which only can work on a specific motion domain or show weak control abilities with diffusion prior. To achieve our goal, we design several domain-aware motion field adapters (\ie, MOFA-Adapters) to control the generated motions in the video generation pipeline. For MOFA-Adapters, we consider the temporal motion consistency of the video and generate the dense motion flow from the given sparse control conditions first, and then, the multi-scale features of the given image are wrapped as a guided feature for stable video diffusion generation. We naively train two motion adapters for the manual trajectories and the human landmarks individually since they both contain sparse information about the control. After training, the MOFA-Adapters in different domains can also work together for more controllable video generation. Project Page: https://myniuuu.github.io/MOFA_Video/
Authors: Fang Li, Hao Zhang, Narendra Ahuja
Abstract: Gaussian Splatting (GS) has significantly elevated scene reconstruction efficiency and novel view synthesis (NVS) accuracy compared to Neural Radiance Fields (NeRF), particularly for dynamic scenes. However, current 4D NVS methods, whether based on GS or NeRF, primarily rely on camera parameters provided by COLMAP and even utilize sparse point clouds generated by COLMAP for initialization, which lack accuracy as well are time-consuming. This sometimes results in poor dynamic scene representation, especially in scenes with large object movements, or extreme camera conditions e.g. small translations combined with large rotations. Some studies simultaneously optimize the estimation of camera parameters and scenes, supervised by additional information like depth, optical flow, etc. obtained from off-the-shelf models. Using this unverified information as ground truth can reduce robustness and accuracy, which does frequently occur for long monocular videos (with e.g. > hundreds of frames). We propose a novel approach that learns a high-fidelity 4D GS scene representation with self-calibration of camera parameters. It includes the extraction of 2D point features that robustly represent 3D structure, and their use for subsequent joint optimization of camera parameters and 3D structure towards overall 4D scene optimization. We demonstrate the accuracy and time efficiency of our method through extensive quantitative and qualitative experimental results on several standard benchmarks. The results show significant improvements over state-of-the-art methods for 4D novel view synthesis. The source code will be released soon at https://github.com/fangli333/SC-4DGS.
Authors: Jianzhao Wang, Yanyan Wei, Dehua Hu, Yilin Zhang, Shengeng Tang, Kun Li, Zhao Zhang
Abstract: This technical report presents our team's solution for the WeatherProof Dataset Challenge: Semantic Segmentation in Adverse Weather at CVPR'24 UG2+. We propose a two-stage deep learning framework for this task. In the first stage, we preprocess the provided dataset by concatenating images into video sequences. Subsequently, we leverage a low-rank video deraining method to generate high-fidelity pseudo ground truths. These pseudo ground truths offer superior alignment compared to the original ground truths, facilitating model convergence during training. In the second stage, we employ the InternImage network to train for the semantic segmentation task using the generated pseudo ground truths. Notably, our meticulously designed framework demonstrates robustness to degraded data captured under adverse weather conditions. In the challenge, our solution achieved a competitive score of 0.43 on the Mean Intersection over Union (mIoU) metric, securing a respectable rank of 4th.
Authors: Yushi Hu, Weijia Shi, Xingyu Fu, Dan Roth, Mari Ostendorf, Luke Zettlemoyer, Noah A Smith, Ranjay Krishna
Abstract: Humans draw to facilitate reasoning: we draw auxiliary lines when solving geometry problems; we mark and circle when reasoning on maps; we use sketches to amplify our ideas and relieve our limited-capacity working memory. However, such actions are missing in current multimodal language models (LMs). Current chain-of-thought and tool-use paradigms only use text as intermediate reasoning steps. In this work, we introduce Sketchpad, a framework that gives multimodal LMs a visual sketchpad and tools to draw on the sketchpad. The LM conducts planning and reasoning according to the visual artifacts it has drawn. Different from prior work, which uses text-to-image models to enable LMs to draw, Sketchpad enables LMs to draw with lines, boxes, marks, etc., which is closer to human sketching and better facilitates reasoning. Sketchpad can also use specialist vision models during the sketching process (e.g., draw bounding boxes with object detection models, draw masks with segmentation models), to further enhance visual perception and reasoning. We experiment with a wide range of math tasks (including geometry, functions, graphs, and chess) and complex visual reasoning tasks. Sketchpad substantially improves performance on all tasks over strong base models with no sketching, yielding an average gain of 12.7% on math tasks, and 8.6% on vision tasks. GPT-4o with Sketchpad sets a new state of the art on all tasks, including V*Bench (80.3%), BLINK spatial reasoning (83.9%), and visual correspondence (80.8%). All codes and data are in https://visualsketchpad.github.io/.
Authors: Jialong Wu, Mirko Meuter, Markus Schoeler, Matthias Rottmann
Abstract: Radar-based perception has gained increasing attention in autonomous driving, yet the inherent sparsity of radars poses challenges. Radar raw data often contains excessive noise, whereas radar point clouds retain only limited information. In this work, we holistically treat the sparse nature of radar data by introducing an adaptive subsampling method together with a tailored network architecture that exploits the sparsity patterns to discover global and local dependencies in the radar signal. Our subsampling module selects a subset of pixels from range-doppler (RD) spectra that contribute most to the downstream perception tasks. To improve the feature extraction on sparse subsampled data, we propose a new way of applying graph neural networks on radar data and design a novel two-branch backbone to capture both global and local neighbor information. An attentive fusion module is applied to combine features from both branches. Experiments on the RADIal dataset show that our SparseRadNet exceeds state-of-the-art (SOTA) performance in object detection and achieves close to SOTA accuracy in freespace segmentation, meanwhile using sparse subsampled input data.
Authors: Jaime Corsetti, Davide Boscaini, Francesco Giuliari, Changjae Oh, Andrea Cavallaro, Fabio Poiesi
Abstract: The generalisation to unseen objects in the 6D pose estimation task is very challenging. While Vision-Language Models (VLMs) enable using natural language descriptions to support 6D pose estimation of unseen objects, these solutions underperform compared to model-based methods. In this work we present Horyon, an open-vocabulary VLM-based architecture that addresses relative pose estimation between two scenes of an unseen object, described by a textual prompt only. We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features. These features are used to extract cross-scene matches for registration. We evaluate our model on a benchmark with a large variety of unseen objects across four datasets, namely REAL275, Toyota-Light, Linemod, and YCB-Video. Our method achieves state-of-the-art performance on all datasets, outperforming by 12.6 in Average Recall the previous best-performing approach.
Authors: Mingrui Wu, Jiayi Ji, Oucheng Huang, Jiale Li, Yuhang Wu, Xiaoshuai Sun, Rongrong Ji
Abstract: The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations, which can be easily alleviated by introducing object detectors. However, these efforts neglect hallucinations in inter-object relationships, which is essential for visual comprehension. In this work, we introduce R-Bench, a novel benchmark for evaluating Vision Relationship Hallucination. R-Bench features image-level questions that focus on the existence of relationships and instance-level questions that assess local visual comprehension. We identify three types of relationship co-occurrences that lead to hallucinations: relationship-relationship, subject-relationship, and relationship-object. The visual instruction tuning dataset's long-tail distribution significantly impacts LVLMs' understanding of visual relationships. Furthermore, our analysis reveals that current LVLMs tend to disregard visual content and overly rely on the common sense knowledge of Large Language Models. They also struggle with reasoning about spatial relationships based on contextual information.
Authors: Renqing Luo, Yuhan Xu
Abstract: This paper introduces MixTex, an end-to-end LaTeX OCR model designed for low-bias multilingual recognition, along with its novel data collection method. In applying Transformer architectures to LaTeX text recognition, we identified specific bias issues, such as the frequent misinterpretation of $e-t$ as $e^{-t}$. We attribute this bias to the characteristics of the arXiv dataset commonly used for training. To mitigate this bias, we propose an innovative data augmentation method. This approach introduces controlled noise into the recognition targets by blending genuine text with pseudo-text and incorporating a small proportion of disruptive characters. We further suggest that this method has broader applicability to various disambiguation recognition tasks, including the accurate identification of erroneous notes in musical performances. MixTex's architecture leverages the Swin Transformer as its encoder and RoBERTa as its decoder. Our experimental results demonstrate that this approach significantly reduces bias in recognition tasks. Notably, when processing clear and unambiguous images, the model adheres strictly to the image rather than over-relying on contextual cues for token prediction.
Authors: Younghyun Kim, Geunmin Hwang, Junyu Zhang, Eunbyung Park
Abstract: Recent surge in large-scale generative models has spurred the development of vast fields in computer vision. In particular, text-to-image diffusion models have garnered widespread adoption across diverse domain due to their potential for high-fidelity image generation. Nonetheless, existing large-scale diffusion models are confined to generate images of up to 1K resolution, which is far from meeting the demands of contemporary commercial applications. Directly sampling higher-resolution images often yields results marred by artifacts such as object repetition and distorted shapes. Addressing the aforementioned issues typically necessitates training or fine-tuning models on higher resolution datasets. However, this undertaking poses a formidable challenge due to the difficulty in collecting large-scale high-resolution contents and substantial computational resources. While several preceding works have proposed alternatives, they often fail to produce convincing results. In this work, we probe the generative ability of diffusion models at higher resolution beyond its original capability and propose a novel progressive approach that fully utilizes generated low-resolution image to guide the generation of higher resolution image. Our method obviates the need for additional training or fine-tuning which significantly lowers the burden of computational costs. Extensive experiments and results validate the efficiency and efficacy of our method. Project page: https://yhyun225.github.io/DiffuseHigh/
Authors: Deyi Ji, Wenwei Jin, Hongtao Lu, Feng Zhao
Abstract: The ascension of Unmanned Aerial Vehicles (UAVs) in various fields necessitates effective UAV image segmentation, which faces challenges due to the dynamic perspectives of UAV-captured images. Traditional segmentation algorithms falter as they cannot accurately mimic the complexity of UAV perspectives, and the cost of obtaining multi-perspective labeled datasets is prohibitive. To address these issues, we introduce the PPTFormer, a novel \textbf{P}seudo Multi-\textbf{P}erspective \textbf{T}rans\textbf{former} network that revolutionizes UAV image segmentation. Our approach circumvents the need for actual multi-perspective data by creating pseudo perspectives for enhanced multi-perspective learning. The PPTFormer network boasts Perspective Representation, novel Perspective Prototypes, and a specialized encoder and decoder that together achieve superior segmentation results through Pseudo Multi-Perspective Attention (PMP Attention) and fusion. Our experiments demonstrate that PPTFormer achieves state-of-the-art performance across five UAV segmentation datasets, confirming its capability to effectively simulate UAV flight perspectives and significantly advance segmentation precision. This work presents a pioneering leap in UAV scene understanding and sets a new benchmark for future developments in semantic segmentation.
Authors: Kunyu Peng, Jia Fu, Kailun Yang, Di Wen, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiaming Zhang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg
Abstract: We introduce a new task called Referring Atomic Video Action Recognition (RAVAR), aimed at identifying atomic actions of a particular person based on a textual description and the video data of this person. This task differs from traditional action recognition and localization, where predictions are delivered for all present individuals. In contrast, we focus on recognizing the correct atomic action of a specific individual, guided by text. To explore this task, we present the RefAVA dataset, containing 36,630 instances with manually annotated textual descriptions of the individuals. To establish a strong initial benchmark, we implement and validate baselines from various domains, e.g., atomic action localization, video question answering, and text-video retrieval. Since these existing methods underperform on RAVAR, we introduce RefAtomNet -- a novel cross-stream attention-driven method specialized for the unique challenges of RAVAR: the need to interpret a textual referring expression for the targeted individual, utilize this reference to guide the spatial localization and harvest the prediction of the atomic actions for the referring person. The key ingredients are: (1) a multi-stream architecture that connects video, text, and a new location-semantic stream, and (2) cross-stream agent attention fusion and agent token fusion which amplify the most relevant information across these streams and consistently surpasses standard attention-based fusion on RAVAR. Extensive experiments demonstrate the effectiveness of RefAtomNet and its building blocks for recognizing the action of the described individual. The dataset and code will be made publicly available at https://github.com/KPeng9510/RAVAR.
Authors: Son Nguyen, Thinh Nguyen, Khoa D Doan, Kok-Seng Wong
Abstract: Federated Learning (FL) is a distributed machine learning approach that maintains data privacy by training on decentralized data sources. Similar to centralized machine learning, FL is also susceptible to backdoor attacks, where an attacker can compromise some clients by injecting a backdoor trigger into local models of those clients, leading to the global model's behavior being manipulated as desired by the attacker. Most backdoor attacks in FL assume a predefined target class and require control over a large number of clients or knowledge of benign clients' information. Furthermore, they are not imperceptible and are easily detected by human inspection due to clear artifacts left on the poison data. To overcome these challenges, we propose Venomancer, an effective backdoor attack that is imperceptible and allows target-on-demand. Specifically, imperceptibility is achieved by using a visual loss function to make the poison data visually indistinguishable from the original data. Target-on-demand property allows the attacker to choose arbitrary target classes via conditional adversarial training. Additionally, experiments showed that the method is robust against state-of-the-art defenses such as Norm Clipping, Weak DP, Krum, Multi-Krum, RLR, FedRAD, Deepsight, and RFLBAT. The source code is available at https://github.com/nguyenhongson1902/Venomancer.
Authors: Yusuke Hirota, Jerone T. A. Andrews, Dora Zhao, Orestis Papakyriakopoulos, Apostolos Modas, Yuta Nakashima, Alice Xiang
Abstract: We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided inpainting models, our approach ensures protected group independence from all attributes and mitigates inpainting biases through data filtering. Evaluations on multi-label image classification and image captioning tasks show our method effectively reduces bias without compromising performance across various models.
Authors: Federico Girella, Ziyue Liu, Franco Fummi, Francesco Setti, Marco Cristani, Luigi Capogrosso
Abstract: Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. State-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples to mitigate problems related to unbalanced training data. These techniques often produce out-of-distribution images, resulting in systems that learn what is not a normal sample but cannot accurately identify what a defect looks like. In this work, we introduce DIAG, a training-free Diffusion-based In-distribution Anomaly Generation pipeline for data augmentation. Unlike conventional image generation techniques, we implement a human-in-the-loop pipeline, where domain experts provide multimodal guidance to the model through text descriptions and region localization of the possible anomalies. This strategic shift enhances the interpretability of results and fosters a more robust human feedback loop, facilitating iterative improvements of the generated outputs. Remarkably, our approach operates in a zero-shot manner, avoiding time-consuming fine-tuning procedures while achieving superior performance. We demonstrate the efficacy and versatility of DIAG with respect to state-of-the-art data augmentation approaches on the challenging KSDD2 dataset, with an improvement in AP of approximately 18% when positive samples are available and 28% when they are missing. The source code is available at https://github.com/intelligolabs/DIAG.
Authors: Anushrut Jignasu, Kelly O. Marshall, Ankush Kumar Mishra, Lucas Nerone Rillo, Baskar Ganapathysubramanian, Aditya Balu, Chinmay Hegde, Adarsh Krishnamurthy
Abstract: G-code (Geometric code) or RS-274 is the most widely used computer numerical control (CNC) and 3D printing programming language. G-code provides machine instructions for the movement of the 3D printer, especially for the nozzle, stage, and extrusion of material for extrusion-based additive manufacturing. Currently there does not exist a large repository of curated CAD models along with their corresponding G-code files for additive manufacturing. To address this issue, we present SLICE-100K, a first-of-its-kind dataset of over 100,000 G-code files, along with their tessellated CAD model, LVIS (Large Vocabulary Instance Segmentation) categories, geometric properties, and renderings. We build our dataset from triangulated meshes derived from Objaverse-XL and Thingi10K datasets. We demonstrate the utility of this dataset by finetuning GPT-2 on a subset of the dataset for G-code translation from a legacy G-code format (Sailfish) to a more modern, widely used format (Marlin). SLICE-100K will be the first step in developing a multimodal foundation model for digital manufacturing.
Authors: Prarthana Bhattacharyya, Joshua Mitton, Ryan Page, Owen Morgan, Ben Menzies, Gabriel Homewood, Kemi Jacobs, Paolo Baesso, Dave Trickett, Chris Mair, Taru Muhonen, Rory Clark, Louis Berridge, Richard Vigars, Iain Wallace
Abstract: This paper introduces Helios, the first extremely low-power, real-time, event-based hand gesture recognition system designed for all-day on smart eyewear. As augmented reality (AR) evolves, current smart glasses like the Meta Ray-Bans prioritize visual and wearable comfort at the expense of functionality. Existing human-machine interfaces (HMIs) in these devices, such as capacitive touch and voice controls, present limitations in ergonomics, privacy and power consumption. Helios addresses these challenges by leveraging natural hand interactions for a more intuitive and comfortable user experience. Our system utilizes a extremely low-power and compact 3mmx4mm/20mW event camera to perform natural hand-based gesture recognition for always-on smart eyewear. The camera's output is processed by a convolutional neural network (CNN) running on a NXP Nano UltraLite compute platform, consuming less than 350mW. Helios can recognize seven classes of gestures, including subtle microgestures like swipes and pinches, with 91% accuracy. We also demonstrate real-time performance across 20 users at a remarkably low latency of 60ms. Our user testing results align with the positive feedback we received during our recent successful demo at AWE-USA-2024.
Authors: Michael Welter
Abstract: Deep learning has been impressively successful in the last decade in predicting human head poses from monocular images. For in-the-wild inputs, the research community has predominantly relied on a single training set of semi-synthetic nature. This paper suggest the combination of different flavors of synthetic data in order to achieve better generalization to natural images. Moreover, additional expansion of the data volume using traditional out-of-plane rotation synthesis is considered. Together with a novel combination of losses and a network architecture with a standard feature-extractor, a competitive model is obtained, both in accuracy and efficiency, which allows full 6 DoF pose estimation in practical real-time applications.
Authors: Mujtaba Hussain Mirza, Maria Rosaria Briglia, Senad Beadini, Iacopo Masi
Abstract: By reinterpreting a robust discriminative classifier as Energy-based Model (EBM), we offer a new take on the dynamics of adversarial training (AT). Our analysis of the energy landscape during AT reveals that untargeted attacks generate adversarial images much more in-distribution (lower energy) than the original data from the point of view of the model. Conversely, we observe the opposite for targeted attacks. On the ground of our thorough analysis, we present new theoretical and practical results that show how interpreting AT energy dynamics unlocks a better understanding: (1) AT dynamic is governed by three phases and robust overfitting occurs in the third phase with a drastic divergence between natural and adversarial energies (2) by rewriting the loss of TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization (TRADES) in terms of energies, we show that TRADES implicitly alleviates overfitting by means of aligning the natural energy with the adversarial one (3) we empirically show that all recent state-of-the-art robust classifiers are smoothing the energy landscape and we reconcile a variety of studies about understanding AT and weighting the loss function under the umbrella of EBMs. Motivated by rigorous evidence, we propose Weighted Energy Adversarial Training (WEAT), a novel sample weighting scheme that yields robust accuracy matching the state-of-the-art on multiple benchmarks such as CIFAR-10 and SVHN and going beyond in CIFAR-100 and Tiny-ImageNet. We further show that robust classifiers vary in the intensity and quality of their generative capabilities, and offer a simple method to push this capability, reaching a remarkable Inception Score (IS) and FID using a robust classifier without training for generative modeling. The code to reproduce our results is available at http://github.com/OmnAI-Lab/Robust-Classifiers-under-the-lens-of-EBM/ .
URLs: http://github.com/OmnAI-Lab/Robust-Classifiers-under-the-lens-of-EBM/
Authors: Yibo Liu, Zheyuan Yang, Guile Wu, Yuan Ren, Kejian Lin, Bingbing Liu, Yang Liu, Jinjun Shan
Abstract: Generating 3D vehicle assets from in-the-wild observations is crucial to autonomous driving. Existing image-to-3D methods cannot well address this problem because they learn generation merely from image RGB information without a deeper understanding of in-the-wild vehicles (such as car models, manufacturers, etc.). This leads to their poor zero-shot prediction capability to handle real-world observations with occlusion or tricky viewing angles. To solve this problem, in this work, we propose VQA-Diff, a novel framework that leverages in-the-wild vehicle images to create photorealistic 3D vehicle assets for autonomous driving. VQA-Diff exploits the real-world knowledge inherited from the Large Language Model in the Visual Question Answering (VQA) model for robust zero-shot prediction and the rich image prior knowledge in the Diffusion model for structure and appearance generation. In particular, we utilize a multi-expert Diffusion Models strategy to generate the structure information and employ a subject-driven structure-controlled generation mechanism to model appearance information. As a result, without the necessity to learn from a large-scale image-to-3D vehicle dataset collected from the real world, VQA-Diff still has a robust zero-shot image-to-novel-view generation ability. We conduct experiments on various datasets, including Pascal 3D+, Waymo, and Objaverse, to demonstrate that VQA-Diff outperforms existing state-of-the-art methods both qualitatively and quantitatively.
Authors: Nithish Kannen, Arif Ahmad, Marco Andreetto, Vinodkumar Prabhakaran, Utsav Prabhu, Adji Bousso Dieng, Pushpak Bhattacharyya, Shachi Dave
Abstract: Text-to-Image (T2I) models are being increasingly adopted in diverse global communities where they create visual representations of their unique cultures. Current T2I benchmarks primarily focus on faithfulness, aesthetics, and realism of generated images, overlooking the critical dimension of cultural competence. In this work, we introduce a framework to evaluate cultural competence of T2I models along two crucial dimensions: cultural awareness and cultural diversity, and present a scalable approach using a combination of structured knowledge bases and large language models to build a large dataset of cultural artifacts to enable this evaluation. In particular, we apply this approach to build CUBE (CUltural BEnchmark for Text-to-Image models), a first-of-its-kind benchmark to evaluate cultural competence of T2I models. CUBE covers cultural artifacts associated with 8 countries across different geo-cultural regions and along 3 concepts: cuisine, landmarks, and art. CUBE consists of 1) CUBE-1K, a set of high-quality prompts that enable the evaluation of cultural awareness, and 2) CUBE-CSpace, a larger dataset of cultural artifacts that serves as grounding to evaluate cultural diversity. We also introduce cultural diversity as a novel T2I evaluation component, leveraging quality-weighted Vendi score. Our evaluations reveal significant gaps in the cultural awareness of existing models across countries and provide valuable insights into the cultural diversity of T2I outputs for under-specified prompts. Our methodology is extendable to other cultural regions and concepts, and can facilitate the development of T2I models that better cater to the global population.
Authors: Bowen Zhang, Yiji Cheng, Chunyu Wang, Ting Zhang, Jiaolong Yang, Yansong Tang, Feng Zhao, Dong Chen, Baining Guo
Abstract: We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image. Existing methods fail to capture intricate details such as hairstyles which we tackle in this paper. We first identify an overlooked problem of catastrophic forgetting that arises when fitting triplanes sequentially on many avatars, caused by the MLP decoder sharing scheme. To overcome this issue, we raise a novel data scheduling strategy and a weight consolidation regularization term, which improves the decoder's capability of rendering sharper details. Additionally, we optimize the guiding effect of the portrait image by computing a finer-grained hierarchical representation that captures rich 2D texture cues, and injecting them to the 3D diffusion model at multiple layers via cross-attention. When trained on 46K avatars with a noise schedule optimized for triplanes, the resulting model can generate 3D avatars with notably better details than previous methods and can generalize to in-the-wild portrait input.
Authors: Zhiting Wang, Qiangong Zhou, Kangjie Yang, Zongyang Liu, Xin Mao
Abstract: This technical report presents the implementation of a state-of-the-art video encoder for video-text modal alignment and a video conversation framework called HiLight, which features dual visual towers. The work is divided into two main parts: 1.alignment of video and text modalities; 2.convenient and efficient way to interact with users. Our goal is to address the task of video comprehension in the context of billiards. The report includes a discussion of the concepts and the final solution developed during the task's implementation.
Authors: Doanh C. Bui, Trinh Thi Le Vuong, Jin Tae Kwak
Abstract: Slide-level classification for whole-slide images (WSIs) has been widely recognized as a crucial problem in digital and computational pathology. Current approaches commonly consider WSIs as a bag of cropped patches and process them via multiple instance learning due to the large number of patches, which cannot fully explore the relationship among patches; in other words, the global information cannot be fully incorporated into decision making. Herein, we propose an efficient and effective slide-level classification model, named as FALFormer, that can process a WSI as a whole so as to fully exploit the relationship among the entire patches and to improve the classification performance. FALFormer is built based upon Transformers and self-attention mechanism. To lessen the computational burden of the original self-attention mechanism and to process the entire patches together in a WSI, FALFormer employs Nystr\"om self-attention which approximates the computation by using a smaller number of tokens or landmarks. For effective learning, FALFormer introduces feature-aware landmarks to enhance the representation power of the landmarks and the quality of the approximation. We systematically evaluate the performance of FALFormer using two public datasets, including CAMELYON16 and TCGA-BRCA. The experimental results demonstrate that FALFormer achieves superior performance on both datasets, outperforming the state-of-the-art methods for the slide-level classification. This suggests that FALFormer can facilitate an accurate and precise analysis of WSIs, potentially leading to improved diagnosis and prognosis on WSIs.
Authors: Guoan Xu, Wenjing Jia, Tao Wu, Ligeng Chen, Guangwei Gao
Abstract: Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions. However, there is still room for enhancement, particularly when considering constraints on computational resources. In this paper, we introduce HAFormer, a model that combines the hierarchical features extraction ability of CNNs with the global dependency modeling capability of Transformers to tackle lightweight semantic segmentation challenges. Specifically, we design a Hierarchy-Aware Pixel-Excitation (HAPE) module for adaptive multi-scale local feature extraction. During the global perception modeling, we devise an Efficient Transformer (ET) module streamlining the quadratic calculations associated with traditional Transformers. Moreover, a correlation-weighted Fusion (cwF) module selectively merges diverse feature representations, significantly enhancing predictive accuracy. HAFormer achieves high performance with minimal computational overhead and compact model size, achieving 74.2% mIoU on Cityscapes and 71.1% mIoU on CamVid test datasets, with frame rates of 105FPS and 118FPS on a single 2080Ti GPU. The source codes are available at https://github.com/XU-GITHUB-curry/HAFormer.
Authors: Linqiang Li, Jinglei Hao, Yongqiang Zhao, Pan Liu, Haofang Yan, Ziqin Zhang, Seong G. Kong
Abstract: Shortwave-infrared(SWIR) spectral information,ranging from 1 {\mu}m to 2.5{\mu}m, breaks the limitations of traditional color cameras in acquiring scene information and has been used in many fields. However, conventional SWIR hyperspectral imaging systems face challenges due to their bulky setups and low acquisition speed. In this work, we introduce a snapshot SWIR hyperspectral imaging system based on a metasurface filter and a corresponding filter selection method to achieve the lowest correlation coefficient among these filters.This systemhas the advantages of small size and snapshot imaging. We propose a novel inter and intra prior learning unfolding framework proposed to achieve high-quality SWIR hyperspectral image reconstruction, which bridges the gap between prior learning and cross-stage information interaction. We also design an adaptive feature transfer mechanism to adaptively the transfer contextual correlation of multi-scale encoder features to prevent detailed information loss in the decoder. Experiment results demonstrate that our method can reconstruct HSI with high speed and superior performance over existing methods.
Authors: Irit Chelly, Shahaf E. Finder, Shira Ifergane, Oren Freifeld
Abstract: Nonlinear activation functions are pivotal to the success of deep neural nets, and choosing the appropriate activation function can significantly affect their performance. Most networks use fixed activation functions (e.g., ReLU, GELU, etc.), and this choice might limit their expressiveness. Furthermore, different layers may benefit from diverse activation functions. Consequently, there has been a growing interest in trainable activation functions. In this paper, we introduce DiTAC, a trainable highly-expressive activation function based on an efficient diffeomorphic transformation (called CPAB). Despite introducing only a negligible number of trainable parameters, DiTAC enhances model expressiveness and performance, often yielding substantial improvements. It also outperforms existing activation functions (regardless whether the latter are fixed or trainable) in tasks such as semantic segmentation, image generation, regression problems, and image classification. Our code is available at https://github.com/BGU-CS-VIL/DiTAC.
Authors: Chenguo Lin, Yuchen Lin, Panwang Pan, Xuanyang Zhang, Yadong Mu
Abstract: Comprehending natural language instructions is a charming property for both 2D and 3D layout synthesis systems. Existing methods implicitly model object joint distributions and express object relations, hindering generation's controllability. We introduce InstructLayout, a novel generative framework that integrates a semantic graph prior and a layout decoder to improve controllability and fidelity for 2D and 3D layout synthesis. The proposed semantic graph prior learns layout appearances and object distributions simultaneously, demonstrating versatility across various downstream tasks in a zero-shot manner. To facilitate the benchmarking for text-driven 2D and 3D scene synthesis, we respectively curate two high-quality datasets of layout-instruction pairs from public Internet resources with large language and multimodal models. Extensive experimental results reveal that the proposed method outperforms existing state-of-the-art approaches by a large margin in both 2D and 3D layout synthesis tasks. Thorough ablation studies confirm the efficacy of crucial design components.
Authors: Vanessa Borst, Timo Dittus, Konstantin M\"uller, Samuel Kounev
Abstract: The aging population poses numerous challenges to healthcare, including the increase in chronic wounds in the elderly. The current approach to wound assessment by therapists based on photographic documentation is subjective, highlighting the need for computer-aided wound recognition from smartphone photos. This offers objective and convenient therapy monitoring, while being accessible to patients from their home at any time. However, despite research in mobile image segmentation, there is a lack of focus on mobile wound segmentation. To address this gap, we conduct initial research on three lightweight architectures to investigate their suitability for smartphone-based wound segmentation. Using public datasets and UNet as a baseline, our results are promising, with both ENet and TopFormer, as well as the larger UNeXt variant, showing comparable performance to UNet. Furthermore, we deploy the models into a smartphone app for visual assessment of live segmentation, where results demonstrate the effectiveness of TopFormer in distinguishing wounds from wound-coloured objects. While our study highlights the potential of transformer models for mobile wound segmentation, future work should aim to further improve the mask contours.
Authors: Wanggui He, Siming Fu, Mushui Liu, Xierui Wang, Wenyi Xiao, Fangxun Shu, Yi Wang, Lei Zhang, Zhelun Yu, Haoyuan Li, Ziwei Huang, LeiLei Gan, Hao Jiang
Abstract: Auto-regressive models have made significant progress in the realm of language generation, yet they do not perform on par with diffusion models in the domain of image synthesis. In this work, we introduce MARS, a novel framework for T2I generation that incorporates a specially designed Semantic Vision-Language Integration Expert (SemVIE). This innovative component integrates pre-trained LLMs by independently processing linguistic and visual information, freezing the textual component while fine-tuning the visual component. This methodology preserves the NLP capabilities of LLMs while imbuing them with exceptional visual understanding. Building upon the powerful base of the pre-trained Qwen-7B, MARS stands out with its bilingual generative capabilities corresponding to both English and Chinese language prompts and the capacity for joint image and text generation. The flexibility of this framework lends itself to migration towards any-to-any task adaptability. Furthermore, MARS employs a multi-stage training strategy that first establishes robust image-text alignment through complementary bidirectional tasks and subsequently concentrates on refining the T2I generation process, significantly augmenting text-image synchrony and the granularity of image details. Notably, MARS requires only 9% of the GPU days needed by SD1.5, yet it achieves remarkable results across a variety of benchmarks, illustrating the training efficiency and the potential for swift deployment in various applications.
Authors: Zhifang Zhang, Beibei Li
Abstract: Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying performance, a major limitation of prompt learning is the demand for labelled data. In real-world scenarios, we may only obtain candidate labels (where the true label is included) instead of the true labels due to data privacy or sensitivity issues. In this paper, we provide the first study on prompt learning with candidate labels for VLMs. We empirically demonstrate that prompt learning is more advantageous than other fine-tuning methods, for handling candidate labels. Nonetheless, its performance drops when the label ambiguity increases. In order to improve its robustness, we propose a simple yet effective framework that better leverages the prior knowledge of VLMs to guide the learning process with candidate labels. Specifically, our framework disambiguates candidate labels by aligning the model output with the mixed class posterior jointly predicted by both the learnable and the handcrafted prompt. Besides, our framework can be equipped with various off-the-shelf training objectives for learning with candidate labels to further improve their performance. Extensive experiments demonstrate the effectiveness of our proposed framework.
Authors: Stefan M. Fischer, Lina Felsner, Richard Osuala, Johannes Kiechle, Daniel M. Lang, Jan C. Peeken, Julia A. Schnabel
Abstract: In this work, we introduce Progressive Growing of Patch Size, a resource-efficient implicit curriculum learning approach for dense prediction tasks. Our curriculum approach is defined by growing the patch size during model training, which gradually increases the task's difficulty. We integrated our curriculum into the nnU-Net framework and evaluated the methodology on all 10 tasks of the Medical Segmentation Decathlon. With our approach, we are able to substantially reduce runtime, computational costs, and CO2 emissions of network training compared to classical constant patch size training. In our experiments, the curriculum approach resulted in improved convergence. We are able to outperform standard nnU-Net training, which is trained with constant patch size, in terms of Dice Score on 7 out of 10 MSD tasks while only spending roughly 50% of the original training runtime. To the best of our knowledge, our Progressive Growing of Patch Size is the first successful employment of a sample-length curriculum in the form of patch size in the field of computer vision. Our code is publicly available at https://github.com/compai-lab/2024-miccai-fischer.
Authors: Xin Zhao, Lin Wang, Qinfei Li, Heng Chen, Shuangrong Liu, Pengkun Hou, Xu Wu, Jianfeng Yuan, Haozhong Gao, Bo Yang
Abstract: This paper proposes a deep learning-based method for generating 3D microstructures from a single two-dimensional (2D) image, capable of producing high-quality, realistic 3D images at low cost. In the method, a framework (CEM3DMG) is designed to synthesize 3D images by learning microstructural information from a 2D backscattered electron (BSE) image. Experimental results show that CEM3DMG can generate realistic 3D images of arbitrary size with a resolution of 0.47 $\mu m$ per pixel. Visual observation confirms that the generated 3D images exhibit similar microstructural features to the 2D images, including pores and particles morphology. Furthermore, quantitative analysis reveals that these 3D microstructures closely match the real 2D microstructure in terms of gray level histogram, phase proportions, and pore size distribution.
Authors: Han Wu, Sareh Rowlands, Johan Wahlstrom
Abstract: Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these models are susceptible to adversarial attacks. While some attacks are limited by strict assumptions on access to the detection system, we propose a novel hardware attack inspired by Man-in-the-Middle attacks in cryptography. This attack generates a Universal Adversarial Perturbations (UAP) and injects the perturbation between the USB camera and the detection system via a hardware attack. Besides, prior research is misled by an evaluation metric that measures the model accuracy rather than the attack performance. In combination with our proposed evaluation metrics, we significantly increased the strength of adversarial perturbations. These findings raise serious concerns for applications of deep learning models in safety-critical systems, such as autonomous driving.
Authors: Grzegorz Rype\'s\'c, Daniel Marczak, Sebastian Cygert, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski
Abstract: Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old knowledge. However, this strategy restricts the model's ability to adapt and effectively distinguish new categories. To address this, we introduce a novel technique integrating a learnable projector with feature distillation, thus enhancing model adaptability without sacrificing past knowledge. The resulting distribution shift of the previously learned categories is mitigated with the auxiliary category adaptation network. We demonstrate that while each component offers modest benefits individually, their combination -- dubbed CAMP (Category Adaptation Meets Projected distillation) -- significantly improves the balance between learning new information and retaining old. CAMP exhibits superior performance across several GCCD scenarios with or without exemplars. Additionally, CAMP translates to a well-established Class Incremental Learning setting, achieving state-of-the-art results.
Authors: Stephanie Abrecht, Alexander Hirsch, Shervin Raafatnia, Matthias Woehrle
Abstract: Recent advances in the field of deep learning and impressive performance of deep neural networks (DNNs) for perception have resulted in an increased demand for their use in automated driving (AD) systems. The safety of such systems is of utmost importance and thus requires to consider the unique properties of DNNs. In order to achieve safety of AD systems with DNN-based perception components in a systematic and comprehensive approach, so-called safety concerns have been introduced as a suitable structuring element. On the one hand, the concept of safety concerns is -- by design -- well aligned to existing standards relevant for safety of AD systems such as ISO 21448 (SOTIF). On the other hand, it has already inspired several academic publications and upcoming standards on AI safety such as ISO PAS 8800. While the concept of safety concerns has been previously introduced, this paper extends and refines it, leveraging feedback from various domain and safety experts in the field. In particular, this paper introduces an additional categorization for a better understanding as well as enabling cross-functional teams to jointly address the concerns.
Authors: Taofeng Xie, Zhuo-Xu Cui, Chen Luo, Huayu Wang, Congcong Liu, Yuanzhi Zhang, Xuemei Wang, Yanjie Zhu, Guoqing Chen, Dong Liang, Qiyu Jin, Yihang Zhou, Haifeng Wang
Abstract: Positron Emission Tomography and Magnetic Resonance Imaging (PET-MRI) systems can obtain functional and anatomical scans. PET suffers from a low signal-to-noise ratio. Meanwhile, the k-space data acquisition process in MRI is time-consuming. The study aims to accelerate MRI and enhance PET image quality. Conventional approaches involve the separate reconstruction of each modality within PET-MRI systems. However, there exists complementary information among multi-modal images. The complementary information can contribute to image reconstruction. In this study, we propose a novel PET-MRI joint reconstruction model employing a mutual consistency-driven diffusion mode, namely MC-Diffusion. MC-Diffusion learns the joint probability distribution of PET and MRI for utilizing complementary information. We conducted a series of contrast experiments about LPLS, Joint ISAT-net and MC-Diffusion by the ADNI dataset. The results underscore the qualitative and quantitative improvements achieved by MC-Diffusion, surpassing the state-of-the-art method.
Authors: Maolin Li, Giacomo Tarroni
Abstract: In the field of medical image analysis, deep learning models have demonstrated remarkable success in enhancing diagnostic accuracy and efficiency. However, the reliability of these models is heavily dependent on the quality of training data, and the existence of label noise (errors in dataset annotations) of medical image data presents a significant challenge. This paper introduces a new sample selection method that enhances the performance of neural networks when trained on noisy datasets. Our approach features estimating the noise rate of a dataset by analyzing the distribution of loss values using Linear Regression. Samples are then ranked according to their loss values, and potentially noisy samples are excluded from the dataset. Additionally, we employ sparse regularization to further enhance the noise robustness of our model. Our proposed method is evaluated on five benchmark datasets and a real-life noisy medical image dataset. Notably, two of these datasets contain 3D medical images. The results of our experiments show that our method outperforms existing noise-robust learning methods, particularly in scenarios with high noise rates. Key words: noise-robust learning, medical image analysis, noise rate estimation, sample selection, sparse regularization
Authors: Ziheng Zhao, Yao Zhang, Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie
Abstract: In this study, we aim to build up a model that can Segment Anything in radiology scans, driven by Text prompts, termed as SAT. Our main contributions are three folds: (i) for dataset construction, we construct the first multi-modal knowledge tree on human anatomy, including 6502 anatomical terminologies; Then we build up the largest and most comprehensive segmentation dataset for training, by collecting over 22K 3D medical image scans from 72 segmentation datasets, across 497 classes, with careful standardization on both image scans and label space; (ii) for architecture design, we propose to inject medical knowledge into a text encoder via contrastive learning, and then formulate a universal segmentation model, that can be prompted by feeding in medical terminologies in text form; (iii) As a result, we have trained SAT-Nano (110M parameters) and SAT-Pro (447M parameters), demonstrating comparable performance to 72 specialist nnU-Nets trained on each dataset/subsets. We validate SAT as a foundational segmentation model, with better generalization ability on external (unseen) datasets, and can be further improved on specific tasks after fine-tuning adaptation. Comparing with interactive segmentation model, for example, MedSAM, segmentation model prompted by text enables superior performance, scalability and robustness. As a use case, we demonstrate that SAT can act as a powerful out-of-the-box agent for large language models, enabling visual grounding in clinical procedures such as report generation. All the data, codes, and models in this work have been released.
Authors: Minghong Duan, Linhao Qu, Zhiwei Yang, Manning Wang, Chenxi Zhang, Zhijian Song
Abstract: High-quality whole-slide scanners are expensive, complex, and time-consuming, thus limiting the acquisition and utilization of high-resolution pathology whole-slide images in daily clinical work. Deep learning-based single-image super-resolution techniques are an effective way to solve this problem by synthesizing high-resolution images from low-resolution ones. However, the existing super-resolution models applied in pathology images can only work in fixed integer magnifications, significantly decreasing their applicability. Though methods based on implicit neural representation have shown promising results in arbitrary-scale super-resolution of natural images, applying them directly to pathology images is inadequate because they have unique fine-grained image textures different from natural images. Thus, we propose an Implicit Self-Texture Enhancement-based dual-branch framework (ISTE) for arbitrary-scale super-resolution of pathology images to address this challenge. ISTE contains a pixel learning branch and a texture learning branch, which first learn pixel features and texture features, respectively. Then, we design a two-stage texture enhancement strategy to fuse the features from the two branches to obtain the super-resolution results, where the first stage is feature-based texture enhancement, and the second stage is spatial-domain-based texture enhancement. Extensive experiments on three public datasets show that ISTE outperforms existing fixed-scale and arbitrary-scale algorithms at multiple magnifications and helps to improve downstream task performance. To the best of our knowledge, this is the first work to achieve arbitrary-scale super-resolution in pathology images. Codes will be available.
Authors: Shyang-En Weng, Shaou-Gang Miaou, Ricky Christanto
Abstract: Human vision relies heavily on available ambient light to perceive objects. Low-light scenes pose two distinct challenges: information loss due to insufficient illumination and undesirable brightness shifts. Low-light image enhancement (LLIE) refers to image enhancement technology tailored to handle this scenario. We introduce CPGA-Net, an innovative LLIE network that combines dark/bright channel priors and gamma correction via deep learning and integrates features inspired by the Atmospheric Scattering Model and the Retinex Theory. This approach combines the use of traditional and deep learning methodologies, designed within a simple yet efficient architectural framework that focuses on essential feature extraction. The resulting CPGA-Net is a lightweight network with only 0.025 million parameters and 0.030 seconds for inference time, yet it achieves superior performance over existing LLIE methods on both objective and subjective evaluation criteria. Furthermore, we utilized knowledge distillation with explainable factors and proposed an efficient version that achieves 0.018 million parameters and 0.006 seconds for inference time. The proposed approaches inject new solution ideas into LLIE, providing practical applications in challenging low-light scenarios.
Authors: Hairong Shi, Songhao Han, Shaofei Huang, Yue Liao, Guanbin Li, Xiangxing Kong, Hua Zhu, Xiaomu Wang, Si Liu
Abstract: Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation data across various medical imaging modalities and equipment, integrating medical knowledge into the Segment Anything Model (SAM) presents promising capability due to its versatility and generalization potential. Recent studies have attempted to enhance SAM with medical expertise by pre-training on large-scale medical segmentation datasets. However, challenges still exist in 3D tumor lesion segmentation owing to tumor complexity and the imbalance in foreground and background regions. Therefore, we introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks, facilitating the generation of more precise segmentation masks. Furthermore, an iterative refinement scheme is implemented in M-SAM to refine the segmentation masks progressively, leading to improved performance. Extensive experiments on seven tumor lesion segmentation datasets indicate that our M-SAM not only achieves high segmentation accuracy but also exhibits robust generalization. The code is available at https://github.com/nanase1025/M-SAM.
Authors: Kashyap Chitta, Daniel Dauner, Andreas Geiger
Abstract: SLEDGE is the first generative simulator for vehicle motion planning trained on real-world driving logs. Its core component is a learned model that is able to generate agent bounding boxes and lane graphs. The model's outputs serve as an initial state for rule-based traffic simulation. The unique properties of the entities to be generated for SLEDGE, such as their connectivity and variable count per scene, render the naive application of most modern generative models to this task non-trivial. Therefore, together with a systematic study of existing lane graph representations, we introduce a novel raster-to-vector autoencoder. It encodes agents and the lane graph into distinct channels in a rasterized latent map. This facilitates both lane-conditioned agent generation and combined generation of lanes and agents with a Diffusion Transformer. Using generated entities in SLEDGE enables greater control over the simulation, e.g. upsampling turns or increasing traffic density. Further, SLEDGE can support 500m long routes, a capability not found in existing data-driven simulators like nuPlan. It presents new challenges for planning algorithms, evidenced by failure rates of over 40% for PDM, the winner of the 2023 nuPlan challenge, when tested on hard routes and dense traffic generated by our model. Compared to nuPlan, SLEDGE requires 500$\times$ less storage to set up (<4 GB), making it a more accessible option and helping with democratizing future research in this field.
Authors: Raphael Sulzer, Florent Lafarge
Abstract: Plane arrangements are a useful tool for surface and volume modelling. However, their main drawback is poor scalability. We introduce two key novelties that enable the construction of plane arrangements for complex objects and entire scenes: (i) an ordering scheme for the plane insertion and (ii) the direct use of input points during arrangement construction. Both ingredients reduce the number of unwanted splits, resulting in improved scalability of the construction mechanism by up to two orders of magnitude compared to existing algorithms. We further introduce a remeshing and simplification technique that allows us to extract low-polygon surface meshes and lightweight convex decompositions of volumes from the arrangement. We show that our approach leads to state-of-the-art results for the aforementioned tasks by comparing it to learning-based and traditional approaches on various different datasets. Our implementation is available at https://github.com/raphaelsulzer/compod .
Authors: Syed Javed, Tariq M. Khan, Abdul Qayyum, Arcot Sowmya, Imran Razzak
Abstract: Accurate segmentation of anatomical structures and abnormalities in medical images is crucial for computer-aided diagnosis and analysis. While deep learning techniques excel at this task, their computational demands pose challenges. Additionally, some cutting-edge segmentation methods, though effective for general object segmentation, may not be optimised for medical images. To address these issues, we propose Mini-Net, a lightweight segmentation network specifically designed for medical images. With fewer than 38,000 parameters, Mini-Net efficiently captures both high- and low-frequency features, enabling real-time applications in various medical imaging scenarios. We evaluate Mini-Net on various datasets, including DRIVE, STARE, ISIC-2016, ISIC-2018, and MoNuSeg, demonstrating its robustness and good performance compared to state-of-the-art methods.
Authors: Kang-il Lee, Minbeom Kim, Seunghyun Yoon, Minsung Kim, Dongryeol Lee, Hyukhun Koh, Kyomin Jung
Abstract: Large Vision-Language Models (LVLMs) have demonstrated outstanding performance across various multimodal tasks. However, they suffer from a problem known as language prior, where responses are generated based solely on textual patterns while disregarding image information. Addressing the issue of language prior is crucial, as it can lead to undesirable biases or hallucinations when dealing with images that are out of training distribution. Despite its importance, current methods for accurately measuring language priors in LVLMs are poorly studied. Although existing benchmarks based on counterfactual or out-of-distribution images can partially be used to measure language priors, they fail to disentangle language priors from other confounding factors. To this end, we propose a new benchmark called VLind-Bench, which is the first benchmark specifically designed to measure the language priors, or blindness, of LVLMs. It not only includes tests on counterfactual images to assess language priors but also involves a series of tests to evaluate more basic capabilities such as commonsense knowledge, visual perception, and commonsense biases. For each instance in our benchmark, we ensure that all these basic tests are passed before evaluating the language priors, thereby minimizing the influence of other factors on the assessment. The evaluation and analysis of recent LVLMs in our benchmark reveal that almost all models exhibit a significant reliance on language priors, presenting a strong challenge in the field.
Authors: Gabriele Campanella, Shengjia Chen, Ruchika Verma, Jennifer Zeng, Aryeh Stock, Matt Croken, Brandon Veremis, Abdulkadir Elmas, Kuan-lin Huang, Ricky Kwan, Jane Houldsworth, Adam J. Schoenfeld, Chad Vanderbilt
Abstract: The use of self-supervised learning (SSL) to train pathology foundation models has increased substantially in the past few years. Notably, several models trained on large quantities of clinical data have been made publicly available in recent months. This will significantly enhance scientific research in computational pathology and help bridge the gap between research and clinical deployment. With the increase in availability of public foundation models of different sizes, trained using different algorithms on different datasets, it becomes important to establish a benchmark to compare the performance of such models on a variety of clinically relevant tasks spanning multiple organs and diseases. In this work, we present a collection of pathology datasets comprising clinical slides associated with clinically relevant endpoints including cancer diagnoses and a variety of biomarkers generated during standard hospital operation from two medical centers. We leverage these datasets to systematically assess the performance of public pathology foundation models and provide insights into best practices for training new foundation models and selecting appropriate pretrained models.
Authors: Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri, Anh Totti Nguyen
Abstract: Large language models with vision capabilities (VLMs), e.g., GPT-4o and Gemini 1.5 Pro are powering countless image-text applications and scoring high on many vision-understanding benchmarks. We propose BlindTest, a suite of 7 visual tasks absurdly easy to humans such as identifying (a) whether two circles overlap; (b) whether two lines intersect; (c) which letter is being circled in a word; and (d) counting the number of circles in a Olympic-like logo. Surprisingly, four state-of-the-art VLMs are, on average, only 56.20% accurate on our benchmark, with \newsonnet being the best (73.77% accuracy). On BlindTest, VLMs struggle with tasks that requires precise spatial information and counting (from 0 to 10), sometimes providing an impression of a person with myopia seeing fine details as blurry and making educated guesses. Code is available at: https://vlmsareblind.github.io/
Authors: Nikita Chernyadev, Nicholas Backshall, Xiao Ma, Yunfan Lu, Younggyo Seo, Stephen James
Abstract: We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.