Authors: Jinhong Lin, Cheng-En Wu, Yibing Wei, Pedro Morgado
Abstract: Our work tackles the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs). Despite the effectiveness of contrastive learning, the substantial computational resources required for training often hinder their practical application. To mitigate this issue, we propose an acceleration framework, leveraging ViT's unique ability to generalize across inputs of varying sequence lengths. Our method employs a mix of sequence compression strategies, including randomized token dropout and flexible patch scaling, to reduce the cost of gradient estimation and accelerate convergence. We further provide an in-depth analysis of the gradient estimation error of various acceleration strategies as well as their impact on downstream tasks, offering valuable insights into the trade-offs between acceleration and performance. We also propose a novel procedure to identify an optimal acceleration schedule to adjust the sequence compression ratios to the training progress, ensuring efficient training without sacrificing downstream performance. Our approach significantly reduces computational overhead across various self-supervised learning algorithms on large-scale datasets. In ImageNet, our method achieves speedups of 4$\times$ in MoCo, 3.3$\times$ in SimCLR, and 2.5$\times$ in DINO, demonstrating substantial efficiency gains.
Authors: Chenghao Xu, Malcolm Mielle, Antoine Laborde, Ali Waseem, Florent Forest, Olga Fink
Abstract: Achieving the EU's climate neutrality goal requires retrofitting existing buildings to reduce energy use and emissions. A critical step in this process is the precise assessment of geometric building envelope characteristics to inform retrofitting decisions. Previous methods for estimating building characteristics, such as window-to-wall ratio, building footprint area, and the location of architectural elements, have primarily relied on applying deep-learning-based detection or segmentation techniques on 2D images. However, these approaches tend to focus on planar facade properties, limiting their accuracy and comprehensiveness when analyzing complete building envelopes in 3D. While neural scene representations have shown exceptional performance in indoor scene reconstruction, they remain under-explored for external building envelope analysis. This work addresses this gap by leveraging cutting-edge neural surface reconstruction techniques based on signed distance function (SDF) representations for 3D building analysis. We propose BuildNet3D, a novel framework to estimate geometric building characteristics from 2D image inputs. By integrating SDF-based representation with semantic modality, BuildNet3D recovers fine-grained 3D geometry and semantics of building envelopes, which are then used to automatically extract building characteristics. Our framework is evaluated on a range of complex building structures, demonstrating high accuracy and generalizability in estimating window-to-wall ratio and building footprint. The results underscore the effectiveness of BuildNet3D for practical applications in building analysis and retrofitting.
Authors: Hieu Le, Federico Stella, Benoit Guillard, Pascal Fua
Abstract: Unsigned Distance Functions (UDFs) can be used to represent non-watertight surfaces in a deep learning framework. However, UDFs tend to be brittle and difficult to learn, in part because the surface is located exactly where the UDF is non-differentiable. In this work, we show that Gradient Distance Functions (GDFs) can remedy this by being differentiable at the surface while still being able to represent open surfaces. This is done by associating to each 3D point a 3D vector whose norm is taken to be the unsigned distance to the surface and whose orientation is taken to be the direction towards the closest surface point. We demonstrate the effectiveness of GDFs on ShapeNet Car, Multi-Garment, and 3D-Scene datasets with both single-shape reconstruction networks or categorical auto-decoders.
Authors: Jijia Yang, Sen Peng, Xiaohua Jia
Abstract: In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the imperative for robust intellectual property protection. Current protection strategies either employ backdoor-based methods, integrating a watermark task as a simpler training objective with the main model task, or embedding watermarks directly into the final output samples. However, the former approach is fragile compared to existing backdoor defense techniques, while the latter fundamentally alters the expected output. In this work, we introduce a novel watermarking framework by embedding the watermark into the whole diffusion process, and theoretically ensure that our final output samples contain no additional information. Furthermore, we utilize statistical algorithms to verify the watermark from internally generated model samples without necessitating triggers as conditions. Detailed theoretical analysis and experimental validation demonstrate the effectiveness of our proposed method.
Authors: Clayton Bromley, Alexander Moore, Amar Saini, Douglas Poland, Carmen Carrano
Abstract: Contemporary state-of-the-art video object segmentation (VOS) models compare incoming unannotated images to a history of image-mask relations via affinity or cross-attention to predict object masks. We refer to the internal memory state of the initial image-mask pair and past image-masks as a working memory buffer. While the current state of the art models perform very well on clean video data, their reliance on a working memory of previous frames leaves room for error. Affinity-based algorithms include the inductive bias that there is temporal continuity between consecutive frames. To account for inconsistent camera views of the desired object, working memory models need an algorithmic modification that regulates the memory updates and avoid writing irrelevant frames into working memory. A simple algorithmic change is proposed that can be applied to any existing working memory-based VOS model to improve performance on inconsistent views, such as sudden camera cuts, frame interjections, and extreme context changes. The resulting model performances show significant improvement on video data with these frame interjections over the same model without the algorithmic addition. Our contribution is a simple decision function that determines whether working memory should be updated based on the detection of sudden, extreme changes and the assumption that the object is no longer in frame. By implementing algorithmic changes, such as this, we can increase the real-world applicability of current VOS models.
Authors: Chenyu Gao, Michael E. Kim, Karthik Ramadass, Praitayini Kanakaraj, Aravind R. Krishnan, Adam M. Saunders, Nancy R. Newlin, Ho Hin Lee, Qi Yang, Warren D. Taylor, Brian D. Boyd, Lori L. Beason-Held, Susan M. Resnick, Lisa L. Barnes, David A. Bennett, Katherine D. Van Schaik, Derek B. Archer, Timothy J. Hohman, Angela L. Jefferson, Ivana I\v{s}gum, Daniel Moyer, Yuankai Huo, Kurt G. Schilling, Lianrui Zuo, Shunxing Bao, Nazirah Mohd Khairi, Zhiyuan Li, Christos Davatzikos, Bennett A. Landman
Abstract: Estimated brain age from magnetic resonance image (MRI) and its deviation from chronological age can provide early insights into potential neurodegenerative diseases, supporting early detection and implementation of prevention strategies. Diffusion MRI (dMRI), a widely used modality for brain age estimation, presents an opportunity to build an earlier biomarker for neurodegenerative disease prediction because it captures subtle microstructural changes that precede more perceptible macrostructural changes. However, the coexistence of macro- and micro-structural information in dMRI raises the question of whether current dMRI-based brain age estimation models are leveraging the intended microstructural information or if they inadvertently rely on the macrostructural information. To develop a microstructure-specific brain age, we propose a method for brain age identification from dMRI that minimizes the model's use of macrostructural information by non-rigidly registering all images to a standard template. Imaging data from 13,398 participants across 12 datasets were used for the training and evaluation. We compare our brain age models, trained with and without macrostructural information minimized, with an architecturally similar T1-weighted (T1w) MRI-based brain age model and two state-of-the-art T1w MRI-based brain age models that primarily use macrostructural information. We observe difference between our dMRI-based brain age and T1w MRI-based brain age across stages of neurodegeneration, with dMRI-based brain age being older than T1w MRI-based brain age in participants transitioning from cognitively normal (CN) to mild cognitive impairment (MCI), but younger in participants already diagnosed with Alzheimer's disease (AD). Approximately 4 years before MCI diagnosis, dMRI-based brain age yields better performance than T1w MRI-based brain ages in predicting transition from CN to MCI.
Authors: Josselin Somerville Roberts, Tony Lee, Chi Heem Wong, Michihiro Yasunaga, Yifan Mai, Percy Liang
Abstract: We introduce Image2Struct, a benchmark to evaluate vision-language models (VLMs) on extracting structure from images. Our benchmark 1) captures real-world use cases, 2) is fully automatic and does not require human judgment, and 3) is based on a renewable stream of fresh data. In Image2Struct, VLMs are prompted to generate the underlying structure (e.g., LaTeX code or HTML) from an input image (e.g., webpage screenshot). The structure is then rendered to produce an output image (e.g., rendered webpage), which is compared against the input image to produce a similarity score. This round-trip evaluation allows us to quantitatively evaluate VLMs on tasks with multiple valid structures. We create a pipeline that downloads fresh data from active online communities upon execution and evaluates the VLMs without human intervention. We introduce three domains (Webpages, LaTeX, and Musical Scores) and use five image metrics (pixel similarity, cosine similarity between the Inception vectors, learned perceptual image patch similarity, structural similarity index measure, and earth mover similarity) that allow efficient and automatic comparison between pairs of images. We evaluate Image2Struct on 14 prominent VLMs and find that scores vary widely, indicating that Image2Struct can differentiate between the performances of different VLMs. Additionally, the best score varies considerably across domains (e.g., 0.402 on sheet music vs. 0.830 on LaTeX equations), indicating that Image2Struct contains tasks of varying difficulty. For transparency, we release the full results at https://crfm.stanford.edu/helm/image2struct/v1.0.1/.
Authors: Gyusam Chang, Jiwon Lee, Donghyun Kim, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sujin Jang, Sangpil Kim
Abstract: Recent advances in 3D object detection leveraging multi-view cameras have demonstrated their practical and economical value in various challenging vision tasks. However, typical supervised learning approaches face challenges in achieving satisfactory adaptation toward unseen and unlabeled target datasets (\ie, direct transfer) due to the inevitable geometric misalignment between the source and target domains. In practice, we also encounter constraints on resources for training models and collecting annotations for the successful deployment of 3D object detectors. In this paper, we propose Unified Domain Generalization and Adaptation (UDGA), a practical solution to mitigate those drawbacks. We first propose Multi-view Overlap Depth Constraint that leverages the strong association between multi-view, significantly alleviating geometric gaps due to perspective view changes. Then, we present a Label-Efficient Domain Adaptation approach to handle unfamiliar targets with significantly fewer amounts of labels (\ie, 1$\%$ and 5$\%)$, while preserving well-defined source knowledge for training efficiency. Overall, UDGA framework enables stable detection performance in both source and target domains, effectively bridging inevitable domain gaps, while demanding fewer annotations. We demonstrate the robustness of UDGA with large-scale benchmarks: nuScenes, Lyft, and Waymo, where our framework outperforms the current state-of-the-art methods.
Authors: Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Min Wu, Ming-Ming Cheng, Ender Konukoglu, Serge Belongie
Abstract: Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud inputs, overlooking the potential benefits of leveraging multimodal information. In this paper, we address this gap by introducing a cost-free multimodal FS-PCS setup, utilizing textual labels and the potentially available 2D image modality. Under this easy-to-achieve setup, we present the MultiModal Few-Shot SegNet (MM-FSS), a model effectively harnessing complementary information from multiple modalities. MM-FSS employs a shared backbone with two heads to extract intermodal and unimodal visual features, and a pretrained text encoder to generate text embeddings. To fully exploit the multimodal information, we propose a Multimodal Correlation Fusion (MCF) module to generate multimodal correlations, and a Multimodal Semantic Fusion (MSF) module to refine the correlations using text-aware semantic guidance. Additionally, we propose a simple yet effective Test-time Adaptive Cross-modal Calibration (TACC) technique to mitigate training bias, further improving generalization. Experimental results on S3DIS and ScanNet datasets demonstrate significant performance improvements achieved by our method. The efficacy of our approach indicates the benefits of leveraging commonly-ignored free modalities for FS-PCS, providing valuable insights for future research. The code is available at https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot .
URLs: https://github.com/ZhaochongAn/Multimodality-3D-Few-Shot
Authors: Joseph Damilola Akinyemi, Kolawole John Adebayo
Abstract: As the global food security landscape continues to evolve, the need for accurate and reliable crop disease diagnosis has never been more pressing. To address global food security concerns, we extend the widely used PlantVillage dataset with additional apple leaf disease classes, enhancing diversity and complexity. Experimental evaluations on both original and extended datasets reveal that existing models struggle with the new additions, highlighting the need for more robust and generalizable computer vision models. Test F1 scores of 99.63% and 97.87% were obtained on the original and extended datasets, respectively. Our study provides a more challenging and diverse benchmark, paving the way for the development of accurate and reliable models for identifying apple leaf diseases under varying imaging conditions. The expanded dataset is available at https://www.kaggle.com/datasets/akinyemijoseph/apple-leaf-disease-dataset-6-classes-v2 enabling future research to build upon our findings.
URLs: https://www.kaggle.com/datasets/akinyemijoseph/apple-leaf-disease-dataset-6-classes-v2
Authors: Ali Pourramezan Fard, Mohammad Mehdi Hosseini, Timothy D. Sweeny, Mohammad H. Mahoor
Abstract: Automated Facial Expression Recognition (FER) is challenging due to intra-class variations and inter-class similarities. FER can be especially difficult when facial expressions reflect a mixture of various emotions (aka compound expressions). Existing FER datasets, such as AffectNet, provide discrete emotion labels (hard-labels), where a single category of emotion is assigned to an expression. To alleviate inter- and intra-class challenges, as well as provide a better facial expression descriptor, we propose a new approach to create FER datasets through a labeling method in which an image is labeled with more than one emotion (called soft-labels), each with different confidences. Specifically, we introduce the notion of soft-labels for facial expression datasets, a new approach to affective computing for more realistic recognition of facial expressions. To achieve this goal, we propose a novel methodology to accurately calculate soft-labels: a vector representing the extent to which multiple categories of emotion are simultaneously present within a single facial expression. Finding smoother decision boundaries, enabling multi-labeling, and mitigating bias and imbalanced data are some of the advantages of our proposed method. Building upon AffectNet, we introduce AffectNet+, the next-generation facial expression dataset. This dataset contains soft-labels, three categories of data complexity subsets, and additional metadata such as age, gender, ethnicity, head pose, facial landmarks, valence, and arousal. AffectNet+ will be made publicly accessible to researchers.
Authors: Ruichen Zhang, Yuguang Yao, Zhen Tan, Zhiming Li, Pan Wang, Jingtong Hu, Sijia Liu, Tianlong Chen
Abstract: Image generation is a prevailing technique for clinical data augmentation for advancing diagnostic accuracy and reducing healthcare disparities. Diffusion Model (DM) has become a leading method in generating synthetic medical images, but it suffers from a critical twofold bias: (1) The quality of images generated for Caucasian individuals is significantly higher, as measured by the Frechet Inception Distance (FID). (2) The ability of the downstream-task learner to learn critical features from disease images varies across different skin tones. These biases pose significant risks, particularly in skin disease detection, where underrepresentation of certain skin tones can lead to misdiagnosis or neglect of specific conditions. To address these challenges, we propose FairSkin, a novel DM framework that mitigates these biases through a three-level resampling mechanism, ensuring fairer representation across racial and disease categories. Our approach significantly improves the diversity and quality of generated images, contributing to more equitable skin disease detection in clinical settings.
Authors: Ishita Bansal, Peder Olsen, Roberto Estev\~ao
Abstract: Italian ryegrass is a grass weed commonly found in winter wheat fields that are competitive with winter wheat for moisture and nutrients. Ryegrass can cause substantial reductions in yield and grain quality if not properly controlled with the use of herbicides. To control the cost and environmental impact we detect weeds in drone and satellite imagery. Satellite imagery is too coarse to be used for precision spraying, but can aid in planning drone flights and treatments. Drone images on the other hand have sufficiently good resolution for precision spraying. However, ryegrass is hard to distinguish from the crop and annotation requires expert knowledge. We used the Python segmentation models library to test more than 600 different neural network architectures for weed segmentation in drone images and we map accuracy versus the cost of the model prediction for these. Our best system applies herbicides to over 99% of the weeds while only spraying an area 30% larger than the annotated weed area. These models yield large savings if the weed covers a small part of the field.
Authors: Yuxuan Yang, Hussein Sibai
Abstract: End-to-end vision-based autonomous driving has achieved impressive success, but safety remains a major concern. The safe control problem has been addressed in low-dimensional settings using safety filters, e.g., those based on control barrier functions. Designing safety filters for vision-based controllers in the high-dimensional settings of autonomous driving can similarly alleviate the safety problem, but is significantly more challenging. In this paper, we address this challenge by using frozen pre-trained vision representation models as perception backbones to design vision-based safety filters, inspired by these models' success as backbones of robotic control policies. We empirically evaluate the offline performance of four common pre-trained vision models in this context. We try three existing methods for training safety filters for black-box dynamics, as the dynamics over representation spaces are not known. We use the DeepAccident dataset that consists of action-annotated videos from multiple cameras on vehicles in CARLA simulating real accident scenarios. Our results show that the filters resulting from our approach are competitive with the ones that are given the ground truth state of the ego vehicle and its environment.
Authors: Royi Rassin, Aviv Slobodkin, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg
Abstract: Text-to-image (T2I) models are remarkable at generating realistic images based on textual descriptions. However, textual prompts are inherently underspecified: they do not specify all possible attributes of the required image. This raises two key questions: Do T2I models generate diverse outputs on underspecified prompts? How can we automatically measure diversity? We propose GRADE: Granular Attribute Diversity Evaluation, an automatic method for quantifying sample diversity. GRADE leverages the world knowledge embedded in large language models and visual question-answering systems to identify relevant concept-specific axes of diversity (e.g., ``shape'' and ``color'' for the concept ``cookie''). It then estimates frequency distributions of concepts and their attributes and quantifies diversity using (normalized) entropy. GRADE achieves over 90% human agreement while exhibiting weak correlation to commonly used diversity metrics. We use GRADE to measure the overall diversity of 12 T2I models using 400 concept-attribute pairs, revealing that all models display limited variation. Further, we find that these models often exhibit default behaviors, a phenomenon where the model consistently generates concepts with the same attributes (e.g., 98% of the cookies are round). Finally, we demonstrate that a key reason for low diversity is due to underspecified captions in training data. Our work proposes a modern, semantically-driven approach to measure sample diversity and highlights the stunning homogeneity in outputs by T2I models.
Authors: Ryozo Masukawa, Sanggeon Yun, Yoshiki Yamaguchi, Mohsen Imani
Abstract: Video crime detection is a significant application of computer vision and artificial intelligence. However, existing datasets primarily focus on detecting severe crimes by analyzing entire video clips, often neglecting the precursor activities (i.e., privacy violations) that could potentially prevent these crimes. To address this limitation, we present PV-VTT (Privacy Violation Video To Text), a unique multimodal dataset aimed at identifying privacy violations. PV-VTT provides detailed annotations for both video and text in scenarios. To ensure the privacy of individuals in the videos, we only provide video feature vectors, avoiding the release of any raw video data. This privacy-focused approach allows researchers to use the dataset while protecting participant confidentiality. Recognizing that privacy violations are often ambiguous and context-dependent, we propose a Graph Neural Network (GNN)-based video description model. Our model generates a GNN-based prompt with image for Large Language Model (LLM), which deliver cost-effective and high-quality video descriptions. By leveraging a single video frame along with relevant text, our method reduces the number of input tokens required, maintaining descriptive quality while optimizing LLM API-usage. Extensive experiments validate the effectiveness and interpretability of our approach in video description tasks and flexibility of our PV-VTT dataset.
Authors: FNU Aryan, Simon Stepputtis, Sarthak Bhagat, Joseph Campbell, Kwonjoon Lee, Hossein Nourkhiz Mahjoub, Katia Sycara
Abstract: Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons over their constituent objects and analyzes their arrangement to infer a scene's meaning. We propose a novel approach that reasons over a scene's scene- and knowledge-graph, capturing spatial information while being able to utilize general domain knowledge in a joint graph search. Empirically, we demonstrate the feasibility of our method on the ADE20K dataset and compare it to current scene understanding approaches.
Authors: Ziyang Gong, Zhixiang Wei, Di Wang, Xianzheng Ma, Hongruixuan Chen, Yuru Jia, Yupeng Deng, Zhenming Ji, Xiangwei Zhu, Naoto Yokoya, Jing Zhang, Bo Du, Liangpei Zhang
Abstract: The field of Remote Sensing Domain Generalization (RSDG) has emerged as a critical and valuable research frontier, focusing on developing models that generalize effectively across diverse scenarios. Despite the substantial domain gaps in RS images that are characterized by variabilities such as location, wavelength, and sensor type, research in this area remains underexplored: (1) Current cross-domain methods primarily focus on Domain Adaptation (DA), which adapts models to predefined domains rather than to unseen ones; (2) Few studies targeting the RSDG issue, especially for semantic segmentation tasks, where existing models are developed for specific unknown domains, struggling with issues of underfitting on other unknown scenarios; (3) Existing RS foundation models tend to prioritize in-domain performance over cross-domain generalization. To this end, we introduce the first vision foundation model for RSDG semantic segmentation, CrossEarth. CrossEarth demonstrates strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline and a model-level Multi-Task Training pipeline. In addition, for the semantic segmentation task, we have curated an RSDG benchmark comprising 28 cross-domain settings across various regions, spectral bands, platforms, and climates, providing a comprehensive framework for testing the generalizability of future RSDG models. Extensive experiments on this benchmark demonstrate the superiority of CrossEarth over existing state-of-the-art methods.
Authors: Edric, Ueta Daisuke, Kurokawa Yukimasa, Karlekar Jayashree, Sugiri Pranata
Abstract: In this paper, we introduce a novel unbiased regression loss for DETR-based detectors. The conventional $L_{1}$ regression loss tends to bias towards larger boxes, as they disproportionately contribute more towards the overall loss compared to smaller boxes. Consequently, the detection performance for small objects suffers. To alleviate this bias, the proposed new unbiased loss, termed Sized $L_{1}$ loss, normalizes the size of all boxes based on their individual width and height. Our experiments demonstrate consistent improvements in both fully-supervised and semi-supervised settings using the MS-COCO benchmark dataset.
Authors: Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Sunil Aryal, Imran Razzak, Hakim Hacid
Abstract: Visual Question Answering (VQA) has emerged as a promising area of research to develop AI-based systems for enabling interactive and immersive learning. Numerous VQA datasets have been introduced to facilitate various tasks, such as answering questions or identifying unanswerable ones. However, most of these datasets are constructed using real-world images, leaving the performance of existing models on cartoon images largely unexplored. Hence, in this paper, we present "SimpsonsVQA", a novel dataset for VQA derived from The Simpsons TV show, designed to promote inquiry-based learning. Our dataset is specifically designed to address not only the traditional VQA task but also to identify irrelevant questions related to images, as well as the reverse scenario where a user provides an answer to a question that the system must evaluate (e.g., as correct, incorrect, or ambiguous). It aims to cater to various visual applications, harnessing the visual content of "The Simpsons" to create engaging and informative interactive systems. SimpsonsVQA contains approximately 23K images, 166K QA pairs, and 500K judgments (https://simpsonsvqa.org). Our experiments show that current large vision-language models like ChatGPT4o underperform in zero-shot settings across all three tasks, highlighting the dataset's value for improving model performance on cartoon images. We anticipate that SimpsonsVQA will inspire further research, innovation, and advancements in inquiry-based learning VQA.
Authors: Shuai Wang, Zexian Li, Tianhui Song, Xubin Li, Tiezheng Ge, Bo Zheng, Limin Wang
Abstract: Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality. Existing transformer-based diffusion methods suffer from quadratic computation cost and limited resolution extrapolation capabilities, making them less effective for this task. In this paper, we propose FlowDCN, a purely convolution-based generative model with linear time and memory complexity, that can efficiently generate high-quality images at arbitrary resolutions. Equipped with a new design of learnable group-wise deformable convolution block, our FlowDCN yields higher flexibility and capability to handle different resolutions with a single model. FlowDCN achieves the state-of-the-art 4.30 sFID on $256\times256$ ImageNet Benchmark and comparable resolution extrapolation results, surpassing transformer-based counterparts in terms of convergence speed (only $\frac{1}{5}$ images), visual quality, parameters ($8\%$ reduction) and FLOPs ($20\%$ reduction). We believe FlowDCN offers a promising solution to scalable and flexible image synthesis.
Authors: Ji Guo, Hongwei Li, Wenbo Jiang, Guoming Lu
Abstract: Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Networks (CNN) across various computer vision tasks. However, akin to CNN, ViTs are vulnerable to backdoor attacks, where the adversary embeds the backdoor into the victim model, causing it to make wrong predictions about testing samples containing a specific trigger. Existing backdoor attacks against ViTs have the limitation of failing to strike an optimal balance between attack stealthiness and attack effectiveness. In this work, we propose an Attention Gradient-based Erosion Backdoor (AGEB) targeted at ViTs. Considering the attention mechanism of ViTs, AGEB selectively erodes pixels in areas of maximal attention gradient, embedding a covert backdoor trigger. Unlike previous backdoor attacks against ViTs, AGEB achieves an optimal balance between attack stealthiness and attack effectiveness, ensuring the trigger remains invisible to human detection while preserving the model's accuracy on clean samples. Extensive experimental evaluations across various ViT architectures and datasets confirm the effectiveness of AGEB, achieving a remarkable Attack Success Rate (ASR) without diminishing Clean Data Accuracy (CDA). Furthermore, the stealthiness of AGEB is rigorously validated, demonstrating minimal visual discrepancies between the clean and the triggered images.
Authors: Parisha Joshi, Daljit Singh J. Dhillon
Abstract: Inverse rendering pipelines are gaining prominence in realizing photo-realistic reconstruction of real-world objects for emulating them in virtual reality scenes. Apart from material reflectances, spectral rendering and in-scene illuminants' spectral power distributions (SPDs) play important roles in producing photo-realistic images. We present a simple, low-cost technique to capture and reconstruct the SPD of uniform illuminants. Instead of requiring a costly spectrometer for such measurements, our method uses a diffractive compact disk (CD-ROM) and a machine learning approach for accurate estimation. We show our method to work well with spotlights under simulations and few real-world examples. Presented results clearly demonstrate the reliability of our approach through quantitative and qualitative evaluations, especially in spectral rendering of iridescent materials.
Authors: Debanjali Bhattacharya, Rajneet Kaur, Ninad Aithal, Neelam Sinha, Thomas Gregor Issac
Abstract: Mild cognitive impairment (MCI), often linked to early neurodegeneration, is characterized by subtle cognitive declines and disruptions in brain connectivity. The present study offers a detailed analysis of topological changes associated with MCI, focusing on two subtypes: Early MCI and Late MCI. This analysis utilizes fMRI time series data from two distinct populations: the publicly available ADNI dataset (Western cohort) and the in-house TLSA dataset (Indian Urban cohort). Persistent Homology, a topological data analysis method, is employed with two distinct filtration techniques - Vietoris-Rips and graph filtration-for classifying MCI subtypes. For Vietoris-Rips filtration, inter-ROI Wasserstein distance matrices between persistent diagrams are used for classification, while graph filtration relies on the top ten most persistent homology features. Comparative analysis shows that the Vietoris-Rips filtration significantly outperforms graph filtration, capturing subtle variations in brain connectivity with greater accuracy. The Vietoris-Rips filtration method achieved the highest classification accuracy of 85.7\% for distinguishing between age and gender matched healthy controls and MCI, whereas graph filtration reached a maximum accuracy of 71.4\% for the same task. This superior performance highlights the sensitivity of Vietoris-Rips filtration in detecting intricate topological features associated with neurodegeneration. The findings underscore the potential of persistent homology, particularly when combined with the Wasserstein distance, as a powerful tool for early diagnosis and precise classification of cognitive impairments, offering valuable insights into brain connectivity changes in MCI.
Authors: Qi Song, Ziyuan Luo, Ka Chun Cheung, Simon See, Renjie Wan
Abstract: Single-view 3D reconstruction methods like Triplane Gaussian Splatting (TGS) have enabled high-quality 3D model generation from just a single image input within seconds. However, this capability raises concerns about potential misuse, where malicious users could exploit TGS to create unauthorized 3D models from copyrighted images. To prevent such infringement, we propose a novel image protection approach that embeds invisible geometry perturbations, termed "geometry cloaks", into images before supplying them to TGS. These carefully crafted perturbations encode a customized message that is revealed when TGS attempts 3D reconstructions of the cloaked image. Unlike conventional adversarial attacks that simply degrade output quality, our method forces TGS to fail the 3D reconstruction in a specific way - by generating an identifiable customized pattern that acts as a watermark. This watermark allows copyright holders to assert ownership over any attempted 3D reconstructions made from their protected images. Extensive experiments have verified the effectiveness of our geometry cloak. Our project is available at https://qsong2001.github.io/geometry_cloak.
Authors: Bohang Sun (School of Information,Software Engineering, University of Electronic Science,Technology of China, Chengdu, China)
Abstract: In this study, we introduce FilterViT, an enhanced version of MobileViT, which leverages an attention-based mechanism for early-stage downsampling. Traditional QKV operations on high-resolution feature maps are computationally intensive due to the abundance of tokens. To address this, we propose a filter attention mechanism using a convolutional neural network (CNN) to generate an importance mask, focusing attention on key image regions. The method significantly reduces computational complexity while maintaining interpretability, as it highlights essential image areas. Experimental results show that FilterViT achieves substantial gains in both efficiency and accuracy compared to other models. We also introduce DropoutViT, a variant that uses a stochastic approach for pixel selection, further enhancing robustness.
Authors: Naijian Cao, Renjie He, Yuchao Dai, Mingyi He
Abstract: Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges due to the quadratic computational complexity of attention mechanisms, especially at high resolutions. However, while existing Transformer-based detector-free local feature matching methods have reduced computational costs using linear attention mechanisms, they still struggle to capture detailed local interactions, which affects the accuracy and robustness of precise local correspondences. In order to enhance representations of attention mechanisms while preserving low computational complexity, we propose the LoFLAT, a novel Local Feature matching using Focused Linear Attention Transformer in this paper. Our LoFLAT consists of three main modules: the Feature Extraction Module, the Feature Transformer Module, and the Matching Module. Specifically, the Feature Extraction Module firstly uses ResNet and a Feature Pyramid Network to extract hierarchical features. The Feature Transformer Module further employs the Focused Linear Attention to refine attention distribution with a focused mapping function and to enhance feature diversity with a depth-wise convolution. Finally, the Matching Module predicts accurate and robust matches through a coarse-to-fine strategy. Extensive experimental evaluations demonstrate that the proposed LoFLAT outperforms the LoFTR method in terms of both efficiency and accuracy.
Authors: HyunJun Jung, Weihang Li, Shun-Cheng Wu, William Bittner, Nikolas Brasch, Jifei Song, Eduardo P\'erez-Pellitero, Zhensong Zhang, Arthur Moreau, Nassir Navab, Benjamin Busam
Abstract: Traditionally, 3d indoor datasets have generally prioritized scale over ground-truth accuracy in order to obtain improved generalization. However, using these datasets to evaluate dense geometry tasks, such as depth rendering, can be problematic as the meshes of the dataset are often incomplete and may produce wrong ground truth to evaluate the details. In this paper, we propose SCRREAM, a dataset annotation framework that allows annotation of fully dense meshes of objects in the scene and registers camera poses on the real image sequence, which can produce accurate ground truth for both sparse 3D as well as dense 3D tasks. We show the details of the dataset annotation pipeline and showcase four possible variants of datasets that can be obtained from our framework with example scenes, such as indoor reconstruction and SLAM, scene editing & object removal, human reconstruction and 6d pose estimation. Recent pipelines for indoor reconstruction and SLAM serve as new benchmarks. In contrast to previous indoor dataset, our design allows to evaluate dense geometry tasks on eleven sample scenes against accurately rendered ground truth depth maps.
Authors: Ji Guo, Wenbo Jiang, Rui Zhang, Guoming Lu, Hongwei Li, Weiren Wu
Abstract: Recently, the success of Text-to-Image (T2I) models has led to the rise of numerous third-party platforms, which claim to provide cheaper API services and more flexibility in model options. However, this also raises a new security concern: Are these third-party services truly offering the models they claim? To address this problem, we propose the first T2I model verification method named Text-to-Image Model Verification via Non-Transferable Adversarial Attacks (TVN). The non-transferability of adversarial examples means that these examples are only effective on a target model and ineffective on other models, thereby allowing for the verification of the target model. TVN utilizes the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to optimize the cosine similarity of a prompt's text encoding, generating non-transferable adversarial prompts. By calculating the CLIP-text scores between the non-transferable adversarial prompts without perturbations and the images, we can verify if the model matches the claimed target model, based on a 3-sigma threshold. The experiments showed that TVN performed well in both closed-set and open-set scenarios, achieving a verification accuracy of over 90\%. Moreover, the adversarial prompts generated by TVN significantly reduced the CLIP-text scores of the target model, while having little effect on other models.
Authors: Junjie Ni, Guofeng Zhang, Guanglin Li, Yijin Li, Xinyang Liu, Zhaoyang Huang, Hujun Bao
Abstract: We tackle the efficiency problem of learning local feature matching.Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel in matching speed, transformer-based methods tend to provide more accurate matches. We propose an efficient transformer-based network architecture for local feature matching.This technique is built on constructing multiple homography hypotheses to approximate the continuous correspondence in the real world and uni-directional cross-attention to accelerate the refinement. On the YFCC100M dataset, our matching accuracy is competitive with LoFTR, a state-of-the-art transformer-based architecture, while the inference speed is boosted to 4 times, even outperforming the CNN-based methods.Comprehensive evaluations on other open datasets such as Megadepth, ScanNet, and HPatches demonstrate our method's efficacy, highlighting its potential to significantly enhance a wide array of downstream applications.
Authors: Andoni Cort\'es, Clemente Rodr\'iguez, Gorka Velez, Javier Barandiar\'an, Marcos Nieto
Abstract: A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts of data costs considerable time, material and effort. To mitigate this problem, the use of synthetic images combined with real data is a popular approach, widely adopted in the scientific community to effectively train various detectors. In this study, we examined the potential of synthetic data-based training in the field of intelligent transportation systems. Our focus is on camera-based traffic sign recognition applications for advanced driver assistance systems and autonomous driving. The proposed augmentation pipeline of synthetic datasets includes novel augmentation processes such as structured shadows and gaussian specular highlights. A well-known DL model was trained with different datasets to compare the performance of synthetic and real image-based trained models. Additionally, a new, detailed method to objectively compare these models is proposed. Synthetic images are generated using a semi-supervised errors-guide method which is also described. Our experiments showed that a synthetic image-based approach outperforms in most cases real image-based training when applied to cross-domain test datasets (+10% precision for GTSRB dataset) and consequently, the generalization of the model is improved decreasing the cost of acquiring images.
Authors: Zheng Yu, Yaohua Wang, Siying Cui, Aixi Zhang, Wei-Long Zheng, Senzhang Wang
Abstract: Facial parts swapping aims to selectively transfer regions of interest from the source image onto the target image while maintaining the rest of the target image unchanged. Most studies on face swapping designed specifically for full-face swapping, are either unable or significantly limited when it comes to swapping individual facial parts, which hinders fine-grained and customized character designs. However, designing such an approach specifically for facial parts swapping is challenged by a reasonable multiple reference feature fusion, which needs to be both efficient and effective. To overcome this challenge, FuseAnyPart is proposed to facilitate the seamless "fuse-any-part" customization of the face. In FuseAnyPart, facial parts from different people are assembled into a complete face in latent space within the Mask-based Fusion Module. Subsequently, the consolidated feature is dispatched to the Addition-based Injection Module for fusion within the UNet of the diffusion model to create novel characters. Extensive experiments qualitatively and quantitatively validate the superiority and robustness of FuseAnyPart. Source codes are available at https://github.com/Thomas-wyh/FuseAnyPart.
Authors: Arash Marioriyad, Parham Rezaei, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Abstract: Text-to-image (T2I) generative models, such as Stable Diffusion and DALL-E, have shown remarkable proficiency in producing high-quality, realistic, and natural images from textual descriptions. However, these models sometimes fail to accurately capture all the details specified in the input prompts, particularly concerning entities, attributes, and spatial relationships. This issue becomes more pronounced when the prompt contains novel or complex compositions, leading to what are known as compositional generation failure modes. Recently, a new open-source diffusion-based T2I model, FLUX, has been introduced, demonstrating strong performance in high-quality image generation. Additionally, autoregressive T2I models like LlamaGen have claimed competitive visual quality performance compared to diffusion-based models. In this study, we evaluate the compositional generation capabilities of these newly introduced models against established models using the T2I-CompBench benchmark. Our findings reveal that LlamaGen, as a vanilla autoregressive model, is not yet on par with state-of-the-art diffusion models for compositional generation tasks under the same criteria, such as model size and inference time. On the other hand, the open-source diffusion-based model FLUX exhibits compositional generation capabilities comparable to the state-of-the-art closed-source model DALL-E3.
Authors: Jerome Gilles, Stanley Osher
Abstract: In this paper, we design a very simple algorithm based on Split Bregman iterations to numerically solve the cartoon + textures decomposition model of Meyer. This results in a significant gain in speed compared to Chambolle's nonlinear projectors.
Authors: Nicholas B. Ferrante, Jerome Gilles
Abstract: Long distance imaging is subject to the impact of the turbulent atmosphere. This results into geometric distortions and some blur effect in the observed frames. Despite the existence of several turbulence mitigation algorithms in the literature, no common dataset exists to objectively evaluate their efficiency. In this paper, we describe a new dataset called OTIS (Open Turbulent Images Set) which contains several sequences (either static or dynamic) acquired through the turbulent atmosphere. For almost all sequences, we provide the corresponding groundtruth in order to make the comparison between algorithms easier. We also discuss possible metrics to perform such comparisons.
Authors: Jerome Gilles, Stanley Osher
Abstract: In this paper, we investigate the extension of the recently proposed weighted Fourier burst accumulation (FBA) method into the wavelet domain. The purpose of FBA is to reconstruct a clean and sharp image from a sequence of blurred frames. This concept lies in the construction of weights to amplify dominant frequencies in the Fourier spectrum of each frame. The reconstructed image is then obtained by taking the inverse Fourier transform of the average of all processed spectra. In this paper, we first suggest to replace the rigid registration step used in the original algorithm by a non-rigid registration in order to be able to process sequences acquired through atmospheric turbulence. Second, we propose to work in a wavelet domain instead of the Fourier one. This leads us to the construction of two types of algorithms. Finally, we propose an alternative approach to replace the weighting idea by an approach promoting the sparsity in the used space. Several experiments are provided to illustrate the efficiency of the proposed methods.
Authors: Mohd. Azfar, Siddhant Bharadwaj, Ashwin Sasikumar
Abstract: Enhancing and preserving the readability of document images, particularly historical ones, is crucial for effective document image analysis. Numerous models have been proposed for this task, including convolutional-based, transformer-based, and hybrid convolutional-transformer architectures. While hybrid models address the limitations of purely convolutional or transformer-based methods, they often suffer from issues like quadratic time complexity. In this work, we propose a Mamba-based architecture for document binarisation, which efficiently handles long sequences by scaling linearly and optimizing memory usage. Additionally, we introduce novel modifications to the skip connections by incorporating Difference of Gaussians (DoG) features, inspired by conventional signal processing techniques. These multiscale high-frequency features enable the model to produce high-quality, detailed outputs.
Authors: Zhiyuan Min, Yawei Luo, Jianwen Sun, Yi Yang
Abstract: Generalizable 3D Gaussian splitting (3DGS) can reconstruct new scenes from sparse-view observations in a feed-forward inference manner, eliminating the need for scene-specific retraining required in conventional 3DGS. However, existing methods rely heavily on epipolar priors, which can be unreliable in complex realworld scenes, particularly in non-overlapping and occluded regions. In this paper, we propose eFreeSplat, an efficient feed-forward 3DGS-based model for generalizable novel view synthesis that operates independently of epipolar line constraints. To enhance multiview feature extraction with 3D perception, we employ a selfsupervised Vision Transformer (ViT) with cross-view completion pre-training on large-scale datasets. Additionally, we introduce an Iterative Cross-view Gaussians Alignment method to ensure consistent depth scales across different views. Our eFreeSplat represents an innovative approach for generalizable novel view synthesis. Different from the existing pure geometry-free methods, eFreeSplat focuses more on achieving epipolar-free feature matching and encoding by providing 3D priors through cross-view pretraining. We evaluate eFreeSplat on wide-baseline novel view synthesis tasks using the RealEstate10K and ACID datasets. Extensive experiments demonstrate that eFreeSplat surpasses state-of-the-art baselines that rely on epipolar priors, achieving superior geometry reconstruction and novel view synthesis quality. Project page: https://tatakai1.github.io/efreesplat/.
Authors: Chinthani Sugandhika, Chen Li, Deepu Rajan, Basura Fernando
Abstract: Graph based representation has been widely used in modelling spatio-temporal relationships in video understanding. Although effective, existing graph-based approaches focus on capturing the human-object relationships while ignoring fine-grained semantic properties of the action components. These semantic properties are crucial for understanding the current situation, such as where does the action takes place, what tools are used and functional properties of the objects. In this work, we propose a graph-based representation called Situational Scene Graph (SSG) to encode both human-object relationships and the corresponding semantic properties. The semantic details are represented as predefined roles and values inspired by situation frame, which is originally designed to represent a single action. Based on our proposed representation, we introduce the task of situational scene graph generation and propose a multi-stage pipeline Interactive and Complementary Network (InComNet) to address the task. Given that the existing datasets are not applicable to the task, we further introduce a SSG dataset whose annotations consist of semantic role-value frames for human, objects and verb predicates of human-object relations. Finally, we demonstrate the effectiveness of our proposed SSG representation by testing on different downstream tasks. Experimental results show that the unified representation can not only benefit predicate classification and semantic role-value classification, but also benefit reasoning tasks on human-centric situation understanding. We will release the code and the dataset soon.
Authors: Kun Hu, Qingle Zhang, Maoxun Yuan, Yitian Zhang
Abstract: Infrared and visible image fusion aims to utilize the complementary information from two modalities to generate fused images with prominent targets and rich texture details. Most existing algorithms only perform pixel-level or feature-level fusion from different modalities in the spatial domain. They usually overlook the information in the frequency domain, and some of them suffer from inefficiency due to excessively complex structures. To tackle these challenges, this paper proposes an efficient Spatial-Frequency Domain Fusion (SFDFusion) network for infrared and visible image fusion. First, we propose a Dual-Modality Refinement Module (DMRM) to extract complementary information. This module extracts useful information from both the infrared and visible modalities in the spatial domain and enhances fine-grained spatial details. Next, to introduce frequency domain information, we construct a Frequency Domain Fusion Module (FDFM) that transforms the spatial domain to the frequency domain through Fast Fourier Transform (FFT) and then integrates frequency domain information. Additionally, we design a frequency domain fusion loss to provide guidance for the fusion process. Extensive experiments on public datasets demonstrate that our method produces fused images with significant advantages in various fusion metrics and visual effects. Furthermore, our method demonstrates high efficiency in image fusion and good performance on downstream detection tasks, thereby satisfying the real-time demands of advanced visual tasks.
Authors: Ahmet Serdar Karadeniz, Dimitrios Mallis, Nesryne Mejri, Kseniya Cherenkova, Anis Kacem, Djamila Aouada
Abstract: This work presents DAVINCI, a unified architecture for single-stage Computer-Aided Design (CAD) sketch parameterization and constraint inference directly from raster sketch images. By jointly learning both outputs, DAVINCI minimizes error accumulation and enhances the performance of constrained CAD sketch inference. Notably, DAVINCI achieves state-of-the-art results on the large-scale SketchGraphs dataset, demonstrating effectiveness on both precise and hand-drawn raster CAD sketches. To reduce DAVINCI's reliance on large-scale annotated datasets, we explore the efficacy of CAD sketch augmentations. We introduce Constraint-Preserving Transformations (CPTs), i.e. random permutations of the parametric primitives of a CAD sketch that preserve its constraints. This data augmentation strategy allows DAVINCI to achieve reasonable performance when trained with only 0.1% of the SketchGraphs dataset. Furthermore, this work contributes a new version of SketchGraphs, augmented with CPTs. The newly introduced CPTSketchGraphs dataset includes 80 million CPT-augmented sketches, thus providing a rich resource for future research in the CAD sketch domain.
Authors: Karan Bania, Tanmay Verlekar
Abstract: Video-based gait analysis can be defined as the task of diagnosing pathologies, such as ataxia, using videos of patients walking in front of a camera. This paper presents a graph convolution network called AtGCN for detecting ataxic gait and identifying its severity using 2D videos. The problem is especially challenging as the deviation of an ataxic gait from a healthy gait is very subtle. The datasets for ataxic gait detection are also quite small, with the largest dataset having only 149 videos. The paper addresses the first problem using special spatiotemporal graph convolution that successfully captures important gait-related features. To handle the small dataset size, a deep spatiotemporal graph convolution network pre-trained on an action recognition dataset is systematically truncated and then fine-tuned on the ataxia dataset to obtain the AtGCN model. The paper also presents an augmentation strategy that segments a video sequence into multiple gait cycles. The proposed AtGCN model then operates on a graph of body part locations belonging to a single gait cycle. The evaluation results support the strength of the proposed AtGCN model, as it outperforms the state-of-the-art in detection and severity prediction with an accuracy of 93.46% and a MAE of 0.4169, respectively.
Authors: Feihong Shen, Chao Li, Yifeng Geng, Yongjian Deng, Hao Chen
Abstract: Image retargeting is the task of adjusting the aspect ratio of images to suit different display devices or presentation environments. However, existing retargeting methods often struggle to balance the preservation of key semantics and image quality, resulting in either deformation or loss of important objects, or the introduction of local artifacts such as discontinuous pixels and inconsistent regenerated content. To address these issues, we propose a content-aware retargeting method called PruneRepaint. It incorporates semantic importance for each pixel to guide the identification of regions that need to be pruned or preserved in order to maintain key semantics. Additionally, we introduce an adaptive repainting module that selects image regions for repainting based on the distribution of pruned pixels and the proportion between foreground size and target aspect ratio, thus achieving local smoothness after pruning. By focusing on the content and structure of the foreground, our PruneRepaint approach adaptively avoids key content loss and deformation, while effectively mitigating artifacts with local repainting. We conduct experiments on the public RetargetMe benchmark and demonstrate through objective experimental results and subjective user studies that our method outperforms previous approaches in terms of preserving semantics and aesthetics, as well as better generalization across diverse aspect ratios. Codes will be available at https://github.com/fhshen2022/PruneRepaint.
Authors: Imad Ali Shah, Fahad Mumtaz Malik, Muhammad Waqas Ashraf
Abstract: Computer vision researchers have extensively worked on fundamental infrared visual recognition for the past few decades. Among various approaches, deep learning has emerged as the most promising candidate. However, Infrared Small Object Segmentation (ISOS) remains a major focus due to several challenges including: 1) the lack of effective utilization of local contrast and global contextual information; 2) the potential loss of small objects in deep models; and 3) the struggling to capture fine-grained details and ignore noise. To address these challenges, we propose a modified U-Net architecture, named SFA-UNet, by combining Scharr Convolution (SC) and Fast Fourier Convolution (FFC) in addition to vertical and horizontal Attention gates (AG) into UNet. SFA-UNet utilizes double convolution layers with the addition of SC and FFC in its encoder and decoder layers. SC helps to learn the foreground-to-background contrast information whereas FFC provide multi-scale contextual information while mitigating the small objects vanishing problem. Additionally, the introduction of vertical AGs in encoder layers enhances the model's focus on the targeted object by ignoring irrelevant regions. We evaluated the proposed approach on publicly available, SIRST and IRSTD datasets, and achieved superior performance by an average 0.75% with variance of 0.025 of all combined metrics in multiple runs as compared to the existing state-of-the-art methods
Authors: Haowen Xiao, Guanghui Liu, Xinyi Gao, Yang Li, Fengmao Lv, Jielei Chu
Abstract: Self-supervised learning (SSL) has achieved impressive results across several computer vision tasks, even rivaling supervised methods. However, its performance degrades on real-world datasets with long-tailed distributions due to difficulties in capturing inherent class imbalances. Although supervised long-tailed learning offers significant insights, the absence of labels in SSL prevents direct transfer of these strategies.To bridge this gap, we introduce Adaptive Paradigm Synergy (APS), a cross-paradigm objective that seeks to unify the strengths of both paradigms. Our approach reexamines contrastive learning from a spatial structure perspective, dynamically adjusting the uniformity of latent space structure through adaptive temperature tuning. Furthermore, we draw on a re-weighting strategy from supervised learning to compensate for the shortcomings of temperature adjustment in explicit quantity perception.Extensive experiments on commonly used long-tailed datasets demonstrate that APS improves performance effectively and efficiently. Our findings reveal the potential for deeper integration between supervised and self-supervised learning, paving the way for robust models that handle real-world class imbalance.
Authors: Youcheng Huang, Fengbin Zhu, Jingkun Tang, Pan Zhou, Wenqiang Lei, Jiancheng Lv, Tat-Seng Chua
Abstract: Visual Language Models (VLMs) are vulnerable to adversarial attacks, especially those from adversarial images, which is however under-explored in literature. To facilitate research on this critical safety problem, we first construct a new laRge-scale Adervsarial images dataset with Diverse hArmful Responses (RADAR), given that existing datasets are either small-scale or only contain limited types of harmful responses. With the new RADAR dataset, we further develop a novel and effective iN-time Embedding-based AdveRSarial Image DEtection (NEARSIDE) method, which exploits a single vector that distilled from the hidden states of VLMs, which we call the attacking direction, to achieve the detection of adversarial images against benign ones in the input. Extensive experiments with two victim VLMs, LLaVA and MiniGPT-4, well demonstrate the effectiveness, efficiency, and cross-model transferrability of our proposed method. Our code is available at https://github.com/mob-scu/RADAR-NEARSIDE
Authors: Mujadded Al Rabbani Alif
Abstract: Accurate vehicle detection is essential for the development of intelligent transportation systems, autonomous driving, and traffic monitoring. This paper presents a detailed analysis of YOLO11, the latest advancement in the YOLO series of deep learning models, focusing exclusively on vehicle detection tasks. Building upon the success of its predecessors, YOLO11 introduces architectural improvements designed to enhance detection speed, accuracy, and robustness in complex environments. Using a comprehensive dataset comprising multiple vehicle types-cars, trucks, buses, motorcycles, and bicycles we evaluate YOLO11's performance using metrics such as precision, recall, F1 score, and mean average precision (mAP). Our findings demonstrate that YOLO11 surpasses previous versions (YOLOv8 and YOLOv10) in detecting smaller and more occluded vehicles while maintaining a competitive inference time, making it well-suited for real-time applications. Comparative analysis shows significant improvements in the detection of complex vehicle geometries, further contributing to the development of efficient and scalable vehicle detection systems. This research highlights YOLO11's potential to enhance autonomous vehicle performance and traffic monitoring systems, offering insights for future developments in the field.
Authors: Amit Bracha, Thomas Dag\`es, Ron Kimmel
Abstract: When matching parts of a surface to its whole, a fundamental question arises: Which points should be included in the matching process? The issue is intensified when using isometry to measure similarity, as it requires the validation of whether distances measured between pairs of surface points should influence the matching process. The approach we propose treats surfaces as manifolds equipped with geodesic distances, and addresses the partial shape matching challenge by introducing a novel criterion to meticulously search for consistent distances between pairs of points. The new criterion explores the relation between intrinsic geodesic distances between the points, geodesic distances between the points and surface boundaries, and extrinsic distances between boundary points measured in the embedding space. It is shown to be less restrictive compared to previous measures and achieves state-of-the-art results when used as a loss function in training networks for partial shape matching.
Authors: Shengkai Zhang, Nianhong Jiao, Tian Li, Chaojie Yang, Chenhui Xue, Boya Niu, Jun Gao
Abstract: We propose an effective method for inserting adapters into text-to-image foundation models, which enables the execution of complex downstream tasks while preserving the generalization ability of the base model. The core idea of this method is to optimize the attention mechanism related to 2D feature maps, which enhances the performance of the adapter. This approach was validated on the task of meme video generation and achieved significant results. We hope this work can provide insights for post-training tasks of large text-to-image models. Additionally, as this method demonstrates good compatibility with SD1.5 derivative models, it holds certain value for the open-source community. Therefore, we will release the related code (\url{https://songkey.github.io/hellomeme}).
Authors: Geng Li, Haozhi Cao, Mingyang Liu, Chenxi Jiang, Jianfei Yang
Abstract: Non-rigid point cloud registration is a critical challenge in 3D scene understanding, particularly in surgical navigation. Although existing methods achieve excellent performance when trained on large-scale, high-quality datasets, these datasets are prohibitively expensive to collect and annotate, e.g., organ data in authentic medical scenarios. With insufficient training samples and data noise, existing methods degrade significantly since non-rigid patterns are more flexible and complicated than rigid ones, and the distributions across samples are more distinct, leading to higher difficulty in representation learning with few data. In this work, we aim to deal with this challenging few-shot non-rigid point cloud registration problem. Based on the observation that complex non-rigid transformation patterns can be decomposed into rigid and small non-rigid transformations, we propose a novel and effective framework, UniRiT. UniRiT adopts a two-step registration strategy that first aligns the centroids of the source and target point clouds and then refines the registration with non-rigid transformations, thereby significantly reducing the problem complexity. To validate the performance of UniRiT on real-world datasets, we introduce a new dataset, MedMatch3D, which consists of real human organs and exhibits high variability in sample distribution. We further establish a new challenging benchmark for few-shot non-rigid registration. Extensive empirical results demonstrate that UniRiT achieves state-of-the-art performance on MedMatch3D, improving the existing best approach by 94.22%.
Authors: Mingxian Li, Hao Sun, Yingtie Lei, Xiaofeng Zhang, Yihang Dong, Yilin Zhou, Zimeng Li, Xuhang Chen
Abstract: Document images are often degraded by various stains, significantly impacting their readability and hindering downstream applications such as document digitization and analysis. The absence of a comprehensive stained document dataset has limited the effectiveness of existing document enhancement methods in removing stains while preserving fine-grained details. To address this challenge, we construct StainDoc, the first large-scale, high-resolution ($2145\times2245$) dataset specifically designed for document stain removal. StainDoc comprises over 5,000 pairs of stained and clean document images across multiple scenes. This dataset encompasses a diverse range of stain types, severities, and document backgrounds, facilitating robust training and evaluation of document stain removal algorithms. Furthermore, we propose StainRestorer, a Transformer-based document stain removal approach. StainRestorer employs a memory-augmented Transformer architecture that captures hierarchical stain representations at part, instance, and semantic levels via the DocMemory module. The Stain Removal Transformer (SRTransformer) leverages these feature representations through a dual attention mechanism: an enhanced spatial attention with an expanded receptive field, and a channel attention captures channel-wise feature importance. This combination enables precise stain removal while preserving document content integrity. Extensive experiments demonstrate StainRestorer's superior performance over state-of-the-art methods on the StainDoc dataset and its variants StainDoc\_Mark and StainDoc\_Seal, establishing a new benchmark for document stain removal. Our work highlights the potential of memory-augmented Transformers for this task and contributes a valuable dataset to advance future research.
Authors: Yihao Wu, Di Zhao, Jingfeng Zhang, Yun Sing Koh
Abstract: Reliable re-identification of individuals within large wildlife populations is crucial for biological studies, ecological research, and wildlife conservation. Classic computer vision techniques offer a promising direction for Animal Re-identification (Animal ReID), but their backbones' close-set nature limits their applicability and generalizability. Despite the demonstrated effectiveness of vision-language models like CLIP in re-identifying persons and vehicles, their application to Animal ReID remains limited due to unique challenges, such as the various visual representations of animals, including variations in poses and forms. To address these limitations, we leverage CLIP's cross-modal capabilities to introduce a two-stage framework, the \textbf{Indiv}idual \textbf{A}nimal \textbf{ID}entity-Driven (IndivAID) framework, specifically designed for Animal ReID. In the first stage, IndivAID trains a text description generator by extracting individual semantic information from each image, generating both image-specific and individual-specific textual descriptions that fully capture the diverse visual concepts of each individual across animal images. In the second stage, IndivAID refines its learning of visual concepts by dynamically incorporating individual-specific textual descriptions with an integrated attention module to further highlight discriminative features of individuals for Animal ReID. Evaluation against state-of-the-art methods across eight benchmark datasets and a real-world Stoat dataset demonstrates IndivAID's effectiveness and applicability. Code is available at \url{https://github.com/ywu840/IndivAID}.
Authors: Antoine Schnepf, Karim Kassab, Jean-Yves Franceschi, Laurent Caraffa, Flavian Vasile, Jeremie Mary, Andrew Comport, Valerie Gouet-Brunet
Abstract: While pre-trained image autoencoders are increasingly utilized in computer vision, the application of inverse graphics in 2D latent spaces has been under-explored. Yet, besides reducing the training and rendering complexity, applying inverse graphics in the latent space enables a valuable interoperability with other latent-based 2D methods. The major challenge is that inverse graphics cannot be directly applied to such image latent spaces because they lack an underlying 3D geometry. In this paper, we propose an Inverse Graphics Autoencoder (IG-AE) that specifically addresses this issue. To this end, we regularize an image autoencoder with 3D-geometry by aligning its latent space with jointly trained latent 3D scenes. We utilize the trained IG-AE to bring NeRFs to the latent space with a latent NeRF training pipeline, which we implement in an open-source extension of the Nerfstudio framework, thereby unlocking latent scene learning for its supported methods. We experimentally confirm that Latent NeRFs trained with IG-AE present an improved quality compared to a standard autoencoder, all while exhibiting training and rendering accelerations with respect to NeRFs trained in the image space. Our project page can be found at https://ig-ae.github.io .
URLs: https://ig-ae.github.io
Authors: Yujin Wang, Tianyi Xu, Fan Zhang, Tianfan Xue, Jinwei Gu
Abstract: Image Signal Processors (ISPs) convert raw sensor signals into digital images, which significantly influence the image quality and the performance of downstream computer vision tasks. Designing ISP pipeline and tuning ISP parameters are two key steps for building an imaging and vision system. To find optimal ISP configurations, recent works use deep neural networks as a proxy to search for ISP parameters or ISP pipelines. However, these methods are primarily designed to maximize the image quality, which are sub-optimal in the performance of high-level computer vision tasks such as detection, recognition, and tracking. Moreover, after training, the learned ISP pipelines are mostly fixed at the inference time, whose performance degrades in dynamic scenes. To jointly optimize ISP structures and parameters, we propose AdaptiveISP, a task-driven and scene-adaptive ISP. One key observation is that for the majority of input images, only a few processing modules are needed to improve the performance of downstream recognition tasks, and only a few inputs require more processing. Based on this, AdaptiveISP utilizes deep reinforcement learning to automatically generate an optimal ISP pipeline and the associated ISP parameters to maximize the detection performance. Experimental results show that AdaptiveISP not only surpasses the prior state-of-the-art methods for object detection but also dynamically manages the trade-off between detection performance and computational cost, especially suitable for scenes with large dynamic range variations. Project website: https://openimaginglab.github.io/AdaptiveISP/.
Authors: Wei Dong, Yuan Sun, Yiting Yang, Xing Zhang, Zhijun Lin, Qingsen Yan, Haokui Zhang, Peng Wang, Yang Yang, Hengtao Shen
Abstract: A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To address this limitation, we propose a novel PEFT approach inspired by Singular Value Decomposition (SVD) for representing the adaptation matrix. SVD decomposes a matrix into the product of a left unitary matrix, a diagonal matrix of scaling values, and a right unitary matrix. We utilize Householder transformations to construct orthogonal matrices that efficiently mimic the unitary matrices, requiring only a vector. The diagonal values are learned in a layer-wise manner, allowing them to flexibly capture the unique properties of each layer. This approach enables the generation of adaptation matrices with varying ranks across different layers, providing greater flexibility in adapting pre-trained models. Experiments on standard downstream vision tasks demonstrate that our method achieves promising fine-tuning performance.
Authors: Shangquan Sun, Wenqi Ren, Zikun Liu, Hyunhee Park, Rui Wang, Xiaochun Cao
Abstract: Image restoration has experienced significant advancements due to the development of deep learning. Nevertheless, it encounters challenges related to ill-posed problems, resulting in deviations between single model predictions and ground-truths. Ensemble learning, as a powerful machine learning technique, aims to address these deviations by combining the predictions of multiple base models. Most existing works adopt ensemble learning during the design of restoration models, while only limited research focuses on the inference-stage ensemble of pre-trained restoration models. Regression-based methods fail to enable efficient inference, leading researchers in academia and industry to prefer averaging as their choice for post-training ensemble. To address this, we reformulate the ensemble problem of image restoration into Gaussian mixture models (GMMs) and employ an expectation maximization (EM)-based algorithm to estimate ensemble weights for aggregating prediction candidates. We estimate the range-wise ensemble weights on a reference set and store them in a lookup table (LUT) for efficient ensemble inference on the test set. Our algorithm is model-agnostic and training-free, allowing seamless integration and enhancement of various pre-trained image restoration models. It consistently outperforms regression based methods and averaging ensemble approaches on 14 benchmarks across 3 image restoration tasks, including super-resolution, deblurring and deraining. The codes and all estimated weights have been released in Github.
Authors: Yuxin Zhang, Dandan Zheng, Biao Gong, Jingdong Chen, Ming Yang, Weiming Dong, Changsheng Xu
Abstract: Lighting plays a pivotal role in ensuring the naturalness of video generation, significantly influencing the aesthetic quality of the generated content. However, due to the deep coupling between lighting and the temporal features of videos, it remains challenging to disentangle and model independent and coherent lighting attributes, limiting the ability to control lighting in video generation. In this paper, inspired by the established controllable T2I models, we propose LumiSculpt, which, for the first time, enables precise and consistent lighting control in T2V generation models.LumiSculpt equips the video generation with strong interactive capabilities, allowing the input of custom lighting reference image sequences. Furthermore, the core learnable plug-and-play module of LumiSculpt facilitates remarkable control over lighting intensity, position, and trajectory in latent video diffusion models based on the advanced DiT backbone.Additionally, to effectively train LumiSculpt and address the issue of insufficient lighting data, we construct LumiHuman, a new lightweight and flexible dataset for portrait lighting of images and videos. Experimental results demonstrate that LumiSculpt achieves precise and high-quality lighting control in video generation.
Authors: Jingkun Ma, Runzhe Zhan, Derek F. Wong, Yang Li, Di Sun, Hou Pong Chan, Lidia S. Chao
Abstract: Although previous research on large language models (LLMs) and large multi-modal models (LMMs) has systematically explored mathematical problem-solving (MPS) within visual contexts, the analysis of how these models process visual information during problem-solving remains insufficient. To address this gap, we present VisAidMath, a benchmark for evaluating the MPS process related to visual information. We follow a rigorous data curation pipeline involving both automated processes and manual annotations to ensure data quality and reliability. Consequently, this benchmark includes 1,200 challenging problems from various mathematical branches, vision-aid formulations, and difficulty levels, collected from diverse sources such as textbooks, examination papers, and Olympiad problems. Based on the proposed benchmark, we conduct comprehensive evaluations on ten mainstream LLMs and LMMs, highlighting deficiencies in the visual-aided reasoning process. For example, GPT-4V only achieves 45.33% accuracy in the visual-aided reasoning task, even with a drop of 2 points when provided with golden visual aids. In-depth analysis reveals that the main cause of deficiencies lies in hallucination regarding the implicit visual reasoning process, shedding light on future research directions in the visual-aided MPS process.
Authors: Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli, David Naccache
Abstract: Interpreting the decisions of Convolutional Neural Networks (CNNs) is essential for understanding their behavior, yet explainability remains a significant challenge, particularly for self-supervised models. Most existing methods for generating saliency maps rely on ground truth labels, restricting their use to supervised tasks. EigenCAM is the only notable label-independent alternative, leveraging Singular Value Decomposition to generate saliency maps applicable across CNN models, but it does not fully exploit the tensorial structure of feature maps. In this work, we introduce the Tucker Saliency Map (TSM) method, which applies Tucker tensor decomposition to better capture the inherent structure of feature maps, producing more accurate singular vectors and values. These are used to generate high-fidelity saliency maps, effectively highlighting objects of interest in the input. We further extend EigenCAM and TSM into multivector variants -Multivec-EigenCAM and Multivector Tucker Saliency Maps (MTSM)- which utilize all singular vectors and values, further improving saliency map quality. Quantitative evaluations on supervised classification models demonstrate that TSM, Multivec-EigenCAM, and MTSM achieve competitive performance with label-dependent methods. Moreover, TSM enhances explainability by approximately 50% over EigenCAM for both supervised and self-supervised models. Multivec-EigenCAM and MTSM further advance state-of-the-art explainability performance on self-supervised models, with MTSM achieving the best results.
Authors: Hongyu Chen, Chengcheng Chen, Fei Wang, Yuhu Shi, Weiming Zeng
Abstract: Recent developments in synthetic aperture radar (SAR) ship detection have seen deep learning techniques achieve remarkable progress in accuracy and speed. However, the detection of small targets against complex backgrounds remains a significant challenge. To tackle these difficulties, this letter presents RSNet, a lightweight framework aimed at enhancing ship detection capabilities in SAR imagery. RSNet features the Waveletpool-ContextGuided (WCG) backbone for enhanced accuracy with fewer parameters, and the Waveletpool-StarFusion (WSF) head for efficient parameter reduction. Additionally, a Lightweight-Shared (LS) module minimizes the detection head's parameter load. Experiments on the SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Image Dataset (HRSID) demonstrate that RSNet achieves a strong balance between lightweight design and detection performance, surpassing many state-of-the-art detectors, reaching 72.5\% and 67.6\% in \textbf{\(\mathbf{mAP_{.50:95}}\) }respectively with 1.49M parameters. Our code will be released soon.
Authors: Tengfei Zhang, Heng Zhang, Ruyang Li, Qi Deng, Yaqian Zhao, Rengang Li
Abstract: This report presents our team's solutions for the Track 1 of the 2024 ECCV ROAD++ Challenge. The task of Track 1 is spatiotemporal agent detection, which aims to construct an "agent tube" for road agents in consecutive video frames. Our solutions focus on the challenges in this task, including extreme-size objects, low-light scenarios, class imbalance, and fine-grained classification. Firstly, the extreme-size object detection heads are introduced to improve the detection performance of large and small objects. Secondly, we design a dual-stream detection model with a low-light enhancement stream to improve the performance of spatiotemporal agent detection in low-light scenes, and the feature fusion module to integrate features from different branches. Subsequently, we develop a multi-branch detection framework to mitigate the issues of class imbalance and fine-grained classification, and we design a pre-training and fine-tuning approach to optimize the above multi-branch framework. Besides, we employ some common data augmentation techniques, and improve the loss function and upsampling operation. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.
Authors: Maciej K. Wozniak, Hariprasath Govindarajan, Marvin Klingner, Camille Maurice, Ravi Kiran, Senthil Yogamani
Abstract: Recent self-supervised clustering-based pre-training techniques like DINO and Cribo have shown impressive results for downstream detection and segmentation tasks. However, real-world applications such as autonomous driving face challenges with imbalanced object class and size distributions and complex scene geometries. In this paper, we propose S3PT a novel scene semantics and structure guided clustering to provide more scene-consistent objectives for self-supervised training. Specifically, our contributions are threefold: First, we incorporate semantic distribution consistent clustering to encourage better representation of rare classes such as motorcycles or animals. Second, we introduce object diversity consistent spatial clustering, to handle imbalanced and diverse object sizes, ranging from large background areas to small objects such as pedestrians and traffic signs. Third, we propose a depth-guided spatial clustering to regularize learning based on geometric information of the scene, thus further refining region separation on the feature level. Our learned representations significantly improve performance in downstream semantic segmentation and 3D object detection tasks on the nuScenes, nuImages, and Cityscapes datasets and show promising domain translation properties.
Authors: Tianxiang Wu, Minxin Nie, Ziqiang Cao
Abstract: The Multimodal Large Language Models (MLLMs) have activated the capabilitiesof Large Language Models (LLMs) in solving visual-language tasks by integratingvisual information. The prevailing approach in existing MLLMs involvesemploying an image encoder to extract visual features, converting thesefeatures into visual tokens via an adapter, and then integrating them with theprompt into the LLM. However, because the process of image encoding isprompt-agnostic, the extracted visual features only provide a coarsedescription of the image, impossible to focus on the requirements of theprompt. On one hand, it is easy for image features to lack information aboutthe prompt-specified objects, resulting in unsatisfactory responses. On theother hand, the visual features contain a large amount of irrelevantinformation, which not only increases the burden on memory but also worsens thegeneration effectiveness. To address the aforementioned issues, we propose\textbf{PIP-MM}, a framework that \textbf{P}re-\textbf{I}ntegrates\textbf{P}rompt information into the visual encoding process using existingmodules of MLLMs. Specifically, We utilize the frozen LLM in the MLLM tovectorize the input prompt, which summarizes the requirements of the prompt.Then, we input the prompt vector into our trained Multi-Layer Perceptron (MLP)to align with the visual input requirements, and subsequently replace the classembedding in the image encoder. Since our model only requires adding atrainable MLP, it can be applied to any MLLM. To validate the effectiveness ofPIP-MM, we conducted experiments on multiple benchmarks. Automated evaluationmetrics and manual assessments demonstrate the strong performance of PIP-MM.Particularly noteworthy is that our model maintains excellent generationresults even when half of the visual tokens are reduced.
Authors: Mingkun Zhang, Keping Bi, Wei Chen, Quanrun Chen, Jiafeng Guo, Xueqi Cheng
Abstract: Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark).
Authors: Ruyang Li, Tengfei Zhang, Heng Zhang, Tiejun Liu, Yanwei Wang, Xuelei Li
Abstract: This report presents our team's technical solution for participating in Track 3 of the 2024 ECCV ROAD++ Challenge. The task of Track 3 is atomic activity recognition, which aims to identify 64 types of atomic activities in road scenes based on video content. Our approach primarily addresses the challenges of small objects, discriminating between single object and a group of objects, as well as model overfitting in this task. Firstly, we construct a multi-branch activity recognition framework that not only separates different object categories but also the tasks of single object and object group recognition, thereby enhancing recognition accuracy. Subsequently, we develop various model ensembling strategies, including integrations of multiple frame sampling sequences, different frame sampling sequence lengths, multiple training epochs, and different backbone networks. Furthermore, we propose an atomic activity recognition data augmentation method, which greatly expands the sample space by flipping video frames and road topology, effectively mitigating model overfitting. Our methods rank first in the test set of Track 3 for the ROAD++ Challenge 2024, and achieve 69% mAP.
Authors: Pengkun Liu, Shuna Ni, Stanislav I. Stoliarov, Pingbo Tang
Abstract: Fire patterns, consisting of fire effects that offer insights into fire behavior and origin, are traditionally classified based on investigators' visual observations, leading to subjective interpretations. This study proposes a framework for quantitative fire pattern classification to support fire investigators, aiming for consistency and accuracy. The framework integrates four components. First, it leverages human-computer interaction to extract fire patterns from surfaces, combining investigator expertise with computational analysis. Second, it employs an aspect ratio-based random forest model to classify fire pattern shapes. Third, fire scene point cloud segmentation enables precise identification of fire-affected areas and the mapping of 2D fire patterns to 3D scenes. Lastly, spatial relationships between fire patterns and indoor elements support an interpretation of the fire scene. These components provide a method for fire pattern analysis that synthesizes qualitative and quantitative data. The framework's classification results achieve 93% precision on synthetic data and 83% on real fire patterns.
Authors: Tassilo Wald, Constantin Ulrich, Gregor K\"ohler, David Zimmerer, Stefan Denner, Michael Baumgartner, Fabian Isensee, Priyank Jaini, Klaus H. Maier-Hein
Abstract: What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still remain largely unanswered, due to their internal high dimensionality and complexity. To address this, one approach is to measure the similarity of activation responses to various inputs. Representational Similarity Matrices (RSMs) distill this similarity into scalar values for each input pair. These matrices encapsulate the entire similarity structure of a system, indicating which input leads to similar responses. While the similarity between images is ambiguous, we argue that the spatial location of semantic objects does neither influence human perception nor deep learning classifiers. Thus this should be reflected in the definition of similarity between image responses for computer vision systems. Revisiting the established similarity calculations for RSMs we expose their sensitivity to spatial alignment. In this paper, we propose to solve this through semantic RSMs, which are invariant to spatial permutation. We measure semantic similarity between input responses by formulating it as a set-matching problem. Further, we quantify the superiority of semantic RSMs over spatio-semantic RSMs through image retrieval and by comparing the similarity between representations to the similarity between predicted class probabilities.
Authors: Hongbo Li, Haikuan Zhu, Sikai Zhong, Ningna Wang, Cheng Lin, Xiaohu Guo, Shiqing Xin, Wenping Wang, Jing Hua, Zichun Zhong
Abstract: This paper introduces a new learning-based method, NASM, for anisotropic surface meshing. Our key idea is to propose a graph neural network to embed an input mesh into a high-dimensional (high-d) Euclidean embedding space to preserve curvature-based anisotropic metric by using a dot product loss between high-d edge vectors. This can dramatically reduce the computational time and increase the scalability. Then, we propose a novel feature-sensitive remeshing on the generated high-d embedding to automatically capture sharp geometric features. We define a high-d normal metric, and then derive an automatic differentiation on a high-d centroidal Voronoi tessellation (CVT) optimization with the normal metric to simultaneously preserve geometric features and curvature anisotropy that exhibit in the original 3D shapes. To our knowledge, this is the first time that a deep learning framework and a large dataset are proposed to construct a high-d Euclidean embedding space for 3D anisotropic surface meshing. Experimental results are evaluated and compared with the state-of-the-art in anisotropic surface meshing on a large number of surface models from Thingi10K dataset as well as tested on extensive unseen 3D shapes from Multi-Garment Network dataset and FAUST human dataset.
Authors: Junjie Wu, Tsz Ting Chung, Kai Chen, Dit-Yan Yeung
Abstract: Despite the outstanding performance in vision-language reasoning, Large Vision-Language Models (LVLMs) might generate hallucinated contents that do not exist in the given image. Most existing LVLM hallucination benchmarks are constrained to evaluate the object-related hallucinations. However, the potential hallucination on the relations between two objects, i.e., relation hallucination, still lacks investigation. To remedy that, in this paper we design a unified framework to measure object and relation hallucination in LVLMs simultaneously. The core idea of our framework is to conduct hallucination evaluation on (object, relation, object) triplets extracted from LVLMs' responses, and thus, could be easily generalized to different vision-language tasks. Based on our framework, we further introduce Tri-HE, a novel Triplet-level Hallucination Evaluation benchmark which can be used to study both object and relation hallucination at the same time. We conduct comprehensive evaluations on Tri-HE and observe that the relation hallucination issue is even more serious than object hallucination among existing LVLMs, highlighting a previously neglected problem towards reliable LVLMs. Moreover, based on our findings, we design a simple yet effective training-free approach to mitigate hallucinations for LVLMs, with which, we exceed all open-sourced counterparts on Tri-HE, achieving comparable performance with the powerful GPT-4V. Our dataset and code for the reproduction of our experiments are available publicly at https://github.com/wujunjie1998/Tri-HE.
Authors: Tassilo Wald, Constantin Ulrich, Stanislav Lukyanenko, Andrei Goncharov, Alberto Paderno, Leander Maerkisch, Paul F. J\"ager, Klaus Maier-Hein
Abstract: Self-Supervised Learning (SSL) presents an exciting opportunity to unlock the potential of vast, untapped clinical datasets, for various downstream applications that suffer from the scarcity of labeled data. While SSL has revolutionized fields like natural language processing and computer vision, their adoption in 3D medical image computing has been limited by three key pitfalls: Small pre-training dataset sizes, architectures inadequate for 3D medical image analysis, and insufficient evaluation practices. We address these issues by i) leveraging a large-scale dataset of 44k 3D brain MRI volumes and ii) using a Residual Encoder U-Net architecture within the state-of-the-art nnU-Net framework. iii) A robust development framework, incorporating 5 development and 8 testing brain MRI segmentation datasets, allowed performance-driven design decisions to optimize the simple concept of Masked Auto Encoders (MAEs) for 3D CNNs. The resulting model not only surpasses previous SSL methods but also outperforms the strong nnU-Net baseline by an average of approximately 3 Dice points. Furthermore, our model demonstrates exceptional stability, achieving the highest average rank of 2 out of 7 methods, compared to the second-best method's mean rank of 3.
Authors: Chiu-Wai Yan, Shi Quan Foo, Van Hoan Trinh, Dit-Yan Yeung, Ka-Hing Wong, Wai-Kin Wong
Abstract: Deep learning approaches have been widely adopted for precipitation nowcasting in recent years. Previous studies mainly focus on proposing new model architectures to improve pixel-wise metrics. However, they frequently result in blurry predictions which provide limited utility to forecasting operations. In this work, we propose a new Fourier Amplitude and Correlation Loss (FACL) which consists of two novel loss terms: Fourier Amplitude Loss (FAL) and Fourier Correlation Loss (FCL). FAL regularizes the Fourier amplitude of the model prediction and FCL complements the missing phase information. The two loss terms work together to replace the traditional $L_2$ losses such as MSE and weighted MSE for the spatiotemporal prediction problem on signal-based data. Our method is generic, parameter-free and efficient. Extensive experiments using one synthetic dataset and three radar echo datasets demonstrate that our method improves perceptual metrics and meteorology skill scores, with a small trade-off to pixel-wise accuracy and structural similarity. Moreover, to improve the error margin in meteorological skill scores such as Critical Success Index (CSI) and Fractions Skill Score (FSS), we propose and adopt the Regional Histogram Divergence (RHD), a distance metric that considers the patch-wise similarity between signal-based imagery patterns with tolerance to local transforms. Code is available at https://github.com/argenycw/FACL
Authors: Meng Ye, Bingyu Xin, Leon Axel, Dimitris Metaxas
Abstract: Current cardiac cine magnetic resonance image (cMR) studies focus on the end diastole (ED) and end systole (ES) phases, while ignoring the abundant temporal information in the whole image sequence. This is because whole sequence segmentation is currently a tedious process and inaccurate. Conventional whole sequence segmentation approaches first estimate the motion field between frames, which is then used to propagate the mask along the temporal axis. However, the mask propagation results could be prone to error, especially for the basal and apex slices, where through-plane motion leads to significant morphology and structural change during the cardiac cycle. Inspired by recent advances in video object segmentation (VOS), based on spatio-temporal memory (STM) networks, we propose a continuous STM (CSTM) network for semi-supervised whole heart and whole sequence cMR segmentation. Our CSTM network takes full advantage of the spatial, scale, temporal and through-plane continuity prior of the underlying heart anatomy structures, to achieve accurate and fast 4D segmentation. Results of extensive experiments across multiple cMR datasets show that our method can improve the 4D cMR segmentation performance, especially for the hard-to-segment regions.
Authors: Kiran Kokilepersaud, Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib
Abstract: In this paper, we propose an algorithm that can be used on top of a wide variety of self-supervised (SSL) approaches to take advantage of hierarchical structures that emerge during training. SSL approaches typically work through some invariance term to ensure consistency between similar samples and a regularization term to prevent global dimensional collapse. Dimensional collapse refers to data representations spanning a lower-dimensional subspace. Recent work has demonstrated that the representation space of these algorithms gradually reflects a semantic hierarchical structure as training progresses. Data samples of the same hierarchical grouping tend to exhibit greater dimensional collapse locally compared to the dataset as a whole due to sharing features in common with each other. Ideally, SSL algorithms would take advantage of this hierarchical emergence to have an additional regularization term to account for this local dimensional collapse effect. However, the construction of existing SSL algorithms does not account for this property. To address this, we propose an adaptive algorithm that performs a weighted decomposition of the denominator of the InfoNCE loss into two terms: local hierarchical and global collapse regularization respectively. This decomposition is based on an adaptive threshold that gradually lowers to reflect the emerging hierarchical structure of the representation space throughout training. It is based on an analysis of the cosine similarity distribution of samples in a batch. We demonstrate that this hierarchical emergence exploitation (HEX) approach can be integrated across a wide variety of SSL algorithms. Empirically, we show performance improvements of up to 5.6% relative improvement over baseline SSL approaches on classification accuracy on Imagenet with 100 epochs of training.
Authors: Muhammad Salman Ali, Sung-Ho Bae, Enzo Tartaglione
Abstract: 3D models have recently been popularized by the potentiality of end-to-end training offered first by Neural Radiance Fields and most recently by 3D Gaussian Splatting models. The latter has the big advantage of naturally providing fast training convergence and high editability. However, as the research around these is still in its infancy, there is still a gap in the literature regarding the model's scalability. In this work, we propose an approach enabling both memory and computation scalability of such models. More specifically, we propose an iterative pruning strategy that removes redundant information encoded in the model. We also enhance compressibility for the model by including in the optimization strategy a differentiable quantization and entropy coding estimator. Our results on popular benchmarks showcase the effectiveness of the proposed approach and open the road to the broad deployability of such a solution even on resource-constrained devices.
Authors: Yitong Li, Morteza Ghahremani, Youssef Wally, Christian Wachinger
Abstract: Diagnosing dementia, particularly for Alzheimer's Disease (AD) and frontotemporal dementia (FTD), is complex due to overlapping symptoms. While magnetic resonance imaging (MRI) and positron emission tomography (PET) data are critical for the diagnosis, integrating these modalities in deep learning faces challenges, often resulting in suboptimal performance compared to using single modalities. Moreover, the potential of multi-modal approaches in differential diagnosis, which holds significant clinical importance, remains largely unexplored. We propose a novel framework, DiaMond, to address these issues with vision Transformers to effectively integrate MRI and PET. DiaMond is equipped with self-attention and a novel bi-attention mechanism that synergistically combine MRI and PET, alongside a multi-modal normalization to reduce redundant dependency, thereby boosting the performance. DiaMond significantly outperforms existing multi-modal methods across various datasets, achieving a balanced accuracy of 92.4% in AD diagnosis, 65.2% for AD-MCI-CN classification, and 76.5% in differential diagnosis of AD and FTD. We also validated the robustness of DiaMond in a comprehensive ablation study. The code is available at https://github.com/ai-med/DiaMond.
Authors: Shentong Mo, Yibing Song
Abstract: Visual content and accompanied audio signals naturally formulate a joint representation to improve audio-visual (AV) related applications. While studies develop various AV representation learning frameworks, the importance of AV data alignment is usually undermined for achieving high-quality representation. We observe that an audio signal may contain background noise interference. Also, non-synchronization may appear between audio and video streams. These non-strict data alignment limits representation quality and downgrade application performance. In this paper, we propose to improve AV joint representations from a data-centric perspective by aligning audio signals to visual data. Our alignment is conducted in an agentic workflow controlled by an LLM-based assistant named AVAgent. For each input AV data pair, our AVAgent uses a multi-modal LLM to convert audio and visual data into language descriptions separately (i.e., tool use). Then, AVAgent reasons whether this paired data is aligned well and plans to edit the audio signal if needed (i.e., planning). The audio editing is executed by predefined actions that filter noise or augment data. Moreover, we use a VLM to evaluate how modified audio signals match the visual content and provide feedback to AVAgent (i.e., reflection). The tool use, planning, and reflection steps operate cyclically to become an agentic workflow where audio signals are gradually aligned to visual content. To this end, existing methods can directly leverage the aligned AV data via our agentic workflow to improve AV joint representations. The experimental results comprehensively demonstrate the state-of-the-art performance of the proposed approach against previous baselines in diverse downstream tasks.
Authors: Yucheng Huang, Luping Ji, Hudong Liu, Mao Ye
Abstract: Deep visual Simultaneous Localization and Mapping (SLAM) techniques, e.g., DROID, have made significant advancements by leveraging deep visual odometry on dense flow fields. In general, they heavily rely on global visual similarity matching. However, the ambiguous similarity interference in uncertain regions could often lead to excessive noise in correspondences, ultimately misleading SLAM in geometric modeling. To address this issue, we propose a Learnable Gaussian Uncertainty (LGU) matching. It mainly focuses on precise correspondence construction. In our scheme, a learnable 2D Gaussian uncertainty model is designed to associate matching-frame pairs. It could generate input-dependent Gaussian distributions for each correspondence map. Additionally, a multi-scale deformable correlation sampling strategy is devised to adaptively fine-tune the sampling of each direction by a priori look-up ranges, enabling reliable correlation construction. Furthermore, a KAN-bias GRU component is adopted to improve a temporal iterative enhancement for accomplishing sophisticated spatio-temporal modeling with limited parameters. The extensive experiments on real-world and synthetic datasets are conducted to validate the effectiveness and superiority of our method.
Authors: Chen Ziwen, Zexiang Xu, Li Fuxin
Abstract: We propose a novel online, point-based 3D reconstruction method from posed monocular RGB videos. Our model maintains a global point cloud representation of the scene, continuously updating the features and 3D locations of points as new images are observed. It expands the point cloud with newly detected points while carefully removing redundancies. The point cloud updates and depth predictions for new points are achieved through a novel ray-based 2D-3D feature matching technique, which is robust against errors in previous point position predictions. In contrast to offline methods, our approach processes infinite-length sequences and provides real-time updates. Additionally, the point cloud imposes no pre-defined resolution or scene size constraints, and its unified global representation ensures view consistency across perspectives. Experiments on the ScanNet dataset show that our method achieves state-of-the-art quality among online MVS approaches. Project page: https://arthurhero.github.io/projects/pointrecon
Authors: Jyh-Jing Hwang, Runsheng Xu, Hubert Lin, Wei-Chih Hung, Jingwei Ji, Kristy Choi, Di Huang, Tong He, Paul Covington, Benjamin Sapp, James Guo, Dragomir Anguelov, Mingxing Tan
Abstract: We introduce EMMA, an End-to-end Multimodal Model for Autonomous driving. Built on a multi-modal large language model foundation, EMMA directly maps raw camera sensor data into various driving-specific outputs, including planner trajectories, perception objects, and road graph elements. EMMA maximizes the utility of world knowledge from the pre-trained large language models, by representing all non-sensor inputs (e.g. navigation instructions and ego vehicle status) and outputs (e.g. trajectories and 3D locations) as natural language text. This approach allows EMMA to jointly process various driving tasks in a unified language space, and generate the outputs for each task using task-specific prompts. Empirically, we demonstrate EMMA's effectiveness by achieving state-of-the-art performance in motion planning on nuScenes as well as competitive results on the Waymo Open Motion Dataset (WOMD). EMMA also yields competitive results for camera-primary 3D object detection on the Waymo Open Dataset (WOD). We show that co-training EMMA with planner trajectories, object detection, and road graph tasks yields improvements across all three domains, highlighting EMMA's potential as a generalist model for autonomous driving applications. However, EMMA also exhibits certain limitations: it can process only a small amount of image frames, does not incorporate accurate 3D sensing modalities like LiDAR or radar and is computationally expensive. We hope that our results will inspire further research to mitigate these issues and to further evolve the state of the art in autonomous driving model architectures.
Authors: Ziyao Shangguan, Chuhan Li, Yuxuan Ding, Yanan Zheng, Yilun Zhao, Tesca Fitzgerald, Arman Cohan
Abstract: Existing benchmarks often highlight the remarkable performance achieved by state-of-the-art Multimodal Foundation Models (MFMs) in leveraging temporal context for video understanding. However, how well do the models truly perform visual temporal reasoning? Our study of existing benchmarks shows that this capability of MFMs is likely overestimated as many questions can be solved by using a single, few, or out-of-order frames. To systematically examine current visual temporal reasoning tasks, we propose three principles with corresponding metrics: (1) Multi-Frame Gain, (2) Frame Order Sensitivity, and (3) Frame Information Disparity. Following these principles, we introduce TOMATO, Temporal Reasoning Multimodal Evaluation, a novel benchmark crafted to rigorously assess MFMs' temporal reasoning capabilities in video understanding. TOMATO comprises 1,484 carefully curated, human-annotated questions spanning six tasks (i.e., action count, direction, rotation, shape & trend, velocity & frequency, and visual cues), applied to 1,417 videos, including 805 self-recorded and -generated videos, that encompass human-centric, real-world, and simulated scenarios. Our comprehensive evaluation reveals a human-model performance gap of 57.3% with the best-performing model. Moreover, our in-depth analysis uncovers more fundamental limitations beyond this gap in current MFMs. While they can accurately recognize events in isolated frames, they fail to interpret these frames as a continuous sequence. We believe TOMATO will serve as a crucial testbed for evaluating the next-generation MFMs and as a call to the community to develop AI systems capable of comprehending human world dynamics through the video modality.
Authors: Yining Hong, Beide Liu, Maxine Wu, Yuanhao Zhai, Kai-Wei Chang, Lingjie Li, Kevin Lin, Chung-Ching Lin, Jianfeng Wang, Zhengyuan Yang, Yingnian Wu, Lijuan Wang
Abstract: Human beings are endowed with a complementary learning system, which bridges the slow learning of general world dynamics with fast storage of episodic memory from a new experience. Previous video generation models, however, primarily focus on slow learning by pre-training on vast amounts of data, overlooking the fast learning phase crucial for episodic memory storage. This oversight leads to inconsistencies across temporally distant frames when generating longer videos, as these frames fall beyond the model's context window. To this end, we introduce SlowFast-VGen, a novel dual-speed learning system for action-driven long video generation. Our approach incorporates a masked conditional video diffusion model for the slow learning of world dynamics, alongside an inference-time fast learning strategy based on a temporal LoRA module. Specifically, the fast learning process updates its temporal LoRA parameters based on local inputs and outputs, thereby efficiently storing episodic memory in its parameters. We further propose a slow-fast learning loop algorithm that seamlessly integrates the inner fast learning loop into the outer slow learning loop, enabling the recall of prior multi-episode experiences for context-aware skill learning. To facilitate the slow learning of an approximate world model, we collect a large-scale dataset of 200k videos with language action annotations, covering a wide range of scenarios. Extensive experiments show that SlowFast-VGen outperforms baselines across various metrics for action-driven video generation, achieving an FVD score of 514 compared to 782, and maintaining consistency in longer videos, with an average of 0.37 scene cuts versus 0.89. The slow-fast learning loop algorithm significantly enhances performances on long-horizon planning tasks as well. Project Website: https://slowfast-vgen.github.io
Authors: Hongbo Zhao, Lue Fan, Yuntao Chen, Haochen Wang, yuran Yang, Xiaojuan Jin, Yixin Zhang, Gaofeng Meng, Zhaoxiang Zhang
Abstract: In this paper, we propose OpenSatMap, a fine-grained, high-resolution satellite dataset for large-scale map construction. Map construction is one of the foundations of the transportation industry, such as navigation and autonomous driving. Extracting road structures from satellite images is an efficient way to construct large-scale maps. However, existing satellite datasets provide only coarse semantic-level labels with a relatively low resolution (up to level 19), impeding the advancement of this field. In contrast, the proposed OpenSatMap (1) has fine-grained instance-level annotations; (2) consists of high-resolution images (level 20); (3) is currently the largest one of its kind; (4) collects data with high diversity. Moreover, OpenSatMap covers and aligns with the popular nuScenes dataset and Argoverse 2 dataset to potentially advance autonomous driving technologies. By publishing and maintaining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.
Authors: Qingyu Shi, Lu Qi, Jianzong Wu, Jinbin Bai, Jingbo Wang, Yunhai Tong, Xiangtai Li, Ming-Husang Yang
Abstract: Customized image generation is crucial for delivering personalized content based on user-provided image prompts, aligning large-scale text-to-image diffusion models with individual needs. However, existing models often overlook the relationships between customized objects in generated images. Instead, this work addresses that gap by focusing on relation-aware customized image generation, which aims to preserve the identities from image prompts while maintaining the predicate relations described in text prompts. Specifically, we introduce RelationBooth, a framework that disentangles identity and relation learning through a well-curated dataset. Our training data consists of relation-specific images, independent object images containing identity information, and text prompts to guide relation generation. Then, we propose two key modules to tackle the two main challenges: generating accurate and natural relations, especially when significant pose adjustments are required, and avoiding object confusion in cases of overlap. First, we introduce a keypoint matching loss that effectively guides the model in adjusting object poses closely tied to their relationships. Second, we incorporate local features from the image prompts to better distinguish between objects, preventing confusion in overlapping cases. Extensive results on three benchmarks demonstrate the superiority of RelationBooth in generating precise relations while preserving object identities across a diverse set of objects and relations. The source code and trained models will be made available to the public.
Authors: Anurag Bagchi, Zhipeng Bao, Yu-Xiong Wang, Pavel Tokmakov, Martial Hebert
Abstract: We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method capitalizes on visual-language representations learned by video diffusion models on Internet-scale datasets. A key insight of our approach is preserving as much of the generative model's original representation as possible, while fine-tuning it on narrow-domain Referral Object Segmentation datasets. As a result, our framework can accurately segment and track rare and unseen objects, despite being trained on object masks from a limited set of categories. Additionally, it can generalize to non-object dynamic concepts, such as waves crashing in the ocean, as demonstrated in our newly introduced benchmark for Referral Video Process Segmentation (Ref-VPS). Our experiments show that REM performs on par with state-of-the-art approaches on in-domain datasets, like Ref-DAVIS, while outperforming them by up to twelve points in terms of region similarity on out-of-domain data, leveraging the power of Internet-scale pre-training.
Authors: Jialin Luo, Yuanzhi Wang, Ziqi Gu, Yide Qiu, Shuaizhen Yao, Fuyun Wang, Chunyan Xu, Wenhua Zhang, Dan Wang, Zhen Cui
Abstract: Recently, the diffusion-based generative paradigm has achieved impressive general image generation capabilities with text prompts due to its accurate distribution modeling and stable training process. However, generating diverse remote sensing (RS) images that are tremendously different from general images in terms of scale and perspective remains a formidable challenge due to the lack of a comprehensive remote sensing image generation dataset with various modalities, ground sample distances (GSD), and scenes. In this paper, we propose a Multi-modal, Multi-GSD, Multi-scene Remote Sensing (MMM-RS) dataset and benchmark for text-to-image generation in diverse remote sensing scenarios. Specifically, we first collect nine publicly available RS datasets and conduct standardization for all samples. To bridge RS images to textual semantic information, we utilize a large-scale pretrained vision-language model to automatically output text prompts and perform hand-crafted rectification, resulting in information-rich text-image pairs (including multi-modal images). In particular, we design some methods to obtain the images with different GSD and various environments (e.g., low-light, foggy) in a single sample. With extensive manual screening and refining annotations, we ultimately obtain a MMM-RS dataset that comprises approximately 2.1 million text-image pairs. Extensive experimental results verify that our proposed MMM-RS dataset allows off-the-shelf diffusion models to generate diverse RS images across various modalities, scenes, weather conditions, and GSD. The dataset is available at https://github.com/ljl5261/MMM-RS.
Authors: Hana Sebia (AISTROSIGHT), Thomas Guyet (AISTROSIGHT), Micka\"el Pereira (CERMEP - imagerie du vivant), Marco Valdebenito (CERMEP - imagerie du vivant), Hugues Berry (AISTROSIGHT), Benjamin Vidal (CERMEP - imagerie du vivant, CRNL)
Abstract: Segmentation of medical images is a fundamental task with numerous applications. While MRI, CT, and PET modalities have significantly benefited from deep learning segmentation techniques, more recent modalities, like functional ultrasound (fUS), have seen limited progress. fUS is a non invasive imaging method that measures changes in cerebral blood volume (CBV) with high spatio-temporal resolution. However, distinguishing arterioles from venules in fUS is challenging due to opposing blood flow directions within the same pixel. Ultrasound localization microscopy (ULM) can enhance resolution by tracking microbubble contrast agents but is invasive, and lacks dynamic CBV quantification. In this paper, we introduce the first deep learning-based segmentation tool for fUS images, capable of differentiating signals from different vascular compartments, based on ULM automatic annotation and enabling dynamic CBV quantification. We evaluate various UNet architectures on fUS images of rat brains, achieving competitive segmentation performance, with 90% accuracy, a 71% F1 score, and an IoU of 0.59, using only 100 temporal frames from a fUS stack. These results are comparable to those from tubular structure segmentation in other imaging modalities. Additionally, models trained on resting-state data generalize well to images captured during visual stimulation, highlighting robustness. This work offers a non-invasive, cost-effective alternative to ULM, enhancing fUS data interpretation and improving understanding of vessel function. Our pipeline shows high linear correlation coefficients between signals from predicted and actual compartments in both cortical and deeperregions, showcasing its ability to accurately capture blood flow dynamics.
Authors: Viacheslav Surkov, Chris Wendler, Mikhail Terekhov, Justin Deschenaux, Robert West, Caglar Gulcehre
Abstract: Sparse autoencoders (SAEs) have become a core ingredient in the reverse engineering of large-language models (LLMs). For LLMs, they have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and subsequent analysis. However, similar analyses and approaches have been lacking for text-to-image models. We investigated the possibility of using SAEs to learn interpretable features for a few-step text-to-image diffusion models, such as SDXL Turbo. To this end, we train SAEs on the updates performed by transformer blocks within SDXL Turbo's denoising U-net. We find that their learned features are interpretable, causally influence the generation process, and reveal specialization among the blocks. In particular, we find one block that deals mainly with image composition, one that is mainly responsible for adding local details, and one for color, illumination, and style. Therefore, our work is an important first step towards better understanding the internals of generative text-to-image models like SDXL Turbo and showcases the potential of features learned by SAEs for the visual domain. Code is available at https://github.com/surkovv/sdxl-unbox
Authors: Dongmin Park, Sebin Kim, Taehong Moon, Minkyu Kim, Kangwook Lee, Jaewoong Cho
Abstract: State-of-the-art text-to-image (T2I) diffusion models often struggle to generate rare compositions of concepts, e.g., objects with unusual attributes. In this paper, we show that the compositional generation power of diffusion models on such rare concepts can be significantly enhanced by the Large Language Model (LLM) guidance. We start with empirical and theoretical analysis, demonstrating that exposing frequent concepts relevant to the target rare concepts during the diffusion sampling process yields more accurate concept composition. Based on this, we propose a training-free approach, R2F, that plans and executes the overall rare-to-frequent concept guidance throughout the diffusion inference by leveraging the abundant semantic knowledge in LLMs. Our framework is flexible across any pre-trained diffusion models and LLMs, and can be seamlessly integrated with the region-guided diffusion approaches. Extensive experiments on three datasets, including our newly proposed benchmark, RareBench, containing various prompts with rare compositions of concepts, R2F significantly surpasses existing models including SD3.0 and FLUX by up to 28.1%p in T2I alignment. Code is available at https://github.com/krafton-ai/Rare2Frequent.
Authors: Naren Sengodan
Abstract: Breast cancer histopathology image classification is crucial for early cancer detection, offering the potential to reduce mortality rates through timely diagnosis. This paper introduces a novel approach integrating Hybrid EfficientNet models with advanced attention mechanisms, including Convolutional Block Attention Module (CBAM), Self-Attention, and Deformable Attention, to enhance feature extraction and focus on critical image regions. We evaluate the performance of our models across multiple magnification scales using publicly available histopathological datasets. Our method achieves significant improvements, with accuracy reaching 98.42% at 400X magnification, surpassing several state-of-the-art models, including VGG and ResNet architectures. The results are validated using metrics such as accuracy, F1-score, precision, and recall, demonstrating the clinical potential of our model in improving diagnostic accuracy. Furthermore, the proposed method shows increased computational efficiency, making it suitable for integration into real-time diagnostic workflows.
Authors: Hongyi Pan, Gorkem Durak, Zheyuan Zhang, Yavuz Taktak, Elif Keles, Halil Ertugrul Aktas, Alpay Medetalibeyoglu, Yury Velichko, Concetto Spampinato, Ivo Schoots, Marco J. Bruno, Rajesh N. Keswani, Pallavi Tiwari, Candice Bolan, Tamas Gonda, Michael G. Goggins, Michael B. Wallace, Ziyue Xu, Ulas Bagci
Abstract: Federated learning (FL) enables collaborative model training across institutions without sharing sensitive data, making it an attractive solution for medical imaging tasks. However, traditional FL methods, such as Federated Averaging (FedAvg), face difficulties in generalizing across domains due to variations in imaging protocols and patient demographics across institutions. This challenge is particularly evident in pancreas MRI segmentation, where anatomical variability and imaging artifacts significantly impact performance. In this paper, we conduct a comprehensive evaluation of FL algorithms for pancreas MRI segmentation and introduce a novel approach that incorporates adaptive aggregation weights. By dynamically adjusting the contribution of each client during model aggregation, our method accounts for domain-specific differences and improves generalization across heterogeneous datasets. Experimental results demonstrate that our approach enhances segmentation accuracy and reduces the impact of domain shift compared to conventional FL methods while maintaining privacy-preserving capabilities. Significant performance improvements are observed across multiple hospitals (centers).
Authors: Siddharath Narayan Shakya, Parimala Kancharla
Abstract: In this work, we designed a completely blind video quality assessment algorithm using the deep video prior. This work mainly explores the utility of deep video prior in estimating the visual quality of the video. In our work, we have used a single distorted video and a reference video pair to learn the deep video prior. At inference time, the learned deep prior is used to restore the original videos from the distorted videos. The ability of learned deep video prior to restore the original video from the distorted video is measured to quantify distortion in the video. Our hypothesis is that the learned deep video prior fails in restoring the highly distorted videos. The restoring ability of deep video prior is proportional to the distortion present in the video. Therefore, we propose to use the distance between the distorted video and the restored video as the perceptual quality of the video. Our algorithm is trained using a single video pair and it does not need any labelled data. We show that our proposed algorithm outperforms the existing unsupervised video quality assessment algorithms in terms of LCC and SROCC on a synthetically distorted video quality assessment dataset.
Authors: Plabon Paul, Md. Nazmul Islam, Fazle Rafsani, Pegah Khorasani, Shovito Barua Soumma
Abstract: Uncontrolled cell division in the brain is what gives rise to brain tumors. If the tumor size increases by more than half, there is little hope for the patient's recovery. This emphasizes the need of rapid and precise brain tumor diagnosis. When it comes to analyzing, diagnosing, and planning therapy for brain tumors, MRI imaging plays a crucial role. A brain tumor's development history is crucial information for doctors to have. When it comes to distinguishing between human soft tissues, MRI scans are superior. In order to get reliable classification results from MRI scans quickly, deep learning is one of the most practical methods. Early human illness diagnosis has been demonstrated to be more accurate when deep learning methods are used. In the case of diagnosing a brain tumor, when even a little misdiagnosis might have serious consequences, accuracy is especially important. Disclosure of brain tumors in medical images is still a difficult task. Brain MRIs are notoriously imprecise in revealing the presence or absence of tumors. Using MRI scans of the brain, a Convolutional Neural Network (CNN) was trained to identify the presence of a tumor in this research. Results from the CNN model showed an accuracy of 99.17%. The CNN model's characteristics were also retrieved. In order to evaluate the CNN model's capability for processing images, we applied the features via the following machine learning models: KNN, Logistic regression, SVM, Random Forest, Naive Bayes, and Perception. CNN and machine learning models were also evaluated using the standard metrics of Precision, Recall, Specificity, and F1 score. The significance of the doctor's diagnosis enhanced the accuracy of the CNN model's assistance in identifying the existence of tumor and treating the patient.
Authors: Dung Thuy Nguyen, Taylor T. Johnson, Kevin Leach
Abstract: Federated Learning (FL) shows promise in preserving privacy and enabling collaborative learning. However, most current solutions focus on private data collected from a single domain. A significant challenge arises when client data comes from diverse domains (i.e., domain shift), leading to poor performance on unseen domains. Existing Federated Domain Generalization approaches address this problem but assume each client holds data for an entire domain, limiting their practicality in real-world scenarios with domain-based heterogeneity and client sampling. To overcome this, we introduce FISC, a novel FL domain generalization paradigm that handles more complex domain distributions across clients. FISC enables learning across domains by extracting an interpolative style from local styles and employing contrastive learning. This strategy gives clients multi-domain representations and unbiased convergent targets. Empirical results on multiple datasets, including PACS, Office-Home, and IWildCam, show FISC outperforms state-of-the-art (SOTA) methods. Our method achieves accuracy improvements ranging from 3.64% to 57.22% on unseen domains. Our code is available at https://anonymous.4open.science/r/FISC-AAAI-16107.
Authors: Guande He, Kaiwen Zheng, Jianfei Chen, Fan Bao, Jun Zhu
Abstract: Diffusion models (DMs) have become the dominant paradigm of generative modeling in a variety of domains by learning stochastic processes from noise to data. Recently, diffusion denoising bridge models (DDBMs), a new formulation of generative modeling that builds stochastic processes between fixed data endpoints based on a reference diffusion process, have achieved empirical success across tasks with coupled data distribution, such as image-to-image translation. However, DDBM's sampling process typically requires hundreds of network evaluations to achieve decent performance, which may impede their practical deployment due to high computational demands. In this work, inspired by the recent advance of consistency models in DMs, we tackle this problem by learning the consistency function of the probability-flow ordinary differential equation (PF-ODE) of DDBMs, which directly predicts the solution at a starting step given any point on the ODE trajectory. Based on a dedicated general-form ODE solver, we propose two paradigms: consistency bridge distillation and consistency bridge training, which is flexible to apply on DDBMs with broad design choices. Experimental results show that our proposed method could sample $4\times$ to $50\times$ faster than the base DDBM and produce better visual quality given the same step in various tasks with pixel resolution ranging from $64 \times 64$ to $256 \times 256$, as well as supporting downstream tasks such as semantic interpolation in the data space.
Authors: Kento Kawaharazuka, Yoshiki Obinata, Naoaki Kanazawa, Kei Okada, Masayuki Inaba
Abstract: State recognition of the environment and objects, such as the open/closed state of doors and the on/off of lights, is indispensable for robots that perform daily life support and security tasks. Until now, state recognition methods have been based on training neural networks from manual annotations, preparing special sensors for the recognition, or manually programming to extract features from point clouds or raw images. In contrast, we propose a robotic state recognition method using a pre-trained vision-language model, which is capable of Image-to-Text Retrieval (ITR) tasks. We prepare several kinds of language prompts in advance, calculate the similarity between these prompts and the current image by ITR, and perform state recognition. By applying the optimal weighting to each prompt using black-box optimization, state recognition can be performed with higher accuracy. Experiments show that this theory enables a variety of state recognitions by simply preparing multiple prompts without retraining neural networks or manual programming. In addition, since only prompts and their weights need to be prepared for each recognizer, there is no need to prepare multiple models, which facilitates resource management. It is possible to recognize the open/closed state of transparent doors, the state of whether water is running or not from a faucet, and even the qualitative state of whether a kitchen is clean or not, which have been challenging so far, through language.
Authors: Ran Hong, Yuxia Huang, Lei Liu, Zhonghui Wu, Bingxuan Li, Xuemei Wang, Qiegen Liu
Abstract: PET imaging is widely employed for observing biological metabolic activities within the human body. However, numerous benign conditions can cause increased uptake of radiopharmaceuticals, confounding differentiation from malignant tumors. Several studies have indicated that dual-time PET imaging holds promise in distinguishing between malignant and benign tumor processes. Nevertheless, the hour-long distribution period of radiopharmaceuticals post-injection complicates the determination of optimal timing for the second scan, presenting challenges in both practical applications and research. Notably, we have identified that delay time PET imaging can be framed as an image-to-image conversion problem. Motivated by this insight, we propose a novel spatial-temporal guided diffusion transformer probabilistic model (st-DTPM) to solve dual-time PET imaging prediction problem. Specifically, this architecture leverages the U-net framework that integrates patch-wise features of CNN and pixel-wise relevance of Transformer to obtain local and global information. And then employs a conditional DDPM model for image synthesis. Furthermore, on spatial condition, we concatenate early scan PET images and noisy PET images on every denoising step to guide the spatial distribution of denoising sampling. On temporal condition, we convert diffusion time steps and delay time to a universal time vector, then embed it to each layer of model architecture to further improve the accuracy of predictions. Experimental results demonstrated the superiority of our method over alternative approaches in preserving image quality and structural information, thereby affirming its efficacy in predictive task.
Authors: Omar Erak, Omar Alhussein, Wen Tong
Abstract: Task-oriented semantic communication systems have emerged as a promising approach to achieving efficient and intelligent data transmission, where only information relevant to a specific task is communicated. However, existing methods struggle to fully disentangle task-relevant and task-irrelevant information, leading to privacy concerns and subpar performance. To address this, we propose an information-bottleneck method, named CLAD (contrastive learning and adversarial disentanglement). CLAD leverages contrastive learning to effectively capture task-relevant features while employing adversarial disentanglement to discard task-irrelevant information. Additionally, due to the lack of reliable and reproducible methods to gain insight into the informativeness and minimality of the encoded feature vectors, we introduce a new technique to compute the information retention index (IRI), a comparative metric used as a proxy for the mutual information between the encoded features and the input, reflecting the minimality of the encoded features. The IRI quantifies the minimality and informativeness of the encoded feature vectors across different task-oriented communication techniques. Our extensive experiments demonstrate that CLAD outperforms state-of-the-art baselines in terms of task performance, privacy preservation, and IRI. CLAD achieves a predictive performance improvement of around 2.5-3%, along with a 77-90% reduction in IRI and a 57-76% decrease in adversarial accuracy.
Authors: Hanlin Wu, Jiangwei Mo, Xiaohui Sun, Jie Ma
Abstract: Recent advancements in diffusion models have significantly improved performance in super-resolution (SR) tasks. However, previous research often overlooks the fundamental differences between SR and general image generation. General image generation involves creating images from scratch, while SR focuses specifically on enhancing existing low-resolution (LR) images by adding typically missing high-frequency details. This oversight not only increases the training difficulty but also limits their inference efficiency. Furthermore, previous diffusion-based SR methods are typically trained and inferred at fixed integer scale factors, lacking flexibility to meet the needs of up-sampling with non-integer scale factors. To address these issues, this paper proposes an efficient and elastic diffusion-based SR model (E$^2$DiffSR), specially designed for continuous-scale SR in remote sensing imagery. E$^2$DiffSR employs a two-stage latent diffusion paradigm. During the first stage, an autoencoder is trained to capture the differential priors between high-resolution (HR) and LR images. The encoder intentionally ignores the existing LR content to alleviate the encoding burden, while the decoder introduces an SR branch equipped with a continuous scale upsampling module to accomplish the reconstruction under the guidance of the differential prior. In the second stage, a conditional diffusion model is learned within the latent space to predict the true differential prior encoding. Experimental results demonstrate that E$^2$DiffSR achieves superior objective metrics and visual quality compared to the state-of-the-art SR methods. Additionally, it reduces the inference time of diffusion-based SR methods to a level comparable to that of non-diffusion methods.
Authors: Jan Ernsting, Phillip Nikolas Beeken, Lynn Ogoniak, Jacqueline Kockwelp, Tim Hahn, Alexander Siegfried Busch, Benjamin Risse
Abstract: Testis size is known to be one of the main predictors of male fertility, usually assessed in clinical workup via palpation or imaging. Despite its potential, population-level evaluation of testicular volume using imaging remains underexplored. Previous studies, limited by small and biased datasets, have demonstrated the feasibility of machine learning for testis volume segmentation. This paper presents an evaluation of segmentation methods for testicular volume using Magnet Resonance Imaging data from the UKBiobank. The best model achieves a median dice score of $0.87$, compared to median dice score of $0.83$ for human interrater reliability on the same dataset, enabling large-scale annotation on a population scale for the first time. Our overall aim is to provide a trained model, comparative baseline methods, and annotated training data to enhance accessibility and reproducibility in testis MRI segmentation research.
Authors: Jialiang Zhang, Haoran Liu, Danshi Li, Xinqiang Yu, Haoran Geng, Yufei Ding, Jiayi Chen, He Wang
Abstract: Grasping in cluttered scenes remains highly challenging for dexterous hands due to the scarcity of data. To address this problem, we present a large-scale synthetic benchmark, encompassing 1319 objects, 8270 scenes, and 427 million grasps. Beyond benchmarking, we also propose a novel two-stage grasping method that learns efficiently from data by using a diffusion model that conditions on local geometry. Our proposed generative method outperforms all baselines in simulation experiments. Furthermore, with the aid of test-time-depth restoration, our method demonstrates zero-shot sim-to-real transfer, attaining 90.7% real-world dexterous grasping success rate in cluttered scenes.
Authors: Qianxu Wang, Congyue Deng, Tyler Ga Wei Lum, Yuanpei Chen, Yaodong Yang, Jeannette Bohg, Yixin Zhu, Leonidas Guibas
Abstract: One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While distilled feature fields from large vision models have enabled semantic correspondences across 3D scenes, their features are point-based and restricted to object surfaces, limiting their capability of modeling complex semantic feature distributions for hand-object interactions. In this work, we propose the \textit{neural attention field} for representing semantic-aware dense feature fields in the 3D space by modeling inter-point relevance instead of individual point features. Core to it is a transformer decoder that computes the cross-attention between any 3D query point with all the scene points, and provides the query point feature with an attention-based aggregation. We further propose a self-supervised framework for training the transformer decoder from only a few 3D pointclouds without hand demonstrations. Post-training, the attention field can be applied to novel scenes for semantics-aware dexterous grasping from one-shot demonstration. Experiments show that our method provides better optimization landscapes by encouraging the end-effector to focus on task-relevant scene regions, resulting in significant improvements in success rates on real robots compared with the feature-field-based methods.
Authors: Pau Rodriguez, Arno Blaas, Michal Klein, Luca Zappella, Nicholas Apostoloff, Marco Cuturi, Xavier Suau
Abstract: The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control model generation by steering model activations in order to effectively induce or prevent the emergence of concepts or behaviors in the generated output. In this paper we introduce Activation Transport (AcT), a general framework to steer activations guided by optimal transport theory that generalizes many previous activation-steering works. AcT is modality-agnostic and provides fine-grained control over the model behavior with negligible computational overhead, while minimally impacting model abilities. We experimentally show the effectiveness and versatility of our approach by addressing key challenges in large language models (LLMs) and text-to-image diffusion models (T2Is). For LLMs, we show that AcT can effectively mitigate toxicity, induce arbitrary concepts, and increase their truthfulness. In T2Is, we show how AcT enables fine-grained style control and concept negation.
Authors: Xiangcen Wu, Yipei Wang, Qianye Yang, Natasha Thorley, Shonit Punwani, Veeru Kasivisvanathan, Ester Bonmati, Yipeng Hu
Abstract: Prostate cancer diagnosis through MR imaging have currently relied on radiologists' interpretation, whilst modern AI-based methods have been developed to detect clinically significant cancers independent of radiologists. In this study, we propose to develop deep learning models that improve the overall cancer diagnostic accuracy, by classifying radiologist-identified patients or lesions (i.e. radiologist-positives), as opposed to the existing models that are trained to discriminate over all patients. We develop a single voxel-level classification model, with a simple percentage threshold to determine positive cases, at levels of lesions, Barzell-zones and patients. Based on the presented experiments from two clinical data sets, consisting of histopathology-labelled MR images from more than 800 and 500 patients in the respective UCLA and UCL PROMIS studies, we show that the proposed strategy can improve the diagnostic accuracy, by augmenting the radiologist reading of the MR imaging. Among varying definition of clinical significance, the proposed strategy, for example, achieved a specificity of 44.1% (with AI assistance) from 36.3% (by radiologists alone), at a controlled sensitivity of 80.0% on the publicly available UCLA data set. This provides measurable clinical values in a range of applications such as reducing unnecessary biopsies, lowering cost in cancer screening and quantifying risk in therapies.
Authors: Guan Zhe Hong, Yin Cui, Ariel Fuxman, Stanely Chan, Enming Luo
Abstract: Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better generalization than pretraining with coarse-labeled data. While there is ample empirical evidence supporting this, the theoretical justification remains an open problem. This paper addresses this gap by introducing a "hierarchical multi-view" structure to confine the input data distribution. Under this framework, we prove that: 1) coarse-grained pretraining only allows a neural network to learn the common features well, while 2) fine-grained pretraining helps the network learn the rare features in addition to the common ones, leading to improved accuracy on hard downstream test samples.
Authors: Abbas Khan, Muhammad Asad, Martin Benning, Caroline Roney, Gregory Slabaugh
Abstract: Cardiac image segmentation is essential for automated cardiac function assessment and monitoring of changes in cardiac structures over time. Inspired by coarse-to-fine approaches in image analysis, we propose a novel multitask compositional segmentation approach that can simultaneously localize the heart in a cardiac image and perform part-based segmentation of different regions of interest. We demonstrate that this compositional approach achieves better results than direct segmentation of the anatomies. Further, we propose a novel Cross-Modal Feature Integration (CMFI) module to leverage the metadata related to cardiac imaging collected during image acquisition. We perform experiments on two different modalities, MRI and ultrasound, using public datasets, Multi-disease, Multi-View, and Multi-Centre (M&Ms-2) and Multi-structure Ultrasound Segmentation (CAMUS) data, to showcase the efficiency of the proposed compositional segmentation method and Cross-Modal Feature Integration module incorporating metadata within the proposed compositional segmentation network. The source code is available: https://github.com/kabbas570/CompSeg-MetaData.
Authors: Tejaswini Medi, Steffen Jung, Margret Keuper
Abstract: Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges, Adversarial Training (AT) has emerged as a prominent solution. Nevertheless, adversarial robustness is often attained at the expense of model fairness during AT, i.e., disparity in class-wise robustness of the model. While distinctive classes become more robust towards such adversaries, hard to detect classes suffer. Recently, research has focused on improving model fairness specifically for perturbed images, overlooking the accuracy of the most likely non-perturbed data. Additionally, despite their robustness against the adversaries encountered during model training, state-of-the-art adversarial trained models have difficulty maintaining robustness and fairness when confronted with diverse adversarial threats or common corruptions. In this work, we address the above concerns by introducing a novel approach called Fair Targeted Adversarial Training (FAIR-TAT). We show that using targeted adversarial attacks for adversarial training (instead of untargeted attacks) can allow for more favorable trade-offs with respect to adversarial fairness. Empirical results validate the efficacy of our approach.
Authors: Songyu Xu, Yicheng Hu, Jionglong Su, Daniel Elson, Baoru Huang
Abstract: Purpose: Drop-in gamma probes are widely used in robotic-assisted minimally invasive surgery (RAMIS) for lymph node detection. However, these devices only provide audio feedback on signal intensity, lacking the visual feedback necessary for precise localisation. Previous work attempted to predict the sensing area location using laparoscopic images, but the prediction accuracy was unsatisfactory. Improvements are needed in the deep learning-based regression approach. Methods: We introduce a three-branch deep learning framework to predict the sensing area of the probe. Specifically, we utilise the stereo laparoscopic images as input for the main branch and develop a Nested ResNet architecture. The framework also incorporates depth estimation via transfer learning and orientation guidance through probe axis sampling. The combined features from each branch enhanced the accuracy of the prediction. Results: Our approach has been evaluated on a publicly available dataset, demonstrating superior performance over previous methods. In particular, our method resulted in a 22.10\% decrease in 2D mean error and a 41.67\% reduction in 3D mean error. Additionally, qualitative comparisons further demonstrated the improved precision of our approach. Conclusion: With extensive evaluation, our solution significantly enhances the accuracy and reliability of sensing area predictions. This advancement enables visual feedback during the use of the drop-in gamma probe in surgery, providing surgeons with more accurate and reliable localisation.}
Authors: Yichao Liang, Nishanth Kumar, Hao Tang, Adrian Weller, Joshua B. Tenenbaum, Tom Silver, Jo\~ao F. Henriques, Kevin Ellis
Abstract: Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on both in- and out-of-distribution tasks across five simulated robotic domains. Results show that our approach offers better sample complexity, stronger out-of-distribution generalization, and improved interpretability.
Authors: Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, Yu Qiao
Abstract: Existing efforts in building GUI agents heavily rely on the availability of robust commercial Vision-Language Models (VLMs) such as GPT-4o and GeminiProVision. Practitioners are often reluctant to use open-source VLMs due to their significant performance lag compared to their closed-source counterparts, particularly in GUI grounding and Out-Of-Distribution (OOD) scenarios. To facilitate future research in this area, we developed OS-Atlas - a foundational GUI action model that excels at GUI grounding and OOD agentic tasks through innovations in both data and modeling. We have invested significant engineering effort in developing an open-source toolkit for synthesizing GUI grounding data across multiple platforms, including Windows, Linux, MacOS, Android, and the web. Leveraging this toolkit, we are releasing the largest open-source cross-platform GUI grounding corpus to date, which contains over 13 million GUI elements. This dataset, combined with innovations in model training, provides a solid foundation for OS-Atlas to understand GUI screenshots and generalize to unseen interfaces. Through extensive evaluation across six benchmarks spanning three different platforms (mobile, desktop, and web), OS-Atlas demonstrates significant performance improvements over previous state-of-the-art models. Our evaluation also uncovers valuable insights into continuously improving and scaling the agentic capabilities of open-source VLMs.
Authors: Yehe Liu, Alexander Krull, Hector Basevi, Ales Leonardis, Michael W. Jenkins
Abstract: Quanta image sensors, such as SPAD arrays, are an emerging sensor technology, producing 1-bit arrays representing photon detection events over exposures as short as a few nanoseconds. In practice, raw data are post-processed using heavy spatiotemporal binning to create more useful and interpretable images at the cost of degrading spatiotemporal resolution. In this work, we propose bit2bit, a new method for reconstructing high-quality image stacks at the original spatiotemporal resolution from sparse binary quanta image data. Inspired by recent work on Poisson denoising, we developed an algorithm that creates a dense image sequence from sparse binary photon data by predicting the photon arrival location probability distribution. However, due to the binary nature of the data, we show that the assumption of a Poisson distribution is inadequate. Instead, we model the process with a Bernoulli lattice process from the truncated Poisson. This leads to the proposal of a novel self-supervised solution based on a masked loss function. We evaluate our method using both simulated and real data. On simulated data from a conventional video, we achieve 34.35 mean PSNR with extremely photon-sparse binary input (<0.06 photons per pixel per frame). We also present a novel dataset containing a wide range of real SPAD high-speed videos under various challenging imaging conditions. The scenes cover strong/weak ambient light, strong motion, ultra-fast events, etc., which will be made available to the community, on which we demonstrate the promise of our approach. Both reconstruction quality and throughput substantially surpass the state-of-the-art methods (e.g., Quanta Burst Photography (QBP)). Our approach significantly enhances the visualization and usability of the data, enabling the application of existing analysis techniques.
Authors: Xiaolin Fang, Bo-Ruei Huang, Jiayuan Mao, Jasmine Shone, Joshua B. Tenenbaum, Tom\'as Lozano-P\'erez, Leslie Pack Kaelbling
Abstract: Generalization to novel object configurations and instances across diverse tasks and environments is a critical challenge in robotics. Keypoint-based representations have been proven effective as a succinct representation for capturing essential object features, and for establishing a reference frame in action prediction, enabling data-efficient learning of robot skills. However, their manual design nature and reliance on additional human labels limit their scalability. In this paper, we propose KALM, a framework that leverages large pre-trained vision-language models (LMs) to automatically generate task-relevant and cross-instance consistent keypoints. KALM distills robust and consistent keypoints across views and objects by generating proposals using LMs and verifies them against a small set of robot demonstration data. Based on the generated keypoints, we can train keypoint-conditioned policy models that predict actions in keypoint-centric frames, enabling robots to generalize effectively across varying object poses, camera views, and object instances with similar functional shapes. Our method demonstrates strong performance in the real world, adapting to different tasks and environments from only a handful of demonstrations while requiring no additional labels. Website: https://kalm-il.github.io/
Authors: Yanke Song, Jonathan Lorraine, Weili Nie, Karsten Kreis, James Lucas
Abstract: Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep inference procedure. To overcome this, diffusion distillation techniques produce student generators capable of matching or surpassing the teacher in a single step. However, the student model's inference speed is limited by the size of the teacher architecture, preventing real-time generation for computationally heavy applications. In this work, we introduce Multi-Student Distillation (MSD), a framework to distill a conditional teacher diffusion model into multiple single-step generators. Each student generator is responsible for a subset of the conditioning data, thereby obtaining higher generation quality for the same capacity. MSD trains multiple distilled students, allowing smaller sizes and, therefore, faster inference. Also, MSD offers a lightweight quality boost over single-student distillation with the same architecture. We demonstrate MSD is effective by training multiple same-sized or smaller students on single-step distillation using distribution matching and adversarial distillation techniques. With smaller students, MSD gets competitive results with faster inference for single-step generation. Using 4 same-sized students, MSD sets a new state-of-the-art for one-step image generation: FID 1.20 on ImageNet-64x64 and 8.20 on zero-shot COCO2014.
Authors: Qi Zhang, Antoni B. Chan
Abstract: Recently multi-view crowd counting using deep neural networks has been proposed to enable counting in large and wide scenes using multiple cameras. The current methods project the camera-view features to the average-height plane of the 3D world, and then fuse the projected multi-view features to predict a 2D scene-level density map on the ground (i.e., birds-eye view). Unlike the previous research, we consider the variable height of the people in the 3D world and propose to solve the multi-view crowd counting task through 3D feature fusion with 3D scene-level density maps, instead of the 2D density map on the ground plane. Compared to 2D fusion, the 3D fusion extracts more information of the people along the z-dimension (height), which helps to address the scale variations across multiple views. The 3D density maps still preserve the 2D density maps property that the sum is the count, while also providing 3D information about the crowd density. Furthermore, instead of using the standard method of copying the features along the view ray in the 2D-to-3D projection, we propose an attention module based on a height estimation network, which forces each 2D pixel to be projected to one 3D voxel along the view ray. We also explore the projection consistency among the 3D prediction and the ground truth in the 2D views to further enhance the counting performance. The proposed method is tested on the synthetic and real-world multiview counting datasets and achieves better or comparable counting performance to the state-of-the-art.
Authors: Linglan Zhao, Dashan Guo, Yunlu Xu, Liang Qiao, Zhanzhan Cheng, Shiliang Pu, Yi Niu, Xiangzhong Fang
Abstract: Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods. Another line of methods also cares about the performance of base classes in addition to the novel ones and thus establishes the incremental FSL scenario. In this paper, we generalize the above two under a more realistic yet complex setting, named by Semi-Supervised Incremental Few-Shot Learning (S2 I-FSL). To tackle the task, we propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data. Extensive experiments on standard FSL, semi-supervised FSL, incremental FSL, and the firstly built S2 I-FSL benchmarks demonstrate the effectiveness of our proposed method.
Authors: Zhouxia Wang, Xintao Wang, Liangbin Xie, Zhongang Qi, Ying Shan, Wenping Wang, Ping Luo
Abstract: This work focuses on generating high-quality images with specific style of reference images and content of provided textual descriptions. Current leading algorithms, i.e., DreamBooth and LoRA, require fine-tuning for each style, leading to time-consuming and computationally expensive processes. In this work, we propose StyleAdapter, a unified stylized image generation model capable of producing a variety of stylized images that match both the content of a given prompt and the style of reference images, without the need for per-style fine-tuning. It introduces a two-path cross-attention (TPCA) module to separately process style information and textual prompt, which cooperate with a semantic suppressing vision model (SSVM) to suppress the semantic content of style images. In this way, it can ensure that the prompt maintains control over the content of the generated images, while also mitigating the negative impact of semantic information in style references. This results in the content of the generated image adhering to the prompt, and its style aligning with the style references. Besides, our StyleAdapter can be integrated with existing controllable synthesis methods, such as T2I-adapter and ControlNet, to attain a more controllable and stable generation process. Extensive experiments demonstrate the superiority of our method over previous works.
Authors: Che Liu, Sibo Cheng, Miaojing Shi, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: In the field of medical Vision-Language Pre-training (VLP), significant efforts have been devoted to deriving text and image features from both clinical reports and associated medical images. However, most existing methods may have overlooked the opportunity in leveraging the inherent hierarchical structure of clinical reports, which are generally split into `findings' for descriptive content and `impressions' for conclusive observation. Instead of utilizing this rich, structured format, current medical VLP approaches often simplify the report into either a unified entity or fragmented tokens. In this work, we propose a novel clinical prior guided VLP framework named IMITATE to learn the structure information from medical reports with hierarchical vision-language alignment. The framework derives multi-level visual features from the chest X-ray (CXR) images and separately aligns these features with the descriptive and the conclusive text encoded in the hierarchical medical report. Furthermore, a new clinical-informed contrastive loss is introduced for cross-modal learning, which accounts for clinical prior knowledge in formulating sample correlations in contrastive learning. The proposed model, IMITATE, outperforms baseline VLP methods across six different datasets, spanning five medical imaging downstream tasks. Comprehensive experimental results highlight the advantages of integrating the hierarchical structure of medical reports for vision-language alignment. The code related to this paper is available at https://github.com/cheliu-computation/IMITATE-TMI2024.
URLs: https://github.com/cheliu-computation/IMITATE-TMI2024.
Authors: Amit Bracha, Thomas Dag\`es, Ron Kimmel
Abstract: While dealing with matching shapes to their parts, we often apply a tool known as functional maps. The idea is to translate the shape matching problem into "convenient" spaces by which matching is performed algebraically by solving a least squares problem. Here, we argue that such formulations, though popular in this field, introduce errors in the estimated match when partiality is invoked. Such errors are unavoidable even for advanced feature extraction networks, and they can be shown to escalate with increasing degrees of shape partiality, adversely affecting the learning capability of such systems. To circumvent these limitations, we propose a novel approach for partial shape matching. Our study of functional maps led us to a novel method that establishes direct correspondence between partial and full shapes through feature matching bypassing the need for functional map intermediate spaces. The Gromov Distance between metric spaces leads to the construction of the first part of our loss functions. For regularization we use two options: a term based on the area preserving property of the mapping, and a relaxed version that avoids the need to resort to functional maps. The proposed approach shows superior performance on the SHREC'16 dataset, outperforming existing unsupervised methods for partial shape matching.Notably, it achieves state-of-the-art results on the SHREC'16 HOLES benchmark, superior also compared to supervised methods. We demonstrate the benefits of the proposed unsupervised method when applied to a new dataset PFAUST for part-to-full shape correspondence.
Authors: Libo Wang, Sijun Dong, Ying Chen, Xiaoliang Meng, Shenghui Fang, Songlin Fei
Abstract: Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation applications, such as land use land cover mapping, environment monitoring, and sustainable development. Driven by rapid developments in artificial intelligence, deep learning (DL) has emerged as the mainstream for semantic segmentation and has achieved many breakthroughs in the field of remote sensing. However, most DL-based methods focus on unimodal visual data while ignoring rich multimodal information involved in the real world. Non-visual data, such as text, can gather extra knowledge from the real world, which can strengthen the interpretability, reliability, and generalization of visual models. Inspired by this, we propose a novel metadata-collaborative segmentation network (MetaSegNet) that applies vision-language representation learning for semantic segmentation of remote sensing images. Unlike the common model structure that only uses unimodal visual data, we extract the key characteristic (e.g. the climate zone) from freely available remote sensing image metadata and transfer it into geographic text prompts via the generic ChatGPT. Then, we construct an image encoder, a text encoder, and a crossmodal attention fusion subnetwork to extract the image and text feature and apply image-text interaction. Benefiting from such a design, the proposed MetaSegNet not only demonstrates superior generalization in zero-shot testing but also achieves competitive accuracy with the state-of-the-art semantic segmentation methods on the large-scale OpenEarthMap dataset (70.4% mIoU) and the Potsdam dataset (93.3% mean F1 score) as well as the LoveDA dataset (52.0% mIoU).
Authors: Will LeVine, Benjamin Pikus, Jacob Phillips, Berk Norman, Fernando Amat Gil, Sean Hendryx
Abstract: As deep neural networks become adopted in high-stakes domains, it is crucial to identify when inference inputs are Out-of-Distribution (OOD) so that users can be alerted of likely drops in performance and calibration despite high confidence -- ultimately to know when networks' decisions (and their uncertainty in those decisions) should be trusted. In this paper we introduce Ablated Learned Temperature Energy (or "AbeT" for short), an OOD detection method which lowers the False Positive Rate at 95\% True Positive Rate (FPR@95) by $43.43\%$ in classification compared to state of the art without training networks in multiple stages or requiring hyperparameters or test-time backward passes. We additionally provide empirical insights as to why our model learns to distinguish between In-Distribution (ID) and OOD samples while only being explicitly trained on ID samples via exposure to misclassified ID examples at training time. Lastly, we show the efficacy of our method in identifying predicted bounding boxes and pixels corresponding to OOD objects in object detection and semantic segmentation, respectively -- with an AUROC increase of $5.15\%$ in object detection and both a decrease in FPR@95 of $41.48\%$ and an increase in AUPRC of $34.20\%$ in semantic segmentation compared to previous state of the art.
Authors: Yongwei Nie, Mingxian Fan, Chengjiang Long, Qing Zhang, Jian Zhu, Xuemiao Xu
Abstract: Human Mesh Recovery (HMR) is the task of estimating a parameterized 3D human mesh from an image. There is a kind of methods first training a regression model for this problem, then further optimizing the pretrained regression model for any specific sample individually at test time. However, the pretrained model may not provide an ideal optimization starting point for the test-time optimization. Inspired by meta-learning, we incorporate the test-time optimization into training, performing a step of test-time optimization for each sample in the training batch before really conducting the training optimization over all the training samples. In this way, we obtain a meta-model, the meta-parameter of which is friendly to the test-time optimization. At test time, after several test-time optimization steps starting from the meta-parameter, we obtain much higher HMR accuracy than the test-time optimization starting from the simply pretrained regression model. Furthermore, we find test-time HMR objectives are different from training-time objectives, which reduces the effectiveness of the learning of the meta-model. To solve this problem, we propose a dual-network architecture that unifies the training-time and test-time objectives. Our method, armed with meta-learning and the dual networks, outperforms state-of-the-art regression-based and optimization-based HMR approaches, as validated by the extensive experiments. The codes are available at https://github.com/fmx789/Meta-HMR.
Authors: Amelia Jim\'enez-S\'anchez, Natalia-Rozalia Avlona, Dovile Juodelyte, Th\'eo Sourget, Caroline Vang-Larsen, Anna Rogers, Hubert Dariusz Zaj\k{a}c, Veronika Cheplygina
Abstract: Medical Imaging (MI) datasets are fundamental to artificial intelligence in healthcare. The accuracy, robustness, and fairness of diagnostic algorithms depend on the data (and its quality) used to train and evaluate the models. MI datasets used to be proprietary, but have become increasingly available to the public, including on community-contributed platforms (CCPs) like Kaggle or HuggingFace. While open data is important to enhance the redistribution of data's public value, we find that the current CCP governance model fails to uphold the quality needed and recommended practices for sharing, documenting, and evaluating datasets. In this paper, we conduct an analysis of publicly available machine learning datasets on CCPs, discussing datasets' context, and identifying limitations and gaps in the current CCP landscape. We highlight differences between MI and computer vision datasets, particularly in the potentially harmful downstream effects from poor adoption of recommended dataset management practices. We compare the analyzed datasets across several dimensions, including data sharing, data documentation, and maintenance. We find vague licenses, lack of persistent identifiers and storage, duplicates, and missing metadata, with differences between the platforms. Our research contributes to efforts in responsible data curation and AI algorithms for healthcare.
Authors: Yihua Zhang, Chongyu Fan, Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jiancheng Liu, Gaoyuan Zhang, Gaowen Liu, Ramana Rao Kompella, Xiaoming Liu, Sijia Liu
Abstract: The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose UnlearnCanvas, a comprehensive high-resolution stylized image dataset that facilitates the evaluation of the unlearning of artistic styles and associated objects. This dataset enables the establishment of a standardized, automated evaluation framework with 7 quantitative metrics assessing various aspects of the unlearning performance for DMs. Through extensive experiments, we benchmark 9 state-of-the-art MU methods for DMs, revealing novel insights into their strengths, weaknesses, and underlying mechanisms. Additionally, we explore challenging unlearning scenarios for DMs to evaluate worst-case performance against adversarial prompts, the unlearning of finer-scale concepts, and sequential unlearning. We hope that this study can pave the way for developing more effective, accurate, and robust DM unlearning methods, ensuring safer and more ethical applications of DMs in the future. The dataset, benchmark, and codes are publicly available at https://unlearn-canvas.netlify.app/.
Authors: Khalil Sabri, C\'elia Djilali, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Wassim Bouachir
Abstract: Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes. To address this object detection problem, this work introduces an adapted detection model that combines the accuracy and speed of single-frame object detection with the richer features offered by video object detection frameworks. This is done by applying aggregated feature maps from consecutive frames processed through motion flow to the YOLOX architecture. This fusion brings a temporal perspective to YOLOX detection abilities, allowing for a better understanding of urban mobility patterns and substantially improving detection reliability. Tested on a custom dataset curated for urban micromobility scenarios, our model showcases substantial improvement over existing state-of-the-art methods, demonstrating the need to consider spatio-temporal information for detecting such small and thin objects. Our approach enhances detection in challenging conditions, including occlusions, ensuring temporal consistency, and effectively mitigating motion blur.
Authors: Yijun Yang, Ruiyuan Gao, Xiao Yang, Jianyuan Zhong, Qiang Xu
Abstract: Recent advancements in Text-to-Image (T2I) models have raised significant safety concerns about their potential misuse for generating inappropriate or Not-Safe-For-Work (NSFW) contents, despite existing countermeasures such as NSFW classifiers or model fine-tuning for inappropriate concept removal. Addressing this challenge, our study unveils GuardT2I, a novel moderation framework that adopts a generative approach to enhance T2I models' robustness against adversarial prompts. Instead of making a binary classification, GuardT2I utilizes a Large Language Model (LLM) to conditionally transform text guidance embeddings within the T2I models into natural language for effective adversarial prompt detection, without compromising the models' inherent performance. Our extensive experiments reveal that GuardT2I outperforms leading commercial solutions like OpenAI-Moderation and Microsoft Azure Moderator by a significant margin across diverse adversarial scenarios. Our framework is available at https://github.com/cure-lab/GuardT2I.
Authors: Tom Sander, Yaodong Yu, Maziar Sanjabi, Alain Durmus, Yi Ma, Kamalika Chaudhuri, Chuan Guo
Abstract: Differentially private (DP) machine learning is considered the gold-standard solution for training a model from sensitive data while still preserving privacy. However, a major barrier to achieving this ideal is its sub-optimal privacy-accuracy trade-off, which is particularly visible in DP representation learning. Specifically, it has been shown that under modest privacy budgets, most models learn representations that are not significantly better than hand-crafted features. In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets. Through a series of engineering tricks, we successfully train a DP image captioner (DP-Cap) on a 233M subset of LAION-2B from scratch using a reasonable amount of computation, and obtaining unprecedented high-quality image features that can be used in a variety of downstream vision and vision-language tasks. For example, under a privacy budget of $\varepsilon=8$ for the LAION dataset, a linear classifier trained on top of learned DP-Cap features attains $65.8\%$ accuracy on ImageNet-1K, considerably improving the previous SOTA of $56.5\%$.
Authors: Zijie Fang, Yifeng Wang, Ye Zhang, Zhi Wang, Jian Zhang, Xiangyang Ji, Yongbing Zhang
Abstract: Recently, pathological diagnosis has achieved superior performance by combining deep learning models with the multiple instance learning (MIL) framework using whole slide images (WSIs). However, the giga-pixeled nature of WSIs poses a great challenge for efficient MIL. Existing studies either do not consider global dependencies among instances, or use approximations such as linear attentions to model the pair-to-pair instance interactions, which inevitably brings performance bottlenecks. To tackle this challenge, we propose a framework named MamMIL for WSI analysis by cooperating the selective structured state space model (i.e., Mamba) with MIL, enabling the modeling of global instance dependencies while maintaining linear complexity. Specifically, considering the irregularity of the tissue regions in WSIs, we represent each WSI as an undirected graph. To address the problem that Mamba can only process 1D sequences, we further propose a topology-aware scanning mechanism to serialize the WSI graphs while preserving the topological relationships among the instances. Finally, in order to further perceive the topological structures among the instances and incorporate short-range feature interactions, we propose an instance aggregation block based on graph neural networks. Experiments show that MamMIL can achieve advanced performance than the state-of-the-art frameworks. The code can be accessed at https://github.com/Vison307/MamMIL.
Authors: Chenyang Ma, Kai Lu, Ta-Ying Cheng, Niki Trigoni, Andrew Markham
Abstract: Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such as articulating dynamic scene changes and motion planning, require a fundamental and explicit 3D understanding beyond current spatial VQA datasets. In this work, we present SpatialPIN, a framework designed to enhance the spatial reasoning capabilities of VLMs through prompting and interacting with priors from multiple 3D foundation models in a zero-shot, training-free manner. Extensive experiments demonstrate that our spatial reasoning-imbued VLM performs well on various forms of spatial VQA and can extend to help in various downstream robotics tasks such as pick and stack and trajectory planning.
Authors: Ye Li, Lingdong Kong, Hanjiang Hu, Xiaohao Xu, Xiaonan Huang
Abstract: The reliability of driving perception systems under unprecedented conditions is crucial for practical usage. Latest advancements have prompted increasing interest in multi-LiDAR perception. However, prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions, failing to capture the complexities of real-world environments accurately. Addressing these gaps, we proposed Place3D, a full-cycle pipeline that encompasses LiDAR placement optimization, data generation, and downstream evaluations. Our framework makes three appealing contributions. 1) To identify the most effective configurations for multi-LiDAR systems, we introduce the Surrogate Metric of the Semantic Occupancy Grids (M-SOG) to evaluate LiDAR placement quality. 2) Leveraging the M-SOG metric, we propose a novel optimization strategy to refine multi-LiDAR placements. 3) Centered around the theme of multi-condition multi-LiDAR perception, we collect a 280,000-frame dataset from both clean and adverse conditions. Extensive experiments demonstrate that LiDAR placements optimized using our approach outperform various baselines. We showcase exceptional results in both LiDAR semantic segmentation and 3D object detection tasks, under diverse weather and sensor failure conditions.
Authors: Diana-Nicoleta Grigore, Mariana-Iuliana Georgescu, Jon Alvarez Justo, Tor Johansen, Andreea Iuliana Ionescu, Radu Tudor Ionescu
Abstract: Few-shot knowledge distillation recently emerged as a viable approach to harness the knowledge of large-scale pre-trained models, using limited data and computational resources. In this paper, we propose a novel few-shot feature distillation approach for vision transformers. Our approach is based on two key steps. Leveraging the fact that vision transformers have a consistent depth-wise structure, we first copy the weights from intermittent layers of existing pre-trained vision transformers (teachers) into shallower architectures (students), where the intermittence factor controls the complexity of the student transformer with respect to its teacher. Next, we employ an enhanced version of Low-Rank Adaptation (LoRA) to distill knowledge into the student in a few-shot scenario, aiming to recover the information processing carried out by the skipped teacher layers. We present comprehensive experiments with supervised and self-supervised transformers as teachers, on six data sets from various domains (natural, medical and satellite images) and tasks (classification and segmentation). The empirical results confirm the superiority of our approach over state-of-the-art competitors. Moreover, the ablation results demonstrate the usefulness of each component of the proposed pipeline. We release our code at https://github.com/dianagrigore/WeCoLoRA.
Authors: Baoru Huang, Yida Wang, Anh Nguyen, Daniel Elson, Francisco Vasconcelos, Danail Stoyanov
Abstract: In surgical oncology, screening colonoscopy plays a pivotal role in providing diagnostic assistance, such as biopsy, and facilitating surgical navigation, particularly in polyp detection. Computer-assisted endoscopic surgery has recently gained attention and amalgamated various 3D computer vision techniques, including camera localization, depth estimation, surface reconstruction, etc. Neural Radiance Fields (NeRFs) and Neural Implicit Surfaces (NeuS) have emerged as promising methodologies for deriving accurate 3D surface models from sets of registered images, addressing the limitations of existing colon reconstruction approaches stemming from constrained camera movement. However, the inadequate tissue texture representation and confused scale problem in monocular colonoscopic image reconstruction still impede the progress of the final rendering results. In this paper, we introduce a novel method for colon section reconstruction by leveraging NeuS applied to endoscopic images, supplemented by a single frame of depth map. Notably, we pioneered the exploration of utilizing only one frame depth map in photorealistic reconstruction and neural rendering applications while this single depth map can be easily obtainable from other monocular depth estimation networks with an object scale. Through rigorous experimentation and validation on phantom imagery, our approach demonstrates exceptional accuracy in completely rendering colon sections, even capturing unseen portions of the surface. This breakthrough opens avenues for achieving stable and consistently scaled reconstructions, promising enhanced quality in cancer screening procedures and treatment interventions.
Authors: Ayumu Saito, Prachi Kudeshia, Jiju Poovvancheri
Abstract: Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in the input space, or the necessity of additional modalities. In order to address these issues, we introduce Point-JEPA, a joint embedding predictive architecture designed specifically for point cloud data. To this end, we introduce a sequencer that orders point cloud tokens to efficiently compute and utilize tokens proximity based on their indices during target and context selection. The sequencer also allows shared computations of the tokens proximity between context and target selection, further improving the efficiency. Experimentally, our method achieves competitive results with state-of-the-art methods while avoiding the reconstruction in the input space or additional modality.
Authors: Yuchuan Tian, Zhijun Tu, Hanting Chen, Jie Hu, Chao Xu, Yunhe Wang
Abstract: Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance and good scalability; but meanwhile, the abandonment of U-Net by DiTs and their following improvements is worth rethinking. To this end, we conduct a simple toy experiment by comparing a U-Net architectured DiT with an isotropic one. It turns out that the U-Net architecture only gain a slight advantage amid the U-Net inductive bias, indicating potential redundancies within the U-Net-style DiT. Inspired by the discovery that U-Net backbone features are low-frequency-dominated, we perform token downsampling on the query-key-value tuple for self-attention that bring further improvements despite a considerable amount of reduction in computation. Based on self-attention with downsampled tokens, we propose a series of U-shaped DiTs (U-DiTs) in the paper and conduct extensive experiments to demonstrate the extraordinary performance of U-DiT models. The proposed U-DiT could outperform DiT-XL/2 with only 1/6 of its computation cost. Codes are available at https://github.com/YuchuanTian/U-DiT.
Authors: Anthony Fuller, Daniel G. Kyrollos, Yousef Yassin, James R. Green
Abstract: High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without finetuning -- ViTs poorly extrapolate to more patches at test time, although transformers offer sequence length flexibility. We attribute this shortcoming to the current patch position encoding methods, which create a distribution shift when extrapolating. We propose a drop-in replacement for the position encoding of plain ViTs that restricts attention heads to fixed fields of view, pointed in different directions, using 2D attention masks. Our novel method, called LookHere, provides translation-equivariance, ensures attention head diversity, and limits the distribution shift that attention heads face when extrapolating. We demonstrate that LookHere improves performance on classification (avg. 1.6%), against adversarial attack (avg. 5.4%), and decreases calibration error (avg. 1.5%) -- on ImageNet without extrapolation. With extrapolation, LookHere outperforms the current SoTA position encoding method, 2D-RoPE, by 21.7% on ImageNet when trained at $224^2$ px and tested at $1024^2$ px. Additionally, we release a high-resolution test set to improve the evaluation of high-resolution image classifiers, called ImageNet-HR.
Authors: Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, Guiguang Ding
Abstract: Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the architectural designs, optimization objectives, data augmentation strategies, and others for YOLOs, achieving notable progress. However, the reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs and adversely impacts the inference latency. Besides, the design of various components in YOLOs lacks the comprehensive and thorough inspection, resulting in noticeable computational redundancy and limiting the model's capability. It renders the suboptimal efficiency, along with considerable potential for performance improvements. In this work, we aim to further advance the performance-efficiency boundary of YOLOs from both the post-processing and model architecture. To this end, we first present the consistent dual assignments for NMS-free training of YOLOs, which brings competitive performance and low inference latency simultaneously. Moreover, we introduce the holistic efficiency-accuracy driven model design strategy for YOLOs. We comprehensively optimize various components of YOLOs from both efficiency and accuracy perspectives, which greatly reduces the computational overhead and enhances the capability. The outcome of our effort is a new generation of YOLO series for real-time end-to-end object detection, dubbed YOLOv10. Extensive experiments show that YOLOv10 achieves state-of-the-art performance and efficiency across various model scales. For example, our YOLOv10-S is 1.8$\times$ faster than RT-DETR-R18 under the similar AP on COCO, meanwhile enjoying 2.8$\times$ smaller number of parameters and FLOPs. Compared with YOLOv9-C, YOLOv10-B has 46\% less latency and 25\% fewer parameters for the same performance.
Authors: Haoxuan Qu, Zhuoling Li, Hossein Rahmani, Yujun Cai, Jun Liu
Abstract: Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis. In this paper, we highlight a fundamental limitation of Gaussian Splatting: its inability to accurately render discontinuities and boundaries in images due to the continuous nature of Gaussian distributions. To address this issue, we propose a novel framework enabling Gaussian Splatting to perform discontinuity-aware image rendering. Additionally, we introduce a B\'ezier-boundary gradient approximation strategy within our framework to keep the "differentiability" of the proposed discontinuity-aware rendering process. Extensive experiments demonstrate the efficacy of our framework.
Authors: Shuangpeng Han, Ziyu Wang, Mengmi Zhang
Abstract: Biological motion perception (BMP) refers to humans' ability to perceive and recognize the actions of living beings solely from their motion patterns, sometimes as minimal as those depicted on point-light displays. While humans excel at these tasks without any prior training, current AI models struggle with poor generalization performance. To close this research gap, we propose the Motion Perceiver (MP). MP solely relies on patch-level optical flows from video clips as inputs. During training, it learns prototypical flow snapshots through a competitive binding mechanism and integrates invariant motion representations to predict action labels for the given video. During inference, we evaluate the generalization ability of all AI models and humans on 62,656 video stimuli spanning 24 BMP conditions using point-light displays in neuroscience. Remarkably, MP outperforms all existing AI models with a maximum improvement of 29% in top-1 action recognition accuracy on these conditions. Moreover, we benchmark all AI models in point-light displays of two standard video datasets in computer vision. MP also demonstrates superior performance in these cases. More interestingly, via psychophysics experiments, we found that MP recognizes biological movements in a way that aligns with human behaviors. Our data and code are available at https://github.com/ZhangLab-DeepNeuroCogLab/MotionPerceiver.
URLs: https://github.com/ZhangLab-DeepNeuroCogLab/MotionPerceiver.
Authors: Thomas W. Mitchel, Michael Taylor, Vincent Sitzmann
Abstract: Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to a general-purpose latent space wherein encodings are related by isometries whenever their corresponding observations are geometrically related in world space. Specifically, we regularize the latent space such that maps between encodings preserve a learned inner product and commute with a learned functional operator, in the same manner as rigid-body transformations commute with the Laplacian. This approach forms an effective backbone for self-supervised representation learning, and we demonstrate that a simple off-the-shelf equivariant network operating in the pre-trained latent space can achieve results on par with meticulously-engineered, handcrafted networks designed to handle complex, nonlinear symmetries. Furthermore, isometric maps capture information about the respective transformations in world space, and we show that this allows us to regress camera poses directly from the coefficients of the maps between encodings of adjacent views of a scene.
Authors: Raman Dutt, Ondrej Bohdal, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales
Abstract: Diffusion models excel in generating images that closely resemble their training data but are also susceptible to data memorization, raising privacy, ethical, and legal concerns, particularly in sensitive domains such as medical imaging. We hypothesize that this memorization stems from the overparameterization of deep models and propose that regularizing model capacity during fine-tuning can mitigate this issue. Firstly, we empirically show that regulating the model capacity via Parameter-efficient fine-tuning (PEFT) mitigates memorization to some extent, however, it further requires the identification of the exact parameter subsets to be fine-tuned for high-quality generation. To identify these subsets, we introduce a bi-level optimization framework, MemControl, that automates parameter selection using memorization and generation quality metrics as rewards during fine-tuning. The parameter subsets discovered through MemControl achieve a superior tradeoff between generation quality and memorization. For the task of medical image generation, our approach outperforms existing state-of-the-art memorization mitigation strategies by fine-tuning as few as 0.019% of model parameters. Moreover, we demonstrate that the discovered parameter subsets are transferable to non-medical domains. Our framework is scalable to large datasets, agnostic to reward functions, and can be integrated with existing approaches for further memorization mitigation. To the best of our knowledge, this is the first study to empirically evaluate memorization in medical images and propose a targeted yet universal mitigation strategy. The code is available at https://github.com/Raman1121/Diffusion_Memorization_HPO
URLs: https://github.com/Raman1121/Diffusion_Memorization_HPO
Authors: Gonca Yilmaz, Songyou Peng, Marc Pollefeys, Francis Engelmann, Hermann Blum
Abstract: Recently, Vision-Language Models (VLMs) have advanced segmentation techniques by shifting from the traditional segmentation of a closed-set of predefined object classes to open-vocabulary segmentation (OVS), allowing users to segment novel classes and concepts unseen during training of the segmentation model. However, this flexibility comes with a trade-off: fully-supervised closed-set methods still outperform OVS methods on base classes, that is on classes on which they have been explicitly trained. This is due to the lack of pixel-aligned training masks for VLMs (which are trained on image-caption pairs), and the absence of domain-specific knowledge, such as autonomous driving. Therefore, we propose the task of open-vocabulary domain adaptation to infuse domain-specific knowledge into VLMs while preserving their open-vocabulary nature. By doing so, we achieve improved performance in base and novel classes. Existing VLM adaptation methods improve performance on base (training) queries, but fail to fully preserve the open-set capabilities of VLMs on novel queries. To address this shortcoming, we combine parameter-efficient prompt tuning with a triplet-loss-based training strategy that uses auxiliary negative queries. Notably, our approach is the only parameter-efficient method that consistently surpasses the original VLM on novel classes. Our adapted VLMs can seamlessly be integrated into existing OVS pipelines, e.g., improving OVSeg by +6.0% mIoU on ADE20K for open-vocabulary 2D segmentation, and OpenMask3D by +4.1% AP on ScanNet++ Offices for open-vocabulary 3D instance segmentation without other changes. The project page is available at https://open-das.github.io/.
Authors: Hao Chen, Yujin Han, Diganta Misra, Xiang Li, Kai Hu, Difan Zou, Masashi Sugiyama, Jindong Wang, Bhiksha Raj
Abstract: Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class pairs. Despite rigorous filtering, these pre-training datasets often inevitably contain corrupted pairs where conditions do not accurately describe the data. This paper presents the first comprehensive study on the impact of such corruption in pre-training data of DMs. We synthetically corrupt ImageNet-1K and CC3M to pre-train and evaluate over 50 conditional DMs. Our empirical findings reveal that various types of slight corruption in pre-training can significantly enhance the quality, diversity, and fidelity of the generated images across different DMs, both during pre-training and downstream adaptation stages. Theoretically, we consider a Gaussian mixture model and prove that slight corruption in the condition leads to higher entropy and a reduced 2-Wasserstein distance to the ground truth of the data distribution generated by the corruptly trained DMs. Inspired by our analysis, we propose a simple method to improve the training of DMs on practical datasets by adding condition embedding perturbations (CEP). CEP significantly improves the performance of various DMs in both pre-training and downstream tasks. We hope that our study provides new insights into understanding the data and pre-training processes of DMs and all models are released at https://huggingface.co/DiffusionNoise.
Authors: Antonio Santo, Juan J. Cabrera, David Valiente, Carlos Viegas, Arturo Gil
Abstract: This paper presents TE-NeXt, a novel and efficient architecture for Traversability Estimation (TE) from sparse LiDAR point clouds based on a residual convolution block. TE-NeXt block fuses notions of current trends such as attention mechanisms and 3D sparse convolutions. TE-NeXt aims to demonstrate high capacity for generalisation in a variety of urban and natural environments, using well-known and accessible datasets such as SemanticKITTI, Rellis-3D and SemanticUSL. Thus, the designed architecture ouperforms state-of-the-art methods in the problem of semantic segmentation, demonstrating better results in unstructured environments and maintaining high reliability and robustness in urbans environments, which leads to better abstraction. Implementation is available in a open repository to the scientific community with the aim of ensuring the reproducibility of results.
Authors: Juan M. Vargas, Taous-Meriem Laleg-Kirati
Abstract: In this study, we propose a novel image contrast enhancement method based on projecting images onto the squared eigenfunctions of the two-dimensional Schr\"odinger operator. This projection relies on a design parameter, $\gamma$, which controls pixel intensity during image reconstruction. The method's performance is evaluated using color images. The selection of $\gamma$ values is guided by priors based on fuzzy logic and clustering, preserving the spatial adjacency information of the image. Additionally, multi-objective optimization using the Non-dominated Sorting Genetic Algorithm II (NSGA-II) is employed to determine the optimal values of $\gamma$ and the semi-classical parameter, $h$, from the 2D-SCSA. Results demonstrate that the proposed method effectively enhances image contrast while preserving the inherent characteristics of the original image, producing the desired enhancement with minimal artifacts.
Authors: Qingsong Xie, Zhenyi Liao, Zhijie Deng, Chen chen, Haonan Lu
Abstract: Distilling latent diffusion models (LDMs) into ones that are fast to sample from is attracting growing research interest. However, the majority of existing methods face two critical challenges: (1) They hinge on long training using a huge volume of real data. (2) They routinely lead to quality degradation for generation, especially in text-image alignment. This paper proposes a novel training-efficient Latent Consistency Model (TLCM) to overcome these challenges. Our method first accelerates LDMs via data-free multistep latent consistency distillation (MLCD), and then data-free latent consistency distillation is proposed to efficiently guarantee the inter-segment consistency in MLCD. Furthermore, we introduce bags of techniques, e.g., distribution matching, adversarial learning, and preference learning, to enhance TLCM's performance at few-step inference without any real data. TLCM demonstrates a high level of flexibility by enabling adjustment of sampling steps within the range of 2 to 8 while still producing competitive outputs compared to full-step approaches. Notably, TLCM enjoys the data-free merit by employing synthetic data from the teacher for distillation. With just 70 training hours on an A100 GPU, a 3-step TLCM distilled from SDXL achieves an impressive CLIP Score of 33.68 and an Aesthetic Score of 5.97 on the MSCOCO-2017 5K benchmark, surpassing various accelerated models and even outperforming the teacher model in human preference metrics. We also demonstrate the versatility of TLCMs in applications including image style transfer, controllable generation, and Chinese-to-image generation.
Authors: Hanlin Chen, Fangyin Wei, Chen Li, Tianxin Huang, Yunsong Wang, Gim Hee Lee
Abstract: Although 3D Gaussian Splatting has been widely studied because of its realistic and efficient novel-view synthesis, it is still challenging to extract a high-quality surface from the point-based representation. Previous works improve the surface by incorporating geometric priors from the off-the-shelf normal estimator. However, there are two main limitations: 1) Supervising normals rendered from 3D Gaussians effectively updates the rotation parameter but is less effective for other geometric parameters; 2) The inconsistency of predicted normal maps across multiple views may lead to severe reconstruction artifacts. In this paper, we propose a Depth-Normal regularizer that directly couples normal with other geometric parameters, leading to full updates of the geometric parameters from normal regularization. We further propose a confidence term to mitigate inconsistencies of normal predictions across multiple views. Moreover, we also introduce a densification and splitting strategy to regularize the size and distribution of 3D Gaussians for more accurate surface modeling. Compared with Gaussian-based baselines, experiments show that our approach obtains better reconstruction quality and maintains competitive appearance quality at faster training speed and 100+ FPS rendering.
Authors: Zesen Cheng, Sicong Leng, Hang Zhang, Yifei Xin, Xin Li, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, Lidong Bing
Abstract: In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. Building upon its predecessor, VideoLLaMA 2 incorporates a tailor-made Spatial-Temporal Convolution (STC) connector, which effectively captures the intricate spatial and temporal dynamics of video data. Additionally, we integrate an Audio Branch into the model through joint training, thereby enriching the multimodal understanding capabilities of the model by seamlessly incorporating audio cues. Comprehensive evaluations on multiple-choice video question answering (MC-VQA), open-ended video question answering (OE-VQA), and video captioning (VC) tasks demonstrate that VideoLLaMA 2 consistently achieves competitive results among open-source models and even gets close to some proprietary models on several benchmarks. Furthermore, VideoLLaMA 2 exhibits reasonable improvements in audio-only and audio-video question-answering (AQA & OE-AVQA) benchmarks over existing models. These advancements underline VideoLLaMA 2's superior performance in multimodal comprehension, setting a new standard for intelligent video analysis systems. All models are public to facilitate further research.
Authors: Zhengrui Xu, Guan'an Wang, Xiaowen Huang, Jitao Sang
Abstract: The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors". In this paper, we propose a novel Denoising Model for Representation Learning (DenoiseRep) to improve feature discrimination with joint feature extraction and denoising. DenoiseRep views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, DenoiseRep fuses the parameters of feature extraction and denoising layers, and theoretically demonstrates its equivalence before and after the fusion, thus making feature denoising computation-free. DenoiseRep is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures.
Authors: Zehui Liao, Shishuai Hu, Yanning Zhang, Yong Xia
Abstract: Addressing mixed closed-set and open-set label noise in medical image classification remains a largely unexplored challenge. Unlike natural image classification, which often separates and processes closed-set and open-set noisy samples from clean ones, medical image classification contends with high inter-class similarity, complicating the identification of open-set noisy samples. Additionally, existing methods often fail to fully utilize open-set noisy samples for label noise mitigation, leading to their exclusion or the application of uniform soft labels. To address these challenges, we propose the Extended Noise-robust Contrastive and Open-set Feature Augmentation framework for medical image classification tasks. This framework incorporates the Extended Noise-robust Supervised Contrastive Loss, which helps differentiate features among both in-distribution and out-of-distribution classes. This loss treats open-set noisy samples as an extended class, improving label noise mitigation by weighting contrastive pairs according to label reliability. Additionally, we develop the Open-set Feature Augmentation module that enriches open-set samples at the feature level and then assigns them dynamic class labels, thereby leveraging the model's capacity and reducing overfitting to noisy data. We evaluated the proposed framework on both a synthetic noisy dataset and a real-world noisy dataset. The results indicate the superiority of our framework over four existing methods and the effectiveness of leveraging open-set noisy samples to combat label noise.
Authors: Panwang Pan, Zhuo Su, Chenguo Lin, Zhen Fan, Yongjie Zhang, Zeming Li, Tingting Shen, Yadong Mu, Yebin Liu
Abstract: Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.
Authors: Ning-Hsu Wang, Yu-Lun Liu
Abstract: Accurately estimating depth in 360-degree imagery is crucial for virtual reality, autonomous navigation, and immersive media applications. Existing depth estimation methods designed for perspective-view imagery fail when applied to 360-degree images due to different camera projections and distortions, whereas 360-degree methods perform inferior due to the lack of labeled data pairs. We propose a new depth estimation framework that utilizes unlabeled 360-degree data effectively. Our approach uses state-of-the-art perspective depth estimation models as teacher models to generate pseudo labels through a six-face cube projection technique, enabling efficient labeling of depth in 360-degree images. This method leverages the increasing availability of large datasets. Our approach includes two main stages: offline mask generation for invalid regions and an online semi-supervised joint training regime. We tested our approach on benchmark datasets such as Matterport3D and Stanford2D3D, showing significant improvements in depth estimation accuracy, particularly in zero-shot scenarios. Our proposed training pipeline can enhance any 360 monocular depth estimator and demonstrates effective knowledge transfer across different camera projections and data types. See our project page for results: https://albert100121.github.io/Depth-Anywhere/
Authors: Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Baizhou Huang, Xu Zhang, Xinyu Hu, Xiaojun Wan
Abstract: Multimodal large language models (MLLMs) are prone to non-factual or outdated knowledge issues, which can manifest as misreading and misrecognition errors due to the complexity of multimodal knowledge. Previous benchmarks have not systematically analyzed the performance of editing methods in correcting these two error types. To better represent and correct these errors, we decompose multimodal knowledge into its visual and textual components. Different error types correspond to different editing formats, which edit distinct parts of the multimodal knowledge. We present MC-MKE, a fine-grained Multimodal Knowledge Editing benchmark emphasizing Modality Consistency. Our benchmark facilitates independent correction of misreading and misrecognition errors by editing the corresponding knowledge component. We evaluate four multimodal knowledge editing methods on MC-MKE, revealing their limitations, particularly in terms of modality consistency. Our work highlights the challenges posed by multimodal knowledge editing and motivates further research in developing effective techniques for this task.
Authors: Xinyu Fang, Kangrui Mao, Haodong Duan, Xiangyu Zhao, Yining Li, Dahua Lin, Kai Chen
Abstract: The advent of large vision-language models (LVLMs) has spurred research into their applications in multi-modal contexts, particularly in video understanding. Traditional VideoQA benchmarks, despite providing quantitative metrics, often fail to encompass the full spectrum of video content and inadequately assess models' temporal comprehension. To address these limitations, we introduce MMBench-Video, a quantitative benchmark designed to rigorously evaluate LVLMs' proficiency in video understanding. MMBench-Video incorporates lengthy videos from YouTube and employs free-form questions, mirroring practical use cases. The benchmark is meticulously crafted to probe the models' temporal reasoning skills, with all questions human-annotated according to a carefully constructed ability taxonomy. We employ GPT-4 for automated assessment, demonstrating superior accuracy and robustness over earlier LLM-based evaluations. Utilizing MMBench-Video, we have conducted comprehensive evaluations that include both proprietary and open-source LVLMs for images and videos. MMBench-Video stands as a valuable resource for the research community, facilitating improved evaluation of LVLMs and catalyzing progress in the field of video understanding. The evalutation code of MMBench-Video will be integrated into VLMEvalKit: https://github.com/open-compass/VLMEvalKit.
Authors: Runzhao Yao, Shaoyi Du, Wenting Cui, Canhui Tang, Chengwu Yang
Abstract: Learning rotation-invariant distinctive features is a fundamental requirement for point cloud registration. Existing methods often use rotation-sensitive networks to extract features, while employing rotation augmentation to learn an approximate invariant mapping rudely. This makes networks fragile to rotations, overweight, and hinders the distinctiveness of features. To tackle these problems, we propose a novel position-aware rotation-equivariant network, for efficient, light-weighted, and robust registration. The network can provide a strong model inductive bias to learn rotation-equivariant/invariant features, thus addressing the aforementioned limitations. To further improve the distinctiveness of descriptors, we propose a position-aware convolution, which can better learn spatial information of local structures. Moreover, we also propose a feature-based hypothesis proposer. It leverages rotation-equivariant features that encode fine-grained structure orientations to generate reliable model hypotheses. Each correspondence can generate a hypothesis, thus it is more efficient than classic estimators that require multiple reliable correspondences. Accordingly, a contrastive rotation loss is presented to enhance the robustness of rotation-equivariant features against data degradation. Extensive experiments on indoor and outdoor datasets demonstrate that our method significantly outperforms the SOTA methods in terms of registration recall while being lightweight and keeping a fast speed. Moreover, experiments on rotated datasets demonstrate its robustness against rotation variations. Code is available at https://github.com/yaorz97/PARENet.
Authors: Xiaoqing Guo, Qianhui Men, J. Alison Noble
Abstract: We present the first automated multimodal summary generation system, MMSummary, for medical imaging video, particularly with a focus on fetal ultrasound analysis. Imitating the examination process performed by a human sonographer, MMSummary is designed as a three-stage pipeline, progressing from keyframe detection to keyframe captioning and finally anatomy segmentation and measurement. In the keyframe detection stage, an innovative automated workflow is proposed to progressively select a concise set of keyframes, preserving sufficient video information without redundancy. Subsequently, we adapt a large language model to generate meaningful captions for fetal ultrasound keyframes in the keyframe captioning stage. If a keyframe is captioned as fetal biometry, the segmentation and measurement stage estimates biometric parameters by segmenting the region of interest according to the textual prior. The MMSummary system provides comprehensive summaries for fetal ultrasound examinations and based on reported experiments is estimated to reduce scanning time by approximately 31.5%, thereby suggesting the potential to enhance clinical workflow efficiency.
Authors: Yizhang Jin, Jian Li, Jiangning Zhang, Jianlong Hu, Zhenye Gan, Xin Tan, Yong Liu, Yabiao Wang, Chengjie Wang, Lizhuang Ma
Abstract: Visual Spatial Description (VSD) aims to generate texts that describe the spatial relationships between objects within images. Traditional visual spatial relationship classification (VSRC) methods typically output the spatial relationship between two objects in an image, often neglecting world knowledge and lacking general language capabilities. In this paper, we propose a Large Language-and-Vision Assistant for Visual Spatial Description, named LLaVA-VSD, which is designed for the classification, description, and open-ended description of visual spatial relationships. Specifically, the model first constructs a VSD instruction-following dataset using given figure-caption pairs for the three tasks. It then employs LoRA to fine-tune a Large Language and Vision Assistant for VSD, which has 13 billion parameters and supports high-resolution images. Finally, a large language model (Qwen-2) is used to refine the generated sentences, enhancing their diversity and accuracy. LLaVA-VSD demonstrates excellent multimodal conversational capabilities and can follow open-ended instructions to assist with inquiries about object relationships in images.
Authors: Chenqian Yan, Songwei Liu, Hongjian Liu, Xurui Peng, Xiaojian Wang, Fangmin Chen, Lean Fu, Xing Mei
Abstract: Stable Diffusion Models (SDMs) have shown remarkable proficiency in image synthesis. However, their broad application is impeded by their large model sizes and intensive computational requirements, which typically require expensive cloud servers for deployment. On the flip side, while there are many compact models tailored for edge devices that can reduce these demands, they often compromise on semantic integrity and visual quality when compared to full-sized SDMs. To bridge this gap, we introduce Hybrid SD, an innovative, training-free SDMs inference framework designed for edge-cloud collaborative inference. Hybrid SD distributes the early steps of the diffusion process to the large models deployed on cloud servers, enhancing semantic planning. Furthermore, small efficient models deployed on edge devices can be integrated for refining visual details in the later stages. Acknowledging the diversity of edge devices with differing computational and storage capacities, we employ structural pruning to the SDMs U-Net and train a lightweight VAE. Empirical evaluations demonstrate that our compressed models achieve state-of-the-art parameter efficiency (225.8M) on edge devices with competitive image quality. Additionally, Hybrid SD reduces the cloud cost by 66% with edge-cloud collaborative inference.
Authors: Liang Geng
Abstract: Apples growing in natural environments often face severe visual obstructions from leaves and branches. This significantly increases the risk of false detections in object detection tasks, thereby escalating the challenge. Addressing this issue, we introduce a technique called "Occlusion-Enhanced Distillation" (OED). This approach utilizes occlusion information to regularize the learning of semantically aligned features on occluded datasets and employs Exponential Moving Average (EMA) to enhance training stability. Specifically, we first design an occlusion-enhanced dataset that integrates Grounding DINO and SAM methods to extract occluding elements such as leaves and branches from each sample, creating occlusion examples that reflect the natural growth state of fruits. Additionally, we propose a multi-scale knowledge distillation strategy, where the student network uses images with increased occlusions as inputs, while the teacher network employs images without natural occlusions. Through this setup, the strategy guides the student network to learn from the teacher across scales of semantic and local features alignment, effectively narrowing the feature distance between occluded and non-occluded targets and enhancing the robustness of object detection. Lastly, to improve the stability of the student network, we introduce the EMA strategy, which aids the student network in learning more generalized feature expressions that are less affected by the noise of individual image occlusions. Our method significantly outperforms current state-of-the-art techniques through extensive comparative experiments.
Authors: Victor Rong, Jingxiang Chen, Sherwin Bahmani, Kiriakos N. Kutulakos, David B. Lindell
Abstract: Gaussian splatting has demonstrated excellent performance for view synthesis and scene reconstruction. The representation achieves photorealistic quality by optimizing the position, scale, color, and opacity of thousands to millions of 2D or 3D Gaussian primitives within a scene. However, since each Gaussian primitive encodes both appearance and geometry, these attributes are strongly coupled--thus, high-fidelity appearance modeling requires a large number of Gaussian primitives, even when the scene geometry is simple (e.g., for a textured planar surface). We propose to texture each 2D Gaussian primitive so that even a single Gaussian can be used to capture appearance details. By employing per-primitive texturing, our appearance representation is agnostic to the topology and complexity of the scene's geometry. We show that our approach, GStex, yields improved visual quality over prior work in texturing Gaussian splats. Furthermore, we demonstrate that our decoupling enables improved novel view synthesis performance compared to 2D Gaussian splatting when reducing the number of Gaussian primitives, and that GStex can be used for scene appearance editing and re-texturing.
Authors: Yifan Duan, Jian Zhao, pengcheng, Junyuan Mao, Hao Wu, Jingyu Xu, Shilong Wang, Caoyuan Ma, Kai Wang, Kun Wang, Xuelong Li
Abstract: Spatio-temporal (ST) prediction has garnered a De facto attention in earth sciences, such as meteorological prediction, human mobility perception. However, the scarcity of data coupled with the high expenses involved in sensor deployment results in notable data imbalances. Furthermore, models that are excessively customized and devoid of causal connections further undermine the generalizability and interpretability. To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process. Going beyond this process, we utilize the back-door adjustment to specifically address the sub-regions identified as non-causal in the upstream phase. Specifically, we employ a novel image inpainting technique. By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts, offering the possibility of reliable extrapolation for potential data distributions. CaPaint overcomes the high complexity dilemma of optimal ST causal discovery models by reducing the data generation complexity from exponential to quasi-linear levels. Extensive experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%. Moreover, compared to traditional mainstream ST augmenters, CaPaint underscores the potential of diffusion models in ST enhancement, offering a novel paradigm for this field. Our project is available at https://anonymous.4open.science/r/12345-DFCC.
Authors: Nishq Poorav Desai, Ali Etemad, Michael Greenspan
Abstract: Self-driving research often underrepresents cyclist collisions and safety. To address this, we present CycleCrash, a novel dataset consisting of 3,000 dashcam videos with 436,347 frames that capture cyclists in a range of critical situations, from collisions to safe interactions. This dataset enables 9 different cyclist collision prediction and classification tasks focusing on potentially hazardous conditions for cyclists and is annotated with collision-related, cyclist-related, and scene-related labels. Next, we propose VidNeXt, a novel method that leverages a ConvNeXt spatial encoder and a non-stationary transformer to capture the temporal dynamics of videos for the tasks defined in our dataset. To demonstrate the effectiveness of our method and create additional baselines on CycleCrash, we apply and compare 7 models along with a detailed ablation. We release the dataset and code at https://github.com/DeSinister/CycleCrash/ .
Authors: Niki Maria Foteinopoulou, Enjie Ghorbel, Djamila Aouada
Abstract: Explainability in artificial intelligence is crucial for restoring trust, particularly in areas like face forgery detection, where viewers often struggle to distinguish between real and fabricated content. Vision and Large Language Models (VLLM) bridge computer vision and natural language, offering numerous applications driven by strong common-sense reasoning. Despite their success in various tasks, the potential of vision and language remains underexplored in face forgery detection, where they hold promise for enhancing explainability by leveraging the intrinsic reasoning capabilities of language to analyse fine-grained manipulation areas. As such, there is a need for a methodology that converts face forgery detection to a Visual Question Answering (VQA) task to systematically and fairly evaluate these capabilities. Previous efforts for unified benchmarks in deepfake detection have focused on the simpler binary task, overlooking evaluation protocols for fine-grained detection and text-generative models. We propose a multi-staged approach that diverges from the traditional binary decision paradigm to address this gap. In the first stage, we assess the models' performance on the binary task and their sensitivity to given instructions using several prompts. In the second stage, we delve deeper into fine-grained detection by identifying areas of manipulation in a multiple-choice VQA setting. In the third stage, we convert the fine-grained detection to an open-ended question and compare several matching strategies for the multi-label classification task. Finally, we qualitatively evaluate the fine-grained responses of the VLLMs included in the benchmark. We apply our benchmark to several popular models, providing a detailed comparison of binary, multiple-choice, and open-ended VQA evaluation across seven datasets. \url{https://nickyfot.github.io/hitchhickersguide.github.io/}
URLs: https://nickyfot.github.io/hitchhickersguide.github.io/
Authors: Alexander Mai, Peter Hedman, George Kopanas, Dor Verbin, David Futschik, Qiangeng Xu, Falko Kuester, Jonathan T. Barron, Yinda Zhang
Abstract: We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering. Unlike recent rasterization based approach by 3D Gaussian Splatting (3DGS), our primitive based representation allows for exact volume rendering, rather than alpha compositing 3D Gaussian billboards. As such, unlike 3DGS our formulation does not suffer from popping artifacts and view dependent density, but still achieves frame rates of $\sim\!30$ FPS at 720p on an NVIDIA RTX4090. Since our approach is built upon ray tracing it enables effects such as defocus blur and camera distortion (e.g. such as from fisheye cameras), which are difficult to achieve by rasterization. We show that our method is more accurate with fewer blending issues than 3DGS and follow-up work on view-consistent rendering, especially on the challenging large-scale scenes from the Zip-NeRF dataset where it achieves sharpest results among real-time techniques.
Authors: Lu Chen, Yingfu Zeng, Haoang Li, Zhitao Deng, Jiafu Yan, Zhenjun Zhao
Abstract: Accurate and affordable indoor 3D reconstruction is critical for effective robot navigation and interaction. Traditional LiDAR-based mapping provides high precision but is costly, heavy, and power-intensive, with limited ability for novel view rendering. Vision-based mapping, while cost-effective and capable of capturing visual data, often struggles with high-quality 3D reconstruction due to sparse point clouds. We propose ES-Gaussian, an end-to-end system using a low-altitude camera and single-line LiDAR for high-quality 3D indoor reconstruction. Our system features Visual Error Construction (VEC) to enhance sparse point clouds by identifying and correcting areas with insufficient geometric detail from 2D error maps. Additionally, we introduce a novel 3DGS initialization method guided by single-line LiDAR, overcoming the limitations of traditional multi-view setups and enabling effective reconstruction in resource-constrained environments. Extensive experimental results on our new Dreame-SR dataset and a publicly available dataset demonstrate that ES-Gaussian outperforms existing methods, particularly in challenging scenarios. The project page is available at https://chenlu-china.github.io/ES-Gaussian/.
Authors: Ruiqi Liu, Boyu Diao, Libo Huang, Zijia An, Zhulin An, Yongjun Xu
Abstract: Continual learning (CL) is designed to learn new tasks while preserving existing knowledge. Replaying samples from earlier tasks has proven to be an effective method to mitigate the forgetting of previously acquired knowledge. However, the current research on the training efficiency of rehearsal-based methods is insufficient, which limits the practical application of CL systems in resource-limited scenarios. The human visual system (HVS) exhibits varying sensitivities to different frequency components, enabling the efficient elimination of visually redundant information. Inspired by HVS, we propose a novel framework called Continual Learning in the Frequency Domain (CLFD). To our knowledge, this is the first study to utilize frequency domain features to enhance the performance and efficiency of CL training on edge devices. For the input features of the feature extractor, CLFD employs wavelet transform to map the original input image into the frequency domain, thereby effectively reducing the size of input feature maps. Regarding the output features of the feature extractor, CLFD selectively utilizes output features for distinct classes for classification, thereby balancing the reusability and interference of output features based on the frequency domain similarity of the classes across various tasks. Optimizing only the input and output features of the feature extractor allows for seamless integration of CLFD with various rehearsal-based methods. Extensive experiments conducted in both cloud and edge environments demonstrate that CLFD consistently improves the performance of state-of-the-art (SOTA) methods in both precision and training efficiency. Specifically, CLFD can increase the accuracy of the SOTA CL method by up to 6.83% and reduce the training time by 2.6$\times$.
Authors: Zhengyang Yu, Zhaoyuan Yang, Jing Zhang
Abstract: Recent text-to-image personalization methods have shown great promise in teaching a diffusion model user-specified concepts given a few images for reusing the acquired concepts in a novel context. With massive efforts being dedicated to personalized generation, a promising extension is personalized editing, namely to edit an image using personalized concepts, which can provide a more precise guidance signal than traditional textual guidance. To address this, a straightforward solution is to incorporate a personalized diffusion model with a text-driven editing framework. However, such a solution often shows unsatisfactory editability on the source image. To address this, we propose DreamSteerer, a plug-in method for augmenting existing T2I personalization methods. Specifically, we enhance the source image conditioned editability of a personalized diffusion model via a novel Editability Driven Score Distillation (EDSD) objective. Moreover, we identify a mode trapping issue with EDSD, and propose a mode shifting regularization with spatial feature guided sampling to avoid such an issue. We further employ two key modifications to the Delta Denoising Score framework that enable high-fidelity local editing with personalized concepts. Extensive experiments validate that DreamSteerer can significantly improve the editability of several T2I personalization baselines while being computationally efficient.
Authors: Zhengxue Wang, Zhiqiang Yan, Jinshan Pan, Guangwei Gao, Kai Zhang, Jian Yang
Abstract: Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from unconventional and unknown degradation due to sensor limitations and complex imaging environments (e.g., low reflective surfaces, varying illumination). Consequently, the performance of these methods significantly declines when real-world degradation deviate from their assumptions. In this paper, we propose the Degradation Oriented and Regularized Network (DORNet), a novel framework designed to adaptively address unknown degradation in real-world scenes through implicit degradation representations. Our approach begins with the development of a self-supervised degradation learning strategy, which models the degradation representations of low-resolution depth data using routing selection-based degradation regularization. To facilitate effective RGB-D fusion, we further introduce a degradation-oriented feature transformation module that selectively propagates RGB content into the depth data based on the learned degradation priors. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our DORNet. The code is available at https://github.com/yanzq95/DORNet.
Authors: Jiayi Liu, Denys Iliash, Angel X. Chang, Manolis Savva, Ali Mahdavi-Amiri
Abstract: We address the challenge of creating 3D assets for household articulated objects from a single image. Prior work on articulated object creation either requires multi-view multi-state input, or only allows coarse control over the generation process. These limitations hinder the scalability and practicality for articulated object modeling. In this work, we propose a method to generate articulated objects from a single image. Observing the object in resting state from an arbitrary view, our method generates an articulated object that is visually consistent with the input image. To capture the ambiguity in part shape and motion posed by a single view of the object, we design a diffusion model that learns the plausible variations of objects in terms of geometry and kinematics. To tackle the complexity of generating structured data with attributes in multiple domains, we design a pipeline that produces articulated objects from high-level structure to geometric details in a coarse-to-fine manner, where we use a part connectivity graph and part abstraction as proxies. Our experiments show that our method outperforms the state-of-the-art in articulated object creation by a large margin in terms of the generated object realism, resemblance to the input image, and reconstruction quality.
Authors: Yousef Yeganeh, Rachmadio Lazuardi, Amir Shamseddin, Emine Dari, Yash Thirani, Nassir Navab, Azade Farshad
Abstract: Surgical data science (SDS) is a field that analyzes patient data before, during, and after surgery to improve surgical outcomes and skills. However, surgical data is scarce, heterogeneous, and complex, which limits the applicability of existing machine learning methods. In this work, we introduce the novel task of future video generation in laparoscopic surgery. This task can augment and enrich the existing surgical data and enable various applications, such as simulation, analysis, and robot-aided surgery. Ultimately, it involves not only understanding the current state of the operation but also accurately predicting the dynamic and often unpredictable nature of surgical procedures. Our proposed method, VISAGE (VIdeo Synthesis using Action Graphs for Surgery), leverages the power of action scene graphs to capture the sequential nature of laparoscopic procedures and utilizes diffusion models to synthesize temporally coherent video sequences. VISAGE predicts the future frames given only a single initial frame, and the action graph triplets. By incorporating domain-specific knowledge through the action graph, VISAGE ensures the generated videos adhere to the expected visual and motion patterns observed in real laparoscopic procedures. The results of our experiments demonstrate high-fidelity video generation for laparoscopy procedures, which enables various applications in SDS.
Authors: Shyamgopal Karthik, Huseyin Coskun, Zeynep Akata, Sergey Tulyakov, Jian Ren, Anil Kag
Abstract: Direct Preference Optimization (DPO) has emerged as a powerful approach to align text-to-image (T2I) models with human feedback. Unfortunately, successful application of DPO to T2I models requires a huge amount of resources to collect and label large-scale datasets, e.g., millions of generated paired images annotated with human preferences. In addition, these human preference datasets can get outdated quickly as the rapid improvements of T2I models lead to higher quality images. In this work, we investigate a scalable approach for collecting large-scale and fully synthetic datasets for DPO training. Specifically, the preferences for paired images are generated using a pre-trained reward function, eliminating the need for involving humans in the annotation process, greatly improving the dataset collection efficiency. Moreover, we demonstrate that such datasets allow averaging predictions across multiple models and collecting ranked preferences as opposed to pairwise preferences. Furthermore, we introduce RankDPO to enhance DPO-based methods using the ranking feedback. Applying RankDPO on SDXL and SD3-Medium models with our synthetically generated preference dataset "Syn-Pic" improves both prompt-following (on benchmarks like T2I-Compbench, GenEval, and DPG-Bench) and visual quality (through user studies). This pipeline presents a practical and scalable solution to develop better preference datasets to enhance the performance of text-to-image models.
Authors: Jialu Li, Yuanzhen Li, Neal Wadhwa, Yael Pritch, David E. Jacobs, Michael Rubinstein, Mohit Bansal, Nataniel Ruiz
Abstract: We introduce the concept of a generative infinite game, a video game that transcends the traditional boundaries of finite, hard-coded systems by using generative models. Inspired by James P. Carse's distinction between finite and infinite games, we leverage recent advances in generative AI to create Unbounded: a game of character life simulation that is fully encapsulated in generative models. Specifically, Unbounded draws inspiration from sandbox life simulations and allows you to interact with your autonomous virtual character in a virtual world by feeding, playing with and guiding it - with open-ended mechanics generated by an LLM, some of which can be emergent. In order to develop Unbounded, we propose technical innovations in both the LLM and visual generation domains. Specifically, we present: (1) a specialized, distilled large language model (LLM) that dynamically generates game mechanics, narratives, and character interactions in real-time, and (2) a new dynamic regional image prompt Adapter (IP-Adapter) for vision models that ensures consistent yet flexible visual generation of a character across multiple environments. We evaluate our system through both qualitative and quantitative analysis, showing significant improvements in character life simulation, user instruction following, narrative coherence, and visual consistency for both characters and the environments compared to traditional related approaches.
Authors: Junsheng Zhou, Weiqi Zhang, Yu-Shen Liu
Abstract: 3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness and unstructured nature. In this work, we propose DiffGS, a general Gaussian generator based on latent diffusion models. DiffGS is a powerful and efficient 3D generative model which is capable of generating Gaussian primitives at arbitrary numbers for high-fidelity rendering with rasterization. The key insight is to represent Gaussian Splatting in a disentangled manner via three novel functions to model Gaussian probabilities, colors and transforms. Through the novel disentanglement of 3DGS, we represent the discrete and unstructured 3DGS with continuous Gaussian Splatting functions, where we then train a latent diffusion model with the target of generating these Gaussian Splatting functions both unconditionally and conditionally. Meanwhile, we introduce a discretization algorithm to extract Gaussians at arbitrary numbers from the generated functions via octree-guided sampling and optimization. We explore DiffGS for various tasks, including unconditional generation, conditional generation from text, image, and partial 3DGS, as well as Point-to-Gaussian generation. We believe that DiffGS provides a new direction for flexibly modeling and generating Gaussian Splatting.
Authors: Akhilbaran Ghosh, Rama Sai Adithya Kalidindi
Abstract: Optimization is critical for optimal performance in deep neural networks (DNNs). Traditional gradient-based methods often face challenges like local minima entrapment. This paper explores population-based metaheuristic optimization algorithms for image classification networks. We propose a novel approach integrating a two-stage training technique with population-based optimization algorithms incorporating local search capabilities. Our experiments demonstrate that the proposed method outperforms state-of-the-art gradient-based techniques, such as ADAM, in accuracy and computational efficiency, particularly with high computational complexity and numerous trainable parameters. The results suggest that our approach offers a robust alternative to traditional methods for weight optimization in convolutional neural networks (CNNs). Future work will explore integrating adaptive mechanisms for parameter tuning and applying the proposed method to other types of neural networks and real-time applications.
Authors: Wei-Yi Chen, Yi-Ling Lin, Yu-An Su, Wei-Hsin Yeh, Lun-Wei Ku
Abstract: Combining sports and machine learning involves leveraging ML algorithms and techniques to extract insight from sports-related data such as player statistics, game footage, and other relevant information. However, datasets related to figure skating in the literature focus primarily on element classification and are currently unavailable or exhibit only limited access, which greatly raise the entry barrier to developing visual sports technology for it. Moreover, when using such data to help athletes improve their skills, we find they are very coarse-grained: they work for learning what an element is, but they are poorly suited to learning whether the element is good or bad. Here we propose air time detection, a novel motion analysis task, the goal of which is to accurately detect the duration of the air time of a jump. We present YourSkatingCoach, a large, novel figure skating dataset which contains 454 videos of jump elements, the detected skater skeletons in each video, along with the gold labels of the start and ending frames of each jump, together as a video benchmark for figure skating. In addition, although this type of task is often viewed as classification, we cast it as a sequential labeling problem and propose a Transformer-based model to calculate the duration. Experimental results show that the proposed model yields a favorable results for a strong baseline. To further verify the generalizability of the fine-grained labels, we apply the same process to other sports as cross-sports tasks but for coarse-grained task action classification. Here we fine-tune the classification to demonstrate that figure skating, as it contains the essential body movements, constitutes a strong foundation for adaptation to other sports.
Authors: ZhenXing Dong, JiaZhou Chen, YangHui Xu
Abstract: The planning of digital orthodontic treatment requires providing tooth alignment, which not only consumes a lot of time and labor to determine manually but also relays clinical experiences heavily. In this work, we proposed a lightweight tooth alignment neural network based on Swin-transformer. We first re-organized 3D point clouds based on virtual arch lines and converted them into order-sorted multi-channel textures, which improves the accuracy and efficiency simultaneously. We then designed two new occlusal loss functions that quantitatively evaluate the occlusal relationship between the upper and lower jaws. They are important clinical constraints, first introduced to the best of our knowledge, and lead to cutting-edge prediction accuracy. To train our network, we collected a large digital orthodontic dataset that has 591 clinical cases, including various complex clinical cases. This dataset will benefit the community after its release since there is no open dataset so far. Furthermore, we also proposed two new orthodontic dataset augmentation methods considering tooth spatial distribution and occlusion. We evaluated our method with this dataset and extensive experiments, including comparisons with STAT methods and ablation studies, and demonstrate the high prediction accuracy of our method.
Authors: Gaurav Hirani, Waleed Abdulla
Abstract: The deep convolutional neural network (DCNN) in computer vision has given promising results. It is widely applied in many areas, from medicine, agriculture, self-driving car, biometric system, and almost all computer vision-based applications. Filters or weights are the critical elements responsible for learning in DCNN. Backpropagation has been the primary learning algorithm for DCNN and provides promising results, but the size and numbers of the filters remain hyper-parameters. Various studies have been done in the last decade on semi-supervised, self-supervised, and unsupervised methods and their properties. The effects of filter initialization, size-shape selection, and the number of filters on learning and optimization have not been investigated in a separate publication to collate all the options. Such attributes are often treated as hyper-parameters and lack mathematical understanding. Computer vision algorithms have many limitations in real-life applications, and understanding the learning process is essential to have some significant improvement. To the best of our knowledge, no separate investigation has been published discussing the filters; this is our primary motivation. This study focuses on arguments for choosing specific physical parameters of filters, initialization, and learning technic over scattered methods. The promising unsupervised approaches have been evaluated. Additionally, the limitations, current challenges, and future scope have been discussed in this paper.
Authors: Hang Guo, Yawei Li, Tao Dai, Shu-Tao Xia, Luca Benini
Abstract: Fine-tuning large-scale text-to-image diffusion models for various downstream tasks has yielded impressive results. However, the heavy computational burdens of tuning large models prevent personal customization. Recent advances have attempted to employ parameter-efficient fine-tuning (PEFT) techniques to adapt the floating-point (FP) or quantized pre-trained weights. Nonetheless, the adaptation parameters in existing works are still restricted to FP arithmetic, hindering hardware-friendly acceleration. In this work, we propose IntLoRA, to further push the efficiency limits by using integer type (INT) low-rank parameters to adapt the quantized diffusion models. By working in the integer arithmetic, our IntLoRA offers three key advantages: (i) for fine-tuning, the pre-trained weights are quantized, reducing memory usage; (ii) for storage, both pre-trained and low-rank weights are in INT which consumes less disk space; (iii) for inference, IntLoRA weights can be naturally merged into quantized pre-trained weights through efficient integer multiplication or bit-shifting, eliminating additional post-training quantization. Extensive experiments demonstrate that IntLoRA can achieve performance on par with or even superior to the vanilla LoRA, accompanied by significant efficiency improvements. Code is available at \url{https://github.com/csguoh/IntLoRA}.
Authors: Lu Yu, Haiyang Zhang, Changsheng Xu
Abstract: Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: the Attention Refinement module and the Attention-based Model Constraint module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness: The Attention Refinement module aligns the text-guided attention obtained from the target model via adversarial examples with the text-guided attention acquired from the original model via clean examples. This alignment enhances the model's robustness. Additionally, the Attention-based Model Constraint module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. The experiments validate that our method yields a 9.58% enhancement in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets. Our code is available at https://github.com/zhyblue424/TGA-ZSR.
Authors: Zhong Ji, Shuo Yang, Jingren Liu, Yanwei Pang, Jungong Han
Abstract: Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data. However, current approaches inadequately address the intrinsic optimization of the co-occurrence matrix $\bar{A}$ based on cosine similarity, failing to achieve zero base-novel regions and adequate sparsity in base and novel domains. To address these deficiencies, we propose a Non-Negative Generalized Category Discovery (NN-GCD) framework. It employs Symmetric Non-negative Matrix Factorization (SNMF) as a mathematical medium to prove the equivalence of optimal K-means with optimal SNMF, and the equivalence of SNMF solver with non-negative contrastive learning (NCL) optimization. Utilizing these theoretical equivalences, it reframes the optimization of $\bar{A}$ and K-means clustering as an NCL optimization problem. Moreover, to satisfy the non-negative constraints and make a GCD model converge to a near-optimal region, we propose a GELU activation function and an NMF NCE loss. To transition $\bar{A}$ from a suboptimal state to the desired $\bar{A}^*$, we introduce a hybrid sparse regularization approach to impose sparsity constraints. Experimental results show NN-GCD outperforms state-of-the-art methods on GCD benchmarks, achieving an average accuracy of 66.1\% on the Semantic Shift Benchmark, surpassing prior counterparts by 4.7\%.
Authors: Shaokai Li, Yixuan Ji, Peng Song, Haoqin Sun, Wenming Zheng
Abstract: In this paper, we propose a novel deep inductive transfer learning framework, named feature distribution adaptation network, to tackle the challenging multi-modal speech emotion recognition problem. Our method aims to use deep transfer learning strategies to align visual and audio feature distributions to obtain consistent representation of emotion, thereby improving the performance of speech emotion recognition. In our model, the pre-trained ResNet-34 is utilized for feature extraction for facial expression images and acoustic Mel spectrograms, respectively. Then, the cross-attention mechanism is introduced to model the intrinsic similarity relationships of multi-modal features. Finally, the multi-modal feature distribution adaptation is performed efficiently with feed-forward network, which is extended using the local maximum mean discrepancy loss. Experiments are carried out on two benchmark datasets, and the results demonstrate that our model can achieve excellent performance compared with existing ones.
Authors: Shenghao Xie, Wenqiang Zu, Mingyang Zhao, Duo Su, Shilong Liu, Ruohua Shi, Guoqi Li, Shanghang Zhang, Lei Ma
Abstract: Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing interest in extending this success to vision foundation models. In this survey, we review the recent advances and discuss future directions for autoregressive vision foundation models. First, we present the trend for next generation of vision foundation models, i.e., unifying both understanding and generation in vision tasks. We then analyze the limitations of existing vision foundation models, and present a formal definition of autoregression with its advantages. Later, we categorize autoregressive vision foundation models from their vision tokenizers and autoregression backbones. Finally, we discuss several promising research challenges and directions. To the best of our knowledge, this is the first survey to comprehensively summarize autoregressive vision foundation models under the trend of unifying understanding and generation. A collection of related resources is available at https://github.com/EmmaSRH/ARVFM.
Authors: Hao Chen, Ankit Shah, Jindong Wang, Ran Tao, Yidong Wang, Xing Xie, Masashi Sugiyama, Rita Singh, Bhiksha Raj
Abstract: Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning tasks. Previous methods tend to propose specific designs for every emerging imprecise label configuration, which is usually unsustainable when multiple configurations of imprecision coexist. In this paper, we introduce imprecise label learning (ILL), a framework for the unification of learning with various imprecise label configurations. ILL leverages expectation-maximization (EM) for modeling the imprecise label information, treating the precise labels as latent variables.Instead of approximating the correct labels for training, it considers the entire distribution of all possible labeling entailed by the imprecise information. We demonstrate that ILL can seamlessly adapt to partial label learning, semi-supervised learning, noisy label learning, and, more importantly, a mixture of these settings. Notably, ILL surpasses the existing specified techniques for handling imprecise labels, marking the first unified framework with robust and effective performance across various challenging settings. We hope our work will inspire further research on this topic, unleashing the full potential of ILL in wider scenarios where precise labels are expensive and complicated to obtain.
Authors: Jingbiao Mei, Jinghong Chen, Weizhe Lin, Bill Byrne, Marcus Tomalin
Abstract: Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our investigation reveals that the embedding space of existing CLIP-based systems lacks sensitivity to subtle differences in memes that are vital for correct hatefulness classification. We propose constructing a hatefulness-aware embedding space through retrieval-guided contrastive training. Our approach achieves state-of-the-art performance on the HatefulMemes dataset with an AUROC of 87.0, outperforming much larger fine-tuned large multimodal models. We demonstrate a retrieval-based hateful memes detection system, which is capable of identifying hatefulness based on data unseen in training. This allows developers to update the hateful memes detection system by simply adding new examples without retraining, a desirable feature for real services in the constantly evolving landscape of hateful memes on the Internet.
Authors: Qixiang Ma, Antoine {\L}ucas, Huazhong Shu, Adrien Kaladji, Pascal Haigron
Abstract: Deep-learning-based automated segmentation of vascular structures in preoperative CT scans contributes to computer-assisted diagnosis and intervention procedure in vascular diseases. While CT angiography (CTA) is the common standard, non-contrast CT imaging is significant as a contrast-risk-free alternative, avoiding complications associated with contrast agents. However, the challenges of labor-intensive labeling and high labeling variability due to the ambiguity of vascular boundaries hinder conventional strong-label-based, fully-supervised learning in non-contrast CTs. This paper introduces a weakly-supervised framework using ellipses' topology in slices, including 1) an efficient annotation process based on predefined standards, 2) ellipse-fitting processing, 3) the generation of 2D Gaussian heatmaps serving as pseudo labels, 4) a training process through a combination of voxel reconstruction loss and distribution loss with the pseudo labels. We assess the effectiveness of the proposed method on one local and two public datasets comprising non-contrast CT scans, particularly focusing on the abdominal aorta. On the local dataset, our weakly-supervised learning approach based on pseudo labels outperforms strong-label-based fully-supervised learning (1.54\% of Dice score on average), reducing labeling time by around 82.0\%. The efficiency in generating pseudo labels allows the inclusion of label-agnostic external data in the training set, leading to an additional improvement in performance (2.74\% of Dice score on average) with a reduction of 66.3\% labeling time, where the labeling time remains considerably less than that of strong labels. On the public dataset, the pseudo labels achieve an overall improvement of 1.95\% in Dice score for 2D models while a reduction of 11.65 voxel spacing in Hausdorff distance for 3D model.
Authors: Bryan Bo Cao, Abhinav Sharma, Lawrence O'Gorman, Michael Coss, Shubham Jain
Abstract: Although accuracy and computation benchmarks are widely available to help choose among neural network models, these are usually trained on datasets with many classes, and do not give a good idea of performance for few (< 10) classes. The conventional procedure to predict performance involves repeated training and testing on the different models and dataset variations. We propose an efficient cosine similarity-based classification difficulty measure S that is calculated from the number of classes and intra- and inter-class similarity metrics of the dataset. After a single stage of training and testing per model family, relative performance for different datasets and models of the same family can be predicted by comparing difficulty measures - without further training and testing. Our proposed method is verified by extensive experiments on 8 CNN and ViT models and 7 datasets. Results show that S is highly correlated to model accuracy with correlation coefficient |r| = 0.796, outperforming the baseline Euclidean distance at |r| = 0.66. We show how a practitioner can use this measure to help select an efficient model 6 to 29x faster than through repeated training and testing. We also describe using the measure for an industrial application in which options are identified to select a model 42% smaller than the baseline YOLOv5-nano model, and if class merging from 3 to 2 classes meets requirements, 85% smaller.
Authors: Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos Storkey, Tim Pearce, Fran\c{c}ois Fleuret
Abstract: World models constitute a promising approach for training reinforcement learning agents in a safe and sample-efficient manner. Recent world models predominantly operate on sequences of discrete latent variables to model environment dynamics. However, this compression into a compact discrete representation may ignore visual details that are important for reinforcement learning. Concurrently, diffusion models have become a dominant approach for image generation, challenging well-established methods modeling discrete latents. Motivated by this paradigm shift, we introduce DIAMOND (DIffusion As a Model Of eNvironment Dreams), a reinforcement learning agent trained in a diffusion world model. We analyze the key design choices that are required to make diffusion suitable for world modeling, and demonstrate how improved visual details can lead to improved agent performance. DIAMOND achieves a mean human normalized score of 1.46 on the competitive Atari 100k benchmark; a new best for agents trained entirely within a world model. We further demonstrate that DIAMOND's diffusion world model can stand alone as an interactive neural game engine by training on static Counter-Strike: Global Offensive gameplay. To foster future research on diffusion for world modeling, we release our code, agents, videos and playable world models at https://diamond-wm.github.io.
Authors: Daniele Baieri, Filippo Maggioli, Zorah L\"ahner, Simone Melzi, Emanuele Rodol\`a
Abstract: In this work, we present the local patch mesh representation for neural signed distance fields. This technique allows to discretize local regions of the level sets of an input SDF by projecting and deforming flat patch meshes onto the level set surface, using exclusively the SDF information and its gradient. Our analysis reveals this method to be more accurate than the standard marching cubes algorithm for approximating the implicit surface. Then, we apply this representation in the setting of handle-guided deformation: we introduce two distinct pipelines, which make use of 3D neural fields to compute As-Rigid-As-Possible deformations of both high-resolution meshes and neural fields under a given set of constraints. We run a comprehensive evaluation of our method and various baselines for neural field and mesh deformation which show both pipelines achieve impressive efficiency and notable improvements in terms of quality of results and robustness. With our novel pipeline, we introduce a scalable approach to solve a well-established geometry processing problem on high-resolution meshes, and pave the way for extending other geometric tasks to the domain of implicit surfaces via local patch meshing.
Authors: Linus Ericsson, Miguel Espinosa, Chenhongyi Yang, Antreas Antoniou, Amos Storkey, Shay B. Cohen, Steven McDonagh, Elliot J. Crowley
Abstract: Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional structures to transformers. This is not least because the search spaces in NAS often aren't diverse enough to include such transformations a priori. Instead, for NAS to provide greater potential for fundamental design shifts, we need a novel expressive search space design which is built from more fundamental operations. To this end, we introduce einspace, a search space based on a parameterised probabilistic context-free grammar. Our space is versatile, supporting architectures of various sizes and complexities, while also containing diverse network operations which allow it to model convolutions, attention components and more. It contains many existing competitive architectures, and provides flexibility for discovering new ones. Using this search space, we perform experiments to find novel architectures as well as improvements on existing ones on the diverse Unseen NAS datasets. We show that competitive architectures can be obtained by searching from scratch, and we consistently find large improvements when initialising the search with strong baselines. We believe that this work is an important advancement towards a transformative NAS paradigm where search space expressivity and strategic search initialisation play key roles.
Authors: Philip Sosnin, Mark N. M\"uller, Maximilian Baader, Calvin Tsay, Matthew Wicker
Abstract: Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains an open problem. In this work, we address this challenge by developing the first framework providing provable guarantees on the behavior of models trained with potentially manipulated data without modifying the model or learning algorithm. In particular, our framework certifies robustness against untargeted and targeted poisoning, as well as backdoor attacks, for bounded and unbounded manipulations of the training inputs and labels. Our method leverages convex relaxations to over-approximate the set of all possible parameter updates for a given poisoning threat model, allowing us to bound the set of all reachable parameters for any gradient-based learning algorithm. Given this set of parameters, we provide bounds on worst-case behavior, including model performance and backdoor success rate. We demonstrate our approach on multiple real-world datasets from applications including energy consumption, medical imaging, and autonomous driving.
Authors: Peng Xia, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu, Wenhao Zheng, Zhaoyang Wang, Xiao Wang, Xuchao Zhang, Chetan Bansal, Marc Niethammer, Junzhou Huang, Hongtu Zhu, Yun Li, Jimeng Sun, Zongyuan Ge, Gang Li, James Zou, Huaxiu Yao
Abstract: Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://cares-ai.github.io/.
Authors: Emiel van Miltenburg
Abstract: This short position paper provides a manually curated list of non-English image captioning datasets (as of May 2024). Through this list, we can observe the dearth of datasets in different languages: only 23 different languages are represented. With the addition of the Crossmodal-3600 dataset (Thapliyal et al., 2022, 36 languages) this number increases somewhat, but still this number is small compared to the +/-500 institutional languages that are out there. This paper closes with some open questions for the field of Vision & Language.
Authors: Arianna Bunnell, Kailee Hung, John A. Shepherd, Peter Sadowski
Abstract: Development of artificial intelligence (AI) for medical imaging demands curation and cleaning of large-scale clinical datasets comprising hundreds of thousands of images. Some modalities, such as mammography, contain highly standardized imaging. In contrast, breast ultrasound imaging (BUS) can contain many irregularities not indicated by scan metadata, such as enhanced scan modes, sonographer annotations, or additional views. We present an open-source software solution for automatically processing clinical BUS datasets. The algorithm performs BUS scan filtering (flagging of invalid and non-B-mode scans), cleaning (dual-view scan detection, scan area cropping, and caliper detection), and knowledge extraction (BI-RADS Labeling and Measurement fields) from sonographer annotations. Its modular design enables users to adapt it to new settings. Experiments on an internal testing dataset of 430 clinical BUS images achieve >95% sensitivity and >98% specificity in detecting every type of text annotation, >98% sensitivity and specificity in detecting scans with blood flow highlighting, alternative scan modes, or invalid scans. A case study on a completely external, public dataset of BUS scans found that BUSClean identified text annotations and scans with blood flow highlighting with 88.6% and 90.9% sensitivity and 98.3% and 99.9% specificity, respectively. Adaptation of the lesion caliper detection method to account for a type of caliper specific to the case study demonstrates the intended use of BUSClean in new data distributions and improved performance in lesion caliper detection from 43.3% and 93.3% out-of-the-box to 92.1% and 92.3% sensitivity and specificity, respectively. Source code, example notebooks, and sample data are available at https://github.com/hawaii-ai/bus-cleaning.
Authors: Wuxin Wang, Weicheng Ni, Tao Han, Taikang Yuan, Xiaoyong Li, Lei Bai, Boheng Duan, Kaijun Ren
Abstract: Recent advancements in Artificial Intelligence (AI) have led to the development of several Large Weather Models (LWMs) that rival State-Of-The-Art (SOTA) Numerical Weather Prediction (NWP) systems. Until now, these models have still relied on traditional NWP-generated analysis fields as input and are far from autonomous. Currently, scientists are increasingly focusing on developing data-driven data assimilation (DA) models for LWMs. To expedite advancements in this field and facilitate the operationalization of data-driven end-to-end weather forecasting systems, we propose DABench, a benchmark constructed by simulated observations, real-world observations, and ERA5 reanalysis. DABench contributes four standard features: (1) sparse and noisy observations provided for both simulated and real-world experiments; (2) a Skillful pre-trained Transformer-based weather prediction model, Sformer, designed to generate background fields while rigorously assessing the impact of assimilation outcomes on predictions; (3) standardized evaluation metrics for the model comparison; (4) a strong DA baseline, 4DVarFormerV2. Our experimental results demonstrate that the end-to-end weather forecasting system, integrating 4DVarFormerV2 and Sformer, can assimilate real-world observations, thereby facilitating a stable DA cycle lasting one year and achieving a skillful forecasting lead time of up to 7 days. The proposed DABench will significantly advance research in AI-based DA, AI-based weather forecasting, and related domains.
Authors: Theo Di Piazza
Abstract: The rapid increase of computed tomography (CT) scans and their time-consuming manual analysis have created an urgent need for robust automated analysis techniques in clinical settings. These aim to assist radiologists and help them managing their growing workload. Existing methods typically generate entire reports directly from 3D CT images, without explicitly focusing on observed abnormalities. This unguided approach often results in repetitive content or incomplete reports, failing to prioritize anomaly-specific descriptions. We propose a new anomaly-guided report generation model, which first predicts abnormalities and then generates targeted descriptions for each. Evaluation on a public dataset demonstrates significant improvements in report quality and clinical relevance. We extend our work by conducting an ablation study to demonstrate its effectiveness.
Authors: John M. Ball, Christopher L. Horner
Abstract: The purpose of this paper is to analyze a nonlinear elasticity model previously introduced by the authors for comparing two images, regarded as bounded open subsets of $\R^n$ together with associated vector-valued intensity maps. Optimal transformations between the images are sought as minimisers of an integral functional among orientation-preserving homeomorphisms. The existence of minimisers is proved under natural coercivity and polyconvexity conditions, assuming only that the intensity functions are bounded measurable. Variants of the existence theorem are also proved, first under the constraint that finite sets of landmark points in the two images are mapped one to the other, and second when one image is to be compared to an unknown part of another. The question is studied as to whether for images related by a linear mapping the unique minimizer is given by that linear mapping. For a natural class of functional integrands an example is given guaranteeing that this property holds for pairs of images in which the second is a scaling of the first by a constant factor. However for the property to hold for arbitrary pairs of linearly related images it is shown that the integrand has to depend on the gradient of the transformation as a convex function of its determinant alone. This suggests a new model in which the integrand depends also on second derivatives of the transformation, and an example is given for which both existence of minimizers is assured and the above property holds for all pairs of linearly related images.
Authors: Pranav Jeevan, Neeraj Nixon, Amit Sethi
Abstract: Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks ($4\times$). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR.
Authors: Zhangpu Li, Changhong Zou, Suxue Ma, Zhicheng Yang, Chen Du, Youbao Tang, Zhenjie Cao, Ning Zhang, Jui-Hsin Lai, Ruei-Sung Lin, Yuan Ni, Xingzhi Sun, Jing Xiao, Jieke Hou, Kai Zhang, Mei Han
Abstract: The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and images provided by a patient in multiple rounds to diagnose her/his health condition, forming a multi-turn multimodal medical dialogue format. Unlike high-quality images captured by professional equipment in traditional medical visual question answering (Med-VQA), the images in our case are taken by patients' mobile phones. These images have poor quality control, with issues such as excessive background elements and the lesion area being significantly off-center, leading to degradation of vision-language alignment in the model training phase. In this paper, we propose ZALM3, a Zero-shot strategy to improve vision-language ALignment in Multi-turn Multimodal Medical dialogue. Since we observe that the preceding text conversations before an image can infer the regions of interest (RoIs) in the image, ZALM3 employs an LLM to summarize the keywords from the preceding context and a visual grounding model to extract the RoIs. The updated images eliminate unnecessary background noise and provide more effective vision-language alignment. To better evaluate our proposed method, we design a new subjective assessment metric for multi-turn unimodal/multimodal medical dialogue to provide a fine-grained performance comparison. Our experiments across three different clinical departments remarkably demonstrate the efficacy of ZALM3 with statistical significance.
Authors: Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch
Abstract: Recent work on studying memorization in self-supervised learning (SSL) suggests that even though SSL encoders are trained on millions of images, they still memorize individual data points. While effort has been put into characterizing the memorized data and linking encoder memorization to downstream utility, little is known about where the memorization happens inside SSL encoders. To close this gap, we propose two metrics for localizing memorization in SSL encoders on a per-layer (layermem) and per-unit basis (unitmem). Our localization methods are independent of the downstream task, do not require any label information, and can be performed in a forward pass. By localizing memorization in various encoder architectures (convolutional and transformer-based) trained on diverse datasets with contrastive and non-contrastive SSL frameworks, we find that (1) while SSL memorization increases with layer depth, highly memorizing units are distributed across the entire encoder, (2) a significant fraction of units in SSL encoders experiences surprisingly high memorization of individual data points, which is in contrast to models trained under supervision, (3) atypical (or outlier) data points cause much higher layer and unit memorization than standard data points, and (4) in vision transformers, most memorization happens in the fully-connected layers. Finally, we show that localizing memorization in SSL has the potential to improve fine-tuning and to inform pruning strategies.
Authors: Yi Pan, Hanqi Jiang, Junhao Chen, Yiwei Li, Huaqin Zhao, Yifan Zhou, Peng Shu, Zihao Wu, Zhengliang Liu, Dajiang Zhu, Xiang Li, Yohannes Abate, Tianming Liu
Abstract: Neuromorphic computing has emerged as a promising energy-efficient alternative to traditional artificial intelligence, predominantly utilizing spiking neural networks (SNNs) implemented on neuromorphic hardware. Significant advancements have been made in SNN-based convolutional neural networks (CNNs) and Transformer architectures. However, neuromorphic computing for the medical imaging domain remains underexplored. In this study, we introduce EG-SpikeFormer, an SNN architecture tailored for clinical tasks that incorporates eye-gaze data to guide the model's attention to the diagnostically relevant regions in medical images. Our developed approach effectively addresses shortcut learning issues commonly observed in conventional models, especially in scenarios with limited clinical data and high demands for model reliability, generalizability, and transparency. Our EG-SpikeFormer not only demonstrates superior energy efficiency and performance in medical image prediction tasks but also enhances clinical relevance through multi-modal information alignment. By incorporating eye-gaze data, the model improves interpretability and generalization, opening new directions for applying neuromorphic computing in healthcare.
Authors: Khiem Le, Nitesh V. Chawla
Abstract: Molecule optimization is a critical task in drug discovery to optimize desired properties of a given molecule through chemical modification. Despite Large Language Models (LLMs) holding the potential to efficiently simulate this task by using natural language to direct the optimization, straightforwardly utilizing shows limited performance. In this work, we facilitate utilizing LLMs in an iterative paradigm by proposing a simple yet highly effective domain feedback provider, namely $\text{Re}^3$DF. In detail, $\text{Re}^3$DF harnesses an external toolkit, RDKit, to handle the molecule hallucination, if the modified molecule is chemically invalid. Otherwise, its desired properties are computed and compared to the original one, establishing reliable domain feedback with correct direction and distance towards the objective, followed by a retrieved example, to explicitly guide the LLM to refine the modified molecule. We conduct experiments across both single- and multi-property objectives with 2 thresholds, where $\text{Re}^3$DF shows significant improvements. Particularly, for 20 single-property objectives, $\text{Re}^3$DF enhances Hit ratio by 16.95% and 20.76% under loose and strict thresholds, respectively. For 32 multi-property objectives, $\text{Re}^3$DF enhances Hit ratio by 6.04% and 5.25%.
Authors: Anh Bui, Long Vuong, Khanh Doan, Trung Le, Paul Montague, Tamas Abraham, Dinh Phung
Abstract: Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A practical solution is to selectively removing target concepts from the model, but this may impact the remaining concepts. Prior approaches have tried to balance this by introducing a loss term to preserve neutral content or a regularization term to minimize changes in the model parameters, yet resolving this trade-off remains challenging. In this work, we propose to identify and preserving concepts most affected by parameter changes, termed as \textit{adversarial concepts}. This approach ensures stable erasure with minimal impact on the other concepts. We demonstrate the effectiveness of our method using the Stable Diffusion model, showing that it outperforms state-of-the-art erasure methods in eliminating unwanted content while maintaining the integrity of other unrelated elements. Our code is available at \url{https://github.com/tuananhbui89/Erasing-Adversarial-Preservation}.
URLs: https://github.com/tuananhbui89/Erasing-Adversarial-Preservation
Authors: Alexander Christie, Matan Leibovich, Miguel Moscoso, Alexei Novikov, George Papanicolaou, Chrysoula Tsogka
Abstract: We propose a methodology that exploits large and diverse data sets to accurately estimate the ambient medium's Green's functions in strongly scattering media. Given these estimates, obtained with and without the use of neural networks, excellent imaging results are achieved, with a resolution that is better than that of a homogeneous medium. This phenomenon, also known as super-resolution, occurs because the ambient scattering medium effectively enhances the physical imaging aperture.
Authors: Sahil Ali Akbar, Ananya Verma
Abstract: Noise, an unwanted component in an image, can be the reason for the degradation of Image at the time of transmission or capturing. Noise reduction from images is still a challenging task. Digital Image Processing is a component of Digital signal processing. A wide variety of algorithms can be used in image processing to apply to an image or an input dataset and obtain important outcomes. In image processing research, removing noise from images before further analysis is essential. Post-noise removal of images improves clarity, enabling better interpretation and analysis across medical imaging, satellite imagery, and radar applications. While numerous algorithms exist, each comes with its own assumptions, strengths, and limitations. The paper aims to evaluate the effectiveness of different filtering techniques on images with eight types of noise. It evaluates methodologies like Wiener, Median, Gaussian, Mean, Low pass, High pass, Laplacian and bilateral filtering, using the performance metric Peak signal to noise ratio. It shows us the impact of different filters on noise models by applying a variety of filters to various kinds of noise. Additionally, it also assists us in determining which filtering strategy is most appropriate for a certain noise model based on the circumstances.
Authors: Guangqi Jiang, Yifei Sun, Tao Huang, Huanyu Li, Yongyuan Liang, Huazhe Xu
Abstract: The pre-training of visual representations has enhanced the efficiency of robot learning. Due to the lack of large-scale in-domain robotic datasets, prior works utilize in-the-wild human videos to pre-train robotic visual representation. Despite their promising results, representations from human videos are inevitably subject to distribution shifts and lack the dynamics information crucial for task completion. We first evaluate various pre-trained representations in terms of their correlation to the downstream robotic manipulation tasks (i.e., manipulation centricity). Interestingly, we find that the "manipulation centricity" is a strong indicator of success rates when applied to downstream tasks. Drawing from these findings, we propose Manipulation Centric Representation (MCR), a foundation representation learning framework capturing both visual features and the dynamics information such as actions and proprioceptions of manipulation tasks to improve manipulation centricity. Specifically, we pre-train a visual encoder on the DROID robotic dataset and leverage motion-relevant data such as robot proprioceptive states and actions. We introduce a novel contrastive loss that aligns visual observations with the robot's proprioceptive state-action dynamics, combined with a behavior cloning (BC)-like actor loss to predict actions during pre-training, along with a time contrastive loss. Empirical results across 4 simulation domains with 20 tasks verify that MCR outperforms the strongest baseline method by 14.8%. Moreover, MCR boosts the performance of data-efficient learning with a UR5e arm on 3 real-world tasks by 76.9%. Project website: https://robots-pretrain-robots.github.io/.