new Copula-Linked Parallel ICA: A Method for Coupling Structural and Functional MRI brain Networks

Authors: Oktay Agcaoglu (for the Alzheimers Disease Neuroimaging Initiative), Rogers F. Silva (for the Alzheimers Disease Neuroimaging Initiative), Deniz Alacam (for the Alzheimers Disease Neuroimaging Initiative), Sergey Plis (for the Alzheimers Disease Neuroimaging Initiative), Tulay Adali (for the Alzheimers Disease Neuroimaging Initiative), Vince Calhoun (for the Alzheimers Disease Neuroimaging Initiative)

Abstract: Different brain imaging modalities offer unique insights into brain function and structure. Combining them enhances our understanding of neural mechanisms. Prior multimodal studies fusing functional MRI (fMRI) and structural MRI (sMRI) have shown the benefits of this approach. Since sMRI lacks temporal data, existing fusion methods often compress fMRI temporal information into summary measures, sacrificing rich temporal dynamics. Motivated by the observation that covarying networks are identified in both sMRI and resting-state fMRI, we developed a novel fusion method, by combining deep learning frameworks, copulas and independent component analysis (ICA), named copula linked parallel ICA (CLiP-ICA). This method estimates independent sources for each modality and links the spatial sources of fMRI and sMRI using a copula-based model for more flexible integration of temporal and spatial data. We tested CLiP-ICA using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our results showed that CLiP-ICA effectively captures both strongly and weakly linked sMRI and fMRI networks, including the cerebellum, sensorimotor, visual, cognitive control, and default mode networks. It revealed more meaningful components and fewer artifacts, addressing the long-standing issue of optimal model order in ICA. CLiP-ICA also detected complex functional connectivity patterns across stages of cognitive decline, with cognitively normal subjects generally showing higher connectivity in sensorimotor and visual networks compared to patients with Alzheimer, along with patterns suggesting potential compensatory mechanisms.

new Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery

Authors: Stefan Maria Ailuro, Anna Nedorubova, Timofey Grigoryev, Evgeny Burnaev, Vladimir Vanovskiy

Abstract: The increase in Arctic marine activity due to rapid warming and significant sea ice loss necessitates highly reliable, short-term sea ice forecasts to ensure maritime safety and operational efficiency. In this work, we present a novel data-driven approach for sea ice condition forecasting in the Gulf of Ob, leveraging sequences of radar images from Sentinel-1, weather observations, and GLORYS forecasts. Our approach integrates advanced video prediction models, originally developed for vision tasks, with domain-specific data preprocessing and augmentation techniques tailored to the unique challenges of Arctic sea ice dynamics. Central to our methodology is the use of uncertainty quantification to assess the reliability of predictions, ensuring robust decision-making in safety-critical applications. Furthermore, we propose a confidence-based model mixture mechanism that enhances forecast accuracy and model robustness, crucial for reliable operations in volatile Arctic environments. Our results demonstrate substantial improvements over baseline approaches, underscoring the importance of uncertainty quantification and specialized data handling for effective and safe operations and reliable forecasting.

new Enhancing Apple's Defect Classification: Insights from Visible Spectrum and Narrow Spectral Band Imaging

Authors: Omar Coello, Mois\'es Coronel, Dar\'io Carpio, Boris Vintimilla, Luis Chuquimarca

Abstract: This study addresses the classification of defects in apples as a crucial measure to mitigate economic losses and optimize the food supply chain. An innovative approach is employed that integrates images from the visible spectrum and 660 nm spectral wavelength to enhance accuracy and efficiency in defect classification. The methodology is based on the use of Single-Input and Multi-Inputs convolutional neural networks (CNNs) to validate the proposed strategies. Steps include image acquisition and preprocessing, classification model training, and performance evaluation. Results demonstrate that defect classification using the 660 nm spectral wavelength reveals details not visible in the entire visible spectrum. It is seen that the use of the appropriate spectral range in the classification process is slightly superior to the entire visible spectrum. The MobileNetV1 model achieves an accuracy of 98.80\% on the validation dataset versus the 98.26\% achieved using the entire visible spectrum. Conclusions highlight the potential to enhance the method by capturing images with specific spectral ranges using filters, enabling more effective network training for classification task. These improvements could further enhance the system's capability to identify and classify defects in apples.

new Resolution Enhancement of Under-sampled Photoacoustic Microscopy Images using Implicit Neural Representations

Authors: Youshen Xiao, Sheng Liao, Xuanyang Tian, Fan Zhang, Xinlong Dong, Yunhui Jiang, Xiyu Chen, Ruixi Sun, Yuyao Zhang, Fei Gao

Abstract: Acoustic-Resolution Photoacoustic Microscopy (AR-PAM) is promising for subcutaneous vascular imaging, but its spatial resolution is constrained by the Point Spread Function (PSF). Traditional deconvolution methods like Richardson-Lucy and model-based deconvolution use the PSF to improve resolution. However, accurately measuring the PSF is difficult, leading to reliance on less accurate blind deconvolution techniques. Additionally, AR-PAM suffers from long scanning times, which can be reduced via down-sampling, but this necessitates effective image recovery from under-sampled data, a task where traditional interpolation methods fall short, particularly at high under-sampling rates. To address these challenges, we propose an approach based on Implicit Neural Representations (INR). This method learns a continuous mapping from spatial coordinates to initial acoustic pressure, overcoming the limitations of discrete imaging and enhancing AR-PAM's resolution. By treating the PSF as a learnable parameter within the INR framework, our technique mitigates inaccuracies associated with PSF estimation. We evaluated our method on simulated vascular data, showing significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) over conventional methods. Qualitative enhancements were also observed in leaf vein and in vivo mouse brain microvasculature images. When applied to a custom AR-PAM system, experiments with pencil lead demonstrated that our method delivers sharper, higher-resolution results, indicating its potential to advance photoacoustic microscopy.

new Leveraging Multi-Temporal Sentinel 1 and 2 Satellite Data for Leaf Area Index Estimation With Deep Learning

Authors: Clement Wang, Antoine Debouchage, Valentin Goldit\'e, Aur\'elien Wery, Jules Salzinger

Abstract: The Leaf Area Index (LAI) is a critical parameter to understand ecosystem health and vegetation dynamics. In this paper, we propose a novel method for pixel-wise LAI prediction by leveraging the complementary information from Sentinel 1 radar data and Sentinel 2 multi-spectral data at multiple timestamps. Our approach uses a deep neural network based on multiple U-nets tailored specifically to this task. To handle the complexity of the different input modalities, it is comprised of several modules that are pre-trained separately to represent all input data in a common latent space. Then, we fine-tune them end-to-end with a common decoder that also takes into account seasonality, which we find to play an important role. Our method achieved 0.06 RMSE and 0.93 R2 score on publicly available data. We make our contributions available at https://github.com/valentingol/LeafNothingBehind for future works to further improve on our current progress.

URLs: https://github.com/valentingol/LeafNothingBehind

new Xeno-learning: knowledge transfer across species in deep learning-based spectral image analysis

Authors: Jan Sellner, Alexander Studier-Fischer, Ahmad Bin Qasim, Silvia Seidlitz, Nicholas Schreck, Minu Tizabi, Manuel Wiesenfarth, Annette Kopp-Schneider, Samuel Kn\"odler, Caelan Max Haney, Gabriel Salg, Berkin \"Ozdemir, Maximilian Dietrich, Maurice Stephan Michel, Felix Nickel, Karl-Friedrich Kowalewski, Lena Maier-Hein

Abstract: Novel optical imaging techniques, such as hyperspectral imaging (HSI) combined with machine learning-based (ML) analysis, have the potential to revolutionize clinical surgical imaging. However, these novel modalities face a shortage of large-scale, representative clinical data for training ML algorithms, while preclinical animal data is abundantly available through standardized experiments and allows for controlled induction of pathological tissue states, which is not ethically possible in patients. To leverage this situation, we propose a novel concept called "xeno-learning", a cross-species knowledge transfer paradigm inspired by xeno-transplantation, where organs from a donor species are transplanted into a recipient species. Using a total of 11,268 HSI images from humans as well as porcine and rat models, we show that although spectral signatures of organs differ across species, shared pathophysiological mechanisms manifest as comparable relative spectral changes across species. Such changes learnt in one species can thus be transferred to a new species via a novel "physiology-based data augmentation" method, enabling the large-scale secondary use of preclinical animal data for humans. The resulting ethical, monetary, and performance benefits of the proposed knowledge transfer paradigm promise a high impact of the methodology on future developments in the field.

new DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks

Authors: Zohreh Aghababaeyan, Manel Abdellatif, Lionel Briand, Ramesh S

Abstract: Deep Neural Networks (DNNs) are increasingly deployed across applications. However, ensuring their reliability remains a challenge, and in many situations, alternative models with similar functionality and accuracy are available. Traditional accuracy-based evaluations often fail to capture behavioral differences between models, especially with limited test datasets, making it difficult to select or combine models effectively. Differential testing addresses this by generating test inputs that expose discrepancies in DNN model behavior. However, existing approaches face significant limitations: many rely on model internals or are constrained by available seed inputs. To address these challenges, we propose DiffGAN, a black-box test image generation approach for differential testing of DNN models. DiffGAN leverages a Generative Adversarial Network (GAN) and the Non-dominated Sorting Genetic Algorithm II to generate diverse and valid triggering inputs that reveal behavioral discrepancies between models. DiffGAN employs two custom fitness functions, focusing on diversity and divergence, to guide the exploration of the GAN input space and identify discrepancies between models' outputs. By strategically searching this space, DiffGAN generates inputs with specific features that trigger differences in model behavior. DiffGAN is black-box, making it applicable in more situations. We evaluate DiffGAN on eight DNN model pairs trained on widely used image datasets. Our results show DiffGAN significantly outperforms a SOTA baseline, generating four times more triggering inputs, with greater diversity and validity, within the same budget. Additionally, the generated inputs improve the accuracy of a machine learning-based model selection mechanism, which selects the best-performing model based on input characteristics and can serve as a smart output voting mechanism when using alternative models.

new Feature Clipping for Uncertainty Calibration

Authors: Linwei Tao, Minjing Dong, Chang Xu

Abstract: Deep neural networks (DNNs) have achieved significant success across various tasks, but ensuring reliable uncertainty estimates, known as model calibration, is crucial for their safe and effective deployment. Modern DNNs often suffer from overconfidence, leading to miscalibration. We propose a novel post-hoc calibration method called feature clipping (FC) to address this issue. FC involves clipping feature values to a specified threshold, effectively increasing entropy in high calibration error samples while maintaining the information in low calibration error samples. This process reduces the overconfidence in predictions, improving the overall calibration of the model. Our extensive experiments on datasets such as CIFAR-10, CIFAR-100, and ImageNet, and models including CNNs and transformers, demonstrate that FC consistently enhances calibration performance. Additionally, we provide a theoretical analysis that validates the effectiveness of our method. As the first calibration technique based on feature modification, feature clipping offers a novel approach to improving model calibration, showing significant improvements over both post-hoc and train-time calibration methods and pioneering a new avenue for feature-based model calibration.

new Stable Diffusion with Continuous-time Neural Network

Authors: Andras Horvath

Abstract: Stable diffusion models have ushered in a new era of advancements in image generation, currently reigning as the state-of-the-art approach, exhibiting unparalleled performance. The process of diffusion, accompanied by denoising through iterative convolutional or transformer network steps, stands at the core of their implementation. Neural networks operating in continuous time naturally embrace the concept of diffusion, this way they could enable more accurate and energy efficient implementation. Within the confines of this paper, my focus delves into an exploration and demonstration of the potential of celllular neural networks in image generation. I will demonstrate their superiority in performance, showcasing their adeptness in producing higher quality images and achieving quicker training times in comparison to their discrete-time counterparts on the commonly cited MNIST dataset.

new Comparing Surface Landmine Object Detection Models on a New Drone Flyby Dataset

Authors: Navin Agrawal-Chung, Zohran Moin

Abstract: Landmine detection using traditional methods is slow, dangerous and prohibitively expensive. Using deep learning-based object detection algorithms drone videos is promising but has multiple challenges due to the small, soda-can size of recently prevalent surface landmines. The literature currently lacks scientific evaluation of optimal ML models for this problem since most object detection research focuses on analysis of ground video surveillance images. In order to help train comprehensive models and drive research for surface landmine detection, we first create a custom dataset comprising drone images of POM-2 and POM-3 Russian surface landmines. Using this dataset, we train, test and compare 4 different computer vision foundation models YOLOF, DETR, Sparse-RCNN and VFNet. Generally, all 4 detectors do well with YOLOF outperforming other models with a mAP score of 0.89 while DETR, VFNET and Sparse-RCNN mAP scores are all around 0.82 for drone images taken from 10m AGL. YOLOF is also quicker to train consuming 56min of training time on a Nvidia V100 compute cluster. Finally, this research contributes landmine image, video datasets and model Jupyter notebooks at https://github.com/UnVeilX/ to enable future research in surface landmine detection.

URLs: https://github.com/UnVeilX/

new LocateBench: Evaluating the Locating Ability of Vision Language Models

Authors: Ting-Rui Chiang, Joshua Robinson, Xinyan Velocity Yu, Dani Yogatama

Abstract: The ability to locate an object in an image according to natural language instructions is crucial for many real-world applications. In this work we propose LocateBench, a high-quality benchmark dedicated to evaluating this ability. We experiment with multiple prompting approaches, and measure the accuracy of several large vision language models. We find that even the accuracy of the strongest model, GPT-4o, lags behind human accuracy by more than 10%.

new Stochastic Flow Matching for Resolving Small-Scale Physics

Authors: Stathi Fotiadis, Noah Brenowitz, Tomas Geffner, Yair Cohen, Michael Pritchard, Arash Vahdat, Morteza Mardani

Abstract: Conditioning diffusion and flow models have proven effective for super-resolving small-scale details in natural images.However, in physical sciences such as weather, super-resolving small-scale details poses significant challenges due to: (i) misalignment between input and output distributions (i.e., solutions to distinct partial differential equations (PDEs) follow different trajectories), (ii) multi-scale dynamics, deterministic dynamics at large scales vs. stochastic at small scales, and (iii) limited data, increasing the risk of overfitting. To address these challenges, we propose encoding the inputs to a latent base distribution that is closer to the target distribution, followed by flow matching to generate small-scale physics. The encoder captures the deterministic components, while flow matching adds stochastic small-scale details. To account for uncertainty in the deterministic part, we inject noise into the encoder output using an adaptive noise scaling mechanism, which is dynamically adjusted based on maximum-likelihood estimates of the encoder predictions. We conduct extensive experiments on both the real-world CWA weather dataset and the PDE-based Kolmogorov dataset, with the CWA task involving super-resolving the weather variables for the region of Taiwan from 25 km to 2 km scales. Our results show that the proposed stochastic flow matching (SFM) framework significantly outperforms existing methods such as conditional diffusion and flows.

new DivShift: Exploring Domain-Specific Distribution Shift in Volunteer-Collected Biodiversity Datasets

Authors: Elena Sierra, Lauren E. Gillespie, Salim Soltani, Moises Exposito-Alonso, Teja Kattenborn

Abstract: Climate change is negatively impacting the world's biodiversity. To build automated systems to monitor these negative biodiversity impacts, large-scale, volunteer-collected datasets like iNaturalist are built from community-identified, natural imagery. However, such volunteer-based data are opportunistic and lack a structured sampling strategy, resulting in geographic, temporal, observation quality, and socioeconomic, biases that stymie uptake of these models for downstream biodiversity monitoring tasks. Here we introduce DivShift North American West Coast (DivShift-NAWC), a curated dataset of almost 8 million iNaturalist plant images across the western coast of North America, for exploring the effects of these biases on deep learning model performance. We compare model performance across four known biases and observe that they indeed confound model performance. We suggest practical strategies for curating datasets to train deep learning models for monitoring climate change's impacts on the world's biodiversity.

new Explainable AI in Handwriting Detection for Dyslexia Using Transfer Learning

Authors: Mahmoud Robaa, Mazen Balat, Rewaa Awaad, Esraa Omar, Salah A. Aly

Abstract: Dyslexia is one of the most common learning disorders, often characterized by distinct features in handwriting. Early detection is essential for effective intervention. In this paper, we propose an explainable AI (XAI) framework for dyslexia detection through handwriting analysis, utilizing transfer learning and transformer-based models. Our approach surpasses state-of-the-art methods, achieving a test accuracy of 0.9958, while ensuring model interpretability through Grad-CAM visualizations that highlight the critical handwriting features influencing model decisions. The main contributions of this work include the integration of XAI for enhanced interpretability, adaptation to diverse languages and writing systems, and demonstration of the method's global applicability. This framework not only improves diagnostic accuracy but also fosters trust and understanding among educators, clinicians, and parents, supporting earlier diagnoses and the development of personalized educational strategies.

new Flame quality monitoring of flare stack based on deep visual features

Authors: Xing Mu

Abstract: Flare stacks play an important role in the treatment of waste gas and waste materials in petroleum fossil energy plants. Monitoring the efficiency of flame combustion is of great significance for environmental protection. The traditional method of monitoring with sensors is not only expensive, but also easily damaged in harsh combustion environments. In this paper, we propose to monitor the quality of flames using only visual features, including the area ratio of flame to smoke, RGB information of flames, angle of flames and other features. Comprehensive use of image segmentation, target detection, target tracking, principal component analysis, GPT-4 and other methods or tools to complete this task. In the end, real-time monitoring of the picture can be achieved, and when the combustion efficiency is low, measures such as adjusting the ratio of air and waste can be taken in time. As far as we know, the method of this paper is relatively innovative and has industrial production value.

new Automating Video Thumbnails Selection and Generation with Multimodal and Multistage Analysis

Authors: Elia Fantini

Abstract: This thesis presents an innovative approach to automate video thumbnail selection for traditional broadcast content. Our methodology establishes stringent criteria for diverse, representative, and aesthetically pleasing thumbnails, considering factors like logo placement space, incorporation of vertical aspect ratios, and accurate recognition of facial identities and emotions. We introduce a sophisticated multistage pipeline that can select candidate frames or generate novel images by blending video elements or using diffusion models. The pipeline incorporates state-of-the-art models for various tasks, including downsampling, redundancy reduction, automated cropping, face recognition, closed-eye and emotion detection, shot scale and aesthetic prediction, segmentation, matting, and harmonization. It also leverages large language models and visual transformers for semantic consistency. A GUI tool facilitates rapid navigation of the pipeline's output. To evaluate our method, we conducted comprehensive experiments. In a study of 69 videos, 53.6% of our proposed sets included thumbnails chosen by professional designers, with 73.9% containing similar images. A survey of 82 participants showed a 45.77% preference for our method, compared to 37.99% for manually chosen thumbnails and 16.36% for an alternative method. Professional designers reported a 3.57-fold increase in valid candidates compared to the alternative method, confirming that our approach meets established criteria. In conclusion, our findings affirm that the proposed method accelerates thumbnail creation while maintaining high-quality standards and fostering greater user engagement.

new GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration

Authors: Silong Yong, Yaqi Xie, Simon Stepputtis, Katia Sycara

Abstract: Volume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue by introducing new neural networks or data structures. In this work, We propose GL-NeRF, a new perspective of computing volume rendering with the Gauss-Laguerre quadrature. GL-NeRF significantly reduces the number of MLP calls needed for volume rendering, introducing no additional data structures or neural networks. The simple formulation makes adopting GL-NeRF in any NeRF model possible. In the paper, we first justify the use of the Gauss-Laguerre quadrature and then demonstrate this plug-and-play attribute by implementing it in two different NeRF models. We show that with a minimal drop in performance, GL-NeRF can significantly reduce the number of MLP calls, showing the potential to speed up any NeRF model.

new Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation

Authors: Ronan Docherty, Antonis Vamvakeros, Samuel J. Cooper

Abstract: The features of self-supervised vision transformers (ViTs) contain strong semantic and positional information relevant to downstream tasks like object localization and segmentation. Recent works combine these features with traditional methods like clustering, graph partitioning or region correlations to achieve impressive baselines without finetuning or training additional networks. We leverage upsampled features from ViT networks (e.g DINOv2) in two workflows: in a clustering based approach for object localization and segmentation, and paired with standard classifiers in weakly supervised materials segmentation. Both show strong performance on benchmarks, especially in weakly supervised segmentation where the ViT features capture complex relationships inaccessible to classical approaches. We expect the flexibility and generalizability of these features will both speed up and strengthen materials characterization, from segmentation to property-prediction.

new Scene-Segmentation-Based Exposure Compensation for Tone Mapping of High Dynamic Range Scenes

Authors: Yuma Kinoshita, Hitoshi Kiya

Abstract: We propose a novel scene-segmentation-based exposure compensation method for multi-exposure image fusion (MEF) based tone mapping. The aim of MEF-based tone mapping is to display high dynamic range (HDR) images on devices with limited dynamic range. To achieve this, this method generates a stack of differently exposed images from an input HDR image and fuses them into a single image. Our approach addresses the limitations of MEF-based tone mapping with existing segmentation-based exposure compensation, which often result in visually unappealing outcomes due to inappropriate exposure value selection. The proposed exposure compensation method first segments the input HDR image into subregions based on luminance values of pixels. It then determines exposure values for multi-exposure images to maximize contrast between regions while preserving relative luminance relationships. This approach contrasts with conventional methods that may invert luminance relationships or compromise contrast between regions. Additionally, we present an improved technique for calculating fusion weights to better reflect the effects of exposure compensation in the final fused image. In a simulation experiment to evaluate the quality of tone-mapped images, the MEF-based tone mapping with the proposed method outperforms three typical tone mapping methods including conventional MEF-based one, in terms of the tone mapped image quality index (TMQI).

new GreenEye: Development of Real-Time Traffic Signal Recognition System for Visual Impairments

Authors: Danu Kim

Abstract: Recognizing a traffic signal, determining if the signal is green or red, and figuring out the time left to cross the crosswalk are significant challenges to visually impaired people. Previous research has focused on recognizing only two traffic signals, green and red lights, using machine learning techniques. The proposed method developed a GreenEye system that recognizes the traffic signals' color and tells the time left for pedestrians to cross the crosswalk in real-time. GreenEye's first training showed the highest precision of 74.6%; four classes reported 40% or lower recognition precision in this training session. The data imbalance caused low precision; thus, extra labeling and database formation were performed to stabilize the number of images between different classes. After the stabilization, all 14 classes showed excelling precision rate of 99.5%.

new YOLO11 and Vision Transformers based 3D Pose Estimation of Immature Green Fruits in Commercial Apple Orchards for Robotic Thinning

Authors: Ranjan Sapkota, Manoj Karkee

Abstract: In this study, a robust method for 3D pose estimation of immature green apples (fruitlets) in commercial orchards was developed, utilizing the YOLO11 object detection and pose estimation algorithm alongside Vision Transformers (ViT) for depth estimation (Dense Prediction Transformer (DPT) and Depth Anything V2). For object detection and pose estimation, performance comparisons of YOLO11 (YOLO11n, YOLO11s, YOLO11m, YOLO11l and YOLO11x) and YOLOv8 (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l and YOLOv8x) were made under identical hyperparameter settings among the all configurations. It was observed that YOLO11n surpassed all configurations of YOLO11 and YOLOv8 in terms of box precision and pose precision, achieving scores of 0.91 and 0.915, respectively. Conversely, YOLOv8n exhibited the highest box and pose recall scores of 0.905 and 0.925, respectively. Regarding the mean average precision at 50\% intersection over union (mAP@50), YOLO11s led all configurations with a box mAP@50 score of 0.94, while YOLOv8n achieved the highest pose mAP@50 score of 0.96. In terms of image processing speed, YOLO11n outperformed all configurations with an impressive inference speed of 2.7 ms, significantly faster than the quickest YOLOv8 configuration, YOLOv8n, which processed images in 7.8 ms. Subsequent integration of ViTs for the green fruit's pose depth estimation revealed that Depth Anything V2 outperformed Dense Prediction Transformer in 3D pose length validation, achieving the lowest Root Mean Square Error (RMSE) of 1.52 and Mean Absolute Error (MAE) of 1.28, demonstrating exceptional precision in estimating immature green fruit lengths. Integration of YOLO11 and Depth Anything Model provides a promising solution to 3D pose estimation of immature green fruits for robotic thinning applications.

new AEPL: Automated and Editable Prompt Learning for Brain Tumor Segmentation

Authors: Yongheng Sun, Mingxia Liu, Chunfeng Lian

Abstract: Brain tumor segmentation is crucial for accurate diagnosisand treatment planning, but the small size and irregular shapeof tumors pose significant challenges. Existing methods of-ten fail to effectively incorporate medical domain knowledgesuch as tumor grade, which correlates with tumor aggres-siveness and morphology, providing critical insights for moreaccurate detection of tumor subregions during segmentation.We propose an Automated and Editable Prompt Learning(AEPL) framework that integrates tumor grade into the seg-mentation process by combining multi-task learning andprompt learning with automatic and editable prompt gen-eration. Specifically, AEPL employs an encoder to extractimage features for both tumor-grade prediction and segmen-tation mask generation. The predicted tumor grades serveas auto-generated prompts, guiding the decoder to produceprecise segmentation masks. This eliminates the need formanual prompts while allowing clinicians to manually editthe auto-generated prompts to fine-tune the segmentation,enhancing both flexibility and precision. The proposed AEPLachieves state-of-the-art performance on the BraTS 2018dataset, demonstrating its effectiveness and clinical potential.The source code can be accessed online.

new Benchmarking Large Language Models for Image Classification of Marine Mammals

Authors: Yijiashun Qi, Shuzhang Cai, Zunduo Zhao, Jiaming Li, Yanbin Lin, Zhiqiang Wang

Abstract: As Artificial Intelligence (AI) has developed rapidly over the past few decades, the new generation of AI, Large Language Models (LLMs) trained on massive datasets, has achieved ground-breaking performance in many applications. Further progress has been made in multimodal LLMs, with many datasets created to evaluate LLMs with vision abilities. However, none of those datasets focuses solely on marine mammals, which are indispensable for ecological equilibrium. In this work, we build a benchmark dataset with 1,423 images of 65 kinds of marine mammals, where each animal is uniquely classified into different levels of class, ranging from species-level to medium-level to group-level. Moreover, we evaluate several approaches for classifying these marine mammals: (1) machine learning (ML) algorithms using embeddings provided by neural networks, (2) influential pre-trained neural networks, (3) zero-shot models: CLIP and LLMs, and (4) a novel LLM-based multi-agent system (MAS). The results demonstrate the strengths of traditional models and LLMs in different aspects, and the MAS can further improve the classification performance. The dataset is available on GitHub: https://github.com/yeyimilk/LLM-Vision-Marine-Animals.git.

URLs: https://github.com/yeyimilk/LLM-Vision-Marine-Animals.git.

new Real-Time Weapon Detection Using YOLOv8 for Enhanced Safety

Authors: Ayush Thakur, Akshat Shrivastav, Rohan Sharma, Triyank Kumar, Kabir Puri

Abstract: This research paper presents the development of an AI model utilizing YOLOv8 for real-time weapon detection, aimed at enhancing safety in public spaces such as schools, airports, and public transportation systems. As incidents of violence continue to rise globally, there is an urgent need for effective surveillance technologies that can quickly identify potential threats. Our approach focuses on leveraging advanced deep learning techniques to create a highly accurate and efficient system capable of detecting weapons in real-time video streams. The model was trained on a comprehensive dataset containing thousands of images depicting various types of firearms and edged weapons, ensuring a robust learning process. We evaluated the model's performance using key metrics such as precision, recall, F1-score, and mean Average Precision (mAP) across multiple Intersection over Union (IoU) thresholds, revealing a significant capability to differentiate between weapon and non-weapon classes with minimal error. Furthermore, we assessed the system's operational efficiency, demonstrating that it can process frames at high speeds suitable for real-time applications. The findings indicate that our YOLOv8-based weapon detection model not only contributes to the existing body of knowledge in computer vision but also addresses critical societal needs for improved safety measures in vulnerable environments. By harnessing the power of artificial intelligence, this research lays the groundwork for developing practical solutions that can be deployed in security settings, ultimately enhancing the protective capabilities of law enforcement and public safety agencies.

new Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection

Authors: Jakob Shack, Katarina Petrovic, Olga Saukh

Abstract: Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates the performance of adversarial patches for the YOLO object detection network in the physical world. Two attacks were tested: a patch designed to be placed anywhere within the scene - global patch, and another patch intended to partially overlap with specific object targeted for removal from detection - local patch. Various factors such as patch size, position, rotation, brightness, and hue were analyzed to understand their impact on the effectiveness of the adversarial patches. The results reveal a notable dependency on these parameters, highlighting the challenges in maintaining attack efficacy in real-world conditions. Learning to align digitally applied transformation parameters with those measured in the real world still results in up to a 64\% discrepancy in patch performance. These findings underscore the importance of understanding environmental influences on adversarial attacks, which can inform the development of more robust defenses for practical machine learning applications.

new Comparing YOLO11 and YOLOv8 for instance segmentation of occluded and non-occluded immature green fruits in complex orchard environment

Authors: Ranjan Sapkota, Manoj Karkee

Abstract: This study conducted a comprehensive performance evaluation on YOLO11 and YOLOv8, the latest in the "You Only Look Once" (YOLO) series, focusing on their instance segmentation capabilities for immature green apples in orchard environments. YOLO11n-seg achieved the highest mask precision across all categories with a notable score of 0.831, highlighting its effectiveness in fruit detection. YOLO11m-seg and YOLO11l-seg excelled in non-occluded and occluded fruitlet segmentation with scores of 0.851 and 0.829, respectively. Additionally, YOLO11x-seg led in mask recall for all categories, achieving a score of 0.815, with YOLO11m-seg performing best for non-occluded immature green fruitlets at 0.858 and YOLOv8x-seg leading the occluded category with 0.800. In terms of mean average precision at a 50\% intersection over union (mAP@50), YOLO11m-seg consistently outperformed, registering the highest scores for both box and mask segmentation, at 0.876 and 0.860 for the "All" class and 0.908 and 0.909 for non-occluded immature fruitlets, respectively. YOLO11l-seg and YOLOv8l-seg shared the top box mAP@50 for occluded immature fruitlets at 0.847, while YOLO11m-seg achieved the highest mask mAP@50 of 0.810. Despite the advancements in YOLO11, YOLOv8n surpassed its counterparts in image processing speed, with an impressive inference speed of 3.3 milliseconds, compared to the fastest YOLO11 series model at 4.8 milliseconds, underscoring its suitability for real-time agricultural applications related to complex green fruit environments.

new Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey

Authors: Kun Shi, Shibo He, Zhenyu Shi, Anjun Chen, Zehui Xiong, Jiming Chen, Jun Luo

Abstract: Multi-modal fusion is imperative to the implementation of reliable object detection and tracking in complex environments. Exploiting the synergy of heterogeneous modal information endows perception systems the ability to achieve more comprehensive, robust, and accurate performance. As a nucleus concern in wireless-vision collaboration, radar-camera fusion has prompted prospective research directions owing to its extensive applicability, complementarity, and compatibility. Nonetheless, there still lacks a systematic survey specifically focusing on deep fusion of radar and camera for object detection and tracking. To fill this void, we embark on an endeavor to comprehensively review radar-camera fusion in a holistic way. First, we elaborate on the fundamental principles, methodologies, and applications of radar-camera fusion perception. Next, we delve into the key techniques concerning sensor calibration, modal representation, data alignment, and fusion operation. Furthermore, we provide a detailed taxonomy covering the research topics related to object detection and tracking in the context of radar and camera technologies.Finally, we discuss the emerging perspectives in the field of radar-camera fusion perception and highlight the potential areas for future research.

new Paved or unpaved? A Deep Learning derived Road Surface Global Dataset from Mapillary Street-View Imagery

Authors: Sukanya Randhawa, Eren Aygun, Guntaj Randhawa, Benjamin Herfort, Sven Lautenbach, Alexander Zipf

Abstract: We have released an open dataset with global coverage on road surface characteristics (paved or unpaved) derived utilising 105 million images from the world's largest crowdsourcing-based street view platform, Mapillary, leveraging state-of-the-art geospatial AI methods. We propose a hybrid deep learning approach which combines SWIN-Transformer based road surface prediction and CLIP-and-DL segmentation based thresholding for filtering of bad quality images. The road surface prediction results have been matched and integrated with OpenStreetMap (OSM) road geometries. This study provides global data insights derived from maps and statistics about spatial distribution of Mapillary coverage and road pavedness on a continent and countries scale, with rural and urban distinction.This dataset expands the availability of global road surface information by over 3 million kilometers, now representing approximately 36% of the total length of the global road network.Most regions showed moderate to high paved road coverage (60-80%), but significant gaps were noted in specific areas of Africa and Asia. Urban areas tend to have near-complete paved coverage, while rural regions display more variability. Model validation against OSM surface data achieved strong performance, with F1 scores for paved roads between 91-97% across continents.Taking forward the work of Mapillary and their contributors and enrichment of OSM road attributes, our work provides valuable insights for applications in urban planning, disaster routing, logistics optimisation and addresses various Sustainable Development Goals (SDGS): especially SDGs 1 (No poverty), 3 (Good health and well-being), 8 (Decent work and economic growth), 9 (Industry, Innovation and Infrastructure), 11 (Sustainable cities and communities), 12 (Responsible consumption and production), and 13 (Climate action).

new A Survey of AI-Generated Video Evaluation

Authors: Xiao Liu, Xinhao Xiang, Zizhong Li, Yongheng Wang, Zhuoheng Li, Zhuosheng Liu, Weidi Zhang, Weiqi Ye, Jiawei Zhang

Abstract: The growing capabilities of AI in generating video content have brought forward significant challenges in effectively evaluating these videos. Unlike static images or text, video content involves complex spatial and temporal dynamics which may require a more comprehensive and systematic evaluation of its contents in aspects like video presentation quality, semantic information delivery, alignment with human intentions, and the virtual-reality consistency with our physical world. This survey identifies the emerging field of AI-Generated Video Evaluation (AIGVE), highlighting the importance of assessing how well AI-generated videos align with human perception and meet specific instructions. We provide a structured analysis of existing methodologies that could be potentially used to evaluate AI-generated videos. By outlining the strengths and gaps in current approaches, we advocate for the development of more robust and nuanced evaluation frameworks that can handle the complexities of video content, which include not only the conventional metric-based evaluations, but also the current human-involved evaluations, and the future model-centered evaluations. This survey aims to establish a foundational knowledge base for both researchers from academia and practitioners from the industry, facilitating the future advancement of evaluation methods for AI-generated video content.

new Topology-aware Mamba for Crack Segmentation in Structures

Authors: Xin Zuo, Yu Sheng, Jifeng Shen, Yongwei Shan

Abstract: CrackMamba, a Mamba-based model, is designed for efficient and accurate crack segmentation for monitoring the structural health of infrastructure. Traditional Convolutional Neural Network (CNN) models struggle with limited receptive fields, and while Vision Transformers (ViT) improve segmentation accuracy, they are computationally intensive. CrackMamba addresses these challenges by utilizing the VMambaV2 with pre-trained ImageNet-1k weights as the encoder and a newly designed decoder for better performance. To handle the random and complex nature of crack development, a Snake Scan module is proposed to reshape crack feature sequences, enhancing feature extraction. Additionally, the three-branch Snake Conv VSS (SCVSS) block is proposed to target cracks more effectively. Experiments show that CrackMamba achieves state-of-the-art (SOTA) performance on the CrackSeg9k and SewerCrack datasets, and demonstrates competitive performance on the retinal vessel segmentation dataset CHASE\underline{~}DB1, highlighting its generalization capability. The code is publicly available at: {https://github.com/shengyu27/CrackMamba.}

URLs: https://github.com/shengyu27/CrackMamba.

new FLAASH: Flow-Attention Adaptive Semantic Hierarchical Fusion for Multi-Modal Tobacco Content Analysis

Authors: Naga VS Raviteja Chappa, Page Daniel Dobbs, Bhiksha Raj, Khoa Luu

Abstract: The proliferation of tobacco-related content on social media platforms poses significant challenges for public health monitoring and intervention. This paper introduces a novel multi-modal deep learning framework named Flow-Attention Adaptive Semantic Hierarchical Fusion (FLAASH) designed to analyze tobacco-related video content comprehensively. FLAASH addresses the complexities of integrating visual and textual information in short-form videos by leveraging a hierarchical fusion mechanism inspired by flow network theory. Our approach incorporates three key innovations, including a flow-attention mechanism that captures nuanced interactions between visual and textual modalities, an adaptive weighting scheme that balances the contribution of different hierarchical levels, and a gating mechanism that selectively emphasizes relevant features. This multi-faceted approach enables FLAASH to effectively process and analyze diverse tobacco-related content, from product showcases to usage scenarios. We evaluate FLAASH on the Multimodal Tobacco Content Analysis Dataset (MTCAD), a large-scale collection of tobacco-related videos from popular social media platforms. Our results demonstrate significant improvements over existing methods, outperforming state-of-the-art approaches in classification accuracy, F1 score, and temporal consistency. The proposed method also shows strong generalization capabilities when tested on standard video question-answering datasets, surpassing current models. This work contributes to the intersection of public health and artificial intelligence, offering an effective tool for analyzing tobacco promotion in digital media.

new Exploring Self-Supervised Learning with U-Net Masked Autoencoders and EfficientNet B7 for Improved Classification

Authors: Vamshi Krishna Kancharla, Pavan Kumar Kaveti

Abstract: We present a self-supervised U-Net-based masked autoencoder and noise removal model designed to reconstruct original images. Once adequately trained, this model extracts high-level features, which are then combined with features from the EfficientNet B7 model. These integrated features are subsequently fed into dense layers for classification. Among the approaches of masked input and Gaussian noise removal, we selected the best U-Net reconstruction model. Additionally, we explored various configurations, including EfficientNet with attention, attention fusion of the autoencoder, and classification utilizing U-Net encoder features. The best performance was achieved with EfficientNet B7 combined with U-Net encoder features. We employed the Adam optimizer with a learning rate of 0.0001, achieving a top accuracy of 0.94 on the validation set.

new Tracking and triangulating firefly flashes in field recordings

Authors: Raphael Sarfati

Abstract: Identifying firefly flashes from other bright features in nature images is complicated. I provide a training dataset and trained neural networks for reliable flash classification. The training set consists of thousands of cropped images (patches) extracted by manual labeling from video recordings of fireflies in their natural habitat. The trained network appears as considerably more reliable to differentiate flashes from other sources of light compared to traditional methods relying solely on intensity thresholding. This robust tracking enables a new calibration-free method for the 3D reconstruction of flash occurrences from stereoscopic 360-degree videos, which I also present here.

new A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT

Authors: Nagarajan Ganapathy, Podakanti Satyajith Chary, Teja Venkata Ramana Kumar Pithani, Pavan Kavati, Arun Kumar S

Abstract: This Paper presents an advanced approach for fine-tuning BiomedCLIP PubMedBERT, a multimodal model, to classify abnormalities in Video Capsule Endoscopy (VCE) frames, aiming to enhance diagnostic efficiency in gastrointestinal healthcare. By integrating the PubMedBERT language model with a Vision Transformer (ViT) to process endoscopic images, our method categorizes images into ten specific classes: angioectasia, bleeding, erosion, erythema, foreign body, lymphangiectasia, polyp, ulcer, worms, and normal. Our workflow incorporates image preprocessing and fine-tunes the BiomedCLIP model to generate high-quality embeddings for both visual and textual inputs, aligning them through similarity scoring for classification. Performance metrics, including classification, accuracy, recall, and F1 score, indicate the models strong ability to accurately identify abnormalities in endoscopic frames, showing promise for practical use in clinical diagnostics.

new Turn-by-Turn Indoor Navigation for the Visually Impaired

Authors: Santosh Srinivasaiah, Sai Kumar Nekkanti, Rohith Reddy Nedhunuri

Abstract: Navigating indoor environments presents significant challenges for visually impaired individuals due to complex layouts and the absence of GPS signals. This paper introduces a novel system that provides turn-by-turn navigation inside buildings using only a smartphone equipped with a camera, leveraging multimodal models, deep learning algorithms, and large language models (LLMs). The smartphone's camera captures real-time images of the surroundings, which are then sent to a nearby Raspberry Pi capable of running on-device LLM models, multimodal models, and deep learning algorithms to detect and recognize architectural features, signage, and obstacles. The interpreted visual data is then translated into natural language instructions by an LLM running on the Raspberry Pi, which is sent back to the user, offering intuitive and context-aware guidance via audio prompts. This solution requires minimal workload on the user's device, preventing it from being overloaded and offering compatibility with all types of devices, including those incapable of running AI models. This approach enables the client to not only run advanced models but also ensure that the training data and other information do not leave the building. Preliminary evaluations demonstrate the system's effectiveness in accurately guiding users through complex indoor spaces, highlighting its potential for widespread application

new OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery

Authors: Philipe Dias, Aristeidis Tsaris, Jordan Bowman, Abhishek Potnis, Jacob Arndt, H. Lexie Yang, Dalton Lunga

Abstract: While the pretraining of Foundation Models (FMs) for remote sensing (RS) imagery is on the rise, models remain restricted to a few hundred million parameters. Scaling models to billions of parameters has been shown to yield unprecedented benefits including emergent abilities, but requires data scaling and computing resources typically not available outside industry R&D labs. In this work, we pair high-performance computing resources including Frontier supercomputer, America's first exascale system, and high-resolution optical RS data to pretrain billion-scale FMs. Our study assesses performance of different pretrained variants of vision Transformers across image classification, semantic segmentation and object detection benchmarks, which highlight the importance of data scaling for effective model scaling. Moreover, we discuss construction of a novel TIU pretraining dataset, model initialization, with data and pretrained models intended for public release. By discussing technical challenges and details often lacking in the related literature, this work is intended to offer best practices to the geospatial community toward efficient training and benchmarking of larger FMs.

new A-MFST: Adaptive Multi-Flow Sparse Tracker for Real-Time Tissue Tracking Under Occlusion

Authors: Yuxin Chen, Zijian Wu, Adam Schmidt, Septimiu E. Salcudean

Abstract: Purpose: Tissue tracking is critical for downstream tasks in robot-assisted surgery. The Sparse Efficient Neural Depth and Deformation (SENDD) model has previously demonstrated accurate and real-time sparse point tracking, but struggled with occlusion handling. This work extends SENDD to enhance occlusion detection and tracking consistency while maintaining real-time performance. Methods: We use the Segment Anything Model2 (SAM2) to detect and mask occlusions by surgical tools, and we develop and integrate into SENDD an Adaptive Multi-Flow Sparse Tracker (A-MFST) with forward-backward consistency metrics, to enhance occlusion and uncertainty estimation. A-MFST is an unsupervised variant of the Multi-Flow Dense Tracker (MFT). Results: We evaluate our approach on the STIR dataset and demonstrate a significant improvement in tracking accuracy under occlusion, reducing average tracking errors by 12 percent in Mean Endpoint Error (MEE) and showing a 6 percent improvement in the averaged accuracy over thresholds of 4, 8, 16, 32, and 64 pixels. The incorporation of forward-backward consistency further improves the selection of optimal tracking paths, reducing drift and enhancing robustness. Notably, these improvements were achieved without compromising the model's real-time capabilities. Conclusions: Using A-MFST and SAM2, we enhance SENDD's ability to track tissue in real time under instrument and tissue occlusions.

new Unsupervised Machine Learning for Detecting and Locating Human-Made Objects in 3D Point Cloud

Authors: Hong Zhao, Huyunting Huang, Tonglin Zhang, Baijian Yang, Jin Wei-Kocsis, Songlin Fei

Abstract: A 3D point cloud is an unstructured, sparse, and irregular dataset, typically collected by airborne LiDAR systems over a geological region. Laser pulses emitted from these systems reflect off objects both on and above the ground, resulting in a dataset containing the longitude, latitude, and elevation of each point, as well as information about the corresponding laser pulse strengths. A widely studied research problem, addressed in many previous works, is ground filtering, which involves partitioning the points into ground and non-ground subsets. This research introduces a novel task: detecting and identifying human-made objects amidst natural tree structures. This task is performed on the subset of non-ground points derived from the ground filtering stage. Marked Point Fields (MPFs) are used as models well-suited to these tasks. The proposed methodology consists of three stages: ground filtering, local information extraction (LIE), and clustering. In the ground filtering stage, a statistical method called One-Sided Regression (OSR) is introduced, addressing the limitations of prior ground filtering methods on uneven terrains. In the LIE stage, unsupervised learning methods are lacking. To mitigate this, a kernel-based method for the Hessian matrix of the MPF is developed. In the clustering stage, the Gaussian Mixture Model (GMM) is applied to the results of the LIE stage to partition the non-ground points into trees and human-made objects. The underlying assumption is that LiDAR points from trees exhibit a three-dimensional distribution, while those from human-made objects follow a two-dimensional distribution. The Hessian matrix of the MPF effectively captures this distinction. Experimental results demonstrate that the proposed ground filtering method outperforms previous techniques, and the LIE method successfully distinguishes between points representing trees and human-made objects.

new Towards Robust Algorithms for Surgical Phase Recognition via Digital Twin-based Scene Representation

Authors: Hao Ding, Yuqian Zhang, Hongchao Shu, Xu Lian, Ji Woong Kim, Axel Krieger, Mathias Unberath

Abstract: Purpose: Surgical phase recognition (SPR) is an integral component of surgical data science, enabling high-level surgical analysis. End-to-end trained neural networks that predict surgical phase directly from videos have shown excellent performance on benchmarks. However, these models struggle with robustness due to non-causal associations in the training set, resulting in poor generalizability. Our goal is to improve model robustness to variations in the surgical videos by leveraging the digital twin (DT) paradigm -- an intermediary layer to separate high-level analysis (SPR) from low-level processing (geometric understanding). This approach takes advantage of the recent vision foundation models that ensure reliable low-level scene understanding to craft DT-based scene representations that support various high-level tasks. Methods: We present a DT-based framework for SPR from videos. The framework employs vision foundation models to extract representations. We embed the representation in place of raw video inputs in the state-of-the-art Surgformer model. The framework is trained on the Cholec80 dataset and evaluated on out-of-distribution (OOD) and corrupted test samples. Results: Contrary to the vulnerability of the baseline model, our framework demonstrates strong robustness on both OOD and corrupted samples, with a video-level accuracy of 51.1 on the challenging CRCD dataset, 96.0 on an internal robotics training dataset, and 64.4 on a highly corrupted Cholec80 test set. Conclusion: Our findings lend support to the thesis that DT-based scene representations are effective in enhancing model robustness. Future work will seek to improve the feature informativeness, automate feature extraction, and incorporate interpretability for a more comprehensive framework.

new SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

Authors: Xuanchi Ren, Yifan Lu, Hanxue Liang, Zhangjie Wu, Huan Ling, Mike Chen, Sanja Fidler, Francis Williams, Jiahui Huang

Abstract: We present SCube, a novel method for reconstructing large-scale 3D scenes (geometry, appearance, and semantics) from a sparse set of posed images. Our method encodes reconstructed scenes using a novel representation VoxSplat, which is a set of 3D Gaussians supported on a high-resolution sparse-voxel scaffold. To reconstruct a VoxSplat from images, we employ a hierarchical voxel latent diffusion model conditioned on the input images followed by a feedforward appearance prediction model. The diffusion model generates high-resolution grids progressively in a coarse-to-fine manner, and the appearance network predicts a set of Gaussians within each voxel. From as few as 3 non-overlapping input images, SCube can generate millions of Gaussians with a 1024^3 voxel grid spanning hundreds of meters in 20 seconds. Past works tackling scene reconstruction from images either rely on per-scene optimization and fail to reconstruct the scene away from input views (thus requiring dense view coverage as input) or leverage geometric priors based on low-resolution models, which produce blurry results. In contrast, SCube leverages high-resolution sparse networks and produces sharp outputs from few views. We show the superiority of SCube compared to prior art using the Waymo self-driving dataset on 3D reconstruction and demonstrate its applications, such as LiDAR simulation and text-to-scene generation.

new ResAD: A Simple Framework for Class Generalizable Anomaly Detection

Authors: Xincheng Yao, Zixin Chen, Chao Gao, Guangtao Zhai, Chongyang Zhang

Abstract: This paper explores the problem of class-generalizable anomaly detection, where the objective is to train one unified AD model that can generalize to detect anomalies in diverse classes from different domains without any retraining or fine-tuning on the target data. Because normal feature representations vary significantly across classes, this will cause the widely studied one-for-one AD models to be poorly classgeneralizable (i.e., performance drops dramatically when used for new classes). In this work, we propose a simple but effective framework (called ResAD) that can be directly applied to detect anomalies in new classes. Our main insight is to learn the residual feature distribution rather than the initial feature distribution. In this way, we can significantly reduce feature variations. Even in new classes, the distribution of normal residual features would not remarkably shift from the learned distribution. Therefore, the learned model can be directly adapted to new classes. ResAD consists of three components: (1) a Feature Converter that converts initial features into residual features; (2) a simple and shallow Feature Constraintor that constrains normal residual features into a spatial hypersphere for further reducing feature variations and maintaining consistency in feature scales among different classes; (3) a Feature Distribution Estimator that estimates the normal residual feature distribution, anomalies can be recognized as out-of-distribution. Despite the simplicity, ResAD can achieve remarkable anomaly detection results when directly used in new classes. The code is available at https://github.com/xcyao00/ResAD.

URLs: https://github.com/xcyao00/ResAD.

new 3D Distance-color-coded Assessment of PCI Stent Apposition via Deep-learning-based Three-dimensional Multi-object Segmentation

Authors: Xiaoyang Qin, Hao Huang, Shuaichen Lin, Xinhao Zeng, Kaizhi Cao, Renxiong Wu, Yuming Huang, Junqing Yang, Yong Liu, Gang Li, Guangming Ni

Abstract: Coronary artery disease poses a significant global health challenge, often necessitating percutaneous coronary intervention (PCI) with stent implantation. Assessing stent apposition holds pivotal importance in averting and identifying PCI complications that lead to in-stent restenosis. Here we proposed a novel three-dimensional (3D) distance-color-coded assessment (DccA)for PCI stent apposition via deep-learning-based 3D multi-object segmentation in intravascular optical coherence tomography (IV-OCT). Our proposed 3D DccA accurately segments 3D vessel lumens and stents in IV-OCT images, using a spatial matching network and dual-layer training with style transfer. It quantifies and maps stent-lumen distances into a 3D color space, facilitating 3D visual assessment of PCI stent apposition. Achieving over 95% segmentation precision, our proposed DccA enhances clinical evaluation of PCI stent deployment and supports personalized treatment planning.

new SFTrack: A Robust Scale and Motion Adaptive Algorithm for Tracking Small and Fast Moving Objects

Authors: InPyo Song, Jangwon Lee

Abstract: This paper addresses the problem of multi-object tracking in Unmanned Aerial Vehicle (UAV) footage. It plays a critical role in various UAV applications, including traffic monitoring systems and real-time suspect tracking by the police. However, this task is highly challenging due to the fast motion of UAVs, as well as the small size of target objects in the videos caused by the high-altitude and wide angle views of drones. In this study, we thus introduce a simple yet more effective method compared to previous work to overcome these challenges. Our approach involves a new tracking strategy, which initiates the tracking of target objects from low-confidence detections commonly encountered in UAV application scenarios. Additionally, we propose revisiting traditional appearance-based matching algorithms to improve the association of low-confidence detections. To evaluate the effectiveness of our method, we conducted benchmark evaluations on two UAV-specific datasets (VisDrone2019, UAVDT) and one general object tracking dataset (MOT17). The results demonstrate that our approach surpasses current state-of-the art methodologies, highlighting its robustness and adaptability in diverse tracking environments. Furthermore, we have improved the annotation of the UAVDT dataset by rectifying several errors and addressing omissions found in the original annotations. We will provide this refined version of the dataset to facilitate better benchmarking in the field.

new UniVST: A Unified Framework for Training-free Localized Video Style Transfer

Authors: Quanjian Song, Mingbao Lin, Wengyi Zhan, Shuicheng Yan, Liujuan Cao

Abstract: This paper presents UniVST, a unified framework for localized video style transfer. It operates without the need for training, offering a distinct advantage over existing methods that transfer style across entire videos. The endeavors of this paper comprise: (1) A point-matching mask propagation strategy that leverages feature maps from the DDIM inversion. This streamlines the model's architecture by obviating the need for tracking models. (2) An AdaIN-guided style transfer mechanism that operates at both the latent and attention levels. This balances content fidelity and style richness, mitigating the loss of localized details commonly associated with direct video stylization. (3) A sliding window smoothing strategy that harnesses optical flow within the pixel representation and refines predicted noise to update the latent space. This significantly enhances temporal consistency and diminishes artifacts in video outputs. Our proposed UniVST has been validated to be superior to existing methods in quantitative and qualitative metrics. It adeptly addresses the challenges of preserving the primary object's style while ensuring temporal consistency and detail preservation.

new Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identification

Authors: Yue Su, Hao Li, Maoguo Gong

Abstract: Visible-infrared pedestrian Re-identification (VI-ReID) aims to match pedestrian images captured by infrared cameras and visible cameras. However, VI-ReID, like other traditional cross-modal image matching tasks, poses significant challenges due to its human-centered nature. This is evidenced by the shortcomings of existing methods, which struggle to extract common features across modalities, while losing valuable information when bridging the gap between them in the implicit feature space, potentially compromising security. To address this vulnerability, this paper introduces the first physical adversarial attack against VI-ReID models. Our method, termed Edge-Attack, specifically tests the models' ability to leverage deep-level implicit features by focusing on edge information, the most salient explicit feature differentiating individuals across modalities. Edge-Attack utilizes a novel two-step approach. First, a multi-level edge feature extractor is trained in a self-supervised manner to capture discriminative edge representations for each individual. Second, a generative model based on Vision Transformer Generative Adversarial Networks (ViTGAN) is employed to generate adversarial patches conditioned on the extracted edge features. By applying these patches to pedestrian clothing, we create realistic, physically-realizable adversarial samples. This black-box, self-supervised approach ensures the generalizability of our attack against various VI-ReID models. Extensive experiments on SYSU-MM01 and RegDB datasets, including real-world deployments, demonstrate the effectiveness of Edge- Attack in significantly degrading the performance of state-of-the-art VI-ReID methods.

new Anatomical 3D Style Transfer Enabling Efficient Federated Learning with Extremely Low Communication Costs

Authors: Yuto Shibata, Yasunori Kudo, Yohei Sugawara

Abstract: In this study, we propose a novel federated learning (FL) approach that utilizes 3D style transfer for the multi-organ segmentation task. The multi-organ dataset, obtained by integrating multiple datasets, has high scalability and can improve generalization performance as the data volume increases. However, the heterogeneity of data owing to different clients with diverse imaging conditions and target organs can lead to severe overfitting of local models. To align models that overfit to different local datasets, existing methods require frequent communication with the central server, resulting in higher communication costs and risk of privacy leakage. To achieve an efficient and safe FL, we propose an Anatomical 3D Frequency Domain Generalization (A3DFDG) method for FL. A3DFDG utilizes structural information of human organs and clusters the 3D styles based on the location of organs. By mixing styles based on these clusters, it preserves the anatomical information and leads models to learn intra-organ diversity, while aligning the optimization of each local model. Experiments indicate that our method can maintain its accuracy even in cases where the communication cost is highly limited (=1.25% of the original cost) while achieving a significant difference compared to baselines, with a higher global dice similarity coefficient score of 4.3%. Despite its simplicity and minimal computational overhead, these results demonstrate that our method has high practicality in real-world scenarios where low communication costs and a simple pipeline are required. The code used in this project will be publicly available.

new GiVE: Guiding Visual Encoder to Perceive Overlooked Information

Authors: Junjie Li, Jianghong Ma, Xiaofeng Zhang, Yuhang Li, Jianyang Shi

Abstract: Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack semantic alignment or overlook non-salient objects. We propose the Guiding Visual Encoder to Perceive Overlooked Information (GiVE) approach. GiVE enhances visual representation with an Attention-Guided Adapter (AG-Adapter) module and an Object-focused Visual Semantic Learning module. These incorporate three novel loss terms: Object-focused Image-Text Contrast (OITC) loss, Object-focused Image-Image Contrast (OIIC) loss, and Object-focused Image Discrimination (OID) loss, improving object consideration, retrieval accuracy, and comprehensiveness. Our contributions include dynamic visual focus adjustment, novel loss functions to enhance object retrieval, and the Multi-Object Instruction (MOInst) dataset. Experiments show our approach achieves state-of-the-art performance.

new Semantic Feature Decomposition based Semantic Communication System of Images with Large-scale Visual Generation Models

Authors: Senran Fan, Zhicheng Bao, Chen Dong, Haotai Liang, Xiaodong Xu, Ping Zhang

Abstract: The end-to-end image communication system has been widely studied in the academic community. The escalating demands on image communication systems in terms of data volume, environmental complexity, and task precision require enhanced communication efficiency, anti-noise ability and semantic fidelity. Therefore, we proposed a novel paradigm based on Semantic Feature Decomposition (SeFD) for the integration of semantic communication and large-scale visual generation models to achieve high-performance, highly interpretable and controllable image communication. According to this paradigm, a Texture-Color based Semantic Communication system of Images TCSCI is proposed. TCSCI decomposing the images into their natural language description (text), texture and color semantic features at the transmitter. During the transmission, features are transmitted over the wireless channel, and at the receiver, a large-scale visual generation model is utilized to restore the image through received features. TCSCI can achieve extremely compressed, highly noise-resistant, and visually similar image semantic communication, while ensuring the interpretability and editability of the transmission process. The experiments demonstrate that the TCSCI outperforms traditional image communication systems and existing semantic communication systems under extreme compression with good anti-noise performance and interpretability.

new AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models

Authors: Yabin Zhang, Lei Zhang

Abstract: Recent research has shown that pre-trained vision-language models are effective at identifying out-of-distribution (OOD) samples by using negative labels as guidance. However, employing consistent negative labels across different OOD datasets often results in semantic misalignments, as these text labels may not accurately reflect the actual space of OOD images. To overcome this issue, we introduce \textit{adaptive negative proxies}, which are dynamically generated during testing by exploring actual OOD images, to align more closely with the underlying OOD label space and enhance the efficacy of negative proxy guidance. Specifically, our approach utilizes a feature memory bank to selectively cache discriminative features from test images, representing the targeted OOD distribution. This facilitates the creation of proxies that can better align with specific OOD datasets. While task-adaptive proxies average features to reflect the unique characteristics of each dataset, the sample-adaptive proxies weight features based on their similarity to individual test samples, exploring detailed sample-level nuances. The final score for identifying OOD samples integrates static negative labels with our proposed adaptive proxies, effectively combining textual and visual knowledge for enhanced performance. Our method is training-free and annotation-free, and it maintains fast testing speed. Extensive experiments across various benchmarks demonstrate the effectiveness of our approach, abbreviated as AdaNeg. Notably, on the large-scale ImageNet benchmark, our AdaNeg significantly outperforms existing methods, with a 2.45\% increase in AUROC and a 6.48\% reduction in FPR95. Codes are available at \url{https://github.com/YBZh/OpenOOD-VLM}.

URLs: https://github.com/YBZh/OpenOOD-VLM

new Detection-Guided Deep Learning-Based Model with Spatial Regularization for Lung Nodule Segmentation

Authors: Jiasen Zhang, Mingrui Yang, Weihong Guo, Brian A. Xavier, Michael Bolen, Xiaojuan Li

Abstract: Lung cancer ranks as one of the leading causes of cancer diagnosis and is the foremost cause of cancer-related mortality worldwide. The early detection of lung nodules plays a pivotal role in improving outcomes for patients, as it enables timely and effective treatment interventions. The segmentation of lung nodules plays a critical role in aiding physicians in distinguishing between malignant and benign lesions. However, this task remains challenging due to the substantial variation in the shapes and sizes of lung nodules, and their frequent proximity to lung tissues, which complicates clear delineation. In this study, we introduce a novel model for segmenting lung nodules in computed tomography (CT) images, leveraging a deep learning framework that integrates segmentation and classification processes. This model is distinguished by its use of feature combination blocks, which facilitate the sharing of information between the segmentation and classification components. Additionally, we employ the classification outcomes as priors to refine the size estimation of the predicted nodules, integrating these with a spatial regularization technique to enhance precision. Furthermore, recognizing the challenges posed by limited training datasets, we have developed an optimal transfer learning strategy that freezes certain layers to further improve performance. The results show that our proposed model can capture the target nodules more accurately compared to other commonly used models. By applying transfer learning, the performance can be further improved, achieving a sensitivity score of 0.885 and a Dice score of 0.814.

new Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models

Authors: Liulei Li, Wenguan Wang, Yi Yang

Abstract: Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on text-image pairs often neglect mid/low-level visual cues and struggle at compositional reasoning. In response, we introduce DIFFUSIONHOI, a new HOI detector shedding light on text-to-image diffusion models. Unlike the aforementioned models, diffusion models excel in discerning mid/low-level visual concepts as generative models, and possess strong compositionality to handle novel concepts expressed in text inputs. Considering diffusion models usually emphasize instance objects, we first devise an inversion-based strategy to learn the expression of relation patterns between humans and objects in embedding space. These learned relation embeddings then serve as textual prompts, to steer diffusion models generate images that depict specific interactions, and extract HOI-relevant cues from images without heavy fine-tuning. Benefited from above, DIFFUSIONHOI achieves SOTA performance on three datasets under both regular and zero-shot setups.

new Your Image is Secretly the Last Frame of a Pseudo Video

Authors: Wenlong Chen, Wenlin Chen, Lapo Rastrelli, Yingzhen Li

Abstract: Diffusion models, which can be viewed as a special case of hierarchical variational autoencoders (HVAEs), have shown profound success in generating photo-realistic images. In contrast, standard HVAEs often produce images of inferior quality compared to diffusion models. In this paper, we hypothesize that the success of diffusion models can be partly attributed to the additional self-supervision information for their intermediate latent states provided by corrupted images, which along with the original image form a pseudo video. Based on this hypothesis, we explore the possibility of improving other types of generative models with such pseudo videos. Specifically, we first extend a given image generative model to their video generative model counterpart, and then train the video generative model on pseudo videos constructed by applying data augmentation to the original images. Furthermore, we analyze the potential issues of first-order Markov data augmentation methods, which are typically used in diffusion models, and propose to use more expressive data augmentation to construct more useful information in pseudo videos. Our empirical results on the CIFAR10 and CelebA datasets demonstrate that improved image generation quality can be achieved with additional self-supervised information from pseudo videos.

new Diff-CXR: Report-to-CXR generation through a disease-knowledge enhanced diffusion model

Authors: Peng Huang, Bowen Guo, Shuyu Liang, Junhu Fu, Yuanyuan Wang, Yi Guo

Abstract: Text-To-Image (TTI) generation is significant for controlled and diverse image generation with broad potential applications. Although current medical TTI methods have made some progress in report-to-Chest-Xray (CXR) generation, their generation performance may be limited due to the intrinsic characteristics of medical data. In this paper, we propose a novel disease-knowledge enhanced Diffusion-based TTI learning framework, named Diff-CXR, for medical report-to-CXR generation. First, to minimize the negative impacts of noisy data on generation, we devise a Latent Noise Filtering Strategy that gradually learns the general patterns of anomalies and removes them in the latent space. Then, an Adaptive Vision-Aware Textual Learning Strategy is designed to learn concise and important report embeddings in a domain-specific Vision-Language Model, providing textual guidance for Chest-Xray generation. Finally, by incorporating the general disease knowledge into the pretrained TTI model via a delicate control adapter, a disease-knowledge enhanced diffusion model is introduced to achieve realistic and precise report-to-CXR generation. Experimentally, our Diff-CXR outperforms previous SOTA medical TTI methods by 33.4\% / 8.0\% and 23.8\% / 56.4\% in the FID and mAUC score on MIMIC-CXR and IU-Xray, with the lowest computational complexity at 29.641 GFLOPs. Downstream experiments on three thorax disease classification benchmarks and one CXR-report generation benchmark demonstrate that Diff-CXR is effective in improving classical CXR analysis methods. Notably, models trained on the combination of 1\% real data and synthetic data can achieve a competitive mAUC score compared to models trained on all data, presenting promising clinical applications.

new Image Generation from Image Captioning -- Invertible Approach

Authors: Nandakishore S Menon, Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi

Abstract: Our work aims to build a model that performs dual tasks of image captioning and image generation while being trained on only one task. The central idea is to train an invertible model that learns a one-to-one mapping between the image and text embeddings. Once the invertible model is efficiently trained on one task, the image captioning, the same model can generate new images for a given text through the inversion process, with no additional training. This paper proposes a simple invertible neural network architecture for this problem and presents our current findings.

new An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation

Authors: Dongdong Lin, Yue Li, Benedetta Tondi, Bin Li, Mauro Barni

Abstract: The rapid proliferation of deep neural networks (DNNs) is driving a surge in model watermarking technologies, as the trained deep models themselves serve as intellectual properties. The core of existing model watermarking techniques involves modifying or tuning the models' weights. However, with the emergence of increasingly complex models, ensuring the efficiency of watermarking process is essential to manage the growing computational demands. Prioritizing efficiency not only optimizes resource utilization, making the watermarking process more applicable, but also minimizes potential impacts on model performance. In this letter, we propose an efficient watermarking method for latent diffusion models (LDMs) which is based on Low-Rank Adaptation (LoRA). We specifically choose to add trainable low-rank matrices to the existing weight matrices of the models to embed watermark, while keeping the original weights frozen. Moreover, we also propose a dynamic loss weight tuning algorithm to balance the generative task with the watermark embedding task, ensuring that the model can be watermarked with a limited impact on the quality of the generated images. Experimental results show that the proposed method ensures fast watermark embedding and maintains a very low bit error rate of the watermark, a high-quality of the generated image, and a zero false negative rate (FNR) for verification.

new CAVE: Classifying Abnormalities in Video Capsule Endoscopy

Authors: Ishita Harish, Saurav Mishra, Neha Bhadoria, Rithik Kumar, Madhav Arora, Syed Rameem Zahra, Ankur Gupta

Abstract: In this study, we explore an ensemble-based approach to improve classification accuracy in complex image datasets. Utilizing a Convolutional Block Attention Module (CBAM) alongside a Deep Neural Network (DNN) we leverage the unique feature-extraction capabilities of each model to enhance the overall accuracy. Additional models, such as Random Forest, XGBoost, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), are introduced to further diversify the predictive power of our ensemble. By leveraging these methods, the proposed approach provides robust feature discrimination and improved classification results. Experimental evaluations demonstrate that the ensemble achieves higher accuracy and robustness across challenging and imbalanced classes, showing significant promise for broader applications in computer vision tasks.

new Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search

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.

new Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning

Authors: Sullam Jeoung, Goeric Huybrechts, Bhavana Ganesh, Aram Galstyan, Sravan Bodapati

Abstract: Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and effectiveness of long-form video understanding by utilizing large language models (LLMs) and their tool-harnessing ability. A key aspect of our method is query-adaptive frame sampling, which leverages the reasoning capabilities of LLMs to process only the most relevant frames in real-time, and addresses an important limitation of existing methods which typically involve sampling redundant or irrelevant frames. To enhance the reasoning abilities of our video-understanding agent, we leverage the self-reflective capabilities of LLMs to provide verbal reinforcement to the agent, which leads to improved performance while minimizing the number of frames accessed. We evaluate our method across several video understanding benchmarks and demonstrate that not only it enhances state-of-the-art performance but also improves efficiency by reducing the number of frames sampled.

new You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models

Authors: Eric Slyman, Anirudh Kanneganti, Sanghyun Hong, Stefan Lee

Abstract: We study the impact of a standard practice in compressing foundation vision-language models - quantization - on the models' ability to produce socially-fair outputs. In contrast to prior findings with unimodal models that compression consistently amplifies social biases, our extensive evaluation of four quantization settings across three datasets and three CLIP variants yields a surprising result: while individual models demonstrate bias, we find no consistent change in bias magnitude or direction across a population of compressed models due to quantization.

new MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

Authors: Haozhe Liu, Shikun Liu, Zijian Zhou, Mengmeng Xu, Yanping Xie, Xiao Han, Juan C. P\'erez, Ding Liu, Kumara Kahatapitiya, Menglin Jia, Jui-Chieh Wu, Sen He, Tao Xiang, J\"urgen Schmidhuber, Juan-Manuel P\'erez-R\'ua

Abstract: We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework. Here, MAR handles temporal planning, while DM focuses on spatial generation in an asymmetric network design: i) a MAR-based planning model containing most of the parameters generates planning signals for each masked frame using low-resolution input; ii) a lightweight generation model uses these signals to produce high-resolution frames via diffusion de-noising. MarDini's MAR enables video generation conditioned on any number of masked frames at any frame positions: a single model can handle video interpolation (e.g., masking middle frames), image-to-video generation (e.g., masking from the second frame onward), and video expansion (e.g., masking half the frames). The efficient design allocates most of the computational resources to the low-resolution planning model, making computationally expensive but important spatio-temporal attention feasible at scale. MarDini sets a new state-of-the-art for video interpolation; meanwhile, within few inference steps, it efficiently generates videos on par with those of much more expensive advanced image-to-video models.

new Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions

Authors: Rawal Khirodkar, Jyun-Ting Song, Jinkun Cao, Zhengyi Luo, Kris Kitani

Abstract: Understanding how humans interact with each other is key to building realistic multi-human virtual reality systems. This area remains relatively unexplored due to the lack of large-scale datasets. Recent datasets focusing on this issue mainly consist of activities captured entirely in controlled indoor environments with choreographed actions, significantly affecting their diversity. To address this, we introduce Harmony4D, a multi-view video dataset for human-human interaction featuring in-the-wild activities such as wrestling, dancing, MMA, and more. We use a flexible multi-view capture system to record these dynamic activities and provide annotations for human detection, tracking, 2D/3D pose estimation, and mesh recovery for closely interacting subjects. We propose a novel markerless algorithm to track 3D human poses in severe occlusion and close interaction to obtain our annotations with minimal manual intervention. Harmony4D consists of 1.66 million images and 3.32 million human instances from more than 20 synchronized cameras with 208 video sequences spanning diverse environments and 24 unique subjects. We rigorously evaluate existing state-of-the-art methods for mesh recovery and highlight their significant limitations in modeling close interaction scenarios. Additionally, we fine-tune a pre-trained HMR2.0 model on Harmony4D and demonstrate an improved performance of 54.8% PVE in scenes with severe occlusion and contact. Code and data are available at https://jyuntins.github.io/harmony4d/.

URLs: https://jyuntins.github.io/harmony4d/.

new Deep Learning, Machine Learning -- Digital Signal and Image Processing: From Theory to Application

Authors: Weiche Hsieh, Ziqian Bi, Junyu Liu, Benji Peng, Sen Zhang, Xuanhe Pan, Jiawei Xu, Jinlang Wang, Keyu Chen, Caitlyn Heqi Yin, Pohsun Feng, Yizhu Wen, Tianyang Wang, Ming Li, Jintao Ren, Qian Niu, Silin Chen, Ming Liu

Abstract: Digital Signal Processing (DSP) and Digital Image Processing (DIP) with Machine Learning (ML) and Deep Learning (DL) are popular research areas in Computer Vision and related fields. We highlight transformative applications in image enhancement, filtering techniques, and pattern recognition. By integrating frameworks like the Discrete Fourier Transform (DFT), Z-Transform, and Fourier Transform methods, we enable robust data manipulation and feature extraction essential for AI-driven tasks. Using Python, we implement algorithms that optimize real-time data processing, forming a foundation for scalable, high-performance solutions in computer vision. This work illustrates the potential of ML and DL to advance DSP and DIP methodologies, contributing to artificial intelligence, automated feature extraction, and applications across diverse domains.

new GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields

Authors: Yusuke Sekikawa, Chingwei Hsu, Satoshi Ikehata, Rei Kawakami, Ikuro Sato

Abstract: We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects. Previous studies have shown that the MoE structure provides high-quality representations of a given large-scale scene consisting of many objects. However, we observe that such a MoE NeRF model often produces low-quality representations in the vicinity of experts' boundaries when applied to the task of novel view synthesis of an unseen object from one/few-shot input. We find that this deterioration is primarily caused by the foresight expert selection mechanism, which may leave an unnatural discontinuity in the object shape near the experts' boundaries. Gumbel-NeRF adopts a hindsight expert selection mechanism, which guarantees continuity in the density field even near the experts' boundaries. Experiments using the SRN cars dataset demonstrate the superiority of Gumbel-NeRF over the baselines in terms of various image quality metrics.

new Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement

Authors: Junhao Tan, Songwen Pei, Wei Qin, Bo Fu, Ximing Li, Libo Huang

Abstract: Frequency information (e.g., Discrete Wavelet Transform and Fast Fourier Transform) has been widely applied to solve the issue of Low-Light Image Enhancement (LLIE). However, existing frequency-based models primarily operate in the simple wavelet or Fourier space of images, which lacks utilization of valid global and local information in each space. We found that wavelet frequency information is more sensitive to global brightness due to its low-frequency component while Fourier frequency information is more sensitive to local details due to its phase component. In order to achieve superior preliminary brightness enhancement by optimally integrating spatial channel information with low-frequency components in the wavelet transform, we introduce channel-wise Mamba, which compensates for the long-range dependencies of CNNs and has lower complexity compared to Diffusion and Transformer models. So in this work, we propose a novel Wavelet-based Mamba with Fourier Adjustment model called WalMaFa, consisting of a Wavelet-based Mamba Block (WMB) and a Fast Fourier Adjustment Block (FFAB). We employ an Encoder-Latent-Decoder structure to accomplish the end-to-end transformation. Specifically, WMB is adopted in the Encoder and Decoder to enhance global brightness while FFAB is adopted in the Latent to fine-tune local texture details and alleviate ambiguity. Extensive experiments demonstrate that our proposed WalMaFa achieves state-of-the-art performance with fewer computational resources and faster speed. Code is now available at: https://github.com/mcpaulgeorge/WalMaFa.

URLs: https://github.com/mcpaulgeorge/WalMaFa.

new Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

Authors: Tianlin Guo, Lingling Zhang, Jiaxin Wang, Yuokuo Lei, Yifei Li, Haofen Wang, Jun Liu

Abstract: Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance.

new R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest

Authors: Xupeng Chen, Zhixin Lai, Kangrui Ruan, Shichu Chen, Jiaxiang Liu, Zuozhu Liu

Abstract: Artificial intelligence has made significant strides in medical visual question answering (Med-VQA), yet prevalent studies often interpret images holistically, overlooking the visual regions of interest that may contain crucial information, potentially aligning with a doctor's prior knowledge that can be incorporated with minimal annotations (e.g., bounding boxes). To address this gap, this paper introduces R-LLaVA, designed to enhance biomedical VQA understanding by integrating simple medical annotations as prior knowledge directly into the image space through CLIP. These annotated visual regions of interest are then fed into the LLaVA model during training, aiming to enrich the model's understanding of biomedical queries. Experimental evaluation on four standard Med-VQA datasets demonstrates R-LLaVA's superiority over existing state-of-the-art (SoTA) methods. Additionally, to verify the model's capability in visual comprehension, a novel multiple-choice medical visual understanding dataset is introduced, confirming the positive impact of focusing on visual regions of interest in advancing biomedical VQA understanding.

new Historical Test-time Prompt Tuning for Vision Foundation Models

Authors: Jingyi Zhang, Jiaxing Huang, Xiaoqin Zhang, Ling Shao, Shijian Lu

Abstract: Test-time prompt tuning, which learns prompts online with unlabelled test samples during the inference stage, has demonstrated great potential by learning effective prompts on-the-fly without requiring any task-specific annotations. However, its performance often degrades clearly along the tuning process when the prompts are continuously updated with the test data flow, and the degradation becomes more severe when the domain of test samples changes continuously. We propose HisTPT, a Historical Test-time Prompt Tuning technique that memorizes the useful knowledge of the learnt test samples and enables robust test-time prompt tuning with the memorized knowledge. HisTPT introduces three types of knowledge banks, namely, local knowledge bank, hard-sample knowledge bank, and global knowledge bank, each of which works with different mechanisms for effective knowledge memorization and test-time prompt optimization. In addition, HisTPT features an adaptive knowledge retrieval mechanism that regularizes the prediction of each test sample by adaptively retrieving the memorized knowledge. Extensive experiments show that HisTPT achieves superior prompt tuning performance consistently while handling different visual recognition tasks (e.g., image classification, semantic segmentation, and object detection) and test samples from continuously changing domains.

new UTSRMorph: A Unified Transformer and Superresolution Network for Unsupervised Medical Image Registration

Authors: Runshi Zhang, Hao Mo, Junchen Wang, Bimeng Jie, Yang He, Nenghao Jin, Liang Zhu

Abstract: Complicated image registration is a key issue in medical image analysis, and deep learning-based methods have achieved better results than traditional methods. The methods include ConvNet-based and Transformer-based methods. Although ConvNets can effectively utilize local information to reduce redundancy via small neighborhood convolution, the limited receptive field results in the inability to capture global dependencies. Transformers can establish long-distance dependencies via a self-attention mechanism; however, the intense calculation of the relationships among all tokens leads to high redundancy. We propose a novel unsupervised image registration method named the unified Transformer and superresolution (UTSRMorph) network, which can enhance feature representation learning in the encoder and generate detailed displacement fields in the decoder to overcome these problems. We first propose a fusion attention block to integrate the advantages of ConvNets and Transformers, which inserts a ConvNet-based channel attention module into a multihead self-attention module. The overlapping attention block, a novel cross-attention method, uses overlapping windows to obtain abundant correlations with match information of a pair of images. Then, the blocks are flexibly stacked into a new powerful encoder. The decoder generation process of a high-resolution deformation displacement field from low-resolution features is considered as a superresolution process. Specifically, the superresolution module was employed to replace interpolation upsampling, which can overcome feature degradation. UTSRMorph was compared to state-of-the-art registration methods in the 3D brain MR (OASIS, IXI) and MR-CT datasets. The qualitative and quantitative results indicate that UTSRMorph achieves relatively better performance. The code and datasets are publicly available at https://github.com/Runshi-Zhang/UTSRMorph.

URLs: https://github.com/Runshi-Zhang/UTSRMorph.

new Idempotent Unsupervised Representation Learning for Skeleton-Based Action Recognition

Authors: Lilang Lin, Lehong Wu, Jiahang Zhang, Jiaying Liu

Abstract: Generative models, as a powerful technique for generation, also gradually become a critical tool for recognition tasks. However, in skeleton-based action recognition, the features obtained from existing pre-trained generative methods contain redundant information unrelated to recognition, which contradicts the nature of the skeleton's spatially sparse and temporally consistent properties, leading to undesirable performance. To address this challenge, we make efforts to bridge the gap in theory and methodology and propose a novel skeleton-based idempotent generative model (IGM) for unsupervised representation learning. More specifically, we first theoretically demonstrate the equivalence between generative models and maximum entropy coding, which demonstrates a potential route that makes the features of generative models more compact by introducing contrastive learning. To this end, we introduce the idempotency constraint to form a stronger consistency regularization in the feature space, to push the features only to maintain the critical information of motion semantics for the recognition task. Our extensive experiments on benchmark datasets, NTU RGB+D and PKUMMD, demonstrate the effectiveness of our proposed method. On the NTU 60 xsub dataset, we observe a performance improvement from 84.6$\%$ to 86.2$\%$. Furthermore, in zero-shot adaptation scenarios, our model demonstrates significant efficacy by achieving promising results in cases that were previously unrecognizable. Our project is available at \url{https://github.com/LanglandsLin/IGM}.

URLs: https://github.com/LanglandsLin/IGM

new RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior

Authors: Mingjiang Liang, Yongkang Cheng, Hualin Liang, Shaoli Huang, Wei Liu

Abstract: We present RopeTP, a novel framework that combines Robust pose estimation with a diffusion Trajectory Prior to reconstruct global human motion from videos. At the heart of RopeTP is a hierarchical attention mechanism that significantly improves context awareness, which is essential for accurately inferring the posture of occluded body parts. This is achieved by exploiting the relationships with visible anatomical structures, enhancing the accuracy of local pose estimations. The improved robustness of these local estimations allows for the reconstruction of precise and stable global trajectories. Additionally, RopeTP incorporates a diffusion trajectory model that predicts realistic human motion from local pose sequences. This model ensures that the generated trajectories are not only consistent with observed local actions but also unfold naturally over time, thereby improving the realism and stability of 3D human motion reconstruction. Extensive experimental validation shows that RopeTP surpasses current methods on two benchmark datasets, particularly excelling in scenarios with occlusions. It also outperforms methods that rely on SLAM for initial camera estimates and extensive optimization, delivering more accurate and realistic trajectories.

new Open-Vocabulary Object Detection via Language Hierarchy

Authors: Jiaxing Huang, Jingyi Zhang, Kai Jiang, Shijian Lu

Abstract: Recent studies on generalizable object detection have attracted increasing attention with additional weak supervision from large-scale datasets with image-level labels. However, weakly-supervised detection learning often suffers from image-to-box label mismatch, i.e., image-level labels do not convey precise object information. We design Language Hierarchical Self-training (LHST) that introduces language hierarchy into weakly-supervised detector training for learning more generalizable detectors. LHST expands the image-level labels with language hierarchy and enables co-regularization between the expanded labels and self-training. Specifically, the expanded labels regularize self-training by providing richer supervision and mitigating the image-to-box label mismatch, while self-training allows assessing and selecting the expanded labels according to the predicted reliability. In addition, we design language hierarchical prompt generation that introduces language hierarchy into prompt generation which helps bridge the vocabulary gaps between training and testing. Extensive experiments show that the proposed techniques achieve superior generalization performance consistently across 14 widely studied object detection datasets.

new Addressing the Pitfalls of Image-Based Structural Health Monitoring: A Focus on False Positives, False Negatives, and Base Rate Bias

Authors: Vagelis Plevris

Abstract: This study explores the limitations of image-based structural health monitoring (SHM) techniques in detecting structural damage. Leveraging machine learning and computer vision, image-based SHM offers a scalable and efficient alternative to manual inspections. However, its reliability is impacted by challenges such as false positives, false negatives, and environmental variability, particularly in low base rate damage scenarios. The Base Rate Bias plays a significant role, as low probabilities of actual damage often lead to misinterpretation of positive results. This study uses both Bayesian analysis and a frequentist approach to evaluate the precision of damage detection systems, revealing that even highly accurate models can yield misleading results when the occurrence of damage is rare. Strategies for mitigating these limitations are discussed, including hybrid systems that combine multiple data sources, human-in-the-loop approaches for critical assessments, and improving the quality of training data. These findings provide essential insights into the practical applicability of image-based SHM techniques, highlighting both their potential and their limitations for real-world infrastructure monitoring.

new Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns

Authors: Ronghui Li, Hongwen Zhang, Yachao Zhang, Yuxiang Zhang, Youliang Zhang, Jie Guo, Yan Zhang, Xiu Li, Yebin Liu

Abstract: We propose Lodge++, a choreography framework to generate high-quality, ultra-long, and vivid dances given the music and desired genre. To handle the challenges in computational efficiency, the learning of complex and vivid global choreography patterns, and the physical quality of local dance movements, Lodge++ adopts a two-stage strategy to produce dances from coarse to fine. In the first stage, a global choreography network is designed to generate coarse-grained dance primitives that capture complex global choreography patterns. In the second stage, guided by these dance primitives, a primitive-based dance diffusion model is proposed to further generate high-quality, long-sequence dances in parallel, faithfully adhering to the complex choreography patterns. Additionally, to improve the physical plausibility, Lodge++ employs a penetration guidance module to resolve character self-penetration, a foot refinement module to optimize foot-ground contact, and a multi-genre discriminator to maintain genre consistency throughout the dance. Lodge++ is validated by extensive experiments, which show that our method can rapidly generate ultra-long dances suitable for various dance genres, ensuring well-organized global choreography patterns and high-quality local motion.

new Depth Attention for Robust RGB Tracking

Authors: Yu Liu, Arif Mahmood, Muhammad Haris Khan

Abstract: RGB video object tracking is a fundamental task in computer vision. Its effectiveness can be improved using depth information, particularly for handling motion-blurred target. However, depth information is often missing in commonly used tracking benchmarks. In this work, we propose a new framework that leverages monocular depth estimation to counter the challenges of tracking targets that are out of view or affected by motion blur in RGB video sequences. Specifically, our work introduces following contributions. To the best of our knowledge, we are the first to propose a depth attention mechanism and to formulate a simple framework that allows seamlessly integration of depth information with state of the art tracking algorithms, without RGB-D cameras, elevating accuracy and robustness. We provide extensive experiments on six challenging tracking benchmarks. Our results demonstrate that our approach provides consistent gains over several strong baselines and achieves new SOTA performance. We believe that our method will open up new possibilities for more sophisticated VOT solutions in real-world scenarios. Our code and models are publicly released: https://github.com/LiuYuML/Depth-Attention.

URLs: https://github.com/LiuYuML/Depth-Attention.

new Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis

Authors: Hongyu Sun, Qiuhong Ke, Yongcai Wang, Wang Chen, Kang Yang, Deying Li, Jianfei Cai

Abstract: This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-efficient prompt tuning. However, we observe that the improvement on downstream tasks comes at the expense of a severe drop in 3D domain generalization. To resolve this challenge, we present a comprehensive regulation framework that allows the learnable prompts to actively interact with the well-learned general knowledge in large 3D models to maintain good generalization. Specifically, the proposed framework imposes multiple explicit constraints on the prompt learning trajectory by maximizing the mutual agreement between task-specific predictions and task-agnostic knowledge. We design the regulation framework as a plug-and-play module to embed into existing representative large 3D models. Surprisingly, our method not only realizes consistently increasing generalization ability but also enhances task-specific 3D recognition performances across various 3DDG benchmarks by a clear margin. Considering the lack of study and evaluation on 3DDG, we also create three new benchmarks, namely base-to-new, cross-dataset and few-shot generalization benchmarks, to enrich the field and inspire future research. Code and benchmarks are available at \url{https://github.com/auniquesun/Point-PRC}.

URLs: https://github.com/auniquesun/Point-PRC

new NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking

Authors: Yu Liu, Arif Mahmood, Muhammad Haris Khan

Abstract: Many current visual object tracking benchmarks such as OTB100, NfS, UAV123, LaSOT, and GOT-10K, predominantly contain day-time scenarios while the challenges posed by the night-time has been less investigated. It is primarily because of the lack of a large-scale, well-annotated night-time benchmark for rigorously evaluating tracking algorithms. To this end, this paper presents NT-VOT211, a new benchmark tailored for evaluating visual object tracking algorithms in the challenging night-time conditions. NT-VOT211 consists of 211 diverse videos, offering 211,000 well-annotated frames with 8 attributes including camera motion, deformation, fast motion, motion blur, tiny target, distractors, occlusion and out-of-view. To the best of our knowledge, it is the largest night-time tracking benchmark to-date that is specifically designed to address unique challenges such as adverse visibility, image blur, and distractors inherent to night-time tracking scenarios. Through a comprehensive analysis of results obtained from 42 diverse tracking algorithms on NT-VOT211, we uncover the strengths and limitations of these algorithms, highlighting opportunities for enhancements in visual object tracking, particularly in environments with suboptimal lighting. Besides, a leaderboard for revealing performance rankings, annotation tools, comprehensive meta-information and all the necessary code for reproducibility of results is made publicly available. We believe that our NT-VOT211 benchmark will not only be instrumental in facilitating field deployment of VOT algorithms, but will also help VOT enhancements and it will unlock new real-world tracking applications. Our dataset and other assets can be found at: {https://github.com/LiuYuML/NV-VOT211.

URLs: https://github.com/LiuYuML/NV-VOT211.

new YourSkatingCoach: A Figure Skating Video Benchmark for Fine-Grained Element Analysis

Authors: Wei-Yi Chen, 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.

new CoralSCOP-LAT: Labeling and Analyzing Tool for Coral Reef Images with Dense Mask

Authors: Yuk-Kwan Wong, Ziqiang Zheng, Mingzhe Zhang, David Suggett, Sai-Kit Yeung

Abstract: Images of coral reefs provide invaluable information, which is essentially critical for surveying and monitoring the coral reef ecosystems. Robust and precise identification of coral reef regions within surveying imagery is paramount for assessing coral coverage, spatial distribution, and other statistical analyses. However, existing coral reef analytical approaches mainly focus on sparse points sampled from the whole imagery, which are highly subject to the sampling density and cannot accurately express the coral ambulance. Meanwhile, the analysis is both time-consuming and labor-intensive, and it is also limited to coral biologists. In this work, we propose CoralSCOP-LAT, an automatic and semi-automatic coral reef labeling and analysis tool, specially designed to segment coral reef regions (dense pixel masks) in coral reef images, significantly promoting analysis proficiency and accuracy. CoralSCOP-LAT leverages the advanced coral reef foundation model to accurately delineate coral regions, supporting dense coral reef analysis and reducing the dependency on manual annotation. The proposed CoralSCOP-LAT surpasses the existing tools by a large margin from analysis efficiency, accuracy, and flexibility. We perform comprehensive evaluations from various perspectives and the comparison demonstrates that CoralSCOP-LAT not only accelerates the coral reef analysis but also improves accuracy in coral segmentation and analysis. Our CoralSCOP-LAT, as the first dense coral reef analysis tool in the market, facilitates repeated large-scale coral reef monitoring analysis, contributing to more informed conservation efforts and sustainable management of coral reef ecosystems. Our tool will be available at https://coralscop.hkustvgd.com/.

URLs: https://coralscop.hkustvgd.com/.

new BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

Authors: Yijin Li, Yichen Shen, Zhaoyang Huang, Shuo Chen, Weikang Bian, Xiaoyu Shi, Fu-Yun Wang, Keqiang Sun, Hujun Bao, Zhaopeng Cui, Guofeng Zhang, Hongsheng Li

Abstract: Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and images. To address this gap, we propose BlinkVision, a large-scale and diverse benchmark with multiple modalities and dense correspondence annotations. BlinkVision offers several valuable features: 1) Rich modalities: It includes both event data and RGB images. 2) Extensive annotations: It provides dense per-pixel annotations covering optical flow, scene flow, and point tracking. 3) Large vocabulary: It contains 410 everyday categories, sharing common classes with popular 2D and 3D datasets like LVIS and ShapeNet. 4) Naturalistic: It delivers photorealistic data and covers various naturalistic factors, such as camera shake and deformation. BlinkVision enables extensive benchmarks on three types of correspondence tasks (optical flow, point tracking, and scene flow estimation) for both image-based and event-based methods, offering new observations, practices, and insights for future research. The benchmark website is https://www.blinkvision.net/.

URLs: https://www.blinkvision.net/.

new Unlocking Comics: The AI4VA Dataset for Visual Understanding

Authors: Peter Gr\"onquist, Deblina Bhattacharjee, Bahar Aydemir, Baran Ozaydin, Tong Zhang, Mathieu Salzmann, Sabine S\"usstrunk

Abstract: In the evolving landscape of deep learning, there is a pressing need for more comprehensive datasets capable of training models across multiple modalities. Concurrently, in digital humanities, there is a growing demand to leverage technology for diverse media adaptation and creation, yet limited by sparse datasets due to copyright and stylistic constraints. Addressing this gap, our paper presents a novel dataset comprising Franco-Belgian comics from the 1950s annotated for tasks including depth estimation, semantic segmentation, saliency detection, and character identification. It consists of two distinct and consistent styles and incorporates object concepts and labels taken from natural images. By including such diverse information across styles, this dataset not only holds promise for computational creativity but also offers avenues for the digitization of art and storytelling innovation. This dataset is a crucial component of the AI4VA Workshop Challenges~\url{https://sites.google.com/view/ai4vaeccv2024}, where we specifically explore depth and saliency. Dataset details at \url{https://github.com/IVRL/AI4VA}.

URLs: https://sites.google.com/view/ai4vaeccv2024, https://github.com/IVRL/AI4VA

new GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation

Authors: Phillip Y. Lee, Taehoon Yoon, Minhyuk Sung

Abstract: We introduce a novel training-free spatial grounding technique for text-to-image generation using Diffusion Transformers (DiT). Spatial grounding with bounding boxes has gained attention for its simplicity and versatility, allowing for enhanced user control in image generation. However, prior training-free approaches often rely on updating the noisy image during the reverse diffusion process via backpropagation from custom loss functions, which frequently struggle to provide precise control over individual bounding boxes. In this work, we leverage the flexibility of the Transformer architecture, demonstrating that DiT can generate noisy patches corresponding to each bounding box, fully encoding the target object and allowing for fine-grained control over each region. Our approach builds on an intriguing property of DiT, which we refer to as semantic sharing. Due to semantic sharing, when a smaller patch is jointly denoised alongside a generatable-size image, the two become "semantic clones". Each patch is denoised in its own branch of the generation process and then transplanted into the corresponding region of the original noisy image at each timestep, resulting in robust spatial grounding for each bounding box. In our experiments on the HRS and DrawBench benchmarks, we achieve state-of-the-art performance compared to previous training-free spatial grounding approaches.

new ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation

Authors: Zongyi Li, Shujie Hu, Shujie Liu, Long Zhou, Jeongsoo Choi, Lingwei Meng, Xun Guo, Jinyu Li, Hefei Ling, Furu Wei

Abstract: Text-to-video models have recently undergone rapid and substantial advancements. Nevertheless, due to limitations in data and computational resources, achieving efficient generation of long videos with rich motion dynamics remains a significant challenge. To generate high-quality, dynamic, and temporally consistent long videos, this paper presents ARLON, a novel framework that boosts diffusion Transformers with autoregressive models for long video generation, by integrating the coarse spatial and long-range temporal information provided by the AR model to guide the DiT model. Specifically, ARLON incorporates several key innovations: 1) A latent Vector Quantized Variational Autoencoder (VQ-VAE) compresses the input latent space of the DiT model into compact visual tokens, bridging the AR and DiT models and balancing the learning complexity and information density; 2) An adaptive norm-based semantic injection module integrates the coarse discrete visual units from the AR model into the DiT model, ensuring effective guidance during video generation; 3) To enhance the tolerance capability of noise introduced from the AR inference, the DiT model is trained with coarser visual latent tokens incorporated with an uncertainty sampling module. Experimental results demonstrate that ARLON significantly outperforms the baseline OpenSora-V1.2 on eight out of eleven metrics selected from VBench, with notable improvements in dynamic degree and aesthetic quality, while delivering competitive results on the remaining three and simultaneously accelerating the generation process. In addition, ARLON achieves state-of-the-art performance in long video generation. Detailed analyses of the improvements in inference efficiency are presented, alongside a practical application that demonstrates the generation of long videos using progressive text prompts. See demos of ARLON at \url{http://aka.ms/arlon}.

URLs: http://aka.ms/arlon

new Referring Human Pose and Mask Estimation in the Wild

Authors: Bo Miao, Mingtao Feng, Zijie Wu, Mohammed Bennamoun, Yongsheng Gao, Ajmal Mian

Abstract: We introduce Referring Human Pose and Mask Estimation (R-HPM) in the wild, where either a text or positional prompt specifies the person of interest in an image. This new task holds significant potential for human-centric applications such as assistive robotics and sports analysis. In contrast to previous works, R-HPM (i) ensures high-quality, identity-aware results corresponding to the referred person, and (ii) simultaneously predicts human pose and mask for a comprehensive representation. To achieve this, we introduce a large-scale dataset named RefHuman, which substantially extends the MS COCO dataset with additional text and positional prompt annotations. RefHuman includes over 50,000 annotated instances in the wild, each equipped with keypoint, mask, and prompt annotations. To enable prompt-conditioned estimation, we propose the first end-to-end promptable approach named UniPHD for R-HPM. UniPHD extracts multimodal representations and employs a proposed pose-centric hierarchical decoder to process (text or positional) instance queries and keypoint queries, producing results specific to the referred person. Extensive experiments demonstrate that UniPHD produces quality results based on user-friendly prompts and achieves top-tier performance on RefHuman val and MS COCO val2017. Data and Code: https://github.com/bo-miao/RefHuman

URLs: https://github.com/bo-miao/RefHuman

new Fractal and Turbulent Feature Extraction and NFT Label Generation for Pollock Style Migration Paintings Based on VGG19

Authors: Yiquan Wang

Abstract: This paper puts forth an innovative approach that fuses deep learning, fractal analysis, and turbulence feature extraction techniques to create abstract artworks in the style of Pollock. The content and style characteristics of the image are extracted by the MindSpore deep learning framework and a pre-trained VGG19 model. An optimisation process is then employed to The method generates high-quality Pollock-style images by combining content loss, style loss and full variance loss to achieve accurate style migration. Furthermore, this paper implements a fractal dimension calculation method based on the difference box-counting method, which effectively estimates the fractal dimension of an image through edge extraction and fractal analysis. The method is based on a two-dimensional discrete wavelet transform using a Haar wavelet to decompose the image in order to extract different frequency information. This is followed by the combination of multiple features to generate unique non-homogeneous token (NFT) labels for the authentication and protection of digital artwork. The experimental results demonstrate that the generated artworks exhibit The method demonstrates significant diversity and complexity in terms of fractal dimensions and turbulence features, while the generated NFT tags ensure the uniqueness and tamperability of each digital collection. The present method organically combines computer vision, digital signal processing and blockchain technology to provide a new solution for the creation and authentication of digital artworks.

new Asynchronous Perception Machine For Efficient Test-Time-Training

Authors: Rajat Modi, Yogesh Singh Rawat

Abstract: In this work, we propose Asynchronous Perception Machine (APM), a computationally-efficient architecture for test-time-training (TTT). APM can process patches of an image one at a time in any order \textit{asymmetrically,} and \textit{still encode} semantic-awareness in the net. We demonstrate APM's ability to recognize out-of-distribution images \textit{without} dataset-specific pre-training, augmentation or any-pretext task. APM offers competitive performance over existing TTT approaches. To perform TTT, APM just distills test sample's representation \textit{once}. APM possesses a unique property: it can learn using just this single representation and starts predicting semantically-aware features. APM demostrates potential applications beyond test-time-training: APM can scale up to a dataset of 2D images and yield semantic-clusterings in a single forward pass. APM also provides first empirical evidence towards validating GLOM's insight, i.e. input percept is a field. Therefore, APM helps us converge towards an implementation which can do \textit{both} interpolation and perception on a \textit{shared}-connectionist hardware. Our code is publicly available at this link: https://github.com/rajatmodi62/apm.

URLs: https://github.com/rajatmodi62/apm.

new SympCam: Remote Optical Measurement of Sympathetic Arousal

Authors: Bj\"orn Braun, Daniel McDuff, Tadas Baltrusaitis, Paul Streli, Max Moebus, Christian Holz

Abstract: Recent work has shown that a person's sympathetic arousal can be estimated from facial videos alone using basic signal processing. This opens up new possibilities in the field of telehealth and stress management, providing a non-invasive method to measure stress only using a regular RGB camera. In this paper, we present SympCam, a new 3D convolutional architecture tailored to the task of remote sympathetic arousal prediction. Our model incorporates a temporal attention module (TAM) to enhance the temporal coherence of our sequential data processing capabilities. The predictions from our method improve accuracy metrics of sympathetic arousal in prior work by 48% to a mean correlation of 0.77. We additionally compare our method with common remote photoplethysmography (rPPG) networks and show that they alone cannot accurately predict sympathetic arousal "out-of-the-box". Furthermore, we show that the sympathetic arousal predicted by our method allows detecting physical stress with a balanced accuracy of 90% - an improvement of 61% compared to the rPPG method commonly used in related work, demonstrating the limitations of using rPPG alone. Finally, we contribute a dataset designed explicitly for the task of remote sympathetic arousal prediction. Our dataset contains synchronized face and hand videos of 20 participants from two cameras synchronized with electrodermal activity (EDA) and photoplethysmography (PPG) measurements. We will make this dataset available to the community and use it to evaluate the methods in this paper. To the best of our knowledge, this is the first dataset available to other researchers designed for remote sympathetic arousal prediction.

new Detection of adrenal anomalous findings in spinal CT images using multi model graph aggregatio

Authors: Shabalin Carmel, Shenkman Israel, Shelef Ilan, Ben-Arie Gal, Alex Geftler, Shahar Yuval

Abstract: Low back pain is the symptom that is the second most frequently reported to primary care physicians, effecting 50 to 80 percent of the population in a lifetime, resulting in multiple referrals of patients suffering from back problems, to CT and MRI scans, which are then examined by radiologists. The radiologists examining these spinal scans naturally focus on spinal pathologies and might miss other types of abnormalities, and in particular, abdominal ones, such as malignancies. Nevertheless, the patients whose spine was scanned might as well have malignant and other abdominal pathologies. Thus, clinicians have suggested the need for computerized assistance and decision support in screening spinal scans for additional abnormalities. In the current study, We have addressed the important case of detecting suspicious lesions in the adrenal glands as an example for the overall methodology we have developed. A patient CT scan is integrated from multiple slices with an axial orientation. Our method determines whether a patient has an abnormal adrenal gland, and localises the abnormality if it exists. Our method is composed of three deep learning models; each model has a different task for achieving the final goal. We call our compound method the Multi Model Graph Aggregation MMGA method. The novelty in this study is twofold. First, the use, for an important screening task, of CT scans that are originally focused and tuned for imaging the spine, which were acquired from patients with potential spinal disorders, for detection of a totally different set of abnormalities such as abdominal Adrenal glands pathologies. Second, we have built a complex pipeline architecture composed from three deep learning models that can be utilized for other organs (such as the pancreas or the kidney), or for similar applications, but using other types of imaging, such as MRI.

new Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization

Authors: Mohammad Hassan Vali, Tom B\"ackstr\"om

Abstract: Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable latent space or discover interpretable directions that require exploiting data labels or annotated synthesized samples for training. However, we propose using a modification of vector quantization called space-filling vector quantization (SFVQ), which quantizes the data on a piece-wise linear curve. SFVQ can capture the underlying morphological structure of the latent space and thus make it interpretable. We apply this technique to model the latent space of pretrained StyleGAN2 and BigGAN networks on various datasets. Our experiments show that the SFVQ curve yields a general interpretable model of the latent space that determines which part of the latent space corresponds to what specific generative factors. Furthermore, we demonstrate that each line of SFVQ's curve can potentially refer to an interpretable direction for applying intelligible image transformations. We also showed that the points located on an SFVQ line can be used for controllable data augmentation.

new Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering

Authors: Meng Wei, Qianyi Wu, Jianmin Zheng, Hamid Rezatofighi, Jianfei Cai

Abstract: Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled high-fidelity novel view synthesis at real-time speeds. However, the noisy and discrete nature of 3D Gaussian primitives hinders accurate surface estimation. Previous attempts to regularize 3D Gaussian normals often degrade rendering quality due to the fundamental disconnect between normal vectors and the rendering pipeline in 3DGS-based methods. Therefore, we introduce Normal-GS, a novel approach that integrates normal vectors into the 3DGS rendering pipeline. The core idea is to model the interaction between normals and incident lighting using the physically-based rendering equation. Our approach re-parameterizes surface colors as the product of normals and a designed Integrated Directional Illumination Vector (IDIV). To optimize memory usage and simplify optimization, we employ an anchor-based 3DGS to implicitly encode locally-shared IDIVs. Additionally, Normal-GS leverages optimized normals and Integrated Directional Encoding (IDE) to accurately model specular effects, enhancing both rendering quality and surface normal precision. Extensive experiments demonstrate that Normal-GS achieves near state-of-the-art visual quality while obtaining accurate surface normals and preserving real-time rendering performance.

new A Framework for Real-Time Volcano-Seismic Event Recognition Based on Multi-Station Seismograms and Semantic Segmentation Models

Authors: Camilo Espinosa-Curilem, Millaray Curilem, Daniel Basualto

Abstract: In volcano monitoring, effective recognition of seismic events is essential for understanding volcanic activity and raising timely warning alerts. Traditional methods rely on manual analysis, which can be subjective and labor-intensive. Furthermore, current automatic approaches often tackle detection and classification separately, mostly rely on single station information and generally require tailored preprocessing and representations to perform predictions. These limitations often hinder their application to real-time monitoring and utilization across different volcano conditions. This study introduces a novel approach that utilizes Semantic Segmentation models to automate seismic event recognition by applying a straight forward transformation of multi-channel 1D signals into 2D representations, enabling their use as images. Our framework employs a data-driven, end-to-end design that integrates multi-station seismic data with minimal preprocessing, performing both detection and classification simultaneously for five seismic event classes. We evaluated four state-of-the-art segmentation models (UNet, UNet++, DeepLabV3+ and SwinUNet) on approximately 25.000 seismic events recorded at four different Chilean volcanoes: Nevados del Chill\'an Volcanic Complex, Laguna del Maule, Villarrica and Puyehue-Cord\'on Caulle. Among these models, the UNet architecture was identified as the most effective model, achieving mean F1 and Intersection over Union (IoU) scores of up to 0.91 and 0.88, respectively, and demonstrating superior noise robustness and model flexibility to unseen volcano datasets.

new Exocentric To Egocentric Transfer For Action Recognition: A Short Survey

Authors: Anirudh Thatipelli, Shao-Yuan Lo, Amit K. Roy-Chowdhury

Abstract: Egocentric vision captures the scene from the point of view of the camera wearer while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The community has regained interest in the field of egocentric vision. While the third-person view and first-person have been thoroughly investigated, very few works aim to study both synchronously. Exocentric videos contain many relevant signals that are transferrable to egocentric videos. In this paper, we provide a broad overview of works combining egocentric and exocentric visions.

new PViT: Prior-augmented Vision Transformer for Out-of-distribution Detection

Authors: Tianhao Zhang, Zhixiang Chen, Lyudmila S. Mihaylova

Abstract: Vision Transformers (ViTs) have achieved remarkable success over various vision tasks, yet their robustness against data distribution shifts and inherent inductive biases remain underexplored. To enhance the robustness of ViT models for image Out-of-Distribution (OOD) detection, we introduce a novel and generic framework named Prior-augmented Vision Transformer (PViT). PViT identifies OOD samples by quantifying the divergence between the predicted class logits and the prior logits obtained from pre-trained models. Unlike existing state-of-the-art OOD detection methods, PViT shapes the decision boundary between ID and OOD by utilizing the proposed prior guide confidence, without requiring additional data modeling, generation methods, or structural modifications. Extensive experiments on the large-scale ImageNet benchmark demonstrate that PViT significantly outperforms existing state-of-the-art OOD detection methods. Additionally, through comprehensive analyses, ablation studies, and discussions, we show how PViT can strategically address specific challenges in managing large vision models, paving the way for new advancements in OOD detection.

new Ant Detective: An Automated Approach for Counting Ants in Densely Populated Images and Gaining Insight into Ant Foraging Behavior

Authors: Mautushi Das, Fang-Ling Chloe Liu, Charly Hartle, Chin-Cheng Scotty Yang, C. P. James Chen

Abstract: Ant foraging behavior is essential to understanding ecological dynamics and developing effective pest management strategies, but quantifying this behavior is challenging due to the labor-intensive nature of manual counting, especially in densely populated images. This study presents an automated approach using computer vision to count ants and analyze their foraging behavior. Leveraging the YOLOv8 model, the system was calibrated and evaluated on datasets encompassing various imaging scenarios and densities. The study results demonstrate that the system achieves average precision and recall of up to 87.96% and 87,78%, respectively, with only 64 calibration images provided when the both calibration and evaluation images share similar imaging backgrounds. When the background is more complex than the calibration images, the system requires a larger calibration set to generalize effectively, with 1,024 images yielding the precision and recall of up to 83.60% and 78.88, respectively. In more challenging scenarios where more than one thousand ants are present in a single image, the system significantly improves detection accuracy by slicing images into smaller patches, reaching a precision and recall of 77.97% and 71.36%, respectively. The system's ability to generate heatmaps visualizes the spatial distribution of ant activity over time, providing valuable insights into their foraging patterns. This spatial-temporal analysis enables a more comprehensive understanding of ant behavior, which is crucial for ecological studies and improving pest control methods. By automating the counting process and offering detailed behavioral analysis, this study provides an efficient tool for researchers and pest control professionals to develop more effective strategies.

new A Comparative Study of Multiple Deep Learning Algorithms for Efficient Localization of Bone Joints in the Upper Limbs of Human Body

Authors: Soumalya Bose, Soham Basu, Indranil Bera, Sambit Mallick, Snigdha Paul, Saumodip Das, Swarnendu Sil, Swarnava Ghosh, Anindya Sen

Abstract: This paper addresses the medical imaging problem of joint detection in the upper limbs, viz. elbow, shoulder, wrist and finger joints. Localization of joints from X-Ray and Computerized Tomography (CT) scans is an essential step for the assessment of various bone-related medical conditions like Osteoarthritis, Rheumatoid Arthritis, and can even be used for automated bone fracture detection. Automated joint localization also detects the corresponding bones and can serve as input to deep learning-based models used for the computerized diagnosis of the aforementioned medical disorders. This in-creases the accuracy of prediction and aids the radiologists with analyzing the scans, which is quite a complex and exhausting task. This paper provides a detailed comparative study between diverse Deep Learning (DL) models - YOLOv3, YOLOv7, EfficientDet and CenterNet in multiple bone joint detections in the upper limbs of the human body. The research analyses the performance of different DL models, mathematically, graphically and visually. These models are trained and tested on a portion of the openly available MURA (musculoskeletal radiographs) dataset. The study found that the best Mean Average Precision (mAP at 0.5:0.95) values of YOLOv3, YOLOv7, EfficientDet and CenterNet are 35.3, 48.3, 46.5 and 45.9 respectively. Besides, it has been found YOLOv7 performed the best for accurately predicting the bounding boxes while YOLOv3 performed the worst in the Visual Analysis test. Code available at https://github.com/Sohambasu07/BoneJointsLocalization

URLs: https://github.com/Sohambasu07/BoneJointsLocalization

new ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings

Authors: Suyoung Lee, Jaeyoung Chung, Jaeyoo Huh, Kyoung Mu Lee

Abstract: Omnidirectional (or 360-degree) images are increasingly being used for 3D applications since they allow the rendering of an entire scene with a single image. Existing works based on neural radiance fields demonstrate successful 3D reconstruction quality on egocentric videos, yet they suffer from long training and rendering times. Recently, 3D Gaussian splatting has gained attention for its fast optimization and real-time rendering. However, directly using a perspective rasterizer to omnidirectional images results in severe distortion due to the different optical properties between two image domains. In this work, we present ODGS, a novel rasterization pipeline for omnidirectional images, with geometric interpretation. For each Gaussian, we define a tangent plane that touches the unit sphere and is perpendicular to the ray headed toward the Gaussian center. We then leverage a perspective camera rasterizer to project the Gaussian onto the corresponding tangent plane. The projected Gaussians are transformed and combined into the omnidirectional image, finalizing the omnidirectional rasterization process. This interpretation reveals the implicit assumptions within the proposed pipeline, which we verify through mathematical proofs. The entire rasterization process is parallelized using CUDA, achieving optimization and rendering speeds 100 times faster than NeRF-based methods. Our comprehensive experiments highlight the superiority of ODGS by delivering the best reconstruction and perceptual quality across various datasets. Additionally, results on roaming datasets demonstrate that ODGS restores fine details effectively, even when reconstructing large 3D scenes. The source code is available on our project page (https://github.com/esw0116/ODGS).

URLs: https://github.com/esw0116/ODGS).

new CIB-SE-YOLOv8: Optimized YOLOv8 for Real-Time Safety Equipment Detection on Construction Sites

Authors: Xiaoyi Liu, Ruina Du, Lianghao Tan, Junran Xu, Chen Chen, Huangqi Jiang, Saleh Aldwais

Abstract: Ensuring safety on construction sites is critical, with helmets playing a key role in reducing injuries. Traditional safety checks are labor-intensive and often insufficient. This study presents a computer vision-based solution using YOLO for real-time helmet detection, leveraging the SHEL5K dataset. Our proposed CIB-SE-YOLOv8 model incorporates SE attention mechanisms and modified C2f blocks, enhancing detection accuracy and efficiency. This model offers a more effective solution for promoting safety compliance on construction sites.

new Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Composition

Authors: Satoshi Ikehata, Yuta Asano

Abstract: In this paper, we present a groundbreaking spectrally multiplexed photometric stereo approach for recovering surface normals of dynamic surfaces without the need for calibrated lighting or sensors, a notable advancement in the field traditionally hindered by stringent prerequisites and spectral ambiguity. By embracing spectral ambiguity as an advantage, our technique enables the generation of training data without specialized multispectral rendering frameworks. We introduce a unique, physics-free network architecture, SpectraM-PS, that effectively processes multiplexed images to determine surface normals across a wide range of conditions and material types, without relying on specific physically-based knowledge. Additionally, we establish the first benchmark dataset, SpectraM14, for spectrally multiplexed photometric stereo, facilitating comprehensive evaluations against existing calibrated methods. Our contributions significantly enhance the capabilities for dynamic surface recovery, particularly in uncalibrated setups, marking a pivotal step forward in the application of photometric stereo across various domains.

new Face-MLLM: A Large Face Perception Model

Authors: Haomiao Sun, Mingjie He, Tianheng Lian, Hu Han, Shiguang Shan

Abstract: Although multimodal large language models (MLLMs) have achieved promising results on a wide range of vision-language tasks, their ability to perceive and understand human faces is rarely explored. In this work, we comprehensively evaluate existing MLLMs on face perception tasks. The quantitative results reveal that existing MLLMs struggle to handle these tasks. The primary reason is the lack of image-text datasets that contain fine-grained descriptions of human faces. To tackle this problem, we design a practical pipeline for constructing datasets, upon which we further build a novel multimodal large face perception model, namely Face-MLLM. Specifically, we re-annotate LAION-Face dataset with more detailed face captions and facial attribute labels. Besides, we re-formulate traditional face datasets using the question-answer style, which is fit for MLLMs. Together with these enriched datasets, we develop a novel three-stage MLLM training method. In the first two stages, our model learns visual-text alignment and basic visual question answering capability, respectively. In the third stage, our model learns to handle multiple specialized face perception tasks. Experimental results show that our model surpasses previous MLLMs on five famous face perception tasks. Besides, on our newly introduced zero-shot facial attribute analysis task, our Face-MLLM also presents superior performance.

new Interpretable Image Classification with Adaptive Prototype-based Vision Transformers

Authors: Chiyu Ma, Jon Donnelly, Wenjun Liu, Soroush Vosoughi, Cynthia Rudin, Chaofan Chen

Abstract: We present ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of learned prototypes, providing explanations of the form ``this looks like that.'' In our model, a prototype consists of \textit{parts}, which can deform over irregular geometries to create a better comparison between images. Unlike existing models that rely on Convolutional Neural Network (CNN) backbones and spatially rigid prototypes, our model integrates Vision Transformer (ViT) backbones into prototype based models, while offering spatially deformed prototypes that not only accommodate geometric variations of objects but also provide coherent and clear prototypical feature representations with an adaptive number of prototypical parts. Our experiments show that our model can generally achieve higher performance than the existing prototype based models. Our comprehensive analyses ensure that the prototypes are consistent and the interpretations are faithful.

new CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

Authors: Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng, Masayoshi Tomizuka, Ping Luo, Mingyu Ding, Varun Jampani, Wei Zhan

Abstract: Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces CompGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfer the well-established 2D compositionality to initialize the Gaussian parameters on an entity-by-entity basis, ensuring both consistent 3D priors for each entity and reasonable interactions among multiple entities; (2) Dynamic Optimization: We propose a dynamic strategy to optimize 3D Gaussians using Score Distillation Sampling (SDS) loss. CompGS first automatically decomposes 3D Gaussians into distinct entity parts, enabling optimization at both the entity and composition levels. Additionally, CompGS optimizes across objects of varying scales by dynamically adjusting the spatial parameters of each entity, enhancing the generation of fine-grained details, particularly in smaller entities. Qualitative comparisons and quantitative evaluations on T3Bench demonstrate the effectiveness of CompGS in generating compositional 3D objects with superior image quality and semantic alignment over existing methods. CompGS can also be easily extended to controllable 3D editing, facilitating scene generation. We hope CompGS will provide new insights to the compositional 3D generation. Project page: https://chongjiange.github.io/compgs.html.

URLs: https://chongjiange.github.io/compgs.html.

new BLAPose: Enhancing 3D Human Pose Estimation with Bone Length Adjustment

Authors: C. Hsu, J. Jang

Abstract: Current approaches in 3D human pose estimation primarily focus on regressing 3D joint locations, often neglecting critical physical constraints such as bone length consistency and body symmetry. This work introduces a recurrent neural network architecture designed to capture holistic information across entire video sequences, enabling accurate prediction of bone lengths. To enhance training effectiveness, we propose a novel augmentation strategy using synthetic bone lengths that adhere to physical constraints. Moreover, we present a bone length adjustment method that preserves bone orientations while substituting bone lengths with predicted values. Our results demonstrate that existing 3D human pose estimation models can be significantly enhanced through this adjustment process. Furthermore, we fine-tune human pose estimation models using inferred bone lengths, observing notable improvements. Our bone length prediction model surpasses the previous best results, and our adjustment and fine-tuning method enhance performance across several metrics on the Human3.6M dataset.

new Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding

Authors: Jiewen Yang, Yiqun Lin, Bin Pu, Xiaomeng Li

Abstract: Quantitative analysis of cardiac motion is crucial for assessing cardiac function. This analysis typically uses imaging modalities such as MRI and Echocardiograms that capture detailed image sequences throughout the heartbeat cycle. Previous methods predominantly focused on the analysis of image pairs lacking consideration of the motion dynamics and spatial variability. Consequently, these methods often overlook the long-term relationships and regional motion characteristic of cardiac. To overcome these limitations, we introduce the \textbf{GPTrack}, a novel unsupervised framework crafted to fully explore the temporal and spatial dynamics of cardiac motion. The GPTrack enhances motion tracking by employing the sequential Gaussian Process in the latent space and encoding statistics by spatial information at each time stamp, which robustly promotes temporal consistency and spatial variability of cardiac dynamics. Also, we innovatively aggregate sequential information in a bidirectional recursive manner, mimicking the behavior of diffeomorphic registration to better capture consistent long-term relationships of motions across cardiac regions such as the ventricles and atria. Our GPTrack significantly improves the precision of motion tracking in both 3D and 4D medical images while maintaining computational efficiency. The code is available at: https://github.com/xmed-lab/GPTrack

URLs: https://github.com/xmed-lab/GPTrack

new SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity

Authors: Kunyun Wang, Jieru Zhao, Shuo Yang, Wenchao Ding, Minyi Guo

Abstract: Deep learning models have become pivotal in the field of video processing and is increasingly critical in practical applications such as autonomous driving and object detection. Although Vision Transformers (ViTs) have demonstrated their power, Convolutional Neural Networks (CNNs) remain a highly efficient and high-performance choice for feature extraction and encoding. However, the intensive computational demands of convolution operations hinder its broader adoption as a video encoder. Given the inherent temporal continuity in video frames, changes between consecutive frames are minimal, allowing for the skipping of redundant computations. This technique, which we term as Diff Computation, presents two primary challenges. First, Diff Computation requires to cache intermediate feature maps to ensure the correctness of non-linear computations, leading to significant memory consumption. Second, the imbalance of sparsity among layers, introduced by Diff Computation, incurs accuracy degradation. To address these issues, we propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation. We integrate these techniques into our framework, SparseTem, to seamlessly support various CNN-based video encoders. SparseTem achieves speedup of 1.79x for EfficientDet and 4.72x for CRNN, with minimal accuracy drop and no additional memory overhead. Extensive experimental results demonstrate that SparseTem sets a new state-of-the-art by effectively utilizing temporal continuity to accelerate CNN-based video encoders.

new Transformer-Based Tooth Alignment Prediction With Occlusion And Collision Constraints

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.

new Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation

Authors: Wenjun Miao, Guansong Pang, Jin Zheng, Xiao Bai

Abstract: One key challenge in Out-of-Distribution (OOD) detection is the absence of ground-truth OOD samples during training. One principled approach to address this issue is to use samples from external datasets as outliers (i.e., pseudo OOD samples) to train OOD detectors. However, we find empirically that the outlier samples often present a distribution shift compared to the true OOD samples, especially in Long-Tailed Recognition (LTR) scenarios, where ID classes are heavily imbalanced, \ie, the true OOD samples exhibit very different probability distribution to the head and tailed ID classes from the outliers. In this work, we propose a novel approach, namely normalized outlier distribution adaptation (AdaptOD), to tackle this distribution shift problem. One of its key components is dynamic outlier distribution adaptation that effectively adapts a vanilla outlier distribution based on the outlier samples to the true OOD distribution by utilizing the OOD knowledge in the predicted OOD samples during inference. Further, to obtain a more reliable set of predicted OOD samples on long-tailed ID data, a novel dual-normalized energy loss is introduced in AdaptOD, which leverages class- and sample-wise normalized energy to enforce a more balanced prediction energy on imbalanced ID samples. This helps avoid bias toward the head samples and learn a substantially better vanilla outlier distribution than existing energy losses during training. It also eliminates the need of manually tuning the sensitive margin hyperparameters in energy losses. Empirical results on three popular benchmarks for OOD detection in LTR show the superior performance of AdaptOD over state-of-the-art methods. Code is available at \url{https://github.com/mala-lab/AdaptOD}.

URLs: https://github.com/mala-lab/AdaptOD

new Fidelity-Imposed Displacement Editing for the Learn2Reg 2024 SHG-BF Challenge

Authors: Jiacheng Wang, Xiang Chen, Renjiu Hu, Rongguang Wang, Min Liu, Yaonan Wang, Jiazheng Wang, Hao Li, Hang Zhang

Abstract: Co-examination of second-harmonic generation (SHG) and bright-field (BF) microscopy enables the differentiation of tissue components and collagen fibers, aiding the analysis of human breast and pancreatic cancer tissues. However, large discrepancies between SHG and BF images pose challenges for current learning-based registration models in aligning SHG to BF. In this paper, we propose a novel multi-modal registration framework that employs fidelity-imposed displacement editing to address these challenges. The framework integrates batch-wise contrastive learning, feature-based pre-alignment, and instance-level optimization. Experimental results from the Learn2Reg COMULISglobe SHG-BF Challenge validate the effectiveness of our method, securing the 1st place on the online leaderboard.

new Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Gaussian Splatting

Authors: Jiawei Xu, Zexin Fan, Jian Yang, Jin Xie

Abstract: Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed.

new Evaluation of neural network algorithms for atmospheric turbulence mitigation

Authors: Tushar Jain, Madeline Lubien, Jerome Gilles

Abstract: A variety of neural networks architectures are being studied to tackle blur in images and videos caused by a non-steady camera and objects being captured. In this paper, we present an overview of these existing networks and perform experiments to remove the blur caused by atmospheric turbulence. Our experiments aim to examine the reusability of existing networks and identify desirable aspects of the architecture in a system that is geared specifically towards atmospheric turbulence mitigation. We compare five different architectures, including a network trained in an end-to-end fashion, thereby removing the need for a stabilization step.

new Novel Object Synthesis via Adaptive Text-Image Harmony

Authors: Zeren Xiong, Zedong Zhang, Zikun Chen, Shuo Chen, Xiang Li, Gan Sun, Jian Yang, Jun Li

Abstract: In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this task, \textit{i.e.}, often generating an object that predominantly reflects either the text or the image due to an imbalance between their inputs. To address this issue, we propose a simple yet effective method called Adaptive Text-Image Harmony (ATIH) to generate novel and surprising objects. First, we introduce a scale factor and an injection step to balance text and image features in cross-attention and to preserve image information in self-attention during the text-image inversion diffusion process, respectively. Second, to better integrate object text and image, we design a balanced loss function with a noise parameter, ensuring both optimal editability and fidelity of the object image. Third, to adaptively adjust these parameters, we present a novel similarity score function that not only maximizes the similarities between the generated object image and the input text/image but also balances these similarities to harmonize text and image integration. Extensive experiments demonstrate the effectiveness of our approach, showcasing remarkable object creations such as colobus-glass jar. Project page: https://xzr52.github.io/ATIH/.

URLs: https://xzr52.github.io/ATIH/.

new ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives

Authors: Wenyang Liu, Kejun Wu, Tianyi Liu, Yi Wang, Kim-Hui Yap, Lap-Pui Chau

Abstract: Multimedia file fragment classification (MFFC) aims to identify file fragment types, e.g., image/video, audio, and text without system metadata. It is of vital importance in multimedia storage and communication. Existing MFFC methods typically treat fragments as 1D byte sequences and emphasize the relations between separate bytes (interbytes) for classification. However, the more informative relations inside bytes (intrabytes) are overlooked and seldom investigated. By looking inside bytes, the bit-level details of file fragments can be accessed, enabling a more accurate classification. Motivated by this, we first propose Byte2Image, a novel visual representation model that incorporates previously overlooked intrabyte information into file fragments and reinterprets these fragments as 2D grayscale images. This model involves a sliding byte window to reveal the intrabyte information and a rowwise stacking of intrabyte ngrams for embedding fragments into a 2D space. Thus, complex interbyte and intrabyte correlations can be mined simultaneously using powerful vision networks. Additionally, we propose an end-to-end dual-branch network ByteNet to enhance robust correlation mining and feature representation. ByteNet makes full use of the raw 1D byte sequence and the converted 2D image through a shallow byte branch feature extraction (BBFE) and a deep image branch feature extraction (IBFE) network. In particular, the BBFE, composed of a single fully-connected layer, adaptively recognizes the co-occurrence of several some specific bytes within the raw byte sequence, while the IBFE, built on a vision Transformer, effectively mines the complex interbyte and intrabyte correlations from the converted image. Experiments on the two representative benchmarks, including 14 cases, validate that our proposed method outperforms state-of-the-art approaches on different cases by up to 12.2%.

new Evaluating Sugarcane Yield Variability with UAV-Derived Cane Height under Different Water and Nitrogen Conditions

Authors: Rajiv Ranjan, Tejasavi Birdh, Nandan Mandal, Dinesh Kumar, Shashank Tamaskar

Abstract: This study investigates the relationship between sugarcane yield and cane height derived under different water and nitrogen conditions from pre-harvest Digital Surface Model (DSM) obtained via Unmanned Aerial Vehicle (UAV) flights over a sugarcane test farm. The farm was divided into 62 blocks based on three water levels (low, medium, and high) and three nitrogen levels (low, medium, and high), with repeated treatments. In pixel distribution of DSM for each block, it provided bimodal distribution representing two peaks, ground level (gaps within canopies) and top of the canopies respectively. Using bimodal distribution, mean cane height was extracted for each block by applying a trimmed mean to the pixel distribution, focusing on the top canopy points. Similarly, the extracted mean elevation of the base was derived from the bottom points, representing ground level. The Derived Cane Height Model (DCHM) was generated by taking the difference between the mean canopy height and mean base elevation for each block. Yield measurements (tons/acre) were recorded post-harvest for each block. By aggregating the data into nine treatment zones (e.g., high water-low nitrogen, low water-high nitrogen), the DCHM and median yield were calculated for each zone. The regression analysis between the DCHM and corresponding yields for the different treatment zones yielded an R 2 of 0.95. This study demonstrates the significant impact of water and nitrogen treatments on sugarcane height and yield, utilizing one-time UAV-derived DSM data.

new The unrealized potential of agroforestry for an emissions-intensive agricultural commodity

Authors: Alexander Becker, Jan D. Wegner, Evans Dawoe, Konrad Schindler, William J. Thompson, Christian Bunn, Rachael D. Garrett, Fabio Castro, Simon P. Hart, Wilma J. Blaser-Hart

Abstract: Reconciling agricultural production with climate-change mitigation and adaptation is one of the most formidable problems in sustainability. One proposed strategy for addressing this problem is the judicious retention of trees in agricultural systems. However, the magnitude of the current and future-potential benefit that trees contribute remains uncertain, particularly in the agricultural sector where trees can also limit production. Here we help to resolve these issues across a West African region responsible for producing $\approx$60% of the world's cocoa, a crop that contributes one of the highest per unit carbon footprints of all foods. We use machine learning to generate spatially-explicit estimates of shade-tree cover and carbon stocks across the region. We find that existing shade-tree cover is low, and not spatially aligned with climate threat. But we also find enormous unrealized potential for the sector to counterbalance a large proportion of their high carbon footprint annually, without threatening production. Our methods can be applied to other globally significant commodities that can be grown in agroforests, and align with accounting requirements of carbon markets, and emerging legislative requirements for sustainability reporting.

new Improving Generalization in Visual Reasoning via Self-Ensemble

Authors: Tien-Huy Nguyen, Quang-Khai Tran, Anh-Tuan Quang-Hoang

Abstract: The cognitive faculty of visual reasoning necessitates the integration of multimodal perceptual processing and commonsense and external knowledge of the world. In recent years, a plethora of large vision-language models (LVLMs) have been proposed, demonstrating outstanding power and exceptional proficiency in commonsense reasoning across diverse domains and tasks. Nevertheless, training such LVLMs requires a lot of costly resources. Recent approaches, instead of training LVLMs from scratch on various large datasets, focus on exploring ways to take advantage of the capabilities of many different LVLMs, such as ensemble methods. In this work, we propose self-ensemble, a novel method that improves the generalization and visual reasoning of the model without updating any parameters, a training-free method. Our key insight is that we realized that LVLM itself can ensemble without the need for any other LVLMs, which helps to unlock their internal capabilities. Extensive experiments on various benchmarks demonstrate the effectiveness of our method in achieving state-of-the-art (SOTA) performance on SketchyVQA, Outside Knowledge VQA, and out-of-distribution VQA tasks.

new Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack

Authors: Shengjing Tian, Yinan Han, Xiantong Zhao, Bin Liu, Xiuping Liu

Abstract: In this study, we delve into the robustness of neural network-based LiDAR point cloud tracking models under adversarial attacks, a critical aspect often overlooked in favor of performance enhancement. These models, despite incorporating advanced architectures like Transformer or Bird's Eye View (BEV), tend to neglect robustness in the face of challenges such as adversarial attacks, domain shifts, or data corruption. We instead focus on the robustness of the tracking models under the threat of adversarial attacks. We begin by establishing a unified framework for conducting adversarial attacks within the context of 3D object tracking, which allows us to thoroughly investigate both white-box and black-box attack strategies. For white-box attacks, we tailor specific loss functions to accommodate various tracking paradigms and extend existing methods such as FGSM, C\&W, and PGD to the point cloud domain. In addressing black-box attack scenarios, we introduce a novel transfer-based approach, the Target-aware Perturbation Generation (TAPG) algorithm, with the dual objectives of achieving high attack performance and maintaining low perceptibility. This method employs a heuristic strategy to enforce sparse attack constraints and utilizes random sub-vector factorization to bolster transferability. Our experimental findings reveal a significant vulnerability in advanced tracking methods when subjected to both black-box and white-box attacks, underscoring the necessity for incorporating robustness against adversarial attacks into the design of LiDAR point cloud tracking models. Notably, compared to existing methods, the TAPG also strikes an optimal balance between the effectiveness of the attack and the concealment of the perturbations.

new Diff-Instruct*: Towards Human-Preferred One-step Text-to-image Generative Models

Authors: Weijian Luo, Colin Zhang, Debing Zhang, Zhengyang Geng

Abstract: In this paper, we introduce the Diff-Instruct*(DI*), a data-free approach for building one-step text-to-image generative models that align with human preference while maintaining the ability to generate highly realistic images. We frame human preference alignment as online reinforcement learning using human feedback (RLHF), where the goal is to maximize the reward function while regularizing the generator distribution to remain close to a reference diffusion process. Unlike traditional RLHF approaches, which rely on the KL divergence for regularization, we introduce a novel score-based divergence regularization, which leads to significantly better performances. Although the direct calculation of this divergence remains intractable, we demonstrate that we can efficiently compute its \emph{gradient} by deriving an equivalent yet tractable loss function. Remarkably, with Stable Diffusion V1.5 as the reference diffusion model, DI* outperforms \emph{all} previously leading models by a large margin. When using the 0.6B PixelArt-$\alpha$ model as the reference diffusion, DI* achieves a new record Aesthetic Score of 6.30 and an Image Reward of 1.31 with only a single generation step, almost doubling the scores of the rest of the models with similar sizes. It also achieves an HPSv2 score of 28.70, establishing a new state-of-the-art benchmark. We also observe that DI* can improve the layout and enrich the colors of generated images.

new IndraEye: Infrared Electro-Optical UAV-based Perception Dataset for Robust Downstream Tasks

Authors: Manjunath D, Prajwal Gurunath, Sumanth Udupa, Aditya Gandhamal, Shrikar Madhu, Aniruddh Sikdar, Suresh Sundaram

Abstract: Deep neural networks (DNNs) have shown exceptional performance when trained on well-illuminated images captured by Electro-Optical (EO) cameras, which provide rich texture details. However, in critical applications like aerial perception, it is essential for DNNs to maintain consistent reliability across all conditions, including low-light scenarios where EO cameras often struggle to capture sufficient detail. Additionally, UAV-based aerial object detection faces significant challenges due to scale variability from varying altitudes and slant angles, adding another layer of complexity. Existing methods typically address only illumination changes or style variations as domain shifts, but in aerial perception, correlation shifts also impact DNN performance. In this paper, we introduce the IndraEye dataset, a multi-sensor (EO-IR) dataset designed for various tasks. It includes 5,612 images with 145,666 instances, encompassing multiple viewing angles, altitudes, seven backgrounds, and different times of the day across the Indian subcontinent. The dataset opens up several research opportunities, such as multimodal learning, domain adaptation for object detection and segmentation, and exploration of sensor-specific strengths and weaknesses. IndraEye aims to advance the field by supporting the development of more robust and accurate aerial perception systems, particularly in challenging conditions. IndraEye dataset is benchmarked with object detection and semantic segmentation tasks. Dataset and source codes are available at https://bit.ly/indraeye.

URLs: https://bit.ly/indraeye.

new Improving Detection of Person Class Using Dense Pooling

Authors: Nouman Ahmad

Abstract: Lately, the continuous development of deep learning models by many researchers in the area of computer vision has attracted more researchers to further improve the accuracy of these models. FasterRCNN [32] has already provided a state-of-the-art approach to improve the accuracy and detection of 80 different objects given in the COCO dataset. To further improve the performance of person detection we have conducted a different approach which gives the state-of-the-art conclusion. An ROI is a step in FasterRCNN that extract the features from the given image with a fixed size and transfer into for further classification. To enhance the ROI performance, we have conducted an approach that implements dense pooling and converts the image into a 3D model to further transform into UV(ultra Violet) images which makes it easy to extract the right features from the images. To implement our approach we have approached the state-of-the-art COCO datasets and extracted 6982 images that include a person object and our final achievements conclude that using our approach has made significant results in detecting the person object in the given image

new BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks

Authors: Yunhan Zhao, Xiang Zheng, Lin Luo, Yige Li, Xingjun Ma, Yu-Gang Jiang

Abstract: Despite their superb multimodal capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks, which are inference-time attacks that induce the model to output harmful responses with tricky prompts. It is thus essential to defend VLMs against potential jailbreaks for their trustworthy deployment in real-world applications. In this work, we focus on black-box defense for VLMs against jailbreak attacks. Existing black-box defense methods are either unimodal or bimodal. Unimodal methods enhance either the vision or language module of the VLM, while bimodal methods robustify the model through text-image representation realignment. However, these methods suffer from two limitations: 1) they fail to fully exploit the cross-modal information, or 2) they degrade the model performance on benign inputs. To address these limitations, we propose a novel blue-team method BlueSuffix that defends the black-box target VLM against jailbreak attacks without compromising its performance. BlueSuffix includes three key components: 1) a visual purifier against jailbreak images, 2) a textual purifier against jailbreak texts, and 3) a blue-team suffix generator fine-tuned via reinforcement learning for enhancing cross-modal robustness. We empirically show on three VLMs (LLaVA, MiniGPT-4, and Gemini) and two safety benchmarks (MM-SafetyBench and RedTeam-2K) that BlueSuffix outperforms the baseline defenses by a significant margin. Our BlueSuffix opens up a promising direction for defending VLMs against jailbreak attacks.

new Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!

Authors: Arash Marioriyad, Mohammadali Banayeeanzade, Reza Abbasi, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah

Abstract: Text-to-image diffusion models, such as Stable Diffusion and DALL-E, are capable of generating high-quality, diverse, and realistic images from textual prompts. However, they sometimes struggle to accurately depict specific entities described in prompts, a limitation known as the entity missing problem in compositional generation. While prior studies suggested that adjusting cross-attention maps during the denoising process could alleviate this problem, they did not systematically investigate which objective functions could best address it. This study examines three potential causes of the entity-missing problem, focusing on cross-attention dynamics: (1) insufficient attention intensity for certain entities, (2) overly broad attention spread, and (3) excessive overlap between attention maps of different entities. We found that reducing overlap in attention maps between entities can effectively minimize the rate of entity missing. Specifically, we hypothesize that tokens related to specific entities compete for attention on certain image regions during the denoising process, which can lead to divided attention across tokens and prevent accurate representation of each entity. To address this issue, we introduced four loss functions, Intersection over Union (IoU), center-of-mass (CoM) distance, Kullback-Leibler (KL) divergence, and clustering compactness (CC) to regulate attention overlap during denoising steps without the need for retraining. Experimental results across a wide variety of benchmarks reveal that these proposed training-free methods significantly improve compositional accuracy, outperforming previous approaches in visual question answering (VQA), captioning scores, CLIP similarity, and human evaluations. Notably, these methods improved human evaluation scores by 9% over the best baseline, demonstrating substantial improvements in compositional alignment.

new MovieCharacter: A Tuning-Free Framework for Controllable Character Video Synthesis

Authors: Di Qiu, Zheng Chen, Rui Wang, Mingyuan Fan, Changqian Yu, Junshi Huan, Xiang Wen

Abstract: Recent advancements in character video synthesis still depend on extensive fine-tuning or complex 3D modeling processes, which can restrict accessibility and hinder real-time applicability. To address these challenges, we propose a simple yet effective tuning-free framework for character video synthesis, named MovieCharacter, designed to streamline the synthesis process while ensuring high-quality outcomes. Our framework decomposes the synthesis task into distinct, manageable modules: character segmentation and tracking, video object removal, character motion imitation, and video composition. This modular design not only facilitates flexible customization but also ensures that each component operates collaboratively to effectively meet user needs. By leveraging existing open-source models and integrating well-established techniques, MovieCharacter achieves impressive synthesis results without necessitating substantial resources or proprietary datasets. Experimental results demonstrate that our framework enhances the efficiency, accessibility, and adaptability of character video synthesis, paving the way for broader creative and interactive applications.

new EEG-Driven 3D Object Reconstruction with Color Consistency and Diffusion Prior

Authors: Xin Xiang, Wenhui Zhou, Guojun Dai

Abstract: EEG-based visual perception reconstruction has become a current research hotspot. Neuroscientific studies have shown that humans can perceive various types of visual information, such as color, shape, and texture, when observing objects. However, existing technical methods often face issues such as inconsistencies in texture, shape, and color between the visual stimulus images and the reconstructed images. In this paper, we propose a method for reconstructing 3D objects with color consistency based on EEG signals. The method adopts a two-stage strategy: in the first stage, we train an implicit neural EEG encoder with the capability of perceiving 3D objects, enabling it to capture regional semantic features; in the second stage, based on the latent EEG codes obtained in the first stage, we integrate a diffusion model, neural style loss, and NeRF to implicitly decode the 3D objects. Finally, through experimental validation, we demonstrate that our method can reconstruct 3D objects with color consistency using EEG.

new Skinned Motion Retargeting with Dense Geometric Interaction Perception

Authors: Zijie Ye, Jia-Wei Liu, Jia Jia, Shikun Sun, Mike Zheng Shou

Abstract: Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook body geometries or add a geometry correction stage after skeletal motion retargeting. This results in conflicts between skeleton interaction and geometry correction, leading to issues such as jittery, interpenetration, and contact mismatches. To address these challenges, we introduce a new retargeting framework, MeshRet, which directly models the dense geometric interactions in motion retargeting. Initially, we establish dense mesh correspondences between characters using semantically consistent sensors (SCS), effective across diverse mesh topologies. Subsequently, we develop a novel spatio-temporal representation called the dense mesh interaction (DMI) field. This field, a collection of interacting SCS feature vectors, skillfully captures both contact and non-contact interactions between body geometries. By aligning the DMI field during retargeting, MeshRet not only preserves motion semantics but also prevents self-interpenetration and ensures contact preservation. Extensive experiments on the public Mixamo dataset and our newly-collected ScanRet dataset demonstrate that MeshRet achieves state-of-the-art performance. Code available at https://github.com/abcyzj/MeshRet.

URLs: https://github.com/abcyzj/MeshRet.

new Push-Forward Signed Distance Functions enable interpretable and robust continuous shape quantification

Authors: Roua Rouatbi, Juan Esteban Suarez, Ivo F. Sbalzarini

Abstract: We introduce the Push-Forward Signed Distance Morphometric (PF-SDM), a novel method for shape quantification in biomedical imaging that is continuous, interpretable, and invariant to shape-preserving transformations. PF-SDM effectively captures the geometric properties of shapes, including their topological skeletons and radial symmetries. This results in a robust and interpretable shape descriptor that generalizes to capture temporal shape dynamics. Importantly, PF-SDM avoids certain issues of previous geometric morphometrics, like Elliptical Fourier Analysis and Generalized Procrustes Analysis, such as coefficient correlations and landmark choices. We present the PF-SDM theory, provide a practically computable algorithm, and benchmark it on synthetic data.

new Informed Deep Abstaining Classifier: Investigating noise-robust training for diagnostic decision support systems

Authors: Helen Schneider, Sebastian Nowak, Aditya Parikh, Yannik C. Layer, Maike Theis, Wolfgang Block, Alois M. Sprinkart, Ulrike Attenberger, Rafet Sifa

Abstract: Image-based diagnostic decision support systems (DDSS) utilizing deep learning have the potential to optimize clinical workflows. However, developing DDSS requires extensive datasets with expert annotations and is therefore costly. Leveraging report contents from radiological data bases with Natural Language Processing to annotate the corresponding image data promises to replace labor-intensive manual annotation. As mining "real world" databases can introduce label noise, noise-robust training losses are of great interest. However, current noise-robust losses do not consider noise estimations that can for example be derived based on the performance of the automatic label generator used. In this study, we expand the noise-robust Deep Abstaining Classifier (DAC) loss to an Informed Deep Abstaining Classifier (IDAC) loss by incorporating noise level estimations during training. Our findings demonstrate that IDAC enhances the noise robustness compared to DAC and several state-of-the-art loss functions. The results are obtained on various simulated noise levels using a public chest X-ray data set. These findings are reproduced on an in-house noisy data set, where labels were extracted from the clinical systems of the University Hospital Bonn by a text-based transformer. The IDAC can therefore be a valuable tool for researchers, companies or clinics aiming to develop accurate and reliable DDSS from routine clinical data.

new Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition

Authors: Mengke Li, Ye Liu, Yang Lu, Yiqun Zhang, Yiu-ming Cheung, Hui Huang

Abstract: Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising Sharpness-Aware Minimization (SAM) can effectively improve the generalization capability of models by seeking out flat minima in the loss landscape, which, however, comes at the cost of doubling the computational time. Since the update rule of SAM necessitates two consecutive (non-parallelizable) forward and backpropagation at each step. To address this issue, we propose a novel method called Random SAM prompt tuning (RSAM-PT) to improve the model generalization, requiring only one-step gradient computation at each step. Specifically, we search for the gradient descent direction within a random neighborhood of the parameters during each gradient update. To amplify the impact of tail-class samples and avoid overfitting, we employ the deferred re-weight scheme to increase the significance of tail-class samples. The classification accuracy of long-tailed data can be significantly improved by the proposed RSAM-PT, particularly for tail classes. RSAM-PT achieves the state-of-the-art performance of 90.3\%, 76.5\%, and 50.1\% on benchmark datasets CIFAR100-LT (IF 100), iNaturalist 2018, and Places-LT, respectively. The source code is temporarily available at https://github.com/Keke921/GNM-PT.

URLs: https://github.com/Keke921/GNM-PT.

new SPOTS-10: Animal Pattern Benchmark Dataset for Machine Learning Algorithms

Authors: John Atanbori

Abstract: Recognising animals based on distinctive body patterns, such as stripes, spots, or other markings, in night images is a complex task in computer vision. Existing methods for detecting animals in images often rely on colour information, which is not always available in night images, posing a challenge for pattern recognition in such conditions. Nevertheless, recognition at night-time is essential for most wildlife, biodiversity, and conservation applications. The SPOTS-10 dataset was created to address this challenge and to provide a resource for evaluating machine learning algorithms in situ. This dataset is an extensive collection of grayscale images showcasing diverse patterns found in ten animal species. Specifically, SPOTS-10 contains 50,000 32 x 32 grayscale images, divided into ten categories, with 5,000 images per category. The training set comprises 40,000 images, while the test set contains 10,000 images. The SPOTS-10 dataset is freely available on the project GitHub page: https://github.com/Amotica/SPOTS-10.git by cloning the repository.

URLs: https://github.com/Amotica/SPOTS-10.git

new Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework

Authors: Vladimir Arkhipkin, Viacheslav Vasilev, Andrei Filatov, Igor Pavlov, Julia Agafonova, Nikolai Gerasimenko, Anna Averchenkova, Evelina Mironova, Anton Bukashkin, Konstantin Kulikov, Andrey Kuznetsov, Denis Dimitrov

Abstract: Text-to-image (T2I) diffusion models are popular for introducing image manipulation methods, such as editing, image fusion, inpainting, etc. At the same time, image-to-video (I2V) and text-to-video (T2V) models are also built on top of T2I models. We present Kandinsky 3, a novel T2I model based on latent diffusion, achieving a high level of quality and photorealism. The key feature of the new architecture is the simplicity and efficiency of its adaptation for many types of generation tasks. We extend the base T2I model for various applications and create a multifunctional generation system that includes text-guided inpainting/outpainting, image fusion, text-image fusion, image variations generation, I2V and T2V generation. We also present a distilled version of the T2I model, evaluating inference in 4 steps of the reverse process without reducing image quality and 3 times faster than the base model. We deployed a user-friendly demo system in which all the features can be tested in the public domain. Additionally, we released the source code and checkpoints for the Kandinsky 3 and extended models. Human evaluations show that Kandinsky 3 demonstrates one of the highest quality scores among open source generation systems.

new KA$^2$ER: Knowledge Adaptive Amalgamation of ExpeRts for Medical Images Segmentation

Authors: Shangde Gao, Yichao Fu, Ke Liu, Hongxia Xu, Jian Wu

Abstract: Recently, many foundation models for medical image analysis such as MedSAM, SwinUNETR have been released and proven to be useful in multiple tasks. However, considering the inherent heterogeneity and inhomogeneity of real-world medical data, directly applying these models to specific medical image segmentation tasks often leads to negative domain shift effects, which can severely weaken the model's segmentation capabilities. To this end, we propose an adaptive amalgamation knowledge framework that aims to train a versatile foundation model to handle the joint goals of multiple expert models, each specialized for a distinct task. Specifically, we first train an nnUNet-based expert model for each task, and reuse the pre-trained SwinUNTER as the target foundation model. Then, the input data for all challenging tasks are encoded in the foundation model and the expert models, respectively, and their backbone features are jointly projected into the adaptive amalgamation layer. Within the hidden layer, the hierarchical attention mechanisms are designed to achieve adaptive merging of the target model to the hidden layer feature knowledge of all experts, which significantly reduces the domain shift arising from the inter-task differences. Finally, the gold amalgamated features and the prompt features are fed into the mask decoder to obtain the segmentation results. Extensive experiments conducted in these challenging tasks demonstrate the effectiveness and adaptability of our foundation model for real-world medical image segmentation.

new Efficient Mixture-of-Expert for Video-based Driver State and Physiological Multi-task Estimation in Conditional Autonomous Driving

Authors: Jiyao Wang, Xiao Yang, Zhenyu Wang, Ximeng Wei, Ange Wang, Dengbo He, Kaishun Wu

Abstract: Road safety remains a critical challenge worldwide, with approximately 1.35 million fatalities annually attributed to traffic accidents, often due to human errors. As we advance towards higher levels of vehicle automation, challenges still exist, as driving with automation can cognitively over-demand drivers if they engage in non-driving-related tasks (NDRTs), or lead to drowsiness if driving was the sole task. This calls for the urgent need for an effective Driver Monitoring System (DMS) that can evaluate cognitive load and drowsiness in SAE Level-2/3 autonomous driving contexts. In this study, we propose a novel multi-task DMS, termed VDMoE, which leverages RGB video input to monitor driver states non-invasively. By utilizing key facial features to minimize computational load and integrating remote Photoplethysmography (rPPG) for physiological insights, our approach enhances detection accuracy while maintaining efficiency. Additionally, we optimize the Mixture-of-Experts (MoE) framework to accommodate multi-modal inputs and improve performance across different tasks. A novel prior-inclusive regularization method is introduced to align model outputs with statistical priors, thus accelerating convergence and mitigating overfitting risks. We validate our method with the creation of a new dataset (MCDD), which comprises RGB video and physiological indicators from 42 participants, and two public datasets. Our findings demonstrate the effectiveness of VDMoE in monitoring driver states, contributing to safer autonomous driving systems. The code and data will be released.

new LiGAR: LiDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition

Authors: Naga Venkata Sai Raviteja Chappa, Khoa Luu

Abstract: Group Activity Recognition (GAR) remains challenging in computer vision due to the complex nature of multi-agent interactions. This paper introduces LiGAR, a LIDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition. LiGAR leverages LiDAR data as a structural backbone to guide the processing of visual and textual information, enabling robust handling of occlusions and complex spatial arrangements. Our framework incorporates a Multi-Scale LIDAR Transformer, Cross-Modal Guided Attention, and an Adaptive Fusion Module to integrate multi-modal data at different semantic levels effectively. LiGAR's hierarchical architecture captures group activities at various granularities, from individual actions to scene-level dynamics. Extensive experiments on the JRDB-PAR, Volleyball, and NBA datasets demonstrate LiGAR's superior performance, achieving state-of-the-art results with improvements of up to 10.6% in F1-score on JRDB-PAR and 5.9% in Mean Per Class Accuracy on the NBA dataset. Notably, LiGAR maintains high performance even when LiDAR data is unavailable during inference, showcasing its adaptability. Our ablation studies highlight the significant contributions of each component and the effectiveness of our multi-modal, multi-scale approach in advancing the field of group activity recognition.

new LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT

Authors: Chi Ding, Qingchao Zhang, Ge Wang, Xiaojing Ye, Yunmei Chen

Abstract: Inverse problems arise in many applications, especially tomographic imaging. We develop a Learned Alternating Minimization Algorithm (LAMA) to solve such problems via two-block optimization by synergizing data-driven and classical techniques with proven convergence. LAMA is naturally induced by a variational model with learnable regularizers in both data and image domains, parameterized as composite functions of neural networks trained with domain-specific data. We allow these regularizers to be nonconvex and nonsmooth to extract features from data effectively. We minimize the overall objective function using Nesterov's smoothing technique and residual learning architecture. It is demonstrated that LAMA reduces network complexity, improves memory efficiency, and enhances reconstruction accuracy, stability, and interpretability. Extensive experiments show that LAMA significantly outperforms state-of-the-art methods on popular benchmark datasets for Computed Tomography.

new Zero-Shot Action Recognition in Surveillance Videos

Authors: Joao Pereira, Vasco Lopes, David Semedo, Joao Neves

Abstract: The growing demand for surveillance in public spaces presents significant challenges due to the shortage of human resources. Current AI-based video surveillance systems heavily rely on core computer vision models that require extensive finetuning, which is particularly difficult in surveillance settings due to limited datasets and difficult setting (viewpoint, low quality, etc.). In this work, we propose leveraging Large Vision-Language Models (LVLMs), known for their strong zero and few-shot generalization, to tackle video understanding tasks in surveillance. Specifically, we explore VideoLLaMA2, a state-of-the-art LVLM, and an improved token-level sampling method, Self-Reflective Sampling (Self-ReS). Our experiments on the UCF-Crime dataset show that VideoLLaMA2 represents a significant leap in zero-shot performance, with 20% boost over the baseline. Self-ReS additionally increases zero-shot action recognition performance to 44.6%. These results highlight the potential of LVLMs, paired with improved sampling techniques, for advancing surveillance video analysis in diverse scenarios.

new Extrapolating Prospective Glaucoma Fundus Images through Diffusion Model in Irregular Longitudinal Sequences

Authors: Zhihao Zhao, Junjie Yang, Shahrooz Faghihroohi, Yinzheng Zhao, Daniel Zapp, Kai Huang, Nassir Navab, M. Ali Nasseri

Abstract: The utilization of longitudinal datasets for glaucoma progression prediction offers a compelling approach to support early therapeutic interventions. Predominant methodologies in this domain have primarily focused on the direct prediction of glaucoma stage labels from longitudinal datasets. However, such methods may not adequately encapsulate the nuanced developmental trajectory of the disease. To enhance the diagnostic acumen of medical practitioners, we propose a novel diffusion-based model to predict prospective images by extrapolating from existing longitudinal fundus images of patients. The methodology delineated in this study distinctively leverages sequences of images as inputs. Subsequently, a time-aligned mask is employed to select a specific year for image generation. During the training phase, the time-aligned mask resolves the issue of irregular temporal intervals in longitudinal image sequence sampling. Additionally, we utilize a strategy of randomly masking a frame in the sequence to establish the ground truth. This methodology aids the network in continuously acquiring knowledge regarding the internal relationships among the sequences throughout the learning phase. Moreover, the introduction of textual labels is instrumental in categorizing images generated within the sequence. The empirical findings from the conducted experiments indicate that our proposed model not only effectively generates longitudinal data but also significantly improves the precision of downstream classification tasks.

new Enhancing Learned Image Compression via Cross Window-based Attention

Authors: Priyanka Mudgal, Feng Liu

Abstract: In recent years, learned image compression methods have demonstrated superior rate-distortion performance compared to traditional image compression methods. Recent methods utilize convolutional neural networks (CNN), variational autoencoders (VAE), invertible neural networks (INN), and transformers. Despite their significant contributions, a main drawback of these models is their poor performance in capturing local redundancy. Therefore, to leverage global features along with local redundancy, we propose a CNN-based solution integrated with a feature encoding module. The feature encoding module encodes important features before feeding them to the CNN and then utilizes cross-scale window-based attention, which further captures local redundancy. Cross-scale window-based attention is inspired by the attention mechanism in transformers and effectively enlarges the receptive field. Both the feature encoding module and the cross-scale window-based attention module in our architecture are flexible and can be incorporated into any other network architecture. We evaluate our method on the Kodak and CLIC datasets and demonstrate that our approach is effective and on par with state-of-the-art methods.

new Synthetica: Large Scale Synthetic Data for Robot Perception

Authors: Ritvik Singh, Jingzhou Liu, Karl Van Wyk, Yu-Wei Chao, Jean-Francois Lafleche, Florian Shkurti, Nathan Ratliff, Ankur Handa

Abstract: Vision-based object detectors are a crucial basis for robotics applications as they provide valuable information about object localisation in the environment. These need to ensure high reliability in different lighting conditions, occlusions, and visual artifacts, all while running in real-time. Collecting and annotating real-world data for these networks is prohibitively time consuming and costly, especially for custom assets, such as industrial objects, making it untenable for generalization to in-the-wild scenarios. To this end, we present Synthetica, a method for large-scale synthetic data generation for training robust state estimators. This paper focuses on the task of object detection, an important problem which can serve as the front-end for most state estimation problems, such as pose estimation. Leveraging data from a photorealistic ray-tracing renderer, we scale up data generation, generating 2.7 million images, to train highly accurate real-time detection transformers. We present a collection of rendering randomization and training-time data augmentation techniques conducive to robust sim-to-real performance for vision tasks. We demonstrate state-of-the-art performance on the task of object detection while having detectors that run at 50-100Hz which is 9 times faster than the prior SOTA. We further demonstrate the usefulness of our training methodology for robotics applications by showcasing a pipeline for use in the real world with custom objects for which there do not exist prior datasets. Our work highlights the importance of scaling synthetic data generation for robust sim-to-real transfer while achieving the fastest real-time inference speeds. Videos and supplementary information can be found at this URL: https://sites.google.com/view/synthetica-vision.

URLs: https://sites.google.com/view/synthetica-vision.

new Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies

Authors: Xiwen Li, Rehman Mohammed, Tristalee Mangin, Surojit Saha, Ross T Whitaker, Kerry E. Kelly, Tolga Tasdizen

Abstract: Idling vehicle detection (IVD) can be helpful in monitoring and reducing unnecessary idling and can be integrated into real-time systems to address the resulting pollution and harmful products. The previous approach [13], a non-end-to-end model, requires extra user clicks to specify a part of the input, making system deployment more error-prone or even not feasible. In contrast, we introduce an end-to-end joint audio-visual IVD task designed to detect vehicles visually under three states: moving, idling and engine off. Unlike feature co-occurrence task such as audio-visual vehicle tracking, our IVD task addresses complementary features, where labels cannot be determined by a single modality alone. To this end, we propose AVIVD-Net, a novel network that integrates audio and visual features through a bidirectional attention mechanism. AVIVD-Net streamlines the input process by learning a joint feature space, reducing the deployment complexity of previous methods. Additionally, we introduce the AVIVD dataset, which is seven times larger than previous datasets, offering significantly more annotated samples to study the IVD problem. Our model achieves performance comparable to prior approaches, making it suitable for automated deployment. Furthermore, by evaluating AVIVDNet on the feature co-occurrence public dataset MAVD [23], we demonstrate its potential for extension to self-driving vehicle video-camera setups.

new Deep Learning-Based Fatigue Cracks Detection in Bridge Girders using Feature Pyramid Networks

Authors: Jiawei Zhang, Jun Li, Reachsak Ly, Yunyi Liu, Jiangpeng Shu

Abstract: For structural health monitoring, continuous and automatic crack detection has been a challenging problem. This study is conducted to propose a framework of automatic crack segmentation from high-resolution images containing crack information about steel box girders of bridges. Considering the multi-scale feature of cracks, convolutional neural network architecture of Feature Pyramid Networks (FPN) for crack detection is proposed. As for input, 120 raw images are processed via two approaches (shrinking the size of images and splitting images into sub-images). Then, models with the proposed structure of FPN for crack detection are developed. The result shows all developed models can automatically detect the cracks at the raw images. By shrinking the images, the computation efficiency is improved without decreasing accuracy. Because of the separable characteristic of crack, models using the splitting method provide more accurate crack segmentations than models using the resizing method. Therefore, for high-resolution images, the FPN structure coupled with the splitting method is an promising solution for the crack segmentation and detection.

new Exploring contextual modeling with linear complexity for point cloud segmentation

Authors: Yong Xien Chng, Xuchong Qiu, Yizeng Han, Yifan Pu, Jiewei Cao, Gao Huang

Abstract: Point cloud segmentation is an important topic in 3D understanding that has traditionally has been tackled using either the CNN or Transformer. Recently, Mamba has emerged as a promising alternative, offering efficient long-range contextual modeling capabilities without the quadratic complexity associated with Transformer's attention mechanisms. However, despite Mamba's potential, early efforts have all failed to achieve better performance than the best CNN-based and Transformer-based methods. In this work, we address this challenge by identifying the key components of an effective and efficient point cloud segmentation architecture. Specifically, we show that: 1) Spatial locality and robust contextual understanding are critical for strong performance, and 2) Mamba features linear computational complexity, offering superior data and inference efficiency compared to Transformers, while still being capable of delivering strong contextual understanding. Additionally, we further enhance the standard Mamba specifically for point cloud segmentation by identifying its two key shortcomings. First, the enforced causality in the original Mamba is unsuitable for processing point clouds that have no such dependencies. Second, its unidirectional scanning strategy imposes a directional bias, hampering its ability to capture the full context of unordered point clouds in a single pass. To address these issues, we carefully remove the causal convolutions and introduce a novel Strided Bidirectional SSM to enhance the model's capability to capture spatial relationships. Our efforts culminate in the development of a novel architecture named MEEPO, which effectively integrates the strengths of CNN and Mamba. MEEPO surpasses the previous state-of-the-art method, PTv3, by up to +0.8 mIoU on multiple key benchmark datasets, while being 42.1% faster and 5.53x more memory efficient.

new Vision Search Assistant: Empower Vision-Language Models as Multimodal Search Engines

Authors: Zhixin Zhang, Yiyuan Zhang, Xiaohan Ding, Xiangyu Yue

Abstract: Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as identifying an object that the model has never seen before. This challenge is particularly pronounced for large vision-language models (VLMs): if the model has not been exposed to the object depicted in an image, it struggles to generate reliable answers to the user's question regarding that image. Moreover, as new objects and events continuously emerge, frequently updating VLMs is impractical due to heavy computational burdens. To address this limitation, we propose Vision Search Assistant, a novel framework that facilitates collaboration between VLMs and web agents. This approach leverages VLMs' visual understanding capabilities and web agents' real-time information access to perform open-world Retrieval-Augmented Generation via the web. By integrating visual and textual representations through this collaboration, the model can provide informed responses even when the image is novel to the system. Extensive experiments conducted on both open-set and closed-set QA benchmarks demonstrate that the Vision Search Assistant significantly outperforms the other models and can be widely applied to existing VLMs.

new AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?

Authors: Han Bao, Yue Huang, Yanbo Wang, Jiayi Ye, Xiangqi Wang, Xiuyin Chen, Mohamed Elhoseiny, Xiangliang Zhang

Abstract: Large Vision-Language Models (LVLMs) have become essential for advancing the integration of visual and linguistic information, facilitating a wide range of complex applications and tasks. However, the evaluation of LVLMs presents significant challenges as the evaluation benchmark always demands lots of human cost for its construction, and remains static, lacking flexibility once constructed. Even though automatic evaluation has been explored in textual modality, the visual modality remains under-explored. As a result, in this work, we address a question: "Can LVLMs serve as a path to automatic benchmarking?". We introduce AutoBench-V, an automated framework for serving evaluation on demand, i.e., benchmarking LVLMs based on specific aspects of model capability. Upon receiving an evaluation capability, AutoBench-V leverages text-to-image models to generate relevant image samples and then utilizes LVLMs to orchestrate visual question-answering (VQA) tasks, completing the evaluation process efficiently and flexibly. Through an extensive evaluation of seven popular LVLMs across five demanded user inputs (i.e., evaluation capabilities), the framework shows effectiveness and reliability. We observe the following: (1) Our constructed benchmark accurately reflects varying task difficulties; (2) As task difficulty rises, the performance gap between models widens; (3) While models exhibit strong performance in abstract level understanding, they underperform in details reasoning tasks; and (4) Constructing a dataset with varying levels of difficulties is critical for a comprehensive and exhaustive evaluation. Overall, AutoBench-V not only successfully utilizes LVLMs for automated benchmarking but also reveals that LVLMs as judges have significant potential in various domains.

new LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

Authors: Hanyu Wang, Saksham Suri, Yixuan Ren, Hao Chen, Abhinav Shrivastava

Abstract: We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches into discrete tokens, LARP introduces a holistic tokenization scheme that gathers information from the visual content using a set of learned holistic queries. This design allows LARP to capture more global and semantic representations, rather than being limited to local patch-level information. Furthermore, it offers flexibility by supporting an arbitrary number of discrete tokens, enabling adaptive and efficient tokenization based on the specific requirements of the task. To align the discrete token space with downstream AR generation tasks, LARP integrates a lightweight AR transformer as a training-time prior model that predicts the next token on its discrete latent space. By incorporating the prior model during training, LARP learns a latent space that is not only optimized for video reconstruction but is also structured in a way that is more conducive to autoregressive generation. Moreover, this process defines a sequential order for the discrete tokens, progressively pushing them toward an optimal configuration during training, ensuring smoother and more accurate AR generation at inference time. Comprehensive experiments demonstrate LARP's strong performance, achieving state-of-the-art FVD on the UCF101 class-conditional video generation benchmark. LARP enhances the compatibility of AR models with videos and opens up the potential to build unified high-fidelity multimodal large language models (MLLMs).

new On Inductive Biases That Enable Generalization of Diffusion Transformers

Authors: Jie An, De Wang, Pengsheng Guo, Jiebo Luo, Alexander Schwing

Abstract: Recent work studying the generalization of diffusion models with UNet-based denoisers reveals inductive biases that can be expressed via geometry-adaptive harmonic bases. However, in practice, more recent denoising networks are often based on transformers, e.g., the diffusion transformer (DiT). This raises the question: do transformer-based denoising networks exhibit inductive biases that can also be expressed via geometry-adaptive harmonic bases? To our surprise, we find that this is not the case. This discrepancy motivates our search for the inductive bias that can lead to good generalization in DiT models. Investigating the pivotal attention modules of a DiT, we find that locality of attention maps are closely associated with generalization. To verify this finding, we modify the generalization of a DiT by restricting its attention windows. We inject local attention windows to a DiT and observe an improvement in generalization. Furthermore, we empirically find that both the placement and the effective attention size of these local attention windows are crucial factors. Experimental results on the CelebA, ImageNet, and LSUN datasets show that strengthening the inductive bias of a DiT can improve both generalization and generation quality when less training data is available. Source code will be released publicly upon paper publication. Project page: dit-generalization.github.io/.

new Enhancing Action Recognition by Leveraging the Hierarchical Structure of Actions and Textual Context

Authors: Manuel Benavent-Lledo, David Mulero-P\'erez, David Ortiz-Perez, Jose Garcia-Rodriguez, Antonis Argyros

Abstract: The sequential execution of actions and their hierarchical structure consisting of different levels of abstraction, provide features that remain unexplored in the task of action recognition. In this study, we present a novel approach to improve action recognition by exploiting the hierarchical organization of actions and by incorporating contextualized textual information, including location and prior actions to reflect the sequential context. To achieve this goal, we introduce a novel transformer architecture tailored for action recognition that utilizes both visual and textual features. Visual features are obtained from RGB and optical flow data, while text embeddings represent contextual information. Furthermore, we define a joint loss function to simultaneously train the model for both coarse and fine-grained action recognition, thereby exploiting the hierarchical nature of actions. To demonstrate the effectiveness of our method, we extend the Toyota Smarthome Untrimmed (TSU) dataset to introduce action hierarchies, introducing the Hierarchical TSU dataset. We also conduct an ablation study to assess the impact of different methods for integrating contextual and hierarchical data on action recognition performance. Results show that the proposed approach outperforms pre-trained SOTA methods when trained with the same hyperparameters. Moreover, they also show a 17.12% improvement in top-1 accuracy over the equivalent fine-grained RGB version when using ground-truth contextual information, and a 5.33% improvement when contextual information is obtained from actual predictions.

cross Less Cybersickness, Please: Demystifying and Detecting Stereoscopic Visual Inconsistencies in Virtual Reality Apps

Authors: Shuqing Li, Cuiyun Gao, Jianping Zhang, Yujia Zhang, Yepang Liu, Jiazhen Gu, Yun Peng, Michael R. Lyu

Abstract: The quality of Virtual Reality (VR) apps is vital, particularly the rendering quality of the VR Graphical User Interface (GUI). Different from traditional 2D apps, VR apps create a 3D digital scene for users, by rendering two distinct 2D images for the user's left and right eyes, respectively. Stereoscopic visual inconsistency (denoted as "SVI") issues, however, undermine the rendering process of the user's brain, leading to user discomfort and even adverse health effects. Such issues commonly exist but remain underexplored. We conduct an empirical analysis on 282 SVI bug reports from 15 VR platforms, summarizing 15 types of manifestations. The empirical analysis reveals that automatically detecting SVI issues is challenging, mainly because: (1) lack of training data; (2) the manifestations of SVI issues are diverse, complicated, and often application-specific; (3) most accessible VR apps are closed-source commercial software. Existing pattern-based supervised classification approaches may be inapplicable or ineffective in detecting the SVI issues. To counter these challenges, we propose an unsupervised black-box testing framework named StereoID to identify the stereoscopic visual inconsistencies, based only on the rendered GUI states. StereoID generates a synthetic right-eye image based on the actual left-eye image and computes distances between the synthetic right-eye image and the actual right-eye image to detect SVI issues. We propose a depth-aware conditional stereo image translator to power the image generation process, which captures the expected perspective shifts between left-eye and right-eye images. We build a large-scale unlabeled VR stereo screenshot dataset with larger than 171K images from 288 real-world VR apps for experiments. After substantial experiments, StereoID demonstrates superior performance for detecting SVI issues in both user reports and wild VR apps.

cross How to Backdoor Consistency Models?

Authors: Chengen Wang, Murat Kantarcioglu

Abstract: Consistency models are a new class of models that generate images by directly mapping noise to data, allowing for one-step generation and significantly accelerating the sampling process. However, their robustness against adversarial attacks has not yet been thoroughly investigated. In this work, we conduct the first study on the vulnerability of consistency models to backdoor attacks. While previous research has explored backdoor attacks on diffusion models, these studies have primarily focused on conventional diffusion models, employing a customized backdoor training process and objective, whereas consistency models have distinct training processes and objectives. Our proposed framework demonstrates the vulnerability of consistency models to backdoor attacks. During image generation, poisoned consistency models produce images with a Fr\'echet Inception Distance (FID) comparable to that of a clean model when sampling from Gaussian noise. However, once the trigger is activated, they generate backdoor target images. We explore various trigger and target configurations to evaluate the vulnerability of consistency models, including the use of random noise as a trigger. This type of trigger is less conspicuous and aligns well with the sampling process of consistency models. Across all configurations, our framework successfully compromises the consistency models while maintaining high utility and specificity.

cross Multi-modal Image and Radio Frequency Fusion for Optimizing Vehicle Positioning

Authors: Ouwen Huan, Tao Luo, Mingzhe Chen

Abstract: In this paper, a multi-modal vehicle positioning framework that jointly localizes vehicles with channel state information (CSI) and images is designed. In particular, we consider an outdoor scenario where each vehicle can communicate with only one BS, and hence, it can upload its estimated CSI to only its associated BS. Each BS is equipped with a set of cameras, such that it can collect a small number of labeled CSI, a large number of unlabeled CSI, and the images taken by cameras. To exploit the unlabeled CSI data and position labels obtained from images, we design an meta-learning based hard expectation-maximization (EM) algorithm. Specifically, since we do not know the corresponding relationship between unlabeled CSI and the multiple vehicle locations in images, we formulate the calculation of the training objective as a minimum matching problem. To reduce the impact of label noises caused by incorrect matching between unlabeled CSI and vehicle locations obtained from images and achieve better convergence, we introduce a weighted loss function on the unlabeled datasets, and study the use of a meta-learning algorithm for computing the weighted loss. Subsequently, the model parameters are updated according to the weighted loss function of unlabeled CSI samples and their matched position labels obtained from images. Simulation results show that the proposed method can reduce the positioning error by up to 61% compared to a baseline that does not use images and uses only CSI fingerprint for vehicle positioning.

cross Data-Driven Cellular Network Selector for Vehicle Teleoperations

Authors: Barak Gahtan, Reuven Cohen, Alex M. Bronstein, Eli Shapira

Abstract: Remote control of robotic systems, also known as teleoperation, is crucial for the development of autonomous vehicle (AV) technology. It allows a remote operator to view live video from AVs and, in some cases, to make real-time decisions. The effectiveness of video-based teleoperation systems is heavily influenced by the quality of the cellular network and, in particular, its packet loss rate and latency. To optimize these parameters, an AV can be connected to multiple cellular networks and determine in real time over which cellular network each video packet will be transmitted. We present an algorithm, called Active Network Selector (ANS), which uses a time series machine learning approach for solving this problem. We compare ANS to a baseline non-learning algorithm, which is used today in commercial systems, and show that ANS performs much better, with respect to both packet loss and packet latency.

cross Radon Implicit Field Transform (RIFT): Learning Scenes from Radar Signals

Authors: Daqian Bao, Alex Saad-Falcon, Justin Romberg

Abstract: Data acquisition in array signal processing (ASP) is costly, as high angular and range resolutions require large antenna apertures and wide frequency bandwidths. Data requirements grow multiplicatively with viewpoints and frequencies, increasing collection burdens. Implicit Neural Representations (INRs)--neural network models of 3D scenes--offer compact, continuous representations with minimal data, interpolating to unseen viewpoints, potentially reducing sampling costs in ASP. We propose the Radon Implicit Field Transform (RIFT), combining a radar forward model (Generalized Radon Transform, GRT) with an INR-based scene representation learned from radar signals. This method extends to other ASP problems by replacing the GRT with appropriate algorithms. In experiments, we synthesize radar data using the GRT and train the INR model by minimizing radar signal reconstruction error. We render the scene using the trained INR and evaluate it against ground truth. We introduce new error metrics: phase-Root Mean Square Error (p-RMSE) and magnitude-Structural Similarity Index Measure (m-SSIM). Compared to traditional scene models, our RIFT model achieves up to 188% improvement in scene reconstruction with only 10% of the data. Using the same amount of data, RIFT achieves 3x better reconstruction and shows a 10% improvement when generalizing to unseen viewpoints.

cross ScreenWriter: Automatic Screenplay Generation and Movie Summarisation

Authors: Louis Mahon, Mirella Lapata

Abstract: The proliferation of creative video content has driven demand for textual descriptions or summaries that allow users to recall key plot points or get an overview without watching. The volume of movie content and speed of turnover motivates automatic summarisation, which is nevertheless challenging, requiring identifying character intentions and very long-range temporal dependencies. The few existing methods attempting this task rely heavily on textual screenplays as input, greatly limiting their applicability. In this work, we propose the task of automatic screenplay generation, and a method, ScreenWriter, that operates only on video and produces output which includes dialogue, speaker names, scene breaks, and visual descriptions. ScreenWriter introduces a novel algorithm to segment the video into scenes based on the sequence of visual vectors, and a novel method for the challenging problem of determining character names, based on a database of actors' faces. We further demonstrate how these automatic screenplays can be used to generate plot synopses with a hierarchical summarisation method based on scene breaks. We test the quality of the final summaries on the recent MovieSum dataset, which we augment with videos, and show that they are superior to a number of comparison models which assume access to goldstandard screenplays.

cross Training Compute-Optimal Vision Transformers for Brain Encoding

Authors: Sana Ahmadi, Francois Paugam, Tristan Glatard, Pierre Lune Bellec

Abstract: The optimal training of a vision transformer for brain encoding depends on three factors: model size, data size, and computational resources. This study investigates these three pillars, focusing on the effects of data scaling, model scaling, and high-performance computing on brain encoding results. Using VideoGPT to extract efficient spatiotemporal features from videos and training a Ridge model to predict brain activity based on these features, we conducted benchmark experiments with varying data sizes (10k, 100k, 1M, 6M) and different model configurations of GPT-2, including hidden layer dimensions, number of layers, and number of attention heads. We also evaluated the effects of training models with 32-bit vs 16-bit floating point representations. Our results demonstrate that increasing the hidden layer dimensions significantly improves brain encoding performance, as evidenced by higher Pearson correlation coefficients across all subjects. In contrast, the number of attention heads does not have a significant effect on the encoding results. Additionally, increasing the number of layers shows some improvement in brain encoding correlations, but the trend is not as consistent as that observed with hidden layer dimensions. The data scaling results show that larger training datasets lead to improved brain encoding performance, with the highest Pearson correlation coefficients observed for the largest dataset size (6M). These findings highlight that the effects of data scaling are more significant compared to model scaling in enhancing brain encoding performance. Furthermore, we explored the impact of floating-point precision by comparing 32-bit and 16-bit representations. Training with 16-bit precision yielded the same brain encoding accuracy as 32-bit, while reducing training time by 1.17 times, demonstrating its efficiency for high-performance computing tasks.

cross Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review

Authors: Ahmad Obeid, Said Boumaraf, Anabia Sohail, Taimur Hassan, Sajid Javed, Jorge Dias, Mohammed Bennamoun, Naoufel Werghi

Abstract: Recent years witnessed remarkable progress in computational histopathology, largely fueled by deep learning. This brought the clinical adoption of deep learning-based tools within reach, promising significant benefits to healthcare, offering a valuable second opinion on diagnoses, streamlining complex tasks, and mitigating the risks of inconsistency and bias in clinical decisions. However, a well-known challenge is that deep learning models may contain up to billions of parameters; supervising their training effectively would require vast labeled datasets to achieve reliable generalization and noise resilience. In medical imaging, particularly histopathology, amassing such extensive labeled data collections places additional demands on clinicians and incurs higher costs, which hinders the art's progress. Addressing this challenge, researchers devised various strategies for leveraging deep learning with limited data and annotation availability. In this paper, we present a comprehensive review of deep learning applications in histopathology, with a focus on the challenges posed by data scarcity over the past decade. We systematically categorize and compare various approaches, evaluate their distinct contributions using benchmarking tables, and highlight their respective advantages and limitations. Additionally, we address gaps in existing reviews and identify underexplored research opportunities, underscoring the potential for future advancements in this field.

cross GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing

Authors: Zhichao Wang, Xinhai Chen, Chunye Gong, Bo Yang, Liang Deng, Yufei Sun, Yufei Pang, Jie Liu

Abstract: Mesh smoothing methods can enhance mesh quality by eliminating distorted elements, leading to improved convergence in simulations. To balance the efficiency and robustness of traditional mesh smoothing process, previous approaches have employed supervised learning and reinforcement learning to train intelligent smoothing models. However, these methods heavily rely on labeled dataset or prior knowledge to guide the models' learning. Furthermore, their limited capacity to enhance mesh connectivity often restricts the effectiveness of smoothing. In this paper, we first systematically analyze the learning mechanisms of recent intelligent smoothing methods and propose a prior-free reinforcement learning model for intelligent mesh smoothing. Our proposed model integrates graph neural networks with reinforcement learning to implement an intelligent node smoothing agent and introduces, for the first time, a mesh connectivity improvement agent. We formalize mesh optimization as a Markov Decision Process and successfully train both agents using Twin Delayed Deep Deterministic Policy Gradient and Double Dueling Deep Q-Network in the absence of any prior data or knowledge. We verified the proposed model on both 2D and 3D meshes. Experimental results demonstrate that our model achieves feature-preserving smoothing on complex 3D surface meshes. It also achieves state-of-the-art results among intelligent smoothing methods on 2D meshes and is 7.16 times faster than traditional optimization-based smoothing methods. Moreover, the connectivity improvement agent can effectively enhance the quality distribution of the mesh.

cross Improving Multimodal Large Language Models Using Continual Learning

Authors: Shikhar Srivastava, Md Yousuf Harun, Robik Shrestha, Christopher Kanan

Abstract: Generative large language models (LLMs) exhibit impressive capabilities, which can be further augmented by integrating a pre-trained vision model into the original LLM to create a multimodal LLM (MLLM). However, this integration often significantly decreases performance on natural language understanding and generation tasks, compared to the original LLM. This study investigates this issue using the LLaVA MLLM, treating the integration as a continual learning problem. We evaluate five continual learning methods to mitigate forgetting and identify a technique that enhances visual understanding while minimizing linguistic performance loss. Our approach reduces linguistic performance degradation by up to 15\% over the LLaVA recipe, while maintaining high multimodal accuracy. We also demonstrate the robustness of our method through continual learning on a sequence of vision-language tasks, effectively preserving linguistic skills while acquiring new multimodal capabilities.

cross Multi-Class Abnormality Classification Task in Video Capsule Endoscopy

Authors: Dev Rishi Verma, Vibhor Saxena, Dhruv Sharma, Arpan Gupta

Abstract: In this work we addressed the challenge of multi-class anomaly classification in Video Capsule Endoscopy (VCE)[1] with a variety of deep learning models, ranging from custom CNNs to advanced transformer architectures. The purpose is to correctly classify diverse gastrointestinal disorders, which is critical for increasing diagnostic efficiency in clinical settings. We started with a proprietary CNN and improved performance with ResNet[7] for better feature extraction, followed by Vision Transformer (ViT)[2] to capture global dependencies. Multiscale Vision Transformer (MViT)[6] improved hierarchical feature extraction, while Dual Attention Vision Transformer (DaViT)[4] delivered cutting-edge results by combining spatial and channel attention methods. This methodology enabled us to improve model accuracy across a wide range of criteria, greatly surpassing older methods.

cross GHIL-Glue: Hierarchical Control with Filtered Subgoal Images

Authors: Kyle B. Hatch, Ashwin Balakrishna, Oier Mees, Suraj Nair, Seohong Park, Blake Wulfe, Masha Itkina, Benjamin Eysenbach, Sergey Levine, Thomas Kollar, Benjamin Burchfiel

Abstract: Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function as high-level planners, generating intermediate subgoals for low-level goal-conditioned policies to reach. However, the performance of these systems can be greatly bottlenecked by the interface between generative models and low-level controllers. For example, generative models may predict photorealistic yet physically infeasible frames that confuse low-level policies. Low-level policies may also be sensitive to subtle visual artifacts in generated goal images. This paper addresses these two facets of generalization, providing an interface to effectively "glue together" language-conditioned image or video prediction models with low-level goal-conditioned policies. Our method, Generative Hierarchical Imitation Learning-Glue (GHIL-Glue), filters out subgoals that do not lead to task progress and improves the robustness of goal-conditioned policies to generated subgoals with harmful visual artifacts. We find in extensive experiments in both simulated and real environments that GHIL-Glue achieves a 25% improvement across several hierarchical models that leverage generative subgoals, achieving a new state-of-the-art on the CALVIN simulation benchmark for policies using observations from a single RGB camera. GHIL-Glue also outperforms other generalist robot policies across 3/4 language-conditioned manipulation tasks testing zero-shot generalization in physical experiments.

cross Transforming Precision: A Comparative Analysis of Vision Transformers, CNNs, and Traditional ML for Knee Osteoarthritis Severity Diagnosis

Authors: Tasnim Sakib Apon, Md. Fahim-Ul-Islam, Nafiz Imtiaz Rafin, Joya Akter, Md. Golam Rabiul Alam

Abstract: Knee osteoarthritis(KO) is a degenerative joint disease that can cause severe pain and impairment. With increased prevalence, precise diagnosis by medical imaging analytics is crucial for appropriate illness management. This research investigates a comparative analysis between traditional machine learning techniques and new deep learning models for diagnosing KO severity from X-ray pictures. This study does not introduce new architectural innovations but rather illuminates the robust applicability and comparative effectiveness of pre-existing ViT models in a medical imaging context, specifically for KO severity diagnosis. The insights garnered from this comparative analysis advocate for the integration of advanced ViT models in clinical diagnostic workflows, potentially revolutionizing the precision and reliability of KO assessments. This study does not introduce new architectural innovations but rather illuminates the robust applicability and comparative effectiveness of pre-existing ViT models in a medical imaging context, specifically for KO severity diagnosis. The insights garnered from this comparative analysis advocate for the integration of advanced ViT models in clinical diagnostic workflows, potentially revolutionizing the precision & reliability of KO assessments. The study utilizes an osteoarthritis dataset from the Osteoarthritis Initiative (OAI) comprising images with 5 severity categories and uneven class distribution. While classic machine learning models like GaussianNB and KNN struggle in feature extraction, Convolutional Neural Networks such as Inception-V3, VGG-19 achieve better accuracy between 55-65% by learning hierarchical visual patterns. However, Vision Transformer architectures like Da-VIT, GCViT and MaxViT emerge as indisputable champions, displaying 66.14% accuracy, 0.703 precision, 0.614 recall, AUC exceeding 0.835 thanks to self-attention processes.

cross Super-resolved virtual staining of label-free tissue using diffusion models

Authors: Yijie Zhang, Luzhe Huang, Nir Pillar, Yuzhu Li, Hanlong Chen, Aydogan Ozcan

Abstract: Virtual staining of tissue offers a powerful tool for transforming label-free microscopy images of unstained tissue into equivalents of histochemically stained samples. This study presents a diffusion model-based super-resolution virtual staining approach utilizing a Brownian bridge process to enhance both the spatial resolution and fidelity of label-free virtual tissue staining, addressing the limitations of traditional deep learning-based methods. Our approach integrates novel sampling techniques into a diffusion model-based image inference process to significantly reduce the variance in the generated virtually stained images, resulting in more stable and accurate outputs. Blindly applied to lower-resolution auto-fluorescence images of label-free human lung tissue samples, the diffusion-based super-resolution virtual staining model consistently outperformed conventional approaches in resolution, structural similarity and perceptual accuracy, successfully achieving a super-resolution factor of 4-5x, increasing the output space-bandwidth product by 16-25-fold compared to the input label-free microscopy images. Diffusion-based super-resolved virtual tissue staining not only improves resolution and image quality but also enhances the reliability of virtual staining without traditional chemical staining, offering significant potential for clinical diagnostics.

cross Prompt Diffusion Robustifies Any-Modality Prompt Learning

Authors: Yingjun Du, Gaowen Liu, Yuzhang Shang, Yuguang Yao, Ramana Kompella, Cees G. M. Snoek

Abstract: Foundation models enable prompt-based classifiers for zero-shot and few-shot learning. Nonetheless, the conventional method of employing fixed prompts suffers from distributional shifts that negatively impact generalizability to unseen samples. This paper introduces prompt diffusion, which uses a diffusion model to gradually refine the prompts to obtain a customized prompt for each sample. Specifically, we first optimize a collection of prompts to obtain over-fitted prompts per sample. Then, we propose a prompt diffusion model within the prompt space, enabling the training of a generative transition process from a random prompt to its overfitted prompt. As we cannot access the label of a test image during inference, our model gradually generates customized prompts solely from random prompts using our trained, prompt diffusion. Our prompt diffusion is generic, flexible, and modality-agnostic, making it a simple plug-and-play module seamlessly embedded into existing prompt learning methods for textual, visual, or multi-modal prompt learning. Our diffusion model uses a fast ODE-based sampling strategy to optimize test sample prompts in just five steps, offering a good trade-off between performance improvement and computational efficiency. For all prompt learning methods tested, adding prompt diffusion yields more robust results for base-to-new generalization, cross-dataset generalization, and domain generalization in classification tasks tested over 15 diverse datasets.

cross LLMs Can Evolve Continually on Modality for X-Modal Reasoning

Authors: Jiazuo Yu, Haomiao Xiong, Lu Zhang, Haiwen Diao, Yunzhi Zhuge, Lanqing Hong, Dong Wang, Huchuan Lu, You He, Long Chen

Abstract: Multimodal Large Language Models (MLLMs) have gained significant attention due to their impressive capabilities in multimodal understanding. However, existing methods rely heavily on extensive modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. In this paper, we propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities that enables MLLMs to continually EVolve on modalities for $\mathbb{X}$-modal reasoning. We leverage the concept of Continual Learning and develop an incremental training strategy atop pre-trained MLLMs, enabling their expansion to new modalities using uni-modal data, without executing joint-modal pretraining. In detail, a novel Adapter-in-Adapter (AnA) framework is introduced, in which uni-modal and cross-modal adapters are seamlessly integrated to facilitate efficient modality alignment and collaboration. Additionally, an MoE-based gating module is applied between two types of adapters to further enhance the multimodal interaction. To investigate the proposed method, we establish a challenging benchmark called Continual Learning of Modality (MCL), which consists of high-quality QA data from five distinct modalities: image, video, audio, depth and point cloud. Extensive experiments demonstrate the effectiveness of the proposed AnA framework on learning plasticity and memory stability during continual learning. Furthermore, PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%. Our code locates at https://github.com/JiazuoYu/PathWeave

URLs: https://github.com/JiazuoYu/PathWeave

cross Transferable Adversarial Attacks on SAM and Its Downstream Models

Authors: Song Xia, Wenhan Yang, Yi Yu, Xun Lin, Henghui Ding, Lingyu Duan, Xudong Jiang

Abstract: The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats of adverse usage. This paper, for the first time, explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM), by solely utilizing the information from the open-sourced SAM. In contrast to prevailing transfer-based adversarial attacks, we demonstrate the existence of adversarial dangers even without accessing the downstream task and dataset to train a similar surrogate model. To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm to extract the intrinsic vulnerability inherent in the foundation model, which is then utilized as the prior knowledge to guide the generation of adversarial perturbations. Moreover, by formulating the gradient difference in the attacking process between the open-sourced SAM and its fine-tuned downstream models, we theoretically demonstrate that a deviation occurs in the adversarial update direction by directly maximizing the distance of encoded feature embeddings in the open-sourced SAM. Consequently, we propose a gradient robust loss that simulates the associated uncertainty with gradient-based noise augmentation to enhance the robustness of generated adversarial examples (AEs) towards this deviation, thus improving the transferability. Extensive experiments demonstrate the effectiveness of the proposed universal meta-initialized and gradient robust adversarial attack (UMI-GRAT) toward SAMs and their downstream models. Code is available at https://github.com/xiasong0501/GRAT.

URLs: https://github.com/xiasong0501/GRAT.

cross Neural Fields in Robotics: A Survey

Authors: Muhammad Zubair Irshad, Mauro Comi, Yen-Chen Lin, Nick Heppert, Abhinav Valada, Rares Ambrus, Zsolt Kira, Jonathan Tremblay

Abstract: Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D data. Leveraging differentiable rendering, Neural Fields encompass both continuous implicit and explicit neural representations enabling high-fidelity 3D reconstruction, integration of multi-modal sensor data, and generation of novel viewpoints. This survey explores their applications in robotics, emphasizing their potential to enhance perception, planning, and control. Their compactness, memory efficiency, and differentiability, along with seamless integration with foundation and generative models, make them ideal for real-time applications, improving robot adaptability and decision-making. This paper provides a thorough review of Neural Fields in robotics, categorizing applications across various domains and evaluating their strengths and limitations, based on over 200 papers. First, we present four key Neural Fields frameworks: Occupancy Networks, Signed Distance Fields, Neural Radiance Fields, and Gaussian Splatting. Second, we detail Neural Fields' applications in five major robotics domains: pose estimation, manipulation, navigation, physics, and autonomous driving, highlighting key works and discussing takeaways and open challenges. Finally, we outline the current limitations of Neural Fields in robotics and propose promising directions for future research. Project page: https://robonerf.github.io

URLs: https://robonerf.github.io

cross EfficientEQA: An Efficient Approach for Open Vocabulary Embodied Question Answering

Authors: Kai Cheng, Zhengyuan Li, Xingpeng Sun, Byung-Cheol Min, Amrit Singh Bedi, Aniket Bera

Abstract: Embodied Question Answering (EQA) is an essential yet challenging task for robotic home assistants. Recent studies have shown that large vision-language models (VLMs) can be effectively utilized for EQA, but existing works either focus on video-based question answering without embodied exploration or rely on closed-form choice sets. In real-world scenarios, a robotic agent must efficiently explore and accurately answer questions in open-vocabulary settings. To address these challenges, we propose a novel framework called EfficientEQA for open-vocabulary EQA, which enables efficient exploration and accurate answering. In EfficientEQA, the robot actively explores unknown environments using Semantic-Value-Weighted Frontier Exploration, a strategy that prioritizes exploration based on semantic importance provided by calibrated confidence from black-box VLMs to quickly gather relevant information. To generate accurate answers, we employ Retrieval-Augmented Generation (RAG), which utilizes BLIP to retrieve useful images from accumulated observations and VLM reasoning to produce responses without relying on predefined answer choices. Additionally, we detect observations that are highly relevant to the question as outliers, allowing the robot to determine when it has sufficient information to stop exploring and provide an answer. Experimental results demonstrate the effectiveness of our approach, showing an improvement in answering accuracy by over 15% and efficiency, measured in running steps, by over 20% compared to state-of-the-art methods.

cross Enhancing Community Vision Screening -- AI Driven Retinal Photography for Early Disease Detection and Patient Trust

Authors: Xiaofeng Lei, Yih-Chung Tham, Jocelyn Hui Lin Goh, Yangqin Feng, Yang Bai, Zhi Da Soh, Rick Siow Mong Goh, Xinxing Xu, Yong Liu, Ching-Yu Cheng

Abstract: Community vision screening plays a crucial role in identifying individuals with vision loss and preventing avoidable blindness, particularly in rural communities where access to eye care services is limited. Currently, there is a pressing need for a simple and efficient process to screen and refer individuals with significant eye disease-related vision loss to tertiary eye care centers for further care. An ideal solution should seamlessly and readily integrate with existing workflows, providing comprehensive initial screening results to service providers, thereby enabling precise patient referrals for timely treatment. This paper introduces the Enhancing Community Vision Screening (ECVS) solution, which addresses the aforementioned concerns with a novel and feasible solution based on simple, non-invasive retinal photography for the detection of pathology-based visual impairment. Our study employs four distinct deep learning models: RETinal photo Quality Assessment (RETQA), Pathology Visual Impairment detection (PVI), Eye Disease Diagnosis (EDD) and Visualization of Lesion Regions of the eye (VLR). We conducted experiments on over 10 datasets, totaling more than 80,000 fundus photos collected from various sources. The models integrated into ECVS achieved impressive AUC scores of 0.98 for RETQA, 0.95 for PVI, and 0.90 for EDD, along with a DICE coefficient of 0.48 for VLR. These results underscore the promising capabilities of ECVS as a straightforward and scalable method for community-based vision screening.

cross Conditional GAN for Enhancing Diffusion Models in Efficient and Authentic Global Gesture Generation from Audios

Authors: Yongkang Cheng, Mingjiang Liang, Shaoli Huang, Gaoge Han, Jifeng Ning, Wei Liu

Abstract: Audio-driven simultaneous gesture generation is vital for human-computer communication, AI games, and film production. While previous research has shown promise, there are still limitations. Methods based on VAEs are accompanied by issues of local jitter and global instability, whereas methods based on diffusion models are hampered by low generation efficiency. This is because the denoising process of DDPM in the latter relies on the assumption that the noise added at each step is sampled from a unimodal distribution, and the noise values are small. DDIM borrows the idea from the Euler method for solving differential equations, disrupts the Markov chain process, and increases the noise step size to reduce the number of denoising steps, thereby accelerating generation. However, simply increasing the step size during the step-by-step denoising process causes the results to gradually deviate from the original data distribution, leading to a significant drop in the quality of the generated actions and the emergence of unnatural artifacts. In this paper, we break the assumptions of DDPM and achieves breakthrough progress in denoising speed and fidelity. Specifically, we introduce a conditional GAN to capture audio control signals and implicitly match the multimodal denoising distribution between the diffusion and denoising steps within the same sampling step, aiming to sample larger noise values and apply fewer denoising steps for high-speed generation.

cross Deep Learning-Driven Microstructure Characterization and Vickers Hardness Prediction of Mg-Gd Alloys

Authors: Lu Wang, Hongchan Chen, Bing Wang, Qian Li, Qun Luo, Yuexing Han

Abstract: In the field of materials science, exploring the relationship between composition, microstructure, and properties has long been a critical research focus. The mechanical performance of solid-solution Mg-Gd alloys is significantly influenced by Gd content, dendritic structures, and the presence of secondary phases. To better analyze and predict the impact of these factors, this study proposes a multimodal fusion learning framework based on image processing and deep learning techniques. This framework integrates both elemental composition and microstructural features to accurately predict the Vickers hardness of solid-solution Mg-Gd alloys. Initially, deep learning methods were employed to extract microstructural information from a variety of solid-solution Mg-Gd alloy images obtained from literature and experiments. This provided precise grain size and secondary phase microstructural features for performance prediction tasks. Subsequently, these quantitative analysis results were combined with Gd content information to construct a performance prediction dataset. Finally, a regression model based on the Transformer architecture was used to predict the Vickers hardness of Mg-Gd alloys. The experimental results indicate that the Transformer model performs best in terms of prediction accuracy, achieving an R^2 value of 0.9. Additionally, SHAP analysis identified critical values for four key features affecting the Vickers hardness of Mg-Gd alloys, providing valuable guidance for alloy design. These findings not only enhance the understanding of alloy performance but also offer theoretical support for future material design and optimization.

cross Vector Quantization Prompting for Continual Learning

Authors: Li Jiao, Qiuxia Lai, Yu Li, Qiang Xu

Abstract: Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i.e., prompts) to encode task knowledge, from which appropriate ones are selected to guide the fixed pre-trained model in generating features tailored to a certain task. However, existing methods rely on predicting prompt identities for prompt selection, where the identity prediction process cannot be optimized with task loss. This limitation leads to sub-optimal prompt selection and inadequate adaptation of pre-trained features for a specific task. Previous efforts have tried to address this by directly generating prompts from input queries instead of selecting from a set of candidates. However, these prompts are continuous, which lack sufficient abstraction for task knowledge representation, making them less effective for continual learning. To address these challenges, we propose VQ-Prompt, a prompt-based continual learning method that incorporates Vector Quantization (VQ) into end-to-end training of a set of discrete prompts. In this way, VQ-Prompt can optimize the prompt selection process with task loss and meanwhile achieve effective abstraction of task knowledge for continual learning. Extensive experiments show that VQ-Prompt outperforms state-of-the-art continual learning methods across a variety of benchmarks under the challenging class-incremental setting. The code is available at \href{https://github.com/jiaolifengmi/VQ-Prompt}{this https URL}.

URLs: https://github.com/jiaolifengmi/VQ-Prompt

cross Guidance Disentanglement Network for Optics-Guided Thermal UAV Image Super-Resolution

Authors: Zhicheng Zhao, Juanjuan Gu, Chenglong Li, Chun Wang, Zhongling Huang, Jin Tang

Abstract: Optics-guided Thermal UAV image Super-Resolution (OTUAV-SR) has attracted significant research interest due to its potential applications in security inspection, agricultural measurement, and object detection. Existing methods often employ single guidance model to generate the guidance features from optical images to assist thermal UAV images super-resolution. However, single guidance models make it difficult to generate effective guidance features under favorable and adverse conditions in UAV scenarios, thus limiting the performance of OTUAV-SR. To address this issue, we propose a novel Guidance Disentanglement network (GDNet), which disentangles the optical image representation according to typical UAV scenario attributes to form guidance features under both favorable and adverse conditions, for robust OTUAV-SR. Moreover, we design an attribute-aware fusion module to combine all attribute-based optical guidance features, which could form a more discriminative representation and fit the attribute-agnostic guidance process. To facilitate OTUAV-SR research in complex UAV scenarios, we introduce VGTSR2.0, a large-scale benchmark dataset containing 3,500 aligned optical-thermal image pairs captured under diverse conditions and scenes. Extensive experiments on VGTSR2.0 demonstrate that GDNet significantly improves OTUAV-SR performance over state-of-the-art methods, especially in the challenging low-light and foggy environments commonly encountered in UAV scenarios. The dataset and code will be publicly available at https://github.com/Jocelyney/GDNet.

URLs: https://github.com/Jocelyney/GDNet.

cross What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration

Authors: Libo Qin, Qiguang Chen, Hao Fei, Zhi Chen, Min Li, Wanxiang Che

Abstract: Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: "What factors affect the performance of MM-ICL?'' To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction using 6 vision large language models and 20 strategies. Our findings highlight (1) the necessity of a multi-modal retriever for demonstration retrieval, (2) the importance of intra-demonstration ordering over inter-demonstration ordering, and (3) the enhancement of task comprehension through introductory instructions in prompts. We hope this study can serve as a foundational guide for optimizing MM-ICL strategies in future research.

cross Search Wide, Focus Deep: Automated Fetal Brain Extraction with Sparse Training Data

Authors: Javid Dadashkarimi, Valeria Pena Trujillo, Camilo Jaimes, Lilla Z\"ollei, Malte Hoffmann

Abstract: Automated fetal brain extraction from full-uterus MRI is a challenging task due to variable head sizes, orientations, complex anatomy, and prevalent artifacts. While deep-learning (DL) models trained on synthetic images have been successful in adult brain extraction, adapting these networks for fetal MRI is difficult due to the sparsity of labeled data, leading to increased false-positive predictions. To address this challenge, we propose a test-time strategy that reduces false positives in networks trained on sparse, synthetic labels. The approach uses a breadth-fine search (BFS) to identify a subvolume likely to contain the fetal brain, followed by a deep-focused sliding window (DFS) search to refine the extraction, pooling predictions to minimize false positives. We train models at different window sizes using synthetic images derived from a small number of fetal brain label maps, augmented with random geometric shapes. Each model is trained on diverse head positions and scales, including cases with partial or no brain tissue. Our framework matches state-of-the-art brain extraction methods on clinical HASTE scans of third-trimester fetuses and exceeds them by up to 5\% in terms of Dice in the second trimester as well as EPI scans across both trimesters. Our results demonstrate the utility of a sliding-window approach and combining predictions from several models trained on synthetic images, for improving brain-extraction accuracy by progressively refining regions of interest and minimizing the risk of missing brain mask slices or misidentifying other tissues as brain.

cross Sebica: Lightweight Spatial and Efficient Bidirectional Channel Attention Super Resolution Network

Authors: Chongxiao Liu

Abstract: Single Image Super-Resolution (SISR) is a vital technique for improving the visual quality of low-resolution images. While recent deep learning models have made significant advancements in SISR, they often encounter computational challenges that hinder their deployment in resource-limited or time-sensitive environments. To overcome these issues, we present Sebica, a lightweight network that incorporates spatial and efficient bidirectional channel attention mechanisms. Sebica significantly reduces computational costs while maintaining high reconstruction quality, achieving PSNR/SSIM scores of 28.29/0.7976 and 30.18/0.8330 on the Div2K and Flickr2K datasets, respectively. These results surpass most baseline lightweight models and are comparable to the highest-performing model, but with only 17% and 15% of the parameters and GFLOPs. Additionally, our small version of Sebica has only 7.9K parameters and 0.41 GFLOPS, representing just 3% of the parameters and GFLOPs of the highest-performing model, while still achieving PSNR and SSIM metrics of 28.12/0.7931 and 0.3009/0.8317, on the Flickr2K dataset respectively. In addition, Sebica demonstrates significant improvements in real-world applications, specifically in object detection tasks, where it enhances detection accuracy in traffic video scenarios.

cross Neural rendering enables dynamic tomography

Authors: Ivan Grega, William F. Whitney, Vikram S. Deshpande

Abstract: Interrupted X-ray computed tomography (X-CT) has been the common way to observe the deformation of materials during an experiment. While this approach is effective for quasi-static experiments, it has never been possible to reconstruct a full 3d tomography during a dynamic experiment which cannot be interrupted. In this work, we propose that neural rendering tools can be used to drive the paradigm shift to enable 3d reconstruction during dynamic events. First, we derive theoretical results to support the selection of projections angles. Via a combination of synthetic and experimental data, we demonstrate that neural radiance fields can reconstruct data modalities of interest more efficiently than conventional reconstruction methods. Finally, we develop a spatio-temporal model with spline-based deformation field and demonstrate that such model can reconstruct the spatio-temporal deformation of lattice samples in real-world experiments.

cross Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient

Authors: Yintai Ma, Diego Klabjan, Jean Utke

Abstract: The development of sophisticated models for video-to-video synthesis has been facilitated by recent advances in deep reinforcement learning and generative adversarial networks (GANs). In this paper, we propose RL-V2V-GAN, a new deep neural network approach based on reinforcement learning for unsupervised conditional video-to-video synthesis. While preserving the unique style of the source video domain, our approach aims to learn a mapping from a source video domain to a target video domain. We train the model using policy gradient and employ ConvLSTM layers to capture the spatial and temporal information by designing a fine-grained GAN architecture and incorporating spatio-temporal adversarial goals. The adversarial losses aid in content translation while preserving style. Unlike traditional video-to-video synthesis methods requiring paired inputs, our proposed approach is more general because it does not require paired inputs. Thus, when dealing with limited videos in the target domain, i.e., few-shot learning, it is particularly effective. Our experiments show that RL-V2V-GAN can produce temporally coherent video results. These results highlight the potential of our approach for further advances in video-to-video synthesis.

cross CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videos

Authors: Jiewen Yang, Yiqun Lin, Bin Pu, Jiarong Guo, Xiaowei Xu, Xiaomeng Li

Abstract: Echocardiogram video plays a crucial role in analysing cardiac function and diagnosing cardiac diseases. Current deep neural network methods primarily aim to enhance diagnosis accuracy by incorporating prior knowledge, such as segmenting cardiac structures or lesions annotated by human experts. However, diagnosing the inconsistent behaviours of the heart, which exist across both spatial and temporal dimensions, remains extremely challenging. For instance, the analysis of cardiac motion acquires both spatial and temporal information from the heartbeat cycle. To address this issue, we propose a novel reconstruction-based approach named CardiacNet to learn a better representation of local cardiac structures and motion abnormalities through echocardiogram videos. CardiacNet is accompanied by the Consistency Deformation Codebook (CDC) and the Consistency Deformed-Discriminator (CDD) to learn the commonalities across abnormal and normal samples by incorporating cardiac prior knowledge. In addition, we propose benchmark datasets named CardiacNet-PAH and CardiacNet-ASD to evaluate the effectiveness of cardiac disease assessment. In experiments, our CardiacNet can achieve state-of-the-art results in three different cardiac disease assessment tasks on public datasets CAMUS, EchoNet, and our datasets. The code and dataset are available at: https://github.com/xmed-lab/CardiacNet.

URLs: https://github.com/xmed-lab/CardiacNet.

cross Scaling-based Data Augmentation for Generative Models and its Theoretical Extension

Authors: Yoshitaka Koike, Takumi Nakagawa, Hiroki Waida, Takafumi Kanamori

Abstract: This paper studies stable learning methods for generative models that enable high-quality data generation. Noise injection is commonly used to stabilize learning. However, selecting a suitable noise distribution is challenging. Diffusion-GAN, a recently developed method, addresses this by using the diffusion process with a timestep-dependent discriminator. We investigate Diffusion-GAN and reveal that data scaling is a key component for stable learning and high-quality data generation. Building on our findings, we propose a learning algorithm, Scale-GAN, that uses data scaling and variance-based regularization. Furthermore, we theoretically prove that data scaling controls the bias-variance trade-off of the estimation error bound. As a theoretical extension, we consider GAN with invertible data augmentations. Comparative evaluations on benchmark datasets demonstrate the effectiveness of our method in improving stability and accuracy.

cross FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space

Authors: Yiyang Guo, Ruizhe Li, Mude Hui, Hanzhong Guo, Chen Zhang, Chuangjian Cai, Le Wan, Shangfei Wang

Abstract: Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication. However, existing watermarking methods fall short in robustness against regeneration attacks. In this paper, we propose a novel method called FreqMark that involves unconstrained optimization of the image latent frequency space obtained after VAE encoding. Specifically, FreqMark embeds the watermark by optimizing the latent frequency space of the images and then extracts the watermark through a pre-trained image encoder. This optimization allows a flexible trade-off between image quality with watermark robustness and effectively resists regeneration attacks. Experimental results demonstrate that FreqMark offers significant advantages in image quality and robustness, permits flexible selection of the encoding bit number, and achieves a bit accuracy exceeding 90% when encoding a 48-bit hidden message under various attack scenarios.

cross BEVPose: Unveiling Scene Semantics through Pose-Guided Multi-Modal BEV Alignment

Authors: Mehdi Hosseinzadeh, Ian Reid

Abstract: In the field of autonomous driving and mobile robotics, there has been a significant shift in the methods used to create Bird's Eye View (BEV) representations. This shift is characterised by using transformers and learning to fuse measurements from disparate vision sensors, mainly lidar and cameras, into a 2D planar ground-based representation. However, these learning-based methods for creating such maps often rely heavily on extensive annotated data, presenting notable challenges, particularly in diverse or non-urban environments where large-scale datasets are scarce. In this work, we present BEVPose, a framework that integrates BEV representations from camera and lidar data, using sensor pose as a guiding supervisory signal. This method notably reduces the dependence on costly annotated data. By leveraging pose information, we align and fuse multi-modal sensory inputs, facilitating the learning of latent BEV embeddings that capture both geometric and semantic aspects of the environment. Our pretraining approach demonstrates promising performance in BEV map segmentation tasks, outperforming fully-supervised state-of-the-art methods, while necessitating only a minimal amount of annotated data. This development not only confronts the challenge of data efficiency in BEV representation learning but also broadens the potential for such techniques in a variety of domains, including off-road and indoor environments.

cross Efficient Bilinear Attention-based Fusion for Medical Visual Question Answering

Authors: Zhilin Zhang, Jie Wang, Ruiqi Zhu, Xiaoliang Gong

Abstract: Medical Visual Question Answering (MedVQA) has gained increasing attention at the intersection of computer vision and natural language processing. Its capability to interpret radiological images and deliver precise answers to clinical inquiries positions MedVQA as a valuable tool for supporting diagnostic decision-making for physicians and alleviating the workload on radiologists. While recent approaches focus on using unified pre-trained large models for multi-modal fusion like cross-modal Transformers, research on more efficient fusion methods remains relatively scarce within this discipline. In this paper, we introduce a novel fusion model that integrates Orthogonality loss, Multi-head attention and Bilinear Attention Network (OMniBAN) to achieve high computational efficiency and strong performance without the need for pre-training. We conduct comprehensive experiments and clarify aspects of how to enhance bilinear attention fusion to achieve performance comparable to that of large models. Experimental results show that OMniBAN outperforms traditional models on key MedVQA benchmarks while maintaining a lower computational cost, which indicates its potential for efficient clinical application in radiology and pathology image question answering.

cross Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models

Authors: Wenda Li, Huijie Zhang, Qing Qu

Abstract: The widespread use of AI-generated content from diffusion models has raised significant concerns regarding misinformation and copyright infringement. Watermarking is a crucial technique for identifying these AI-generated images and preventing their misuse. In this paper, we introduce Shallow Diffuse, a new watermarking technique that embeds robust and invisible watermarks into diffusion model outputs. Unlike existing approaches that integrate watermarking throughout the entire diffusion sampling process, Shallow Diffuse decouples these steps by leveraging the presence of a low-dimensional subspace in the image generation process. This method ensures that a substantial portion of the watermark lies in the null space of this subspace, effectively separating it from the image generation process. Our theoretical and empirical analyses show that this decoupling strategy greatly enhances the consistency of data generation and the detectability of the watermark. Extensive experiments further validate that our Shallow Diffuse outperforms existing watermarking methods in terms of robustness and consistency. The codes will be released at https://github.com/liwd190019/Shallow-Diffuse.

URLs: https://github.com/liwd190019/Shallow-Diffuse.

cross KaLDeX: Kalman Filter based Linear Deformable Cross Attention for Retina Vessel Segmentation

Authors: Zhihao Zhao, Shahrooz Faghihroohi, Yinzheng Zhao, Junjie Yang, Shipeng Zhong, Kai Huang, Nassir Navab, Boyang Li, M. Ali Nasseri

Abstract: Background and Objective: In the realm of ophthalmic imaging, accurate vascular segmentation is paramount for diagnosing and managing various eye diseases. Contemporary deep learning-based vascular segmentation models rival human accuracy but still face substantial challenges in accurately segmenting minuscule blood vessels in neural network applications. Due to the necessity of multiple downsampling operations in the CNN models, fine details from high-resolution images are inevitably lost. The objective of this study is to design a structure to capture the delicate and small blood vessels. Methods: To address these issues, we propose a novel network (KaLDeX) for vascular segmentation leveraging a Kalman filter based linear deformable cross attention (LDCA) module, integrated within a UNet++ framework. Our approach is based on two key components: Kalman filter (KF) based linear deformable convolution (LD) and cross-attention (CA) modules. The LD module is designed to adaptively adjust the focus on thin vessels that might be overlooked in standard convolution. The CA module improves the global understanding of vascular structures by aggregating the detailed features from the LD module with the high level features from the UNet++ architecture. Finally, we adopt a topological loss function based on persistent homology to constrain the topological continuity of the segmentation. Results: The proposed method is evaluated on retinal fundus image datasets (DRIVE, CHASE_BD1, and STARE) as well as the 3mm and 6mm of the OCTA-500 dataset, achieving an average accuracy (ACC) of 97.25%, 97.77%, 97.85%, 98.89%, and 98.21%, respectively. Conclusions: Empirical evidence shows that our method outperforms the current best models on different vessel segmentation datasets. Our source code is available at: https://github.com/AIEyeSystem/KalDeX.

URLs: https://github.com/AIEyeSystem/KalDeX.

cross Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

Authors: Qintong Zhang, Victor Shea-Jay Huang, Bin Wang, Junyuan Zhang, Zhengren Wang, Hao Liang, Shawn Wang, Matthieu Lin, Wentao Zhang, Conghui He

Abstract: Document parsing is essential for converting unstructured and semi-structured documents-such as contracts, academic papers, and invoices-into structured, machine-readable data. Document parsing extract reliable structured data from unstructured inputs, providing huge convenience for numerous applications. Especially with recent achievements in Large Language Models, document parsing plays an indispensable role in both knowledge base construction and training data generation. This survey presents a comprehensive review of the current state of document parsing, covering key methodologies, from modular pipeline systems to end-to-end models driven by large vision-language models. Core components such as layout detection, content extraction (including text, tables, and mathematical expressions), and multi-modal data integration are examined in detail. Additionally, this paper discusses the challenges faced by modular document parsing systems and vision-language models in handling complex layouts, integrating multiple modules, and recognizing high-density text. It emphasizes the importance of developing larger and more diverse datasets and outlines future research directions.

cross Multi-modal AI for comprehensive breast cancer prognostication

Authors: Jan Witowski, Ken Zeng, Joseph Cappadona, Jailan Elayoubi, Elena Diana Chiru, Nancy Chan, Young-Joon Kang, Frederick Howard, Irina Ostrovnaya, Carlos Fernandez-Granda, Freya Schnabel, Ugur Ozerdem, Kangning Liu, Zoe Steinsnyder, Nitya Thakore, Mohammad Sadic, Frank Yeung, Elisa Liu, Theodore Hill, Benjamin Swett, Danielle Rigau, Andrew Clayburn, Valerie Speirs, Marcus Vetter, Lina Sojak, Simone Muenst Soysal, Daniel Baumhoer, Khalil Choucair, Yu Zong, Lina Daoud, Anas Saad, Waleed Abdulsattar, Rafic Beydoun, Jia-Wern Pan, Haslina Makmur, Soo-Hwang Teo, Linda Ma Pak, Victor Angel, Dovile Zilenaite-Petrulaitiene, Arvydas Laurinavicius, Natalie Klar, Brian D. Piening, Carlo Bifulco, Sun-Young Jun, Jae Pak Yi, Su Hyun Lim, Adam Brufsky, Francisco J. Esteva, Lajos Pusztai, Yann LeCun, Krzysztof J. Geras

Abstract: Treatment selection in breast cancer is guided by molecular subtypes and clinical characteristics. Recurrence risk assessment plays a crucial role in personalizing treatment. Current methods, including genomic assays, have limited accuracy and clinical utility, leading to suboptimal decisions for many patients. We developed a test for breast cancer patient stratification based on digital pathology and clinical characteristics using novel AI methods. Specifically, we utilized a vision transformer-based pan-cancer foundation model trained with self-supervised learning to extract features from digitized H&E-stained slides. These features were integrated with clinical data to form a multi-modal AI test predicting cancer recurrence and death. The test was developed and evaluated using data from a total of 8,161 breast cancer patients across 15 cohorts originating from seven countries. Of these, 3,502 patients from five cohorts were used exclusively for evaluation, while the remaining patients were used for training. Our test accurately predicted our primary endpoint, disease-free interval, in the five external cohorts (C-index: 0.71 [0.68-0.75], HR: 3.63 [3.02-4.37, p<0.01]). In a direct comparison (N=858), the AI test was more accurate than Oncotype DX, the standard-of-care 21-gene assay, with a C-index of 0.67 [0.61-0.74] versus 0.61 [0.49-0.73], respectively. Additionally, the AI test added independent information to Oncotype DX in a multivariate analysis (HR: 3.11 [1.91-5.09, p<0.01)]). The test demonstrated robust accuracy across all major breast cancer subtypes, including TNBC (C-index: 0.71 [0.62-0.81], HR: 3.81 [2.35-6.17, p=0.02]), where no diagnostic tools are currently recommended by clinical guidelines. These results suggest that our AI test can improve accuracy, extend applicability to a wider range of patients, and enhance access to treatment selection tools.

cross OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup

Authors: Xize Cheng, Siqi Zheng, Zehan Wang, Minghui Fang, Ziang Zhang, Rongjie Huang, Ziyang Ma, Shengpeng Ji, Jialong Zuo, Tao Jin, Zhou Zhao

Abstract: The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scaling up the training data, as most natural audio contains diverse interfering signals. To address this limitation, we introduce Omni-modal Sound Separation (OmniSep), a novel framework capable of isolating clean soundtracks based on omni-modal queries, encompassing both single-modal and multi-modal composed queries. Specifically, we introduce the Query-Mixup strategy, which blends query features from different modalities during training. This enables OmniSep to optimize multiple modalities concurrently, effectively bringing all modalities under a unified framework for sound separation. We further enhance this flexibility by allowing queries to influence sound separation positively or negatively, facilitating the retention or removal of specific sounds as desired. Finally, OmniSep employs a retrieval-augmented approach known as Query-Aug, which enables open-vocabulary sound separation. Experimental evaluations on MUSIC, VGGSOUND-CLEAN+, and MUSIC-CLEAN+ datasets demonstrate effectiveness of OmniSep, achieving state-of-the-art performance in text-, image-, and audio-queried sound separation tasks. For samples and further information, please visit the demo page at \url{https://omnisep.github.io/}.

URLs: https://omnisep.github.io/

cross GPT-4o System Card

Authors: OpenAI (Tony), : (Tony), Aaron Hurst (Tony), Adam Lerer (Tony), Adam P. Goucher (Tony), Adam Perelman (Tony), Aditya Ramesh (Tony), Aidan Clark (Tony), AJ Ostrow (Tony), Akila Welihinda (Tony), Alan Hayes (Tony), Alec Radford (Tony), Aleksander M\k{a}dry (Tony), Alex Baker-Whitcomb (Tony), Alex Beutel (Tony), Alex Borzunov (Tony), Alex Carney (Tony), Alex Chow (Tony), Alex Kirillov (Tony), Alex Nichol (Tony), Alex Paino (Tony), Alex Renzin (Tony), Alex Tachard Passos (Tony), Alexander Kirillov (Tony), Alexi Christakis (Tony), Alexis Conneau (Tony), Ali Kamali (Tony), Allan Jabri (Tony), Allison Moyer (Tony), Allison Tam (Tony), Amadou Crookes (Tony), Amin Tootoochian (Tony), Amin Tootoonchian (Tony), Ananya Kumar (Tony), Andrea Vallone (Tony), Andrej Karpathy (Tony), Andrew Braunstein (Tony), Andrew Cann (Tony), Andrew Codispoti (Tony), Andrew Galu (Tony), Andrew Kondrich (Tony), Andrew Tulloch (Tony), Andrey Mishchenko (Tony), Angela Baek (Tony), Angela Jiang (Tony), Antoine Pelisse (Tony), Antonia Woodford (Tony), Anuj Gosalia (Tony), Arka Dhar (Tony), Ashley Pantuliano (Tony), Avi Nayak (Tony), Avital Oliver (Tony), Barret Zoph (Tony), Behrooz Ghorbani (Tony), Ben Leimberger (Tony), Ben Rossen (Tony), Ben Sokolowsky (Tony), Ben Wang (Tony), Benjamin Zweig (Tony), Beth Hoover (Tony), Blake Samic (Tony), Bob McGrew (Tony), Bobby Spero (Tony), Bogo Giertler (Tony), Bowen Cheng (Tony), Brad Lightcap (Tony), Brandon Walkin (Tony), Brendan Quinn (Tony), Brian Guarraci (Tony), Brian Hsu (Tony), Bright Kellogg (Tony), Brydon Eastman (Tony), Camillo Lugaresi (Tony), Carroll Wainwright (Tony), Cary Bassin (Tony), Cary Hudson (Tony), Casey Chu (Tony), Chad Nelson (Tony), Chak Li (Tony), Chan Jun Shern (Tony), Channing Conger (Tony), Charlotte Barette (Tony), Chelsea Voss (Tony), Chen Ding (Tony), Cheng Lu (Tony), Chong Zhang (Tony), Chris Beaumont (Tony), Chris Hallacy (Tony), Chris Koch (Tony), Christian Gibson (Tony), Christina Kim (Tony), Christine Choi (Tony), Christine McLeavey (Tony), Christopher Hesse (Tony), Claudia Fischer (Tony), Clemens Winter (Tony), Coley Czarnecki (Tony), Colin Jarvis (Tony), Colin Wei (Tony), Constantin Koumouzelis (Tony), Dane Sherburn (Tony), Daniel Kappler (Tony), Daniel Levin (Tony), Daniel Levy (Tony), David Carr (Tony), David Farhi (Tony), David Mely (Tony), David Robinson (Tony), David Sasaki (Tony), Denny Jin (Tony), Dev Valladares (Tony), Dimitris Tsipras (Tony), Doug Li (Tony), Duc Phong Nguyen (Tony), Duncan Findlay (Tony), Edede Oiwoh (Tony), Edmund Wong (Tony), Ehsan Asdar (Tony), Elizabeth Proehl (Tony), Elizabeth Yang (Tony), Eric Antonow (Tony), Eric Kramer (Tony), Eric Peterson (Tony), Eric Sigler (Tony), Eric Wallace (Tony), Eugene Brevdo (Tony), Evan Mays (Tony), Farzad Khorasani (Tony), Felipe Petroski Such (Tony), Filippo Raso (Tony), Francis Zhang (Tony), Fred von Lohmann (Tony), Freddie Sulit (Tony), Gabriel Goh (Tony), Gene Oden (Tony), Geoff Salmon (Tony), Giulio Starace (Tony), Greg Brockman (Tony), Hadi Salman (Tony), Haiming Bao (Tony), Haitang Hu (Tony), Hannah Wong (Tony), Haoyu Wang (Tony), Heather Schmidt (Tony), Heather Whitney (Tony), Heewoo Jun (Tony), Hendrik Kirchner (Tony), Henrique Ponde de Oliveira Pinto (Tony), Hongyu Ren (Tony), Huiwen Chang (Tony), Hyung Won Chung (Tony), Ian Kivlichan (Tony), Ian O'Connell (Tony), Ian O'Connell (Tony), Ian Osband (Tony), Ian Silber (Tony), Ian Sohl (Tony), Ibrahim Okuyucu (Tony), Ikai Lan (Tony), Ilya Kostrikov (Tony), Ilya Sutskever (Tony), Ingmar Kanitscheider (Tony), Ishaan Gulrajani (Tony), Jacob Coxon (Tony), Jacob Menick (Tony), Jakub Pachocki (Tony), James Aung (Tony), James Betker (Tony), James Crooks (Tony), James Lennon (Tony), Jamie Kiros (Tony), Jan Leike (Tony), Jane Park (Tony), Jason Kwon (Tony), Jason Phang (Tony), Jason Teplitz (Tony), Jason Wei (Tony), Jason Wolfe (Tony), Jay Chen (Tony), Jeff Harris (Tony), Jenia Varavva (Tony), Jessica Gan Lee (Tony), Jessica Shieh (Tony), Ji Lin (Tony), Jiahui Yu (Tony), Jiayi Weng (Tony), Jie Tang (Tony), Jieqi Yu (Tony), Joanne Jang (Tony), Joaquin Quinonero Candela (Tony), Joe Beutler (Tony), Joe Landers (Tony), Joel Parish (Tony), Johannes Heidecke (Tony), John Schulman (Tony), Jonathan Lachman (Tony), Jonathan McKay (Tony), Jonathan Uesato (Tony), Jonathan Ward (Tony), Jong Wook Kim (Tony), Joost Huizinga (Tony), Jordan Sitkin (Tony), Jos Kraaijeveld (Tony), Josh Gross (Tony), Josh Kaplan (Tony), Josh Snyder (Tony), Joshua Achiam (Tony), Joy Jiao (Tony), Joyce Lee (Tony), Juntang Zhuang (Tony), Justyn Harriman (Tony), Kai Fricke (Tony), Kai Hayashi (Tony), Karan Singhal (Tony), Katy Shi (Tony), Kavin Karthik (Tony), Kayla Wood (Tony), Kendra Rimbach (Tony), Kenny Hsu (Tony), Kenny Nguyen (Tony), Keren Gu-Lemberg (Tony), Kevin Button (Tony), Kevin Liu (Tony), Kiel Howe (Tony), Krithika Muthukumar (Tony), Kyle Luther (Tony), Lama Ahmad (Tony), Larry Kai (Tony), Lauren Itow (Tony), Lauren Workman (Tony), Leher Pathak (Tony), Leo Chen (Tony), Li Jing (Tony), Lia Guy (Tony), Liam Fedus (Tony), Liang Zhou (Tony), Lien Mamitsuka (Tony), Lilian Weng (Tony), Lindsay McCallum (Tony), Lindsey Held (Tony), Long Ouyang (Tony), Louis Feuvrier (Tony), Lu Zhang (Tony), Lukas Kondraciuk (Tony), Lukasz Kaiser (Tony), Luke Hewitt (Tony), Luke Metz (Tony), Lyric Doshi (Tony), Mada Aflak (Tony), Maddie Simens (Tony), Madelaine Boyd (Tony), Madeleine Thompson (Tony), Marat Dukhan (Tony), Mark Chen (Tony), Mark Gray (Tony), Mark Hudnall (Tony), Marvin Zhang (Tony), Marwan Aljubeh (Tony), Mateusz Litwin (Tony), Matthew Zeng (Tony), Max Johnson (Tony), Maya Shetty (Tony), Mayank Gupta (Tony), Meghan Shah (Tony), Mehmet Yatbaz (Tony), Meng Jia Yang (Tony), Mengchao Zhong (Tony), Mia Glaese (Tony), Mianna Chen (Tony), Michael Janner (Tony), Michael Lampe (Tony), Michael Petrov (Tony), Michael Wu (Tony), Michele Wang (Tony), Michelle Fradin (Tony), Michelle Pokrass (Tony), Miguel Castro (Tony), Miguel Oom Temudo de Castro (Tony), Mikhail Pavlov (Tony), Miles Brundage (Tony), Miles Wang (Tony), Minal Khan (Tony), Mira Murati (Tony), Mo Bavarian (Tony), Molly Lin (Tony), Murat Yesildal (Tony), Nacho Soto (Tony), Natalia Gimelshein (Tony), Natalie Cone (Tony), Natalie Staudacher (Tony), Natalie Summers (Tony), Natan LaFontaine (Tony), Neil Chowdhury (Tony), Nick Ryder (Tony), Nick Stathas (Tony), Nick Turley (Tony), Nik Tezak (Tony), Niko Felix (Tony), Nithanth Kudige (Tony), Nitish Keskar (Tony), Noah Deutsch (Tony), Noel Bundick (Tony), Nora Puckett (Tony), Ofir Nachum (Tony), Ola Okelola (Tony), Oleg Boiko (Tony), Oleg Murk (Tony), Oliver Jaffe (Tony), Olivia Watkins (Tony), Olivier Godement (Tony), Owen Campbell-Moore (Tony), Patrick Chao (Tony), Paul McMillan (Tony), Pavel Belov (Tony), Peng Su (Tony), Peter Bak (Tony), Peter Bakkum (Tony), Peter Deng (Tony), Peter Dolan (Tony), Peter Hoeschele (Tony), Peter Welinder (Tony), Phil Tillet (Tony), Philip Pronin (Tony), Philippe Tillet (Tony), Prafulla Dhariwal (Tony), Qiming Yuan (Tony), Rachel Dias (Tony), Rachel Lim (Tony), Rahul Arora (Tony), Rajan Troll (Tony), Randall Lin (Tony), Rapha Gontijo Lopes (Tony), Raul Puri (Tony), Reah Miyara (Tony), Reimar Leike (Tony), Renaud Gaubert (Tony), Reza Zamani (Tony), Ricky Wang (Tony), Rob Donnelly (Tony), Rob Honsby (Tony), Rocky Smith (Tony), Rohan Sahai (Tony), Rohit Ramchandani (Tony), Romain Huet (Tony), Rory Carmichael (Tony), Rowan Zellers (Tony), Roy Chen (Tony), Ruby Chen (Tony), Ruslan Nigmatullin (Tony), Ryan Cheu (Tony), Saachi Jain (Tony), Sam Altman (Tony), Sam Schoenholz (Tony), Sam Toizer (Tony), Samuel Miserendino (Tony), Sandhini Agarwal (Tony), Sara Culver (Tony), Scott Ethersmith (Tony), Scott Gray (Tony), Sean Grove (Tony), Sean Metzger (Tony), Shamez Hermani (Tony), Shantanu Jain (Tony), Shengjia Zhao (Tony), Sherwin Wu (Tony), Shino Jomoto (Tony), Shirong Wu (Tony), Shuaiqi (Tony), Xia, Sonia Phene, Spencer Papay, Srinivas Narayanan, Steve Coffey, Steve Lee, Stewart Hall, Suchir Balaji, Tal Broda, Tal Stramer, Tao Xu, Tarun Gogineni, Taya Christianson, Ted Sanders, Tejal Patwardhan, Thomas Cunninghman, Thomas Degry, Thomas Dimson, Thomas Raoux, Thomas Shadwell, Tianhao Zheng, Todd Underwood, Todor Markov, Toki Sherbakov, Tom Rubin, Tom Stasi, Tomer Kaftan, Tristan Heywood, Troy Peterson, Tyce Walters, Tyna Eloundou, Valerie Qi, Veit Moeller, Vinnie Monaco, Vishal Kuo, Vlad Fomenko, Wayne Chang, Weiyi Zheng, Wenda Zhou, Wesam Manassra, Will Sheu, Wojciech Zaremba, Yash Patil, Yilei Qian, Yongjik Kim, Youlong Cheng, Yu Zhang, Yuchen He, Yuchen Zhang, Yujia Jin, Yunxing Dai, Yury Malkov

Abstract: GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

replace Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators

Authors: Patrick Stotko, Michael Weinmann, Reinhard Klein

Abstract: We present incomplete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators. In particular, we reveal the relation of the classical localized $ L_1 $ estimator, used in the LOP operator for point cloud denoising, to the common Mean Shift framework via a novel kernel. Furthermore, we generalize this result to a whole family of kernels that are built upon the incomplete gamma function and each represents a localized $ L_p $ estimator. By deriving various properties of the kernel family concerning distributional, Mean Shift induced, and other aspects such as strict positive definiteness, we obtain a deeper understanding of the operator's projection behavior. From these theoretical insights, we illustrate several applications ranging from an improved Weighted LOP (WLOP) density weighting scheme and a more accurate Continuous LOP (CLOP) kernel approximation to the definition of a novel set of robust loss functions. These incomplete gamma losses include the Gaussian and LOP loss as special cases and can be applied to various tasks including normal filtering. Furthermore, we show that the novel kernels can be included as priors into neural networks. We demonstrate the effects of each application in a range of quantitative and qualitative experiments that highlight the benefits induced by our modifications.

replace Illuminating Salient Contributions in Neuron Activation with Attribution Equilibrium

Authors: Woo-Jeoung Nam, Seong-Whan Lee

Abstract: With the remarkable success of deep neural networks, there is a growing interest in research aimed at providing clear interpretations of their decision-making processes. In this paper, we introduce Attribution Equilibrium, a novel method to decompose output predictions into fine-grained attributions, balancing positive and negative relevance for clearer visualization of the evidence behind a network decision. We carefully analyze conventional approaches to decision explanation and present a different perspective on the conservation of evidence. We define the evidence as a gap between positive and negative influences among gradient-derived initial contribution maps. Then, we incorporate antagonistic elements and a user-defined criterion for the degree of positive attribution during propagation. Additionally, we consider the role of inactivated neurons in the propagation rule, thereby enhancing the discernment of less relevant elements such as the background. We conduct various assessments in a verified experimental environment with PASCAL VOC 2007, MS COCO 2014, and ImageNet datasets. The results demonstrate that our method outperforms existing attribution methods both qualitatively and quantitatively in identifying the key input features that influence model decisions.

replace Convex Relaxations for Isometric and Equiareal NRSfM

Authors: Agniva Sengupta, Adrien Bartoli

Abstract: Extensible objects form a challenging case for NRSfM, owing to the lack of a sufficiently constrained extensible model of the point-cloud. We tackle the challenge by proposing 1) convex relaxations of the isometric model up to quasi-isometry, and 2) convex relaxations involving the equiareal deformation model, which preserves local area and has not been used in NRSfM. The equiareal model is appealing because it is physically plausible and widely applicable. However, it has two main difficulties: first, when used on its own, it is ambiguous, and second, it involves quartic, hence highly nonconvex, constraints. Our approach handles the first difficulty by mixing the equiareal with the isometric model and the second difficulty by new convex relaxations. We validate our methods on multiple real and synthetic data, including well-known benchmarks.

replace BlinkFlow: A Dataset to Push the Limits of Event-based Optical Flow Estimation

Authors: Yijin Li, Zhaoyang Huang, Shuo Chen, Xiaoyu Shi, Hongsheng Li, Hujun Bao, Zhaopeng Cui, Guofeng Zhang

Abstract: Event cameras provide high temporal precision, low data rates, and high dynamic range visual perception, which are well-suited for optical flow estimation. While data-driven optical flow estimation has obtained great success in RGB cameras, its generalization performance is seriously hindered in event cameras mainly due to the limited and biased training data. In this paper, we present a novel simulator, BlinkSim, for the fast generation of large-scale data for event-based optical flow. BlinkSim incorporates a configurable rendering engine alongside an event simulation suite. By leveraging the wealth of current 3D assets, the rendering engine enables us to automatically build up thousands of scenes with different objects, textures, and motion patterns and render very high-frequency images for realistic event data simulation. Based on BlinkSim, we construct a large training dataset and evaluation benchmark BlinkFlow that contains sufficient, diversiform, and challenging event data with optical flow ground truth. Experiments show that BlinkFlow improves the generalization performance of state-of-the-art methods by more than 40\% on average and up to 90\%. Moreover, we further propose an Event-based optical Flow transFormer (E-FlowFormer) architecture. Powered by our BlinkFlow, E-FlowFormer outperforms the SOTA methods by up to 91\% on the MVSEC dataset and 14\% on the DSEC dataset and presents the best generalization performance. The source code and data are available at https://zju3dv.github.io/blinkflow/.

URLs: https://zju3dv.github.io/blinkflow/.

replace Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

Authors: Huali Xu, Shuaifeng Zhi, Shuzhou Sun, Vishal M. Patel, Li Liu

Abstract: While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the target tasks with very few labeled examples by leveraging prior knowledge from related tasks. However, traditional FSL assumes that both the related and target tasks come from the same domain, which is a restrictive assumption in many real-world scenarios where domain differences are common. To overcome this limitation, Cross-domain few-shot learning (CDFSL) has gained attention, as it allows source and target data to come from different domains and label spaces. This paper presents the first comprehensive review of Cross-domain Few-shot Learning (CDFSL), a field that has received less attention compared to traditional FSL due to its unique challenges. We aim to provide both a position paper and a tutorial for researchers, covering key problems, existing methods, and future research directions. The review begins with a formal definition of CDFSL, outlining its core challenges, followed by a systematic analysis of current approaches, organized under a clear taxonomy. Finally, we discuss promising future directions in terms of problem setups, applications, and theoretical advancements.

replace Decoupled Kullback-Leibler Divergence Loss

Authors: Jiequan Cui, Zhuotao Tian, Zhisheng Zhong, Xiaojuan Qi, Bei Yu, Hanwang Zhang

Abstract: In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels. Thanks to the decomposed formulation of DKL loss, we have identified two areas for improvement. Firstly, we address the limitation of KL/DKL in scenarios like knowledge distillation by breaking its asymmetric optimization property. This modification ensures that the $\mathbf{w}$MSE component is always effective during training, providing extra constructive cues. Secondly, we introduce class-wise global information into KL/DKL to mitigate bias from individual samples. With these two enhancements, we derive the Improved Kullback-Leibler (IKL) Divergence loss and evaluate its effectiveness by conducting experiments on CIFAR-10/100 and ImageNet datasets, focusing on adversarial training, and knowledge distillation tasks. The proposed approach achieves new state-of-the-art adversarial robustness on the public leaderboard -- RobustBench and competitive performance on knowledge distillation, demonstrating the substantial practical merits. Our code is available at https://github.com/jiequancui/DKL.

URLs: https://github.com/jiequancui/DKL.

replace Prompt-based test-time real image dehazing: a novel pipeline

Authors: Zixuan Chen, Zewei He, Ziqian Lu, Xuecheng Sun, Zhe-Ming Lu

Abstract: Existing methods attempt to improve models' generalization ability on real-world hazy images by exploring well-designed training schemes (\eg, CycleGAN, prior loss). However, most of them need very complicated training procedures to achieve satisfactory results. For the first time, we present a novel pipeline called Prompt-based Test-Time Dehazing (PTTD) to help generate visually pleasing results of real-captured hazy images during the inference phase. We experimentally observe that given a dehazing model trained on synthetic data, fine-tuning the statistics (\ie, mean and standard deviation) of encoding features is able to narrow the domain gap, boosting the performance of real image dehazing. Accordingly, we first apply a prompt generation module (PGM) to generate a visual prompt, which is the reference of appropriate statistical perturbations for mean and standard deviation. Then, we employ a feature adaptation module (FAM) into the existing dehazing models for adjusting the original statistics with the guidance of the generated prompt. PTTD is model-agnostic and can be equipped with various state-of-the-art dehazing models trained on synthetic hazy-clean pairs to tackle the real image dehazing task. Extensive experimental results demonstrate that our PTTD is effective, achieving superior performance against state-of-the-art dehazing methods in real-world scenarios. The code is available at \url{https://github.com/cecret3350/PTTD-Dehazing}.

URLs: https://github.com/cecret3350/PTTD-Dehazing

replace Aligning Text-to-Image Diffusion Models with Reward Backpropagation

Authors: Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak, Katerina Fragkiadaki

Abstract: Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training datasets. Due to their unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult. Recent works finetune diffusion models to downstream reward functions using vanilla reinforcement learning, notorious for the high variance of the gradient estimators. In this paper, we propose AlignProp, a method that aligns diffusion models to downstream reward functions using end-to-end backpropagation of the reward gradient through the denoising process. While naive implementation of such backpropagation would require prohibitive memory resources for storing the partial derivatives of modern text-to-image models, AlignProp finetunes low-rank adapter weight modules and uses gradient checkpointing, to render its memory usage viable. We test AlignProp in finetuning diffusion models to various objectives, such as image-text semantic alignment, aesthetics, compressibility and controllability of the number of objects present, as well as their combinations. We show AlignProp achieves higher rewards in fewer training steps than alternatives, while being conceptually simpler, making it a straightforward choice for optimizing diffusion models for differentiable reward functions of interest. Code and Visualization results are available at https://align-prop.github.io/.

URLs: https://align-prop.github.io/.

replace Distillation Improves Visual Place Recognition for Low Quality Images

Authors: Anbang Yang, Ge Jin, Junjie Huang, Yao Wang, John-Ross Rizzo, Chen Feng

Abstract: Real-time visual localization often utilizes online computing, for which query images or videos are transmitted to remote servers for visual place recognition (VPR). However, limited network bandwidth necessitates image-quality reduction and thus the degradation of global image descriptors, reducing VPR accuracy. We address this issue at the descriptor extraction level with a knowledge-distillation methodology that learns feature representations from high-quality images to extract more discriminative descriptors from low-quality images. Our approach includes the Inter-channel Correlation Knowledge Distillation (ICKD) loss, Mean Squared Error (MSE) loss, and Triplet loss. We validate the proposed losses on multiple VPR methods and datasets subjected to JPEG compression, resolution reduction, and video quantization. We obtain significant improvements in VPR recall rates under all three tested modalities of lowered image quality. Furthermore, we fill a gap in VPR literature on video-based data and its influence on VPR performance. This work contributes to more reliable place recognition in resource-constrained environments.

replace Audio-Visual Instance Segmentation

Authors: Ruohao Guo, Xianghua Ying, Yaru Chen, Dantong Niu, Guangyao Li, Liao Qu, Yanyu Qi, Bowei Xing, Wenzhen Yue, Ji Shi, Qixun Wang, Peiliang Zhang, Buwen Liang

Abstract: In this paper, we propose a new multi-modal task, termed audio-visual instance segmentation (AVIS), which aims to simultaneously identify, segment and track individual sounding object instances in audible videos. To facilitate this research, we introduce a high-quality benchmark named AVISeg, containing over 90K instance masks from 26 semantic categories in 926 long videos. Additionally, we propose a strong baseline model for this task. Our model first localizes sound source within each frame, and condenses object-specific contexts into concise tokens. Then it builds long-range audio-visual dependencies between these tokens using window-based attention, and tracks sounding objects among the entire video sequences. Extensive experiments reveal that our method performs best on AVISeg, surpassing the existing methods from related tasks. We further conduct the evaluation on several multi-modal large models; however, they exhibits subpar performance on instance-level sound source localization and temporal perception. We expect that AVIS will inspire the community towards a more comprehensive multi-modal understanding.

replace Toward Open Vocabulary Aerial Object Detection with CLIP-Activated Student-Teacher Learning

Authors: Yan Li, Weiwei Guo, Xue Yang, Ning Liao, Dunyun He, Jiaqi Zhou, Wenxian Yu

Abstract: An increasingly massive number of remote-sensing images spurs the development of extensible object detectors that can detect objects beyond training categories without costly collecting new labeled data. In this paper, we aim to develop open-vocabulary object detection (OVD) technique in aerial images that scales up object vocabulary size beyond training data. The performance of OVD greatly relies on the quality of class-agnostic region proposals and pseudo-labels for novel object categories. To simultaneously generate high-quality proposals and pseudo-labels, we propose CastDet, a CLIP-activated student-teacher open-vocabulary object Detection framework. Our end-to-end framework following the student-teacher self-learning mechanism employs the RemoteCLIP model as an extra omniscient teacher with rich knowledge. By doing so, our approach boosts not only novel object proposals but also classification. Furthermore, we devise a dynamic label queue strategy to maintain high-quality pseudo labels during batch training. We conduct extensive experiments on multiple existing aerial object detection datasets, which are set up for the OVD task. Experimental results demonstrate our CastDet achieving superior open-vocabulary detection performance, e.g., reaching 46.5% mAP on VisDroneZSD novel categories, which outperforms the state-of-the-art open-vocabulary detectors by 21.0% mAP. To our best knowledge, this is the first work to apply and develop the open-vocabulary object detection technique for aerial images. The code is available at https://github.com/lizzy8587/CastDet.

URLs: https://github.com/lizzy8587/CastDet.

replace GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation

Authors: Zhanyu Wang, Longyue Wang, Zhen Zhao, Minghao Wu, Chenyang Lyu, Huayang Li, Deng Cai, Luping Zhou, Shuming Shi, Zhaopeng Tu

Abstract: While the recent advances in Multimodal Large Language Models (MLLMs) constitute a significant leap forward in the field, these models are predominantly confined to the realm of input-side multimodal comprehension, lacking the capacity for multimodal content generation. To fill this gap, we present GPT4Video, a unified multi-model framework that empowers Large Language Models (LLMs) with the capability of both video understanding and generation. Specifically, we develop an instruction-following-based approach integrated with the stable diffusion generative model, which has demonstrated to effectively and securely handle video generation scenarios. GPT4Video offers the following benefits: 1) It exhibits impressive capabilities in both video understanding and generation scenarios. For example, GPT4Video outperforms Valley by 11.8\% on the Video Question Answering task, and surpasses NExt-GPT by 2.3\% on the Text to Video generation task. 2) it endows the LLM/MLLM with video generation capabilities without requiring additional training parameters and can flexibly interface with a wide range of models to perform video generation. 3) it maintains a safe and healthy conversation not only in output-side but also the input side in an end-to-end manner. Qualitative and qualitative experiments demonstrate that GPT4Video holds the potential to function as a effective, safe and Humanoid-like video assistant that can handle both video understanding and generation scenarios.

replace Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation

Authors: Yu Zheng, Guangming Wang, Jiuming Liu, Marc Pollefeys, Hesheng Wang

Abstract: LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Recently, many works project the point cloud onto the 2D image and adopt the 2D Convolutional Neural Networks (CNNs) or vision transformer for LiDAR point cloud semantic segmentation. However, since more than one point can be projected onto the same 2D position but only one point can be preserved, the previous 2D image-based segmentation methods suffer from inevitable quantized information loss. To avoid quantized information loss, in this paper, we propose a novel spherical frustum structure. The points projected onto the same 2D position are preserved in the spherical frustums. Moreover, we propose a memory-efficient hash-based representation of spherical frustums. Through the hash-based representation, we propose the Spherical Frustum sparse Convolution (SFC) and Frustum Fast Point Sampling (F2PS) to convolve and sample the points stored in spherical frustums respectively. Finally, we present the Spherical Frustum sparse Convolution Network (SFCNet) to adopt 2D CNNs for LiDAR point cloud semantic segmentation without quantized information loss. Extensive experiments on the SemanticKITTI and nuScenes datasets demonstrate that our SFCNet outperforms the 2D image-based semantic segmentation methods based on conventional spherical projection. Codes will be available at https://github.com/IRMVLab/SFCNet.

URLs: https://github.com/IRMVLab/SFCNet.

replace SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference

Authors: Feng Wang, Jieru Mei, Alan Yuille

Abstract: Recent advances in contrastive language-image pretraining (CLIP) have demonstrated strong capabilities in zero-shot classification by aligning visual representations with target text embeddings in an image level. However, in dense prediction tasks, CLIP often struggles to localize visual features within an image and fails to give accurate pixel-level predictions, which prevents it from functioning as a generalized visual foundation model. In this work, we aim to enhance CLIP's potential for semantic segmentation with minimal modifications to its pretrained models. By rethinking self-attention, we surprisingly find that CLIP can adapt to dense prediction tasks by simply introducing a novel Correlative Self-Attention (CSA) mechanism. Specifically, we replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module and reuse its pretrained projection matrices of query, key, and value, leading to a training-free adaptation approach for CLIP's zero-shot semantic segmentation. Extensive experiments show the advantage of CSA: we obtain a 38.2% average zero-shot mIoU across eight semantic segmentation benchmarks highlighted in this paper, significantly outperforming the existing SoTA's 33.9% and the vanilla CLIP's 14.1%.

replace How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection

Authors: Felix Meissen, Johannes Getzner, Alexander Ziller, \"Ozg\"un Turgut, Georgios Kaissis, Martin J. Menten, Daniel Rueckert

Abstract: Unsupervised anomaly detection (UAD) alleviates large labeling efforts by training exclusively on unlabeled in-distribution data and detecting outliers as anomalies. Generally, the assumption prevails that large training datasets allow the training of higher-performing UAD models. However, in this work, we show that UAD with extremely few training samples can already match -- and in some cases even surpass -- the performance of training with the whole training dataset. Building upon this finding, we propose an unsupervised method to reliably identify prototypical samples to further boost UAD performance. We demonstrate the utility of our method on seven different established UAD benchmarks from computer vision, industrial defect detection, and medicine. With just 25 selected samples, we even exceed the performance of full training in $25/67$ categories in these benchmarks. Additionally, we show that the prototypical in-distribution samples identified by our proposed method generalize well across models and datasets and that observing their sample selection criteria allows for a successful manual selection of small subsets of high-performing samples. Our code is available at https://anonymous.4open.science/r/uad_prototypical_samples/

URLs: https://anonymous.4open.science/r/uad_prototypical_samples/

replace Joint Explicit and Implicit Cross-Modal Interaction Network for Anterior Chamber Inflammation Diagnosis

Authors: Qian Shao, Ye Dai, Haochao Ying, Kan Xu, Jinhong Wang, Wei Chi, Jian Wu

Abstract: Uveitis demands the precise diagnosis of anterior chamber inflammation (ACI) for optimal treatment. However, current diagnostic methods only rely on a limited single-modal disease perspective, which leads to poor performance. In this paper, we investigate a promising yet challenging way to fuse multimodal data for ACI diagnosis. Notably, existing fusion paradigms focus on empowering implicit modality interactions (i.e., self-attention and its variants), but neglect to inject explicit modality interactions, especially from clinical knowledge and imaging property. To this end, we propose a jointly Explicit and implicit Cross-Modal Interaction Network (EiCI-Net) for Anterior Chamber Inflammation Diagnosis that uses anterior segment optical coherence tomography (AS-OCT) images, slit-lamp images, and clinical data jointly. Specifically, we first develop CNN-Based Encoders and Tabular Processing Module (TPM) to extract efficient feature representations in different modalities. Then, we devise an Explicit Cross-Modal Interaction Module (ECIM) to generate attention maps as a kind of explicit clinical knowledge based on the tabular feature maps, then integrated them into the slit-lamp feature maps, allowing the CNN-Based Encoder to focus on more effective informativeness of the slit-lamp images. After that, the Implicit Cross-Modal Interaction Module (ICIM), a transformer-based network, further implicitly enhances modality interactions. Finally, we construct a considerable real-world dataset from our collaborative hospital and conduct sufficient experiments to demonstrate the superior performance of our proposed EiCI-Net compared with the state-of-the-art classification methods in various metrics.

replace DUSt3R: Geometric 3D Vision Made Easy

Authors: Shuzhe Wang, Vincent Leroy, Yohann Cabon, Boris Chidlovskii, Jerome Revaud

Abstract: Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate corresponding pixels in 3D space, which is the core of all best performing MVS algorithms. In this work, we take an opposite stance and introduce DUSt3R, a radically novel paradigm for Dense and Unconstrained Stereo 3D Reconstruction of arbitrary image collections, i.e. operating without prior information about camera calibration nor viewpoint poses. We cast the pairwise reconstruction problem as a regression of pointmaps, relaxing the hard constraints of usual projective camera models. We show that this formulation smoothly unifies the monocular and binocular reconstruction cases. In the case where more than two images are provided, we further propose a simple yet effective global alignment strategy that expresses all pairwise pointmaps in a common reference frame. We base our network architecture on standard Transformer encoders and decoders, allowing us to leverage powerful pretrained models. Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera. Exhaustive experiments on all these tasks showcase that the proposed DUSt3R can unify various 3D vision tasks and set new SoTAs on monocular/multi-view depth estimation as well as relative pose estimation. In summary, DUSt3R makes many geometric 3D vision tasks easy.

replace Attack-Resilient Image Watermarking Using Stable Diffusion

Authors: Lijun Zhang, Xiao Liu, Antoni Viros Martin, Cindy Xiong Bearfield, Yuriy Brun, Hui Guan

Abstract: Watermarking images is critical for tracking image provenance and proving ownership. With the advent of generative models, such as stable diffusion, that can create fake but realistic images, watermarking has become particularly important to make human-created images reliably identifiable. Unfortunately, the very same stable diffusion technology can remove watermarks injected using existing methods. To address this problem, we present ZoDiac, which uses a pre-trained stable diffusion model to inject a watermark into the trainable latent space, resulting in watermarks that can be reliably detected in the latent vector even when attacked. We evaluate ZoDiac on three benchmarks, MS-COCO, DiffusionDB, and WikiArt, and find that ZoDiac is robust against state-of-the-art watermark attacks, with a watermark detection rate above 98% and a false positive rate below 6.4%, outperforming state-of-the-art watermarking methods. We hypothesize that the reciprocating denoising process in diffusion models may inherently enhance the robustness of the watermark when faced with strong attacks and validate the hypothesis. Our research demonstrates that stable diffusion is a promising approach to robust watermarking, able to withstand even stable-diffusion--based attack methods. ZoDiac is open-sourced and available at https://github.com/zhanglijun95/ZoDiac.

URLs: https://github.com/zhanglijun95/ZoDiac.

replace Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes

Authors: Weifeng Liu, Tianyi She, Jiawei Liu, Boheng Li, Dongyu Yao, Ziyou Liang, Run Wang

Abstract: In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, but these methods also pose potential and severe security threats to humanity. DeepFake can be bifurcated into entertainment applications like face swapping and illicit uses such as lip-syncing fraud. However, lip-forgery videos, which neither change identity nor have discernible visual artifacts, present a formidable challenge to existing DeepFake detection methods. Our preliminary experiments have shown that the effectiveness of the existing methods often drastically decrease or even fail when tackling lip-syncing videos. In this paper, for the first time, we propose a novel approach dedicated to lip-forgery identification that exploits the inconsistency between lip movements and audio signals. We also mimic human natural cognition by capturing subtle biological links between lips and head regions to boost accuracy. To better illustrate the effectiveness and advances of our proposed method, we create a high-quality LipSync dataset, AVLips, by employing the state-of-the-art lip generators. We hope this high-quality and diverse dataset could be well served the further research on this challenging and interesting field. Experimental results show that our approach gives an average accuracy of more than 95.3% in spotting lip-syncing videos, significantly outperforming the baselines. Extensive experiments demonstrate the capability to tackle deepfakes and the robustness in surviving diverse input transformations. Our method achieves an accuracy of up to 90.2% in real-world scenarios (e.g., WeChat video call) and shows its powerful capabilities in real scenario deployment. To facilitate the progress of this research community, we release all resources at https://github.com/AaronComo/LipFD.

URLs: https://github.com/AaronComo/LipFD.

replace Advancing Video Anomaly Detection: A Concise Review and a New Dataset

Authors: Liyun Zhu, Lei Wang, Arjun Raj, Tom Gedeon, Chen Chen

Abstract: Video Anomaly Detection (VAD) finds widespread applications in security surveillance, traffic monitoring, industrial monitoring, and healthcare. Despite extensive research efforts, there remains a lack of concise reviews that provide insightful guidance for researchers. Such reviews would serve as quick references to grasp current challenges, research trends, and future directions. In this paper, we present such a review, examining models and datasets from various perspectives. We emphasize the critical relationship between model and dataset, where the quality and diversity of datasets profoundly influence model performance, and dataset development adapts to the evolving needs of emerging approaches. Our review identifies practical issues, including the absence of comprehensive datasets with diverse scenarios. To address this, we introduce a new dataset, Multi-Scenario Anomaly Detection (MSAD), comprising 14 distinct scenarios captured from various camera views. Our dataset has diverse motion patterns and challenging variations, such as different lighting and weather conditions, providing a robust foundation for training superior models. We conduct an in-depth analysis of recent representative models using MSAD and highlight its potential in addressing the challenges of detecting anomalies across diverse and evolving surveillance scenarios. [Project website: https://msad-dataset.github.io/]

URLs: https://msad-dataset.github.io/]

replace Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery

Authors: Pedro H. V. Valois, Jo\~ao Macedo, Leo S. F. Ribeiro, Jefersson A. dos Santos, Sandra Avila

Abstract: Crime in the 21st century is split into a virtual and real world. However, the former has become a global menace to people's well-being and security in the latter. The challenges it presents must be faced with unified global cooperation, and we must rely more than ever on automated yet trustworthy tools to combat the ever-growing nature of online offenses. Over 10 million child sexual abuse reports are submitted to the US National Center for Missing \& Exploited Children every year, and over 80% originate from online sources. Therefore, investigation centers cannot manually process and correctly investigate all imagery. In light of that, reliable automated tools that can securely and efficiently deal with this data are paramount. In this sense, the scene classification task looks for contextual cues in the environment, being able to group and classify child sexual abuse data without requiring to be trained on sensitive material. The scarcity and limitations of working with child sexual abuse images lead to self-supervised learning, a machine-learning methodology that leverages unlabeled data to produce powerful representations that can be more easily transferred to downstream tasks. This work shows that self-supervised deep learning models pre-trained on scene-centric data can reach 71.6% balanced accuracy on our indoor scene classification task and, on average, 2.2 percentage points better performance than a fully supervised version. We cooperate with Brazilian Federal Police experts to evaluate our indoor classification model on actual child abuse material. The results demonstrate a notable discrepancy between the features observed in widely used scene datasets and those depicted on sensitive materials.

replace Effectiveness Assessment of Recent Large Vision-Language Models

Authors: Yao Jiang, Xinyu Yan, Ge-Peng Ji, Keren Fu, Meijun Sun, Huan Xiong, Deng-Ping Fan, Fahad Shahbaz Khan

Abstract: The advent of large vision-language models (LVLMs) represents a remarkable advance in the quest for artificial general intelligence. However, the model's effectiveness in both specialized and general tasks warrants further investigation. This paper endeavors to evaluate the competency of popular LVLMs in specialized and general tasks, respectively, aiming to offer a comprehensive understanding of these novel models. To gauge their effectiveness in specialized tasks, we employ six challenging tasks in three different application scenarios: natural, healthcare, and industrial. These six tasks include salient/camouflaged/transparent object detection, as well as polyp detection, skin lesion detection, and industrial anomaly detection. We examine the performance of three recent open-source LVLMs, including MiniGPT-v2, LLaVA-1.5, and Shikra, on both visual recognition and localization in these tasks. Moreover, we conduct empirical investigations utilizing the aforementioned LVLMs together with GPT-4V, assessing their multi-modal understanding capabilities in general tasks including object counting, absurd question answering, affordance reasoning, attribute recognition, and spatial relation reasoning. Our investigations reveal that these LVLMs demonstrate limited proficiency not only in specialized tasks but also in general tasks. We delve deep into this inadequacy and uncover several potential factors, including limited cognition in specialized tasks, object hallucination, text-to-image interference, and decreased robustness in complex problems. We hope that this study can provide useful insights for the future development of LVLMs, helping researchers improve LVLMs for both general and specialized applications.

replace Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis

Authors: Muxi Chen, Yi Liu, Jian Yi, Changran Xu, Qiuxia Lai, Hongliang Wang, Tsung-Yi Ho, Qiang Xu

Abstract: In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework categorizes evaluations into two distinct groups: first, focusing on image qualities such as aesthetics and realism, and second, examining text conditions through concept coverage and fairness. We introduce an innovative aesthetic score prediction model that assesses the visual appeal of generated images and unveils the first dataset marked with low-quality regions in generated human images to facilitate automatic defect detection. Our exploration into concept coverage probes the model's effectiveness in interpreting and rendering text-based concepts accurately, while our analysis of fairness reveals biases in model outputs, with an emphasis on gender, race, and age. While our study is grounded in human imagery, this dual-faceted approach is designed with the flexibility to be applicable to other forms of image generation, enhancing our understanding of generative models and paving the way to the next generation of more sophisticated, contextually aware, and ethically attuned generative models. Code and data, including the dataset annotated with defective areas, are available at \href{https://github.com/cure-lab/EvaluateAIGC}{https://github.com/cure-lab/EvaluateAIGC}.

URLs: https://github.com/cure-lab/EvaluateAIGC, https://github.com/cure-lab/EvaluateAIGC

replace Spatiotemporal Representation Learning for Short and Long Medical Image Time Series

Authors: Chengzhi Shen, Martin J. Menten, Hrvoje Bogunovi\'c, Ursula Schmidt-Erfurth, Hendrik Scholl, Sobha Sivaprasad, Andrew Lotery, Daniel Rueckert, Paul Hager, Robbie Holland

Abstract: Analyzing temporal developments is crucial for the accurate prognosis of many medical conditions. Temporal changes that occur over short time scales are key to assessing the health of physiological functions, such as the cardiac cycle. Moreover, tracking longer term developments that occur over months or years in evolving processes, such as age-related macular degeneration (AMD), is essential for accurate prognosis. Despite the importance of both short and long term analysis to clinical decision making, they remain understudied in medical deep learning. State of the art methods for spatiotemporal representation learning, developed for short natural videos, prioritize the detection of temporal constants rather than temporal developments. Moreover, they do not account for varying time intervals between acquisitions, which are essential for contextualizing observed changes. To address these issues, we propose two approaches. First, we combine clip-level contrastive learning with a novel temporal embedding to adapt to irregular time series. Second, we propose masking and predicting latent frame representations of the temporal sequence. Our two approaches outperform all prior methods on temporally-dependent tasks including cardiac output estimation and three prognostic AMD tasks. Overall, this enables the automated analysis of temporal patterns which are typically overlooked in applications of deep learning to medicine.

replace Veagle: Advancements in Multimodal Representation Learning

Authors: Rajat Chawla, Arkajit Datta, Tushar Verma, Adarsh Jha, Anmol Gautam, Ayush Vatsal, Sukrit Chaterjee, Mukunda NS, Ishaan Bhola

Abstract: Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual information. Multimodal models, an extension of Large Language Models (LLMs), have exhibited remarkable capabilities in addressing a diverse array of tasks, ranging from image captioning and visual question answering (VQA) to visual grounding. While these models have showcased significant advancements, challenges persist in accurately interpreting images and answering the question, a common occurrence in real-world scenarios. This paper introduces a novel approach to enhance the multimodal capabilities of existing models. In response to the limitations observed in current Vision Language Models (VLMs) and Multimodal Large Language Models (MLLMs), our proposed model Veagle, incorporates a unique mechanism inspired by the successes and insights of previous works. Veagle leverages a dynamic mechanism to project encoded visual information directly into the language model. This dynamic approach allows for a more nuanced understanding of intricate details present in visual contexts. To validate the effectiveness of Veagle, we conduct comprehensive experiments on benchmark datasets, emphasizing tasks such as visual question answering and image understanding. Our results indicate a improvement of 5-6 \% in performance, with Veagle outperforming existing models by a notable margin. The outcomes underscore the model's versatility and applicability beyond traditional benchmarks.

replace iSeg: Interactive 3D Segmentation via Interactive Attention

Authors: Itai Lang, Fei Xu, Dale Decatur, Sudarshan Babu, Rana Hanocka

Abstract: We present iSeg, a new interactive technique for segmenting 3D shapes. Previous works have focused mainly on leveraging pre-trained 2D foundation models for 3D segmentation based on text. However, text may be insufficient for accurately describing fine-grained spatial segmentations. Moreover, achieving a consistent 3D segmentation using a 2D model is highly challenging, since occluded areas of the same semantic region may not be visible together from any 2D view. Thus, we design a segmentation method conditioned on fine user clicks, which operates entirely in 3D. Our system accepts user clicks directly on the shape's surface, indicating the inclusion or exclusion of regions from the desired shape partition. To accommodate various click settings, we propose a novel interactive attention module capable of processing different numbers and types of clicks, enabling the training of a single unified interactive segmentation model. We apply iSeg to a myriad of shapes from different domains, demonstrating its versatility and faithfulness to the user's specifications. Our project page is at https://threedle.github.io/iSeg/.

URLs: https://threedle.github.io/iSeg/.

replace Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models

Authors: Sangwon Jang, Jaehyeong Jo, Kimin Lee, Sung Ju Hwang

Abstract: Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed identities with combined attributes from different subjects. In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects. Our main idea is to utilize segmented subjects generated by a foundation model for segmentation (Segment Anything) for both training and inference, as a form of data augmentation for training and initialization for the generation process. Moreover, we further introduce a new metric to better evaluate the performance of our method on multi-subject personalization. Experimental results show that our MuDI can produce high-quality personalized images without identity mixing, even for highly similar subjects as shown in Figure 1. Specifically, in human evaluation, MuDI obtains twice the success rate for personalizing multiple subjects without identity mixing over existing baselines and is preferred over 70% against the strongest baseline.

replace Binomial Self-compensation for Motion Error in Dynamic 3D Scanning

Authors: Geyou Zhang, Ce Zhu, Kai Liu

Abstract: Phase shifting profilometry (PSP) is favored in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise property. However, a fundamental assumption of PSP that the object should remain static is violated in dynamic measurement, making PSP susceptible to object moving, resulting in ripple-like errors in the point clouds. We propose a pixel-wise and frame-wise loopable binomial self-compensation (BSC) algorithm to effectively and flexibly eliminate motion error in the four-step PSP. Our mathematical model demonstrates that by summing successive motion-affected phase frames weighted by binomial coefficients, motion error exponentially diminishes as the binomial order increases, accomplishing automatic error compensation through the motion-affected phase sequence, without the assistance of any intermediate variable. Extensive experiments show that our BSC outperforms the existing methods in reducing motion error, while achieving a depth map frame rate equal to the camera's acquisition rate (90 fps), enabling high-accuracy 3D reconstruction with a quasi-single-shot frame rate.

replace Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlooks

Authors: Fulong Ma, Weiqing Qi, Guoyang Zhao, Linwei Zheng, Sheng Wang, Yuxuan Liu, Ming Liu, Jun Ma

Abstract: 3D lane detection is essential in autonomous driving as it extracts structural and traffic information from the road in three-dimensional space, aiding self-driving cars in logical, safe, and comfortable path planning and motion control. Given the cost of sensors and the advantages of visual data in color information, 3D lane detection based on monocular vision is an important research direction in the realm of autonomous driving, increasingly gaining attention in both industry and academia. Regrettably, recent advancements in visual perception seem inadequate for the development of fully reliable 3D lane detection algorithms, which also hampers the progress of vision-based fully autonomous vehicles. We believe that there is still considerable room for improvement in 3D lane detection algorithms for autonomous vehicles using visual sensors, and significant enhancements are needed. This review looks back and analyzes the current state of achievements in the field of 3D lane detection research. It covers all current monocular-based 3D lane detection processes, discusses the performance of these cutting-edge algorithms, analyzes the time complexity of various algorithms, and highlights the main achievements and limitations of ongoing research efforts. The survey also includes a comprehensive discussion of available 3D lane detection datasets and the challenges that researchers face but have not yet resolved. Finally, our work outlines future research directions and invites researchers and practitioners to join this exciting field.

replace OneActor: Consistent Character Generation via Cluster-Conditioned Guidance

Authors: Jiahao Wang, Caixia Yan, Haonan Lin, Weizhan Zhang, Mengmeng Wang, Tieliang Gong, Guang Dai, Hao Sun

Abstract: Text-to-image diffusion models benefit artists with high-quality image generation. Yet their stochastic nature hinders artists from creating consistent images of the same subject. Existing methods try to tackle this challenge and generate consistent content in various ways. However, they either depend on external restricted data or require expensive tuning of the diffusion model. For this issue, we propose a novel one-shot tuning paradigm, termed OneActor. It efficiently performs consistent subject generation solely driven by prompts via a learned semantic guidance to bypass the laborious backbone tuning. We lead the way to formalize the objective of consistent subject generation from a clustering perspective, and thus design a cluster-conditioned model. To mitigate the overfitting challenge shared by one-shot tuning pipelines, we augment the tuning with auxiliary samples and devise two inference strategies: semantic interpolation and cluster guidance. These techniques are later verified to significantly improve the generation quality. Comprehensive experiments show that our method outperforms a variety of baselines with satisfactory subject consistency, superior prompt conformity as well as high image quality. Our method is capable of multi-subject generation and compatible with popular diffusion extensions. Besides, we achieve a 4 times faster tuning speed than tuning-based baselines and, if desired, avoid increasing the inference time. Furthermore, our method can be naturally utilized to pre-train a consistent subject generation network from scratch, which will implement this research task into more practical applications. (Project page: https://johnneywang.github.io/OneActor-webpage/)

URLs: https://johnneywang.github.io/OneActor-webpage/)

replace Customizing Text-to-Image Models with a Single Image Pair

Authors: Maxwell Jones, Sheng-Yu Wang, Nupur Kumari, David Bau, Jun-Yan Zhu

Abstract: Art reinterpretation is the practice of creating a variation of a reference work, making a paired artwork that exhibits a distinct artistic style. We ask if such an image pair can be used to customize a generative model to capture the demonstrated stylistic difference. We propose Pair Customization, a new customization method that learns stylistic difference from a single image pair and then applies the acquired style to the generation process. Unlike existing methods that learn to mimic a single concept from a collection of images, our method captures the stylistic difference between paired images. This allows us to apply a stylistic change without overfitting to the specific image content in the examples. To address this new task, we employ a joint optimization method that explicitly separates the style and content into distinct LoRA weight spaces. We optimize these style and content weights to reproduce the style and content images while encouraging their orthogonality. During inference, we modify the diffusion process via a new style guidance based on our learned weights. Both qualitative and quantitative experiments show that our method can effectively learn style while avoiding overfitting to image content, highlighting the potential of modeling such stylistic differences from a single image pair.

replace Parallel Backpropagation for Shared-Feature Visualization

Authors: Alexander Lappe, Anna Bogn\'ar, Ghazaleh Ghamkhari Nejad, Albert Mukovskiy, Lucas Martini, Martin A. Giese, Rufin Vogels

Abstract: High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this finding holds on average, some out-of-category stimuli also activate neurons in these regions. This may be due to visual features common among the preferred class also being present in other images. Here, we propose a deep-learning-based approach for visualizing these features. For each neuron, we identify relevant visual features driving its selectivity by modelling responses to images based on latent activations of a deep neural network. Given an out-of-category image which strongly activates the neuron, our method first identifies a reference image from the preferred category yielding a similar feature activation pattern. We then backpropagate latent activations of both images to the pixel level, while enhancing the identified shared dimensions and attenuating non-shared features. The procedure highlights image regions containing shared features driving responses of the model neuron. We apply the algorithm to novel recordings from body-selective regions in macaque IT cortex in order to understand why some images of objects excite these neurons. Visualizations reveal object parts which resemble parts of a macaque body, shedding light on neural preference of these objects.

replace Images that Sound: Composing Images and Sounds on a Single Canvas

Authors: Ziyang Chen, Daniel Geng, Andrew Owens

Abstract: Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these visual spectrograms images that sound. Our approach is simple and zero-shot, and it leverages pre-trained text-to-image and text-to-spectrogram diffusion models that operate in a shared latent space. During the reverse process, we denoise noisy latents with both the audio and image diffusion models in parallel, resulting in a sample that is likely under both models. Through quantitative evaluations and perceptual studies, we find that our method successfully generates spectrograms that align with a desired audio prompt while also taking the visual appearance of a desired image prompt. Please see our project page for video results: https://ificl.github.io/images-that-sound/

URLs: https://ificl.github.io/images-that-sound/

replace RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar

Authors: Fangqiang Ding, Xiangyu Wen, Yunzhou Zhu, Yiming Li, Chris Xiaoxuan Lu

Abstract: 3D occupancy-based perception pipeline has significantly advanced autonomous driving by capturing detailed scene descriptions and demonstrating strong generalizability across various object categories and shapes. Current methods predominantly rely on LiDAR or camera inputs for 3D occupancy prediction. These methods are susceptible to adverse weather conditions, limiting the all-weather deployment of self-driving cars. To improve perception robustness, we leverage the recent advances in automotive radars and introduce a novel approach that utilizes 4D imaging radar sensors for 3D occupancy prediction. Our method, RadarOcc, circumvents the limitations of sparse radar point clouds by directly processing the 4D radar tensor, thus preserving essential scene details. RadarOcc innovatively addresses the challenges associated with the voluminous and noisy 4D radar data by employing Doppler bins descriptors, sidelobe-aware spatial sparsification, and range-wise self-attention mechanisms. To minimize the interpolation errors associated with direct coordinate transformations, we also devise a spherical-based feature encoding followed by spherical-to-Cartesian feature aggregation. We benchmark various baseline methods based on distinct modalities on the public K-Radar dataset. The results demonstrate RadarOcc's state-of-the-art performance in radar-based 3D occupancy prediction and promising results even when compared with LiDAR- or camera-based methods. Additionally, we present qualitative evidence of the superior performance of 4D radar in adverse weather conditions and explore the impact of key pipeline components through ablation studies.

replace Flatten Anything: Unsupervised Neural Surface Parameterization

Authors: Qijian Zhang, Junhui Hou, Wenping Wang, Ying He

Abstract: Surface parameterization plays an essential role in numerous computer graphics and geometry processing applications. Traditional parameterization approaches are designed for high-quality meshes laboriously created by specialized 3D modelers, thus unable to meet the processing demand for the current explosion of ordinary 3D data. Moreover, their working mechanisms are typically restricted to certain simple topologies, thus relying on cumbersome manual efforts (e.g., surface cutting, part segmentation) for pre-processing. In this paper, we introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization via learning point-wise mappings between 3D points on the target geometric surface and adaptively-deformed UV coordinates within the 2D parameter domain. To mimic the actual physical procedures, we ingeniously construct geometrically-interpretable sub-networks with specific functionalities of surface cutting, UV deforming, unwrapping, and wrapping, which are assembled into a bi-directional cycle mapping framework. Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information, thus significantly reducing the strict requirements for mesh quality and even applicable to unstructured point cloud data. More importantly, our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies, since its learning process adaptively finds reasonable cutting seams and UV boundaries. Extensive experiments demonstrate the universality, superiority, and inspiring potential of our proposed neural surface parameterization paradigm. Our code is available at https://github.com/keeganhk/FlattenAnything.

URLs: https://github.com/keeganhk/FlattenAnything.

replace RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Authors: Zhicheng Sun, Zhenhao Yang, Yang Jin, Haozhe Chi, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Yang Song, Kun Gai, Yadong Mu

Abstract: Customizing diffusion models to generate identity-preserving images from user-provided reference images is an intriguing new problem. The prevalent approaches typically require training on extensive domain-specific images to achieve identity preservation, which lacks flexibility across different use cases. To address this issue, we exploit classifier guidance, a training-free technique that steers diffusion models using an existing classifier, for personalized image generation. Our study shows that based on a recent rectified flow framework, the major limitation of vanilla classifier guidance in requiring a special classifier can be resolved with a simple fixed-point solution, allowing flexible personalization with off-the-shelf image discriminators. Moreover, its solving procedure proves to be stable when anchored to a reference flow trajectory, with a convergence guarantee. The derived method is implemented on rectified flow with different off-the-shelf image discriminators, delivering advantageous personalization results for human faces, live subjects, and certain objects. Code is available at https://github.com/feifeiobama/RectifID.

URLs: https://github.com/feifeiobama/RectifID.

replace HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting

Authors: Yuanhao Cai, Zihao Xiao, Yixun Liang, Minghan Qin, Yulun Zhang, Xiaokang Yang, Yaoyao Liu, Alan Yuille

Abstract: High dynamic range (HDR) novel view synthesis (NVS) aims to create photorealistic images from novel viewpoints using HDR imaging techniques. The rendered HDR images capture a wider range of brightness levels containing more details of the scene than normal low dynamic range (LDR) images. Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. In this paper, we propose a new framework, High Dynamic Range Gaussian Splatting (HDR-GS), which can efficiently render novel HDR views and reconstruct LDR images with a user input exposure time. Specifically, we design a Dual Dynamic Range (DDR) Gaussian point cloud model that uses spherical harmonics to fit HDR color and employs an MLP-based tone-mapper to render LDR color. The HDR and LDR colors are then fed into two Parallel Differentiable Rasterization (PDR) processes to reconstruct HDR and LDR views. To establish the data foundation for the research of 3D Gaussian splatting-based methods in HDR NVS, we recalibrate the camera parameters and compute the initial positions for Gaussian point clouds. Experiments demonstrate that our HDR-GS surpasses the state-of-the-art NeRF-based method by 3.84 and 1.91 dB on LDR and HDR NVS while enjoying 1000x inference speed and only requiring 6.3% training time. Code and recalibrated data will be publicly available at https://github.com/caiyuanhao1998/HDR-GS . A brief video introduction of our work is available at https://youtu.be/wtU7Kcwe7ck

URLs: https://github.com/caiyuanhao1998/HDR-GS, https://youtu.be/wtU7Kcwe7ck

replace Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model

Authors: Mingyang Yi, Aoxue Li, Yi Xin, Zhenguo Li

Abstract: Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion image generator. Despite the success of DPM in practice, the mechanism behind it remains to be explored. To fill this blank, we begin by examining the intermediate statuses during the gradual denoising generation process in DPM. The empirical observations indicate, the shape of image is reconstructed after the first few denoising steps, and then the image is filled with details (e.g., texture). The phenomenon is because the low-frequency signal (shape relevant) of the noisy image is not corrupted until the final stage in the forward process (initial stage of generation) of adding noise in DPM. Inspired by the observations, we proceed to explore the influence of each token in the text prompt during the two stages. After a series of experiments of T2I generations conditioned on a set of text prompts. We conclude that in the earlier generation stage, the image is mostly decided by the special token [\texttt{EOS}] in the text prompt, and the information in the text prompt is already conveyed in this stage. After that, the diffusion model completes the details of generated images by information from themselves. Finally, we propose to apply this observation to accelerate the process of T2I generation by properly removing text guidance, which finally accelerates the sampling up to 25\%+.

replace Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers

Authors: Chau Pham, Bryan A. Plummer

Abstract: Multi-Channel Imaging (MCI) contains an array of challenges for encoding useful feature representations not present in traditional images. For example, images from two different satellites may both contain RGB channels, but the remaining channels can be different for each imaging source. Thus, MCI models must support a variety of channel configurations at test time. Recent work has extended traditional visual encoders for MCI, such as Vision Transformers (ViT), by supplementing pixel information with an encoding representing the channel configuration. However, these methods treat each channel equally, i.e., they do not consider the unique properties of each channel type, which can result in needless and potentially harmful redundancies in the learned features. For example, if RGB channels are always present, the other channels can focus on extracting information that cannot be captured by the RGB channels. To this end, we propose DiChaViT, which aims to enhance the diversity in the learned features of MCI-ViT models. This is achieved through a novel channel sampling strategy that encourages the selection of more distinct channel sets for training. Additionally, we employ regularization and initialization techniques to increase the likelihood that new information is learned from each channel. Many of our improvements are architecture agnostic and can be incorporated into new architectures as they are developed. Experiments on both satellite and cell microscopy datasets, CHAMMI, JUMP-CP, and So2Sat, report DiChaViT yields a 1.5 - 5.0% gain over the state-of-the-art. Our code is publicly available at https://github.com/chaudatascience/diverse_channel_vit.

URLs: https://github.com/chaudatascience/diverse_channel_vit.

replace LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling

Authors: Yaohua Zha, Naiqi Li, Yanzi Wang, Tao Dai, Hang Guo, Bin Chen, Zhi Wang, Zhihao Ouyang, Shu-Tao Xia

Abstract: The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder, hindering their practice application. To address this limitation, we first conduct a comprehensive analysis of existing Transformer-based MPM, emphasizing the idea that redundancy reduction is crucial for point cloud analysis. To this end, we propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density. Extensive experimental results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency, especially our LCM-based Point-MAE model, compared to the Transformer-based model, achieved an improvement of 1.84%, 0.67%, and 0.60% in average accuracy on the three variants of ScanObjectNN while reducing parameters by 88% and computation by 73%. Code is available at https://github.com/zyh16143998882/LCM.

URLs: https://github.com/zyh16143998882/LCM.

replace Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability

Authors: Shenyuan Gao, Jiazhi Yang, Li Chen, Kashyap Chitta, Yihang Qiu, Andreas Geiger, Jun Zhang, Hongyang Li

Abstract: World models can foresee the outcomes of different actions, which is of paramount importance for autonomous driving. Nevertheless, existing driving world models still have limitations in generalization to unseen environments, prediction fidelity of critical details, and action controllability for flexible application. In this paper, we present Vista, a generalizable driving world model with high fidelity and versatile controllability. Based on a systematic diagnosis of existing methods, we introduce several key ingredients to address these limitations. To accurately predict real-world dynamics at high resolution, we propose two novel losses to promote the learning of moving instances and structural information. We also devise an effective latent replacement approach to inject historical frames as priors for coherent long-horizon rollouts. For action controllability, we incorporate a versatile set of controls from high-level intentions (command, goal point) to low-level maneuvers (trajectory, angle, and speed) through an efficient learning strategy. After large-scale training, the capabilities of Vista can seamlessly generalize to different scenarios. Extensive experiments on multiple datasets show that Vista outperforms the most advanced general-purpose video generator in over 70% of comparisons and surpasses the best-performing driving world model by 55% in FID and 27% in FVD. Moreover, for the first time, we utilize the capacity of Vista itself to establish a generalizable reward for real-world action evaluation without accessing the ground truth actions.

replace MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities

Authors: Hao Dong, Yue Zhao, Eleni Chatzi, Olga Fink

Abstract: Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios on image data. However, real-world applications are inherently multimodal, which makes it essential to leverage information from multiple modalities to enhance the efficacy of OOD detection. To establish a foundation for more realistic Multimodal OOD Detection, we introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes and varying modality combinations. We first evaluate existing unimodal OOD detection algorithms on MultiOOD, observing that the mere inclusion of additional modalities yields substantial improvements. This underscores the importance of utilizing multiple modalities for OOD detection. Based on the observation of Modality Prediction Discrepancy between in-distribution (ID) and OOD data, and its strong correlation with OOD performance, we propose the Agree-to-Disagree (A2D) algorithm to encourage such discrepancy during training. Moreover, we introduce a novel outlier synthesis method, NP-Mix, which explores broader feature spaces by leveraging the information from nearest neighbor classes and complements A2D to strengthen OOD detection performance. Extensive experiments on MultiOOD demonstrate that training with A2D and NP-Mix improves existing OOD detection algorithms by a large margin. Our source code and MultiOOD benchmark are available at https://github.com/donghao51/MultiOOD.

URLs: https://github.com/donghao51/MultiOOD.

replace SarcNet: A Novel AI-based Framework to Automatically Analyze and Score Sarcomere Organizations in Fluorescently Tagged hiPSC-CMs

Authors: Huyen Le, Khiet Dang, Tien Lai, Nhung Nguyen, Mai Tran, Hieu Pham

Abstract: Quantifying sarcomere structure organization in human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) is crucial for understanding cardiac disease pathology, improving drug screening, and advancing regenerative medicine. Traditional methods, such as manual annotation and Fourier transform analysis, are labor-intensive, error-prone, and lack high-throughput capabilities. In this study, we present a novel deep learning-based framework that leverages cell images and integrates cell features to automatically evaluate the sarcomere structure of hiPSC-CMs from the onset of differentiation. This framework overcomes the limitations of traditional methods through automated, high-throughput analysis, providing consistent, reliable results while accurately detecting complex sarcomere patterns across diverse samples. The proposed framework contains the SarcNet, a linear layers-added ResNet-18 module, to output a continuous score ranging from one to five that captures the level of sarcomere structure organization. It is trained and validated on an open-source dataset of hiPSC-CMs images with the endogenously GFP-tagged alpha-actinin-2 structure developed by the Allen Institute for Cell Science (AICS). SarcNet achieves a Spearman correlation of 0.831 with expert evaluations, demonstrating superior performance and an improvement of 0.075 over the current state-of-the-art approach, which uses Linear Regression. Our results also show a consistent pattern of increasing organization from day 18 to day 32 of differentiation, aligning with expert evaluations. By integrating the quantitative features calculated directly from the images with the visual features learned during the deep learning model, our framework offers a more comprehensive and accurate assessment, thereby enhancing the further utility of hiPSC-CMs in medical research and therapy development.

replace Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

Authors: Kailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan, Hanyang Wang, Yating Hu, Yueqi Duan, Kaisheng Ma

Abstract: In this work, we introduce Unique3D, a novel image-to-3D framework for efficiently generating high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability. Previous methods based on Score Distillation Sampling (SDS) can produce diversified 3D results by distilling 3D knowledge from large 2D diffusion models, but they usually suffer from long per-case optimization time with inconsistent issues. Recent works address the problem and generate better 3D results either by finetuning a multi-view diffusion model or training a fast feed-forward model. However, they still lack intricate textures and complex geometries due to inconsistency and limited generated resolution. To simultaneously achieve high fidelity, consistency, and efficiency in single image-to-3D, we propose a novel framework Unique3D that includes a multi-view diffusion model with a corresponding normal diffusion model to generate multi-view images with their normal maps, a multi-level upscale process to progressively improve the resolution of generated orthographic multi-views, as well as an instant and consistent mesh reconstruction algorithm called ISOMER, which fully integrates the color and geometric priors into mesh results. Extensive experiments demonstrate that our Unique3D significantly outperforms other image-to-3D baselines in terms of geometric and textural details.

replace What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights

Authors: Xin Wen, Bingchen Zhao, Yilun Chen, Jiangmiao Pang, Xiaojuan Qi

Abstract: Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates significant effectiveness in learning generalizable representations. With an aim to investigate the reasons behind this finding, we conduct controlled experiments to study various underlying factors, and reveal that CLIP's pretext task forms a dynamic classification problem wherein only a subset of classes is present in training. This isolates the bias from dominant classes and implicitly balances the learning signal. Furthermore, the robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts, which are inaccessible to supervised learning. Our study not only uncovers the mechanisms behind CLIP's generalizability beyond data imbalance but also provides transferable insights for the research community. The findings are validated in both supervised and self-supervised learning, enabling models trained on imbalanced data to achieve CLIP-level performance on diverse recognition tasks. Code and data are available at: https://github.com/CVMI-Lab/clip-beyond-tail.

URLs: https://github.com/CVMI-Lab/clip-beyond-tail.

replace Parameter-Inverted Image Pyramid Networks

Authors: Xizhou Zhu, Xue Yang, Zhaokai Wang, Hao Li, Wenhan Dou, Junqi Ge, Lewei Lu, Yu Qiao, Jifeng Dai

Abstract: Image pyramids are commonly used in modern computer vision tasks to obtain multi-scale features for precise understanding of images. However, image pyramids process multiple resolutions of images using the same large-scale model, which requires significant computational cost. To overcome this issue, we propose a novel network architecture known as the Parameter-Inverted Image Pyramid Networks (PIIP). Our core idea is to use models with different parameter sizes to process different resolution levels of the image pyramid, thereby balancing computational efficiency and performance. Specifically, the input to PIIP is a set of multi-scale images, where higher resolution images are processed by smaller networks. We further propose a feature interaction mechanism to allow features of different resolutions to complement each other and effectively integrate information from different spatial scales. Extensive experiments demonstrate that the PIIP achieves superior performance in tasks such as object detection, segmentation, and image classification, compared to traditional image pyramid methods and single-branch networks, while reducing computational cost. Notably, when applying our method on a large-scale vision foundation model InternViT-6B, we improve its performance by 1%-2% on detection and segmentation with only 40%-60% of the original computation. These results validate the effectiveness of the PIIP approach and provide a new technical direction for future vision computing tasks. Our code and models are available at https://github.com/OpenGVLab/PIIP.

URLs: https://github.com/OpenGVLab/PIIP.

replace BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Authors: Yang Sui, Yanyu Li, Anil Kag, Yerlan Idelbayev, Junli Cao, Ju Hu, Dhritiman Sagar, Bo Yuan, Sergey Tulyakov, Jian Ren

Abstract: Diffusion-based image generation models have achieved great success in recent years by showing the capability of synthesizing high-quality content. However, these models contain a huge number of parameters, resulting in a significantly large model size. Saving and transferring them is a major bottleneck for various applications, especially those running on resource-constrained devices. In this work, we develop a novel weight quantization method that quantizes the UNet from Stable Diffusion v1.5 to 1.99 bits, achieving a model with 7.9X smaller size while exhibiting even better generation quality than the original one. Our approach includes several novel techniques, such as assigning optimal bits to each layer, initializing the quantized model for better performance, and improving the training strategy to dramatically reduce quantization error. Furthermore, we extensively evaluate our quantized model across various benchmark datasets and through human evaluation to demonstrate its superior generation quality.

replace Visual Prompt Tuning in Null Space for Continual Learning

Authors: Yue Lu, Shizhou Zhang, De Cheng, Yinghui Xing, Nannan Wang, Peng Wang, Yanning Zhang

Abstract: Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features, so as to ensure no interference on tasks that have been learned to overcome catastrophic forgetting in CL. However, different from the orthogonal projection in the traditional CNN architecture, the prompt gradient orthogonal projection in the ViT architecture shows completely different and greater challenges, i.e., 1) the high-order and non-linear self-attention operation; 2) the drift of prompt distribution brought by the LayerNorm in the transformer block. Theoretically, we have finally deduced two consistency conditions to achieve the prompt gradient orthogonal projection, which provide a theoretical guarantee of eliminating interference on previously learned knowledge via the self-attention mechanism in visual prompt tuning. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient orthogonal projection. Extensive experimental results demonstrate the effectiveness of anti-forgetting on four class-incremental benchmarks with diverse pre-trained baseline models, and our approach achieves superior performances to state-of-the-art methods. Our code is available at https://github.com/zugexiaodui/VPTinNSforCL.

URLs: https://github.com/zugexiaodui/VPTinNSforCL.

replace Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation

Authors: Yuanhao Zhai, Kevin Lin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Chung-Ching Lin, David Doermann, Junsong Yuan, Lijuan Wang

Abstract: Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in public video datasets. This affects the performance of both teacher and student video diffusion models. Our study aims to improve video diffusion distillation while improving frame appearance using abundant high-quality image data. We propose motion consistency model (MCM), a single-stage video diffusion distillation method that disentangles motion and appearance learning. Specifically, MCM includes a video consistency model that distills motion from the video teacher model, and an image discriminator that enhances frame appearance to match high-quality image data. This combination presents two challenges: (1) conflicting frame learning objectives, as video distillation learns from low-quality video frames while the image discriminator targets high-quality images; and (2) training-inference discrepancies due to the differing quality of video samples used during training and inference. To address these challenges, we introduce disentangled motion distillation and mixed trajectory distillation. The former applies the distillation objective solely to the motion representation, while the latter mitigates training-inference discrepancies by mixing distillation trajectories from both the low- and high-quality video domains. Extensive experiments show that our MCM achieves the state-of-the-art video diffusion distillation performance. Additionally, our method can enhance frame quality in video diffusion models, producing frames with high aesthetic scores or specific styles without corresponding video data.

replace Self-Attention-Based Contextual Modulation Improves Neural System Identification

Authors: Isaac Lin, Tianye Wang, Shang Gao, Shiming Tang, Tai Sing Lee

Abstract: Convolutional neural networks (CNNs) have been shown to be state-of-the-art models for visual cortical neurons. Cortical neurons in the primary visual cortex are sensitive to contextual information mediated by extensive horizontal and feedback connections. Standard CNNs integrate global contextual information to model contextual modulation via two mechanisms: successive convolutions and a fully connected readout layer. In this paper, we find that self-attention (SA), an implementation of non-local network mechanisms, can improve neural response predictions over parameter-matched CNNs in two key metrics: tuning curve correlation and peak tuning. We introduce peak tuning as a metric to evaluate a model's ability to capture a neuron's feature preference. We factorize networks to assess each context mechanism, revealing that information in the local receptive field is most important for modeling overall tuning, but surround information is critically necessary for characterizing the tuning peak. We find that self-attention can replace posterior spatial-integration convolutions when learned incrementally, and is further enhanced in the presence of a fully connected readout layer, suggesting that the two context mechanisms are complementary. Finally, we find that decomposing receptive field learning and contextual modulation learning in an incremental manner may be an effective and robust mechanism for learning surround-center interactions.

replace Real-world Image Dehazing with Coherence-based Label Generator and Cooperative Unfolding Network

Authors: Chengyu Fang, Chunming He, Fengyang Xiao, Yulun Zhang, Longxiang Tang, Yuelin Zhang, Kai Li, Xiu Li

Abstract: Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings. This task remains challenging due to the complexities in accurately modeling real haze distributions and the scarcity of paired real-world data. To address these challenges, we first introduce a cooperative unfolding network that jointly models atmospheric scattering and image scenes, effectively integrating physical knowledge into deep networks to restore haze-contaminated details. Additionally, we propose the first RID-oriented iterative mean-teacher framework, termed the Coherence-based Label Generator, to generate high-quality pseudo labels for network training. Specifically, we provide an optimal label pool to store the best pseudo-labels during network training, leveraging both global and local coherence to select high-quality candidates and assign weights to prioritize haze-free regions. We verify the effectiveness of our method, with experiments demonstrating that it achieves state-of-the-art performance on RID tasks. Code will be available at \url{https://github.com/cnyvfang/CORUN-Colabator}.

URLs: https://github.com/cnyvfang/CORUN-Colabator

replace SimGen: Simulator-conditioned Driving Scene Generation

Authors: Yunsong Zhou, Michael Simon, Zhenghao Peng, Sicheng Mo, Hongzi Zhu, Minyi Guo, Bolei Zhou

Abstract: Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on small-scale datasets like nuScenes, which lack appearance and layout diversity. Moreover, overfitting often happens, where the trained models can only generate images based on the layout data from the validation set of the same dataset. In this work, we introduce a simulator-conditioned scene generation framework called SimGen that can learn to generate diverse driving scenes by mixing data from the simulator and the real world. It uses a novel cascade diffusion pipeline to address challenging sim-to-real gaps and multi-condition conflicts. A driving video dataset DIVA is collected to enhance the generative diversity of SimGen, which contains over 147.5 hours of real-world driving videos from 73 locations worldwide and simulated driving data from the MetaDrive simulator. SimGen achieves superior generation quality and diversity while preserving controllability based on the text prompt and the layout pulled from a simulator. We further demonstrate the improvements brought by SimGen for synthetic data augmentation on the BEV detection and segmentation task and showcase its capability in safety-critical data generation.

replace GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation

Authors: Chubin Zhang, Hongliang Song, Yi Wei, Yu Chen, Jiwen Lu, Yansong Tang

Abstract: In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. This limits these methods to a low-resolution representation and makes it difficult to scale up to the dense views for better quality. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms to effectively integrate image features into 3D representations. We implement this solution through a two-stage pipeline: initially, a lightweight proposal network generates a sparse set of 3D anchor points from the posed image inputs; subsequently, a specialized reconstruction transformer refines the geometry and retrieves textural details. Extensive experimental results demonstrate that GeoLRM significantly outperforms existing models, especially for dense view inputs. We also demonstrate the practical applicability of our model with 3D generation tasks, showcasing its versatility and potential for broader adoption in real-world applications. The project page: https://linshan-bin.github.io/GeoLRM/.

URLs: https://linshan-bin.github.io/GeoLRM/.

replace Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models

Authors: Yicheng Xu, Yuxin Chen, Jiahao Nie, Yusong Wang, Huiping Zhuang, Manabu Okumura

Abstract: Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VLMs, we need not only to prevent the catastrophic forgetting on incrementally learned knowledge but also to preserve the zero-shot ability of VLMs. However, existing methods require additional reference datasets to maintain such zero-shot ability and rely on domain-identity hints to classify images across different domains. In this study, we propose Regression-based Analytic Incremental Learning (RAIL), which utilizes a recursive ridge regression-based adapter to learn from a sequence of domains in a non-forgetting manner and decouple the cross-domain correlations by projecting features to a higher-dimensional space. Cooperating with a training-free fusion module, RAIL absolutely preserves the VLM's zero-shot ability on unseen domains without any reference data. Additionally, we introduce Cross-domain Task-Agnostic Incremental Learning (X-TAIL) setting. In this setting, a CL learner is required to incrementally learn from multiple domains and classify test images from both seen and unseen domains without any domain-identity hint. We theoretically prove RAIL's absolute memorization on incrementally learned domains. Experiment results affirm RAIL's state-of-the-art performance in both X-TAIL and existing Multi-domain Task-Incremental Learning settings. The code is released at https://github.com/linghan1997/Regression-based-Analytic-Incremental-Learning.

URLs: https://github.com/linghan1997/Regression-based-Analytic-Incremental-Learning.

replace Neural Graphics Texture Compression Supporting Random Access

Authors: Farzad Farhadzadeh, Qiqi Hou, Hoang Le, Amir Said, Randall Rauwendaal, Alex Bourd, Fatih Porikli

Abstract: Advances in rendering have led to tremendous growth in texture assets, including resolution, complexity, and novel textures components, but this growth in data volume has not been matched by advances in its compression. Meanwhile Neural Image Compression (NIC) has advanced significantly and shown promising results, but the proposed methods cannot be directly adapted to neural texture compression. First, texture compression requires on-demand and real-time decoding with random access during parallel rendering (e.g. block texture decompression on GPUs). Additionally, NIC does not support multi-resolution reconstruction (mip-levels), nor does it have the ability to efficiently jointly compress different sets of texture channels. In this work, we introduce a novel approach to texture set compression that integrates traditional GPU texture representation and NIC techniques, designed to enable random access and support many-channel texture sets. To achieve this goal, we propose an asymmetric auto-encoder framework that employs a convolutional encoder to capture detailed information in a bottleneck-latent space, and at decoder side we utilize a fully connected network, whose inputs are sampled latent features plus positional information, for a given texture coordinate and mip level. This latent data is defined to enable simplified access to multi-resolution data by simply changing the scanning strides. Experimental results demonstrate that this approach provides much better results than conventional texture compression, and significant improvement over the latest method using neural networks.

replace Addressing a fundamental limitation in deep vision models: lack of spatial attention

Authors: Ali Borji

Abstract: The primary aim of this manuscript is to underscore a significant limitation in current deep learning models, particularly vision models. Unlike human vision, which efficiently selects only the essential visual areas for further processing, leading to high speed and low energy consumption, deep vision models process the entire image. In this work, we examine this issue from a broader perspective and propose two solutions that could pave the way for the next generation of more efficient vision models. In the first solution, convolution and pooling operations are selectively applied to altered regions, with a change map sent to subsequent layers. This map indicates which computations need to be repeated. In the second solution, only the modified regions are processed by a semantic segmentation model, and the resulting segments are inserted into the corresponding areas of the previous output map. The code is available at https://github.com/aliborji/spatial_attention.

URLs: https://github.com/aliborji/spatial_attention.

replace GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing

Authors: Zhenyu Wang, Aoxue Li, Zhenguo Li, Xihui Liu

Abstract: Despite the success achieved by existing image generation and editing methods, current models still struggle with complex problems including intricate text prompts, and the absence of verification and self-correction mechanisms makes the generated images unreliable. Meanwhile, a single model tends to specialize in particular tasks and possess the corresponding capabilities, making it inadequate for fulfilling all user requirements. We propose GenArtist, a unified image generation and editing system, coordinated by a multimodal large language model (MLLM) agent. We integrate a comprehensive range of existing models into the tool library and utilize the agent for tool selection and execution. For a complex problem, the MLLM agent decomposes it into simpler sub-problems and constructs a tree structure to systematically plan the procedure of generation, editing, and self-correction with step-by-step verification. By automatically generating missing position-related inputs and incorporating position information, the appropriate tool can be effectively employed to address each sub-problem. Experiments demonstrate that GenArtist can perform various generation and editing tasks, achieving state-of-the-art performance and surpassing existing models such as SDXL and DALL-E 3, as can be seen in Fig. 1. Project page is https://zhenyuw16.github.io/GenArtist_page.

URLs: https://zhenyuw16.github.io/GenArtist_page.

replace Understanding Visual Feature Reliance through the Lens of Complexity

Authors: Thomas Fel, Louis Bethune, Andrew Kyle Lampinen, Thomas Serre, Katherine Hermann

Abstract: Recent studies suggest that deep learning models inductive bias towards favoring simpler features may be one of the sources of shortcut learning. Yet, there has been limited focus on understanding the complexity of the myriad features that models learn. In this work, we introduce a new metric for quantifying feature complexity, based on $\mathscr{V}$-information and capturing whether a feature requires complex computational transformations to be extracted. Using this $\mathscr{V}$-information metric, we analyze the complexities of 10,000 features, represented as directions in the penultimate layer, that were extracted from a standard ImageNet-trained vision model. Our study addresses four key questions: First, we ask what features look like as a function of complexity and find a spectrum of simple to complex features present within the model. Second, we ask when features are learned during training. We find that simpler features dominate early in training, and more complex features emerge gradually. Third, we investigate where within the network simple and complex features flow, and find that simpler features tend to bypass the visual hierarchy via residual connections. Fourth, we explore the connection between features complexity and their importance in driving the networks decision. We find that complex features tend to be less important. Surprisingly, important features become accessible at earlier layers during training, like a sedimentation process, allowing the model to build upon these foundational elements.

replace XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach

Authors: Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Hung Cao

Abstract: Recent advancements in deep learning have significantly improved visual quality inspection and predictive maintenance within industrial settings. However, deploying these technologies on low-resource edge devices poses substantial challenges due to their high computational demands and the inherent complexity of Explainable AI (XAI) methods. This paper addresses these challenges by introducing a novel XAI-integrated Visual Quality Inspection framework that optimizes the deployment of semantic segmentation models on low-resource edge devices. Our framework incorporates XAI and the Large Vision Language Model to deliver human-centered interpretability through visual and textual explanations to end-users. This is crucial for end-user trust and model interpretability. We outline a comprehensive methodology consisting of six fundamental modules: base model fine-tuning, XAI-based explanation generation, evaluation of XAI approaches, XAI-guided data augmentation, development of an edge-compatible model, and the generation of understandable visual and textual explanations. Through XAI-guided data augmentation, the enhanced model incorporating domain expert knowledge with visual and textual explanations is successfully deployed on mobile devices to support end-users in real-world scenarios. Experimental results showcase the effectiveness of the proposed framework, with the mobile model achieving competitive accuracy while significantly reducing model size. This approach paves the way for the broader adoption of reliable and interpretable AI tools in critical industrial applications, where decisions must be both rapid and justifiable. Our code for this work can be found at https://github.com/Analytics-Everywhere-Lab/vqixai.

URLs: https://github.com/Analytics-Everywhere-Lab/vqixai.

replace ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map

Authors: Yilin Ye, Shishi Xiao, Xingchen Zeng, Wei Zeng

Abstract: Multi-modal embeddings form the foundation for vision-language models, such as CLIP embeddings, the most widely used text-image embeddings. However, these embeddings are vulnerable to subtle misalignment of cross-modal features, resulting in decreased model performance and diminished generalization. To address this problem, we design ModalChorus, an interactive system for visual probing and alignment of multi-modal embeddings. ModalChorus primarily offers a two-stage process: 1) embedding probing with Modal Fusion Map (MFM), a novel parametric dimensionality reduction method that integrates both metric and nonmetric objectives to enhance modality fusion; and 2) embedding alignment that allows users to interactively articulate intentions for both point-set and set-set alignments. Quantitative and qualitative comparisons for CLIP embeddings with existing dimensionality reduction (e.g., t-SNE and MDS) and data fusion (e.g., data context map) methods demonstrate the advantages of MFM in showcasing cross-modal features over common vision-language datasets. Case studies reveal that ModalChorus can facilitate intuitive discovery of misalignment and efficient re-alignment in scenarios ranging from zero-shot classification to cross-modal retrieval and generation.

replace Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

Authors: Chao Gong, Kai Chen, Zhipeng Wei, Jingjing Chen, Yu-Gang Jiang

Abstract: Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often exhibit incomplete erasure, consume a lot of computing resources, and inadvertently damage generation ability. In this work, we introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. Specifically, RECE efficiently leverages a closed-form solution to derive new target embeddings, which are capable of regenerating erased concepts within the unlearned model. To mitigate inappropriate content potentially represented by derived embeddings, RECE further aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts. Besides, to preserve the model's generation ability, RECE introduces an additional regularization term during the derivation process, resulting in minimizing the impact on unrelated concepts during the erasure process. All the processes above are in closed-form, guaranteeing extremely efficient erasure in only 3 seconds. Benchmarking against previous approaches, our method achieves more efficient and thorough erasure with minor damage to original generation ability and demonstrates enhanced robustness against red-teaming tools. Code is available at \url{https://github.com/CharlesGong12/RECE}.

URLs: https://github.com/CharlesGong12/RECE

replace Assessing Brittleness of Image-Text Retrieval Benchmarks from Vision-Language Models Perspective

Authors: Mariya Hendriksen, Shuo Zhang, Ridho Reinanda, Mohamed Yahya, Edgar Meij, Maarten de Rijke

Abstract: We examine the brittleness of the image-text retrieval (ITR) evaluation pipeline with a focus on concept granularity. We start by analyzing two common benchmarks, MS-COCO and Flickr30k, and compare them with augmented, fine-grained versions, MS-COCO-FG and Flickr30k-FG, given a specified set of linguistic features capturing concept granularity. Flickr30k-FG and MS COCO-FG consistently give rise to higher scores across all the selected features. To further our understanding of the impact of granularity we consider a novel taxonomy of query perturbations. We apply these perturbations to the selected datasets. We evaluate four diverse state-of-the-art Vision-Language models on both the standard and fine-grained datasets under zero-shot conditions, with and without the applied perturbations. The results demonstrate that although perturbations generally degrade model performance, the fine-grained datasets exhibit a smaller performance drop than their standard counterparts. The relative performance drop across all setups is consistent across all models and datasets, indicating that the issue lies within the benchmarks themselves. We conclude by providing an agenda for improving ITR evaluation pipelines.

replace CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning

Authors: Emanuele Frascaroli, Aniello Panariello, Pietro Buzzega, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara

Abstract: With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting strategies to adapt transformer-based models without incurring catastrophic forgetting. However, these strategies often compromise the original zero-shot capabilities of the pre-trained CLIP model and struggle to adapt to domains that significantly deviate from the pre-training data. In this work, we propose Continual Generative training for Incremental prompt-Learning, a simple and novel approach to mitigate forgetting while adapting CLIP. Briefly, we employ Variational Autoencoders (VAEs) to learn class-conditioned distributions within the embedding space of the visual encoder. We then exploit these distributions to sample new synthetic visual embeddings and train the corresponding class-specific textual prompts during subsequent tasks. Through extensive experiments on different domains, we show that such a generative replay approach can adapt to new tasks while improving zero-shot capabilities, evaluated using a novel metric tailored for CL scenarios. Notably, further analysis reveals that our approach can bridge the gap with joint prompt tuning. The codebase is available at https://github.com/aimagelab/mammoth.

URLs: https://github.com/aimagelab/mammoth.

replace Neural Surface Detection for Unsigned Distance Fields

Authors: Federico Stella, Nicolas Talabot, Hieu Le, Pascal Fua

Abstract: Extracting surfaces from Signed Distance Fields (SDFs) can be accomplished using traditional algorithms, such as Marching Cubes. However, since they rely on sign flips across the surface, these algorithms cannot be used directly on Unsigned Distance Fields (UDFs). In this work, we introduce a deep-learning approach to taking a UDF and turning it locally into an SDF, so that it can be effectively triangulated using existing algorithms. We show that it achieves better accuracy in surface detection than existing methods. Furthermore it generalizes well to unseen shapes and datasets, while being parallelizable. We also demonstrate the flexibily of the method by using it in conjunction with DualMeshUDF, a state of the art dual meshing method that can operate on UDFs, improving its results and removing the need to tune its parameters.

replace SAM 2: Segment Anything in Images and Videos

Authors: Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman R\"adle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Doll\'ar, Christoph Feichtenhofer

Abstract: We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, dataset, as well as code for model training and our demo.

replace Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid

Authors: Mingxin Huang, Yuliang Liu, Dingkang Liang, Lianwen Jin, Xiang Bai

Abstract: Recently, scaling images to high resolution has received much attention in multimodal large language models (MLLMs). Most existing practices adopt a sliding-window-style cropping strategy to adapt to resolution increase. Such a cropping strategy, however, can easily cut off objects and connected regions, which introduces semantic discontinuity and therefore impedes MLLMs from recognizing small or irregularly shaped objects or text, leading to a phenomenon we call the semantic sawtooth effect. This effect is particularly evident in lightweight MLLMs. To address this issue, we introduce a Complementary Image Pyramid (CIP), a simple, effective, and plug-and-play solution designed to mitigate semantic discontinuity during high-resolution image processing. In particular, CIP dynamically constructs an image pyramid to provide complementary semantic information for the cropping-based MLLMs, enabling them to richly acquire semantics at all levels. Furthermore, we introduce a Scale Compression Mechanism (SCM) to reduce the additional computational overhead by compressing the redundant visual tokens. Our experiments demonstrate that CIP can consistently enhance the performance across diverse architectures (e.g., MiniCPM-V-2, InternVL2, and LLaVA-OneVision), various model capacity (1B$\rightarrow$8B), and different usage configurations (training-free and fine-tuning). Leveraging the proposed CIP and SCM, we introduce a lightweight MLLM, Mini-Monkey, which achieves remarkable performance in both general multimodal understanding and document understanding. On the OCRBench, the 2B-version Mini-Monkey even surpasses the 8B model InternVL2-8B by 12 score. Additionally, training Mini-Monkey is cheap, requiring only eight RTX 3090 GPUs. The code is available at https://github.com/Yuliang-Liu/Monkey.

URLs: https://github.com/Yuliang-Liu/Monkey.

replace LLaVA-OneVision: Easy Visual Task Transfer

Authors: Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li

Abstract: We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT blog series. Our experimental results demonstrate that LLaVA-OneVision is the first single model that can simultaneously push the performance boundaries of open LMMs in three important computer vision scenarios: single-image, multi-image, and video scenarios. Importantly, the design of LLaVA-OneVision allows strong transfer learning across different modalities/scenarios, yielding new emerging capabilities. In particular, strong video understanding and cross-scenario capabilities are demonstrated through task transfer from images to videos.

replace Boosting Adverse Weather Crowd Counting via Multi-queue Contrastive Learning

Authors: Tianhang Pan, Xiuyi Jia

Abstract: Currently, most crowd counting methods have outstanding performance under normal weather conditions. However, they often struggle to maintain their performance in extreme and adverse weather conditions due to significant differences in the domain and a lack of adverse weather images for training. To address this issue and enhance the model's robustness in adverse weather, we propose a two-stage crowd counting method. Specifically, in the first stage, we introduce a multi-queue MoCo contrastive learning strategy to tackle the problem of weather class imbalance. This strategy facilitates the learning of weather-aware representations by the model. In the second stage, we propose to refine the representations under the guidance of contrastive learning, enabling the conversion of the weather-aware representations to the normal weather domain. While significantly improving the robustness, our method only marginally increases the weight of the model. In addition, we also create a new synthetic adverse weather dataset. Extensive experimental results show that our method achieves competitive performance.

replace FungiTastic: A multi-modal dataset and benchmark for image categorization

Authors: Lukas Picek, Klara Janouskova, Milan Sulc, Jiri Matas

Abstract: We introduce a new, challenging benchmark and a dataset, FungiTastic, based on fungal records continuously collected over a twenty-year span. The dataset is labeled and curated by experts and consists of about 350k multimodal observations of 5k fine-grained categories (species). The fungi observations include photographs and additional data, e.g., meteorological and climatic data, satellite images, and body part segmentation masks. FungiTastic is one of the few benchmarks that include a test set with DNA-sequenced ground truth of unprecedented label reliability. The benchmark is designed to support (i) standard closed-set classification, (ii) open-set classification, (iii) multi-modal classification, (iv) few-shot learning, (v) domain shift, and many more. We provide baseline methods tailored for many use-cases, a multitude of ready-to-use pre-trained models on HuggingFace and a framework for model training. A comprehensive documentation describing the dataset features and the baselines are available at https://bohemianvra.github.io/FungiTastic/ and https://www.kaggle.com/datasets/picekl/fungitastic.

URLs: https://bohemianvra.github.io/FungiTastic/, https://www.kaggle.com/datasets/picekl/fungitastic.

replace PatternPaint: Generating Layout Patterns Using Generative AI and Inpainting Techniques

Authors: Guanglei Zhou, Bhargav Korrapati, Gaurav Rajavendra Reddy, Jiang Hu, Yiran Chen, Dipto G. Thakurta

Abstract: Generation of diverse VLSI layout patterns is crucial for various downstream tasks in design for manufacturing (DFM) studies. However, the lengthy design cycles often hinder the creation of a comprehensive layout pattern library, and new detrimental patterns may be discovered late in the product development process. Existing training-based ML pattern generation approaches struggle to produce legal layout patterns in the early stages of technology node development due to the limited availability of training samples.To address this challenge, we propose PatternPaint, a training-free framework capable of generating legal patterns with limited DRC Clean training samples. PatternPaint simplifies complex layout pattern generation into a series of inpainting processes with a template-based denoising scheme. Our framework enables even a general pre-trained image foundation model (stable-diffusion), to generate valuable pattern variations, thereby enhancing the library. Notably, PatternPaint can operate with any input size. Furthermore, we explore fine-tuning a pre-trained model with VLSI layout images, resulting in a 2x generation efficiency compared to the base model. Our results show that the proposed model can generate legal patterns in complex 2D metal interconnect design rule settings and achieves a high diversity score. The designed system, with its flexible settings, supports pattern generation with localized changes and design rule violation correction. Validated on a sub-3nm technology node (Intel 18A), PatternPaint is the first framework to generate a complex 2D layout pattern library using only 20 design rule clean layout patterns as input.

replace SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion

Authors: Ming Dai, Lingfeng Yang, Yihao Xu, Zhenhua Feng, Wankou Yang

Abstract: Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or encoder-decoder architectures for modal interaction and query reasoning. However, their performance significantly drops when dealing with complex textual expressions. This is because the former paradigm only utilizes limited downstream data to fit the multi-modal feature fusion. Therefore, it is only effective when the textual expressions are relatively simple. In contrast, given the wide diversity of textual expressions and the uniqueness of downstream training data, the existing fusion module, which extracts multimodal content from a visual-linguistic context, has not been fully investigated. In this paper, we present a simple yet robust transformer-based framework, SimVG, for visual grounding. Specifically, we decouple visual-linguistic feature fusion from downstream tasks by leveraging existing multimodal pre-trained models and incorporating additional object tokens to facilitate deep integration of downstream and pre-training tasks. Furthermore, we design a dynamic weight-balance distillation method in the multi-branch synchronous learning process to enhance the representation capability of the simpler branch. This branch only consists of a lightweight MLP, which simplifies the structure and improves reasoning speed. Experiments on six widely used VG datasets, i.e., RefCOCO/+/g, ReferIt, Flickr30K, and GRefCOCO, demonstrate the superiority of SimVG. Finally, the proposed method not only achieves improvements in efficiency and convergence speed but also attains new state-of-the-art performance on these benchmarks. Codes and models will be available at \url{https://github.com/Dmmm1997/SimVG}.

URLs: https://github.com/Dmmm1997/SimVG

replace MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

Authors: Tieyuan Chen, Huabin Liu, Tianyao He, Yihang Chen, Chaofan Gan, Xiao Ma, Cheng Zhong, Yang Zhang, Yingxue Wang, Hui Lin, Weiyao Lin

Abstract: Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively.

replace Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Authors: Jing He, Haodong Li, Wei Yin, Yixun Liang, Leheng Li, Kaiqiang Zhou, Hongbo Zhang, Bingbing Liu, Ying-Cong Chen

Abstract: Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, existing methods often uncritically use the original diffusion formulation, which may not be optimal due to the fundamental differences between dense prediction and image generation. In this paper, we provide a systemic analysis of the diffusion formulation for the dense prediction, focusing on both quality and efficiency. And we find that the original parameterization type for image generation, which learns to predict noise, is harmful for dense prediction; the multi-step noising/denoising diffusion process is also unnecessary and challenging to optimize. Based on these insights, we introduce Lotus, a diffusion-based visual foundation model with a simple yet effective adaptation protocol for dense prediction. Specifically, Lotus is trained to directly predict annotations instead of noise, thereby avoiding harmful variance. We also reformulate the diffusion process into a single-step procedure, simplifying optimization and significantly boosting inference speed. Additionally, we introduce a novel tuning strategy called detail preserver, which achieves more accurate and fine-grained predictions. Without scaling up the training data or model capacity, Lotus achieves SoTA performance in zero-shot depth and normal estimation across various datasets. It also enhances efficiency, being significantly faster than most existing diffusion-based methods. Lotus' superior quality and efficiency also enable a wide range of practical applications, such as joint estimation, single/multi-view 3D reconstruction, etc. Project page: https://lotus3d.github.io/.

URLs: https://lotus3d.github.io/.

replace PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

Authors: Qihang Zhou, Jiangtao Yan, Shibo He, Wenchao Meng, Jiming Chen

Abstract: Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection. This paper introduces PointAD, a novel approach that transfers the strong generalization capabilities of CLIP for recognizing 3D anomalies on unseen objects. PointAD provides a unified framework to comprehend 3D anomalies from both points and pixels. In this framework, PointAD renders 3D anomalies into multiple 2D renderings and projects them back into 3D space. To capture the generic anomaly semantics into PointAD, we propose hybrid representation learning that optimizes the learnable text prompts from 3D and 2D through auxiliary point clouds. The collaboration optimization between point and pixel representations jointly facilitates our model to grasp underlying 3D anomaly patterns, contributing to detecting and segmenting anomalies of unseen diverse 3D objects. Through the alignment of 3D and 2D space, our model can directly integrate RGB information, further enhancing the understanding of 3D anomalies in a plug-and-play manner. Extensive experiments show the superiority of PointAD in ZS 3D anomaly detection across diverse unseen objects.

replace DisEnvisioner: Disentangled and Enriched Visual Prompt for Customized Image Generation

Authors: Jing He, Haodong Li, Yongzhe Hu, Guibao Shen, Yingjie Cai, Weichao Qiu, Ying-Cong Chen

Abstract: In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting the subject-essential attributes from the visual prompt. This leads to subject-irrelevant attributes infiltrating the generation process, ultimately compromising the personalization quality in both editability and ID preservation. In this paper, we present DisEnvisioner, a novel approach for effectively extracting and enriching the subject-essential features while filtering out -irrelevant information, enabling exceptional customization performance, in a tuning-free manner and using only a single image. Specifically, the feature of the subject and other irrelevant components are effectively separated into distinctive visual tokens, enabling a much more accurate customization. Aiming to further improving the ID consistency, we enrich the disentangled features, sculpting them into more granular representations. Experiments demonstrate the superiority of our approach over existing methods in instruction response (editability), ID consistency, inference speed, and the overall image quality, highlighting the effectiveness and efficiency of DisEnvisioner. Project page: https://disenvisioner.github.io/.

URLs: https://disenvisioner.github.io/.

replace SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution

Authors: Qi Tang, Yao Zhao, Meiqin Liu, Chao Yao

Abstract: Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level alignment is ineffective for diffusion-processed frames because of iterative disruptions. To overcome this, we introduce SeeClear--a novel VSR framework leveraging conditional video generation, orchestrated by instance-centric and channel-wise semantic controls. This framework integrates a Semantic Distiller and a Pixel Condenser, which synergize to extract and upscale semantic details from low-resolution frames. The Instance-Centric Alignment Module (InCAM) utilizes video-clip-wise tokens to dynamically relate pixels within and across frames, enhancing coherency. Additionally, the Channel-wise Texture Aggregation Memory (CaTeGory) infuses extrinsic knowledge, capitalizing on long-standing semantic textures. Our method also innovates the blurring diffusion process with the ResShift mechanism, finely balancing between sharpness and diffusion effects. Comprehensive experiments confirm our framework's advantage over state-of-the-art diffusion-based VSR techniques. The code is available: https://github.com/Tang1705/SeeClear-NeurIPS24.

URLs: https://github.com/Tang1705/SeeClear-NeurIPS24.

replace TinyEmo: Scaling down Emotional Reasoning via Metric Projection

Authors: Cristian Gutierrez

Abstract: This paper introduces TinyEmo, a family of small multi-modal language models for emotional reasoning and classification. Our approach features: (1) a synthetic emotional instruct dataset for both pre-training and fine-tuning stages, (2) a Metric Projector that delegates classification from the language model allowing for more efficient training and inference, (3) a multi-modal large language model (MM-LLM) for emotional reasoning, and (4) a semi-automated framework for bias detection. TinyEmo is able to perform emotion classification and emotional reasoning, all while using substantially fewer parameters than comparable models. This efficiency allows us to freely incorporate more diverse emotional datasets, enabling strong performance on classification tasks, with our smallest model (700M parameters) outperforming larger state-of-the-art models based on general-purpose MM-LLMs with over 7B parameters. Additionally, the Metric Projector allows for interpretability and indirect bias detection in large models without additional training, offering an approach to understand and improve AI systems. We release code, models, and dataset at https://github.com/ggcr/TinyEmo

URLs: https://github.com/ggcr/TinyEmo

replace Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos

Authors: Cuong Le, Viktor Johansson, Manon Kok, Bastian Wandt

Abstract: Human motion capture from monocular videos has made significant progress in recent years. However, modern approaches often produce temporal artifacts, e.g. in form of jittery motion and struggle to achieve smooth and physically plausible motions. Explicitly integrating physics, in form of internal forces and exterior torques, helps alleviating these artifacts. Current state-of-the-art approaches make use of an automatic PD controller to predict torques and reaction forces in order to re-simulate the input kinematics, i.e. the joint angles of a predefined skeleton. However, due to imperfect physical models, these methods often require simplifying assumptions and extensive preprocessing of the input kinematics to achieve good performance. To this end, we propose a novel method to selectively incorporate the physics models with the kinematics observations in an online setting, inspired by a neural Kalman-filtering approach. We develop a control loop as a meta-PD controller to predict internal joint torques and external reaction forces, followed by a physics-based motion simulation. A recurrent neural network is introduced to realize a Kalman filter that attentively balances the kinematics input and simulated motion, resulting in an optimal-state dynamics prediction. We show that this filtering step is crucial to provide an online supervision that helps balancing the shortcoming of the respective input motions, thus being important for not only capturing accurate global motion trajectories but also producing physically plausible human poses. The proposed approach excels in the physics-based human pose estimation task and demonstrates the physical plausibility of the predictive dynamics, compared to state of the art. The code is available on https://github.com/cuongle1206/OSDCap

URLs: https://github.com/cuongle1206/OSDCap

replace LOBG:Less Overfitting for Better Generalization in Vision-Language Model

Authors: Chenhao Ding, Xinyuan Gao, Songlin Dong, Yuhang He, Qiang Wang, Alex Kot, Yihong Gong

Abstract: Existing prompt learning methods in Vision-Language Models (VLM) have effectively enhanced the transfer capability of VLM to downstream tasks, but they suffer from a significant decline in generalization due to severe overfitting. To address this issue, we propose a framework named LOBG for vision-language models. Specifically, we use CLIP to filter out fine-grained foreground information that might cause overfitting, thereby guiding prompts with basic visual concepts. To further mitigate overfitting, we devel oped a structural topology preservation (STP) loss at the feature level, which endows the feature space with overall plasticity, allowing effective reshaping of the feature space during optimization. Additionally, we employed hierarchical logit distilation (HLD) at the output level to constrain outputs, complementing STP at the output end. Extensive experimental results demonstrate that our method significantly improves generalization capability and alleviates overfitting compared to state-of-the-art approaches.

replace Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models

Authors: Jingzhi Bao, Xueting Li, Ming-Hsuan Yang

Abstract: 3D meshes are widely used in computer vision and graphics for their efficiency in animation and minimal memory use, playing a crucial role in movies, games, AR, and VR. However, creating temporally consistent and realistic textures for mesh sequences remains labor-intensive for professional artists. On the other hand, while video diffusion models excel at text-driven video generation, they often lack 3D geometry awareness and struggle with achieving multi-view consistent texturing for 3D meshes. In this work, we present Tex4D, a zero-shot approach that integrates inherent 3D geometry knowledge from mesh sequences with the expressiveness of video diffusion models to produce multi-view and temporally consistent 4D textures. Given an untextured mesh sequence and a text prompt as inputs, our method enhances multi-view consistency by synchronizing the diffusion process across different views through latent aggregation in the UV space. To ensure temporal consistency, we leverage prior knowledge from a conditional video generation model for texture synthesis. However, straightforwardly combining the video diffusion model and the UV texture aggregation leads to blurry results. We analyze the underlying causes and propose a simple yet effective modification to the DDIM sampling process to address this issue. Additionally, we introduce a reference latent texture to strengthen the correlation between frames during the denoising process. To the best of our knowledge, Tex4D is the first method specifically designed for 4D scene texturing. Extensive experiments demonstrate its superiority in producing multi-view and multi-frame consistent videos based on untextured mesh sequences.

replace DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM

Authors: Yingjun Shen, Haizhao Dai, Qihe Chen, Yan Zeng, Jiakai Zhang, Yuan Pei, Jingyi Yu

Abstract: Foundation models in computer vision have demonstrated exceptional performance in zero-shot and few-shot tasks by extracting multi-purpose features from large-scale datasets through self-supervised pre-training methods. However, these models often overlook the severe corruption in cryogenic electron microscopy (cryo-EM) images by high-level noises. We introduce DRACO, a Denoising-Reconstruction Autoencoder for CryO-EM, inspired by the Noise2Noise (N2N) approach. By processing cryo-EM movies into odd and even images and treating them as independent noisy observations, we apply a denoising-reconstruction hybrid training scheme. We mask both images to create denoising and reconstruction tasks. For DRACO's pre-training, the quality of the dataset is essential, we hence build a high-quality, diverse dataset from an uncurated public database, including over 270,000 movies or micrographs. After pre-training, DRACO naturally serves as a generalizable cryo-EM image denoiser and a foundation model for various cryo-EM downstream tasks. DRACO demonstrates the best performance in denoising, micrograph curation, and particle picking tasks compared to state-of-the-art baselines.

replace LESS: Label-Efficient and Single-Stage Referring 3D Segmentation

Authors: Xuexun Liu, Xiaoxu Xu, Jinlong Li, Qiudan Zhang, Xu Wang, Nicu Sebe, Lin Ma

Abstract: Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic instance segmentation then matching with given text query. However, the semantic concepts from text query and visual cues are separately interacted during the training, and both instance and semantic labels for each object are required, which is time consuming and human-labor intensive. To mitigate these issues, we propose a novel Referring 3D Segmentation pipeline, Label-Efficient and Single-Stage, dubbed LESS, which is only under the supervision of efficient binary mask. Specifically, we design a Point-Word Cross-Modal Alignment module for aligning the fine-grained features of points and textual embedding. Query Mask Predictor module and Query-Sentence Alignment module are introduced for coarse-grained alignment between masks and query. Furthermore, we propose an area regularization loss, which coarsely reduces irrelevant background predictions on a large scale. Besides, a point-to-point contrastive loss is proposed concentrating on distinguishing points with subtly similar features. Through extensive experiments, we achieve state-of-the-art performance on ScanRefer dataset by surpassing the previous methods about 3.7% mIoU using only binary labels. Code is available at https://github.com/mellody11/LESS.

URLs: https://github.com/mellody11/LESS.

replace SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing

Authors: Bin Wang, Fei Deng, Shuang Wang, Wen Luo, Zhixuan Zhang, Gulan Zhang, Peifan Jiang

Abstract: Semantic segmentation of remote sensing (RS) images is a challenging yet crucial task. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field, acquiring high-quality labeled data is expensive and time-consuming. Additionally, variations in ground sampling distance, imaging equipment, and geographic differences cause domain shifts between datasets, which limit model performance across domains. Unsupervised domain adaptation (UDA) offers a solution by enabling models to learn from unlabeled target domain data while training on labeled source domain data. Recent self-supervised learning approaches using pseudo-label generation have shown promise in addressing domain discrepancies. Combining source and target images with their true and pseudo labels has proven effective in reducing domain bias. However, the use of pseudo-labeling for RS image segmentation is underexplored. Existing methods often rely on high-confidence pixel points as pseudo-labels, reducing supervision in low-confidence areas. Noise in pseudo-labels further weakens the model's ability to learn target domain semantics. While some methods assign confidence weights, noisy pseudo-labels remain an issue. To address these limitations, we propose integrating contrastive learning into UDA, enhancing the model's capacity to capture semantic information by maximizing the similarity between augmented views of the same image. This provides additional supervision to improve performance in the target domain. Extensive experiments on key RS datasets (Potsdam, Vaihingen, LoveDA) demonstrate that our SimSeg method outperforms existing approaches, achieving state-of-the-art results. Visualization and quantitative analyses confirm its superior ability to learn from the target domain. The code is available at \url{https://github.com/woldier/SiamSeg}.

URLs: https://github.com/woldier/SiamSeg

replace VidPanos: Generative Panoramic Videos from Casual Panning Videos

Authors: Jingwei Ma, Erika Lu, Roni Paiss, Shiran Zada, Aleksander Holynski, Tali Dekel, Brian Curless, Michael Rubinstein, Forrester Cole

Abstract: Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, but when objects are moving, a still panorama cannot capture the scene. We present a method for synthesizing a panoramic video from a casually-captured panning video, as if the original video were captured with a wide-angle camera. We pose panorama synthesis as a space-time outpainting problem, where we aim to create a full panoramic video of the same length as the input video. Consistent completion of the space-time volume requires a powerful, realistic prior over video content and motion, for which we adapt generative video models. Existing generative models do not, however, immediately extend to panorama completion, as we show. We instead apply video generation as a component of our panorama synthesis system, and demonstrate how to exploit the strengths of the models while minimizing their limitations. Our system can create video panoramas for a range of in-the-wild scenes including people, vehicles, and flowing water, as well as stationary background features.

replace Extreme Precipitation Nowcasting using Multi-Task Latent Diffusion Models

Authors: Li Chaorong, Ling Xudong, Yang Qiang, Qin Fengqing, Huang Yuanyuan

Abstract: Deep learning models have made remarkable strides in precipitation prediction, yet they continue to struggle with capturing the spatial details of the features of radar images, particularly over high precipitation intensity areas. This shortcoming is evident in the form of low forecast accuracy in the spatial positioning of radar echo images across varying precipitation intensity regions. To address this challenge, we introduce the multi-task latent diffusion model(MTLDM), a novel approach for precipitation prediction. The basic concept of the MTLDM is based on the understanding that the radar image representing precipitation is the result of multiple factors. Therefore, we adopt a divide-and-conquer approach, that is, we decompose the radar image using decomposition technology and then predict the decomposed sub-images separately. We conceptualize the precipitation image as a composition of various components corresponding to different precipitation intensities. The MTLDM decomposes the precipitation image into these distinct components and employs a dedicated task to predict each one. This method enables spatiotemporally consistent prediction of real-world precipitation areas up to 5-80 min in advance, outperforming existing state-of-the-art techniques across multiple evaluation metrics.

replace Unlabeled Action Quality Assessment Based on Multi-dimensional Adaptive Constrained Dynamic Time Warping

Authors: Renguang Chen, Guolong Zheng, Xu Yang, Zhide Chen, Jiwu Shu, Wencheng Yang, Kexin Zhu, Chen Feng

Abstract: The growing popularity of online sports and exercise necessitates effective methods for evaluating the quality of online exercise executions. Previous action quality assessment methods, which relied on labeled scores from motion videos, exhibited slightly lower accuracy and discriminability. This limitation hindered their rapid application to newly added exercises. To address this problem, this paper presents an unlabeled Multi-Dimensional Exercise Distance Adaptive Constrained Dynamic Time Warping (MED-ACDTW) method for action quality assessment. Our approach uses an athletic version of DTW to compare features from template and test videos, eliminating the need for score labels during training. The result shows that utilizing both 2D and 3D spatial dimensions, along with multiple human body features, improves the accuracy by 2-3% compared to using either 2D or 3D pose estimation alone. Additionally, employing MED for score calculation enhances the precision of frame distance matching, which significantly boosts overall discriminability. The adaptive constraint scheme enhances the discriminability of action quality assessment by approximately 30%. Furthermore, to address the absence of a standardized perspective in sports class evaluations, we introduce a new dataset called BGym.

replace WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction

Authors: Heng Zhai, Jilin Mei, Chen Min, Liang Chen, Fangzhou Zhao, Yu Hu

Abstract: 3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes. Off-road environments are rich in geometric information, therefore it is suitable for 3D semantic occupancy prediction tasks to reconstruct such scenes. However, most of researches concentrate on on-road environments, and few methods are designed for off-road 3D semantic occupancy prediction due to the lack of relevant datasets and benchmarks. In response to this gap, we introduce WildOcc, to our knowledge, the first benchmark to provide dense occupancy annotations for off-road 3D semantic occupancy prediction tasks. A ground truth generation pipeline is proposed in this paper, which employs a coarse-to-fine reconstruction to achieve a more realistic result. Moreover, we introduce a multi-modal 3D semantic occupancy prediction framework, which fuses spatio-temporal information from multi-frame images and point clouds at voxel level. In addition, a cross-modality distillation function is introduced, which transfers geometric knowledge from point clouds to image features.

replace Data-Efficient CLIP-Powered Dual-Branch Networks for Source-Free Unsupervised Domain Adaptation

Authors: Yongguang Li, Yueqi Cao, Jindong Li, Qi Wang, Shengsheng Wang

Abstract: Source-free Unsupervised Domain Adaptation (SF-UDA) aims to transfer a model's performance from a labeled source domain to an unlabeled target domain without direct access to source samples, addressing critical data privacy concerns. However, most existing SF-UDA approaches assume the availability of abundant source domain samples, which is often impractical due to the high cost of data annotation. To address the dual challenges of limited source data and privacy concerns, we introduce a data-efficient, CLIP-powered dual-branch network (CDBN). This architecture consists of a cross-domain feature transfer branch and a target-specific feature learning branch, leveraging high-confidence target domain samples to transfer text features of source domain categories while learning target-specific soft prompts. By fusing the outputs of both branches, our approach not only effectively transfers source domain category semantic information to the target domain but also reduces the negative impacts of noise and domain gaps during target training. Furthermore, we propose an unsupervised optimization strategy driven by accurate classification and diversity, preserving the classification capability learned from the source domain while generating more confident and diverse predictions in the target domain. CDBN achieves near state-of-the-art performance with far fewer source domain samples than existing methods across 31 transfer tasks on seven datasets.

replace Hybrid Architecture for Real-Time Video Anomaly Detection: Integrating Spatial and Temporal Analysis

Authors: Fabien Poirier

Abstract: We propose a new architecture for real-time anomaly detection in video data, inspired by human behavior by combining spatial and temporal analyses. This approach uses two distinct models: for temporal analysis, a recurrent convolutional network (CNN + RNN) is employed, associating VGG19 and a GRU to process video sequences. Regarding spatial analysis, it is performed using YOLOv7 to analyze individual images. These two analyses can be carried out either in parallel, with a final prediction that combines the results of both analyses, or in series, where the spatial analysis enriches the data before the temporal analysis. In this article, we will compare these two architectural configurations with each other, to evaluate the effectiveness of our hybrid approach in video anomaly detection.

replace Foundation Models for Remote Sensing and Earth Observation: A Survey

Authors: Aoran Xiao, Weihao Xuan, Junjue Wang, Jiaxing Huang, Dacheng Tao, Shijian Lu, Naoto Yokoya

Abstract: Remote Sensing (RS) is a crucial technology for observing, monitoring, and interpreting our planet, with broad applications across geoscience, economics, humanitarian fields, etc. While artificial intelligence (AI), particularly deep learning, has achieved significant advances in RS, unique challenges persist in developing more intelligent RS systems, including the complexity of Earth's environments, diverse sensor modalities, distinctive feature patterns, varying spatial and spectral resolutions, and temporal dynamics. Meanwhile, recent breakthroughs in large Foundation Models (FMs) have expanded AI's potential across many domains due to their exceptional generalizability and zero-shot transfer capabilities. However, their success has largely been confined to natural data like images and video, with degraded performance and even failures for RS data of various non-optical modalities. This has inspired growing interest in developing Remote Sensing Foundation Models (RSFMs) to address the complex demands of Earth Observation (EO) tasks, spanning the surface, atmosphere, and oceans. This survey systematically reviews the emerging field of RSFMs. It begins with an outline of their motivation and background, followed by an introduction of their foundational concepts. It then categorizes and reviews existing RSFM studies including their datasets and technical contributions across Visual Foundation Models (VFMs), Visual-Language Models (VLMs), Large Language Models (LLMs), and beyond. In addition, we benchmark these models against publicly available datasets, discuss existing challenges, and propose future research directions in this rapidly evolving field. A project associated with this survey has been built at https://github.com/xiaoaoran/awesome-RSFMs .

URLs: https://github.com/xiaoaoran/awesome-RSFMs

replace PathMoCo: A Novel Framework to Improve Feature Embedding in Self-supervised Contrastive Learning for Histopathological Images

Authors: Hamid Manoochehri, Bodong Zhang, Beatrice S. Knudsen, Tolga Tasdizen

Abstract: Self-supervised contrastive learning has become a cornerstone in various areas, particularly histopathological image analysis. Image augmentation plays a crucial role in self-supervised contrastive learning, as it generates variations in image samples. However, traditional image augmentation techniques often overlook the unique characteristics of histopathological images. In this paper, we propose a new histopathology-specific image augmentation method called stain reconstruction augmentation (SRA). We integrate our SRA with MoCo v3, a leading model in self-supervised contrastive learning, along with our additional contrastive loss terms, and call the new model PathMoCo. We demonstrate that our PathMoCo always outperforms the standard MoCo v3 across various downstream tasks and achieves comparable or superior performance to other foundation models pre-trained on significantly larger histopathology datasets.

replace CARLA2Real: a tool for reducing the sim2real gap in CARLA simulator

Authors: Stefanos Pasios, Nikos Nikolaidis

Abstract: Simulators are indispensable for research in autonomous systems such as self-driving cars, autonomous robots and drones. Despite significant progress in various simulation aspects, such as graphical realism, an evident gap persists between the virtual and real-world environments. Since the ultimate goal is to deploy the autonomous systems in the real world, closing the sim2real gap is of utmost importance. In this paper, we employ a state-of-the-art approach to enhance the photorealism of simulated data, aligning them with the visual characteristics of real-world datasets. Based on this, we developed CARLA2Real, an easy-to-use, publicly available tool (plug-in) for the widely used and open-source CARLA simulator. This tool enhances the output of CARLA in near real-time, achieving a frame rate of 13 FPS, translating it to the visual style and realism of real-world datasets such as Cityscapes, KITTI, and Mapillary Vistas. By employing the proposed tool, we generated synthetic datasets from both the simulator and the enhancement model outputs, including their corresponding ground truth annotations for tasks related to autonomous driving. Then, we performed a number of experiments to evaluate the impact of the proposed approach on feature extraction and semantic segmentation methods when trained on the enhanced synthetic data. The results demonstrate that the sim2real gap is significant and can indeed be reduced by the introduced approach.

replace Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing

Authors: Haonan Lin, Mengmeng Wang, Jiahao Wang, Wenbin An, Yan Chen, Yong Liu, Feng Tian, Guang Dai, Jingdong Wang, Qianying Wang

Abstract: Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. These errors accumulate during the diffusion process, resulting in inferior content preservation and edit fidelity, especially with conditional inputs. We address these challenges by investigating the primary contributors to error accumulation in DDIM inversion and identify the singularity problem in traditional noise schedules as a key issue. To resolve this, we introduce the Logistic Schedule, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. This schedule reduces noise prediction errors, enabling more faithful editing that preserves the original content of the source image. Our approach requires no additional retraining and is compatible with various existing editing methods. Experiments across eight editing tasks demonstrate the Logistic Schedule's superior performance in content preservation and edit fidelity compared to traditional noise schedules, highlighting its adaptability and effectiveness.

replace Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis

Authors: Liang Han, Junsheng Zhou, Yu-Shen Liu, Zhizhong Han

Abstract: Novel view synthesis from sparse inputs is a vital yet challenging task in 3D computer vision. Previous methods explore 3D Gaussian Splatting with neural priors (e.g. depth priors) as an additional supervision, demonstrating promising quality and efficiency compared to the NeRF based methods. However, the neural priors from 2D pretrained models are often noisy and blurry, which struggle to precisely guide the learning of radiance fields. In this paper, We propose a novel method for synthesizing novel views from sparse views with Gaussian Splatting that does not require external prior as supervision. Our key idea lies in exploring the self-supervisions inherent in the binocular stereo consistency between each pair of binocular images constructed with disparity-guided image warping. To this end, we additionally introduce a Gaussian opacity constraint which regularizes the Gaussian locations and avoids Gaussian redundancy for improving the robustness and efficiency of inferring 3D Gaussians from sparse views. Extensive experiments on the LLFF, DTU, and Blender datasets demonstrate that our method significantly outperforms the state-of-the-art methods.

replace x-RAGE: eXtended Reality -- Action & Gesture Events Dataset

Authors: Vivek Parmar, Dwijay Bane, Syed Shakib Sarwar, Kleber Stangherlin, Barbara De Salvo, Manan Suri

Abstract: With the emergence of the Metaverse and focus on wearable devices in the recent years gesture based human-computer interaction has gained significance. To enable gesture recognition for VR/AR headsets and glasses several datasets focusing on egocentric i.e. first-person view have emerged in recent years. However, standard frame-based vision suffers from limitations in data bandwidth requirements as well as ability to capture fast motions. To overcome these limitation bio-inspired approaches such as event-based cameras present an attractive alternative. In this work, we present the first event-camera based egocentric gesture dataset for enabling neuromorphic, low-power solutions for XR-centric gesture recognition. The dataset has been made available publicly at the following URL: https://gitlab.com/NVM_IITD_Research/xrage.

URLs: https://gitlab.com/NVM_IITD_Research/xrage.

replace-cross Adversarial robustness of VAEs through the lens of local geometry

Authors: Asif Khan, Amos Storkey

Abstract: In an unsupervised attack on variational autoencoders (VAEs), an adversary finds a small perturbation in an input sample that significantly changes its latent space encoding, thereby compromising the reconstruction for a fixed decoder. A known reason for such vulnerability is the distortions in the latent space resulting from a mismatch between approximated latent posterior and a prior distribution. Consequently, a slight change in an input sample can move its encoding to a low/zero density region in the latent space resulting in an unconstrained generation. This paper demonstrates that an optimal way for an adversary to attack VAEs is to exploit a directional bias of a stochastic pullback metric tensor induced by the encoder and decoder networks. The pullback metric tensor of an encoder measures the change in infinitesimal latent volume from an input to a latent space. Thus, it can be viewed as a lens to analyse the effect of input perturbations leading to latent space distortions. We propose robustness evaluation scores using the eigenspectrum of a pullback metric tensor. Moreover, we empirically show that the scores correlate with the robustness parameter $\beta$ of the $\beta-$VAE. Since increasing $\beta$ also degrades reconstruction quality, we demonstrate a simple alternative using \textit{mixup} training to fill the empty regions in the latent space, thus improving robustness with improved reconstruction.

replace-cross An Improved Multi-State Constraint Kalman Filter for Visual-Inertial Odometry

Authors: M. R. Abdollahi, Seid H. Pourtakdoust, M. H. Yoosefian Nooshabadi, H. N. Pishkenari

Abstract: Fast pose estimation (PE) is of vital importance for successful mission performance of agile autonomous robots. Global Positioning Systems such as GPS and GNSS have been typically used in fusion with Inertial Navigation Systems (INS) for PE. However, the low update rate and lack of proper signals make their utility impractical for indoor and urban applications. On the other hand, Visual-Inertial Odometry (VIO) is gaining popularity as a practical alternative for GNSS/INS systems in GPS-denied environments. Among the many VIO-based methods, the Multi-State Constraint Kalman Filter (MSCKF) has received a greater attention due to its robustness, speed and accuracy. To this end, the high computational cost associated with image processing for real-time implementation of MSCKF on resource-constrained vehicles is still a challenging ongoing research. In this paper, an enhanced version of the MSCKF is proposed. To this aim, different feature marginalization and state pruning strategies are suggested that result in a much faster algorithm. The proposed algorithm is tested both on an open-source dataset and in real-world experiments for validation. It is demonstrated that the proposed Fast-MSCKF (FMSCKF) is about six times faster and at least 20% more accurate in final position estimation than the standard MSCKF algorithm.

replace-cross Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides

Authors: Maren H{\o}ib{\o}, Andr\'e Pedersen, Vibeke Grotnes Dale, Sissel Marie Berget, Borgny Ytterhus, Cecilia Lindskog, Elisabeth Wik, Lars A. Akslen, Ingerid Reinertsen, Erik Smistad, Marit Valla

Abstract: Digital pathology enables automatic analysis of histopathological sections using artificial intelligence (AI). Automatic evaluation could improve diagnostic efficiency and help find associations between morphological features and clinical outcome. For development of such prediction models, identifying invasive epithelial cells, and separating these from benign epithelial cells and in situ lesions would be the first step. In this study, we aimed to develop an AI model for segmentation of epithelial cells in sections from breast cancer. We generated epithelial ground truth masks by restaining hematoxylin and eosin (HE) sections with cytokeratin (CK) AE1/AE3, and by pathologists' annotations. HE/CK image pairs were used to train a convolutional neural network, and data augmentation was used to make the model more robust. Tissue microarrays (TMAs) from 839 patients, and whole slide images from two patients were used for training and evaluation of the models. The sections were derived from four cohorts of breast cancer patients. TMAs from 21 patients from a fifth cohort was used as a second test set. In quantitative evaluation, a mean Dice score of 0.70, 0.79, and 0.75 for invasive epithelial cells, benign epithelial cells, and in situ lesions, respectively, were achieved. In qualitative scoring (0-5) by pathologists, results were best for all epithelium and invasive epithelium, with scores of 4.7 and 4.4. Scores for benign epithelium and in situ lesions were 3.7 and 2.0. The proposed model segmented epithelial cells in HE stained breast cancer slides well, but further work is needed for accurate division between the classes. Immunohistochemistry, together with pathologists' annotations, enabled the creation of accurate ground truths. The model is made freely available in FastPathology and the code is available at https://github.com/AICAN-Research/breast-epithelium-segmentation

URLs: https://github.com/AICAN-Research/breast-epithelium-segmentation

replace-cross Self-supervised learning for skin cancer diagnosis with limited training data

Authors: Hamish Haggerty, Rohitash Chandra

Abstract: Early cancer detection is crucial for prognosis, but many cancer types lack large labelled datasets required for developing deep learning models. This paper investigates self-supervised learning (SSL) as an alternative to the standard supervised pre-training on ImageNet data for scenarios with limited training data using the ResNet-50 deep learning model. We first demonstrate that SSL pre-training on ImageNet (via the Barlow Twins SSL algorithm) outperforms supervised pre-training (SL) using a skin lesion dataset with limited training samples. We then consider further SSL pre-training (of the two ImageNet pre-trained models) on task-specific datasets, where our implementation is motivated by supervised transfer learning. The SSL significantly enhances initially SL pre-trained models, closing the performance gap with initially SSL pre-trained ones. Surprisingly, further pre-training on just the limited fine-tuning data achieves this performance equivalence. We implement a linear probe training strategy in the RestNet-50 model, and our experiments reveal that improvement stems from enhanced feature extraction. We find that minimal further SSL pre-training on task-specific data can be as effective as large-scale SSL pre-training on ImageNet for medical image classification tasks with limited labelled data. We validate these results on an oral cancer histopathology dataset, suggesting broader applicability across medical imaging domains facing labelled data scarcity.

replace-cross On $f$-Divergence Principled Domain Adaptation: An Improved Framework

Authors: Ziqiao Wang, Yongyi Mao

Abstract: Unsupervised domain adaptation (UDA) plays a crucial role in addressing distribution shifts in machine learning. In this work, we improve the theoretical foundations of UDA proposed in Acuna et al. (2021) by refining their $f$-divergence-based discrepancy and additionally introducing a new measure, $f$-domain discrepancy ($f$-DD). By removing the absolute value function and incorporating a scaling parameter, $f$-DD obtains novel target error and sample complexity bounds, allowing us to recover previous KL-based results and bridging the gap between algorithms and theory presented in Acuna et al. (2021). Using a localization technique, we also develop a fast-rate generalization bound. Empirical results demonstrate the superior performance of $f$-DD-based learning algorithms over previous works in popular UDA benchmarks.

replace-cross Adversarial Robustness Through Artifact Design

Authors: Tsufit Shua, Liron David, Mahmood Sharif

Abstract: Adversarial examples arose as a challenge for machine learning. To hinder them, most defenses alter how models are trained (e.g., adversarial training) or inference is made (e.g., randomized smoothing). Still, while these approaches markedly improve models' adversarial robustness, models remain highly susceptible to adversarial examples. Identifying that, in certain domains such as traffic-sign recognition, objects are implemented per standards specifying how artifacts (e.g., signs) should be designed, we propose a novel approach for improving adversarial robustness. Specifically, we offer a method to redefine standards, making minor changes to existing ones, to defend against adversarial examples. We formulate the problem of artifact design as a robust optimization problem, and propose gradient-based and greedy search methods to solve it. We evaluated our approach in the domain of traffic-sign recognition, allowing it to alter traffic-sign pictograms (i.e., symbols within the signs) and their colors. We found that, combined with adversarial training, our approach led to up to 25.18\% higher robust accuracy compared to state-of-the-art methods against two adversary types, while further increasing accuracy on benign inputs. Notably, a user study we conducted showed that traffic signs produced by our approach are also easily recognizable by human subjects.

replace-cross Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis

Authors: Yuanhao Cai, Yixun Liang, Jiahao Wang, Angtian Wang, Yulun Zhang, Xiaokang Yang, Zongwei Zhou, Alan Yuille

Abstract: X-ray is widely applied for transmission imaging due to its stronger penetration than natural light. When rendering novel view X-ray projections, existing methods mainly based on NeRF suffer from long training time and slow inference speed. In this paper, we propose a 3D Gaussian splatting-based framework, namely X-Gaussian, for X-ray novel view synthesis. Firstly, we redesign a radiative Gaussian point cloud model inspired by the isotropic nature of X-ray imaging. Our model excludes the influence of view direction when learning to predict the radiation intensity of 3D points. Based on this model, we develop a Differentiable Radiative Rasterization (DRR) with CUDA implementation. Secondly, we customize an Angle-pose Cuboid Uniform Initialization (ACUI) strategy that directly uses the parameters of the X-ray scanner to compute the camera information and then uniformly samples point positions within a cuboid enclosing the scanned object. Experiments show that our X-Gaussian outperforms state-of-the-art methods by 6.5 dB while enjoying less than 15% training time and over 73x inference speed. The application on sparse-view CT reconstruction also reveals the practical values of our method. Code is publicly available at https://github.com/caiyuanhao1998/X-Gaussian . A video demo of the training process visualization is at https://www.youtube.com/watch?v=gDVf_Ngeghg .

URLs: https://github.com/caiyuanhao1998/X-Gaussian, https://www.youtube.com/watch?v=gDVf_Ngeghg

replace-cross Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains

Authors: Lei Wang, Jieming Bian, Letian Zhang, Chen Chen, Jie Xu

Abstract: Federated learning (FL) allows collaborative machine learning training without sharing private data. While most FL methods assume identical data domains across clients, real-world scenarios often involve heterogeneous data domains. Federated Prototype Learning (FedPL) addresses this issue, using mean feature vectors as prototypes to enhance model generalization. However, existing FedPL methods create the same number of prototypes for each client, leading to cross-domain performance gaps and disparities for clients with varied data distributions. To mitigate cross-domain feature representation variance, we introduce FedPLVM, which establishes variance-aware dual-level prototypes clustering and employs a novel $\alpha$-sparsity prototype loss. The dual-level prototypes clustering strategy creates local clustered prototypes based on private data features, then performs global prototypes clustering to reduce communication complexity and preserve local data privacy. The $\alpha$-sparsity prototype loss aligns samples from underrepresented domains, enhancing intra-class similarity and reducing inter-class similarity. Evaluations on Digit-5, Office-10, and DomainNet datasets demonstrate our method's superiority over existing approaches.

replace-cross Probing Multimodal LLMs as World Models for Driving

Authors: Shiva Sreeram, Tsun-Hsuan Wang, Alaa Maalouf, Guy Rosman, Sertac Karaman, Daniela Rus

Abstract: We provide a sober look at the application of Multimodal Large Language Models (MLLMs) in autonomous driving, challenging common assumptions about their ability to interpret dynamic driving scenarios. Despite advances in models like GPT-4o, their performance in complex driving environments remains largely unexplored. Our experimental study assesses various MLLMs as world models using in-car camera perspectives and reveals that while these models excel at interpreting individual images, they struggle to synthesize coherent narratives across frames, leading to considerable inaccuracies in understanding (i) ego vehicle dynamics, (ii) interactions with other road actors, (iii) trajectory planning, and (iv) open-set scene reasoning. We introduce the Eval-LLM-Drive dataset and DriveSim simulator to enhance our evaluation, highlighting gaps in current MLLM capabilities and the need for improved models in dynamic real-world environments.

replace-cross Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

Authors: Shengfang Zhai, Huanran Chen, Yinpeng Dong, Jiajun Li, Qingni Shen, Yansong Gao, Hang Su, Yang Liu

Abstract: Text-to-image diffusion models have achieved tremendous success in the field of controllable image generation, while also coming along with issues of privacy leakage and data copyrights. Membership inference arises in these contexts as a potential auditing method for detecting unauthorized data usage. While some efforts have been made on diffusion models, they are not applicable to text-to-image diffusion models due to the high computation overhead and enhanced generalization capabilities. In this paper, we first identify a conditional overfitting phenomenon in text-to-image diffusion models, indicating that these models tend to overfit the conditional distribution of images given the corresponding text rather than the marginal distribution of images only. Based on this observation, we derive an analytical indicator, namely Conditional Likelihood Discrepancy (CLiD), to perform membership inference, which reduces the stochasticity in estimating memorization of individual samples. Experimental results demonstrate that our method significantly outperforms previous methods across various data distributions and dataset scales. Additionally, our method shows superior resistance to overfitting mitigation strategies, such as early stopping and data augmentation.

replace-cross Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models

Authors: Regev Cohen, Idan Kligvasser, Ehud Rivlin, Daniel Freedman

Abstract: The pursuit of high perceptual quality in image restoration has driven the development of revolutionary generative models, capable of producing results often visually indistinguishable from real data. However, as their perceptual quality continues to improve, these models also exhibit a growing tendency to generate hallucinations - realistic-looking details that do not exist in the ground truth images. Hallucinations in these models create uncertainty about their reliability, raising major concerns about their practical application. This paper investigates this phenomenon through the lens of information theory, revealing a fundamental tradeoff between uncertainty and perception. We rigorously analyze the relationship between these two factors, proving that the global minimal uncertainty in generative models grows in tandem with perception. In particular, we define the inherent uncertainty of the restoration problem and show that attaining perfect perceptual quality entails at least twice this uncertainty. Additionally, we establish a relation between distortion, uncertainty and perception, through which we prove the aforementioned uncertainly-perception tradeoff induces the well-known perception-distortion tradeoff. We demonstrate our theoretical findings through experiments with super-resolution and inpainting algorithms. This work uncovers fundamental limitations of generative models in achieving both high perceptual quality and reliable predictions for image restoration. Thus, we aim to raise awareness among practitioners about this inherent tradeoff, empowering them to make informed decisions and potentially prioritize safety over perceptual performance.

replace-cross Does Diffusion Beat GAN in Image Super Resolution?

Authors: Denis Kuznedelev, Valerii Startsev, Daniil Shlenskii, Sergey Kastryulin

Abstract: There is a prevalent opinion that diffusion-based models outperform GAN-based counterparts in the Image Super Resolution (ISR) problem. However, in most studies, diffusion-based ISR models employ larger networks and are trained longer than the GAN baselines. This raises the question of whether the high performance stems from the superiority of the diffusion paradigm or if it is a consequence of the increased scale and the greater computational resources of the contemporary studies. In our work, we thoroughly compare diffusion-based and GAN-based Super Resolution models under controlled settings, with both approaches having matched architecture, model and dataset sizes, and computational budget. We show that a GAN-based model can achieve results comparable or superior to a diffusion-based model. Additionally, we explore the impact of popular design choices, such as text conditioning and augmentation on the performance of ISR models, showcasing their effect in several downstream tasks. We will release the inference code and weights of our scaled GAN.

replace-cross Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions

Authors: Zhe Hu, Tuo Liang, Jing Li, Yiren Lu, Yunlai Zhou, Yiran Qiao, Jing Ma, Yu Yin

Abstract: Recent advancements in large multimodal language models have demonstrated remarkable proficiency across a wide range of tasks. Yet, these models still struggle with understanding the nuances of human humor through juxtaposition, particularly when it involves nonlinear narratives that underpin many jokes and humor cues. This paper investigates this challenge by focusing on comics with contradictory narratives, where each comic consists of two panels that create a humorous contradiction. We introduce the YesBut benchmark, which comprises tasks of varying difficulty aimed at assessing AI's capabilities in recognizing and interpreting these comics, ranging from literal content comprehension to deep narrative reasoning. Through extensive experimentation and analysis of recent commercial or open-sourced large (vision) language models, we assess their capability to comprehend the complex interplay of the narrative humor inherent in these comics. Our results show that even state-of-the-art models still lag behind human performance on this task. Our findings offer insights into the current limitations and potential improvements for AI in understanding human creative expressions.

replace-cross R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction

Authors: Ruyi Zha, Tao Jun Lin, Yuanhao Cai, Jiwen Cao, Yanhao Zhang, Hongdong Li

Abstract: 3D Gaussian splatting (3DGS) has shown promising results in image rendering and surface reconstruction. However, its potential in volumetric reconstruction tasks, such as X-ray computed tomography, remains under-explored. This paper introduces R$^2$-Gaussian, the first 3DGS-based framework for sparse-view tomographic reconstruction. By carefully deriving X-ray rasterization functions, we discover a previously unknown integration bias in the standard 3DGS formulation, which hampers accurate volume retrieval. To address this issue, we propose a novel rectification technique via refactoring the projection from 3D to 2D Gaussians. Our new method presents three key innovations: (1) introducing tailored Gaussian kernels, (2) extending rasterization to X-ray imaging, and (3) developing a CUDA-based differentiable voxelizer. Experiments on synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art approaches in accuracy and efficiency. Crucially, it delivers high-quality results in 4 minutes, which is 12$\times$ faster than NeRF-based methods and on par with traditional algorithms. Code and models are available on the project page https://github.com/Ruyi-Zha/r2_gaussian.

URLs: https://github.com/Ruyi-Zha/r2_gaussian.

replace-cross Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching

Authors: Yongqi Wang, Wenxiang Guo, Rongjie Huang, Jiawei Huang, Zehan Wang, Fuming You, Ruiqi Li, Zhou Zhao

Abstract: Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transformer and channel-level cross-modal feature fusion with strong temporal alignment, our model generates audio that is highly synchronized with the input video. Furthermore, through reflow and one-step distillation with guided vector field, our model can generate decent audio in a few, or even only one sampling step. Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment on VGGSound, with alignment accuracy reaching 97.22%, and 6.2% improvement in inception score over the strong diffusion-based baseline. Audio samples are available at http://frieren-v2a.github.io.

URLs: http://frieren-v2a.github.io.

replace-cross Enhancing Domain Adaptation through Prompt Gradient Alignment

Authors: Hoang Phan, Lam Tran, Quyen Tran, Trung Le

Abstract: Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt learning leverages the power of large-scale pre-trained vision-language models to learn both domain-invariant and specific features through a set of domain-agnostic and domain-specific learnable prompts. Those studies typically enforce invariant constraints on representation, output, or prompt space to learn such prompts. Differently, we cast UDA as a multiple-objective optimization problem in which each objective is represented by a domain loss. Under this new framework, we propose aligning per-objective gradients to foster consensus between them. Additionally, to prevent potential overfitting when fine-tuning this deep learning architecture, we penalize the norm of these gradients. To achieve these goals, we devise a practical gradient update procedure that can work under both single-source and multi-source UDA. Empirically, our method consistently surpasses other prompt-based baselines by a large margin on different UDA benchmarks.

replace-cross SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation

Authors: Yixia Li, Boya Xiong, Guanhua Chen, Yun Chen

Abstract: Out-of-distribution (OOD) detection is crucial for the safe deployment of neural networks. Existing CLIP-based approaches perform OOD detection by devising novel scoring functions or sophisticated fine-tuning methods. In this work, we propose SeTAR, a novel, training-free OOD detection method that leverages selective low-rank approximation of weight matrices in vision-language and vision-only models. SeTAR enhances OOD detection via post-hoc modification of the model's weight matrices using a simple greedy search algorithm. Based on SeTAR, we further propose SeTAR+FT, a fine-tuning extension optimizing model performance for OOD detection tasks. Extensive evaluations on ImageNet1K and Pascal-VOC benchmarks show SeTAR's superior performance, reducing the relatively false positive rate by up to 18.95% and 36.80% compared to zero-shot and fine-tuning baselines. Ablation studies further validate SeTAR's effectiveness, robustness, and generalizability across different model backbones. Our work offers a scalable, efficient solution for OOD detection, setting a new state-of-the-art in this area.

replace-cross CollaFuse: Collaborative Diffusion Models

Authors: Simeon Allmendinger, Domenique Zipperling, Lukas Struppek, Niklas K\"uhl

Abstract: In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly concerning data availability, computational requirements, and privacy. Traditional approaches to address these shortcomings, like federated learning, often impose significant computational burdens on individual clients, especially those with constrained resources. In response to these challenges, we introduce a novel approach for distributed collaborative diffusion models inspired by split learning. Our approach facilitates collaborative training of diffusion models while alleviating client computational burdens during image synthesis. This reduced computational burden is achieved by retaining data and computationally inexpensive processes locally at each client while outsourcing the computationally expensive processes to shared, more efficient server resources. Through experiments on the common CelebA dataset, our approach demonstrates enhanced privacy by reducing the necessity for sharing raw data. These capabilities hold significant potential across various application areas, including the design of edge computing solutions. Thus, our work advances distributed machine learning by contributing to the evolution of collaborative diffusion models.

replace-cross Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding

Authors: Yue Fan, Lei Ding, Ching-Chen Kuo, Shan Jiang, Yang Zhao, Xinze Guan, Jie Yang, Yi Zhang, Xin Eric Wang

Abstract: Graphical User Interfaces (GUIs) are central to our interaction with digital devices and growing efforts have been made to build models for various GUI understanding tasks. However, these efforts largely overlook an important GUI-referring task: screen reading based on user-indicated points, which we name the Screen Point-and-Read (ScreenPR) task. Currently, this task is predominantly handled by rigid accessible screen reading tools, in great need of new models driven by advancements in Multimodal Large Language Models (MLLMs). In this paper, we propose a Tree-of-Lens (ToL) agent, utilizing a novel ToL grounding mechanism, to address the ScreenPR task. Based on the input point coordinate and the corresponding GUI screenshot, our ToL agent constructs a Hierarchical Layout Tree. Based on the tree, our ToL agent not only comprehends the content of the indicated area but also articulates the layout and spatial relationships between elements. Such layout information is crucial for accurately interpreting information on the screen, distinguishing our ToL agent from other screen reading tools. We also thoroughly evaluate the ToL agent against other baselines on a newly proposed ScreenPR benchmark, which includes GUIs from mobile, web, and operating systems. Last but not least, we test the ToL agent on mobile GUI navigation tasks, demonstrating its utility in identifying incorrect actions along the path of agent execution trajectories. Code and data: https://screen-point-and-read.github.io

URLs: https://screen-point-and-read.github.io

replace-cross Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model

Authors: Zhening Liu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang

Abstract: With the rapid advancement of stereo vision technologies, stereo image compression has emerged as a crucial field that continues to draw significant attention. Previous approaches have primarily employed a unidirectional paradigm, where the compression of one view is dependent on the other, resulting in imbalanced compression. To address this issue, we introduce a symmetric bidirectional stereo image compression architecture, named BiSIC. Specifically, we propose a 3D convolution based codec backbone to capture local features and incorporate bidirectional attention blocks to exploit global features. Moreover, we design a novel cross-dimensional entropy model that integrates various conditioning factors, including the spatial context, channel context, and stereo dependency, to effectively estimate the distribution of latent representations for entropy coding. Extensive experiments demonstrate that our proposed BiSIC outperforms conventional image/video compression standards, as well as state-of-the-art learning-based methods, in terms of both PSNR and MS-SSIM.

replace-cross High-Quality, ROS Compatible Video Encoding and Decoding for High-Definition Datasets

Authors: Jian Li, Bowen Xu, S\"oren Schwertfeger

Abstract: Robotic datasets are important for scientific benchmarking and developing algorithms, for example for Simultaneous Localization and Mapping (SLAM). Modern robotic datasets feature video data of high resolution and high framerates. Storing and sharing those datasets becomes thus very costly, especially if more than one camera is used for the datasets. It is thus essential to store this video data in a compressed format. This paper investigates the use of modern video encoders for robotic datasets. We provide a software that can replay mp4 videos within ROS 1 and ROS 2 frameworks, supporting the synchronized playback in simulated time. Furthermore, the paper evaluates different encoders and their settings to find optimal configurations in terms of resulting size, quality and encoding time. Through this work we show that it is possible to store and share even highest quality video datasets within reasonable storage constraints.

replace-cross deepmriprep: Voxel-based Morphometry (VBM) Preprocessing via Deep Neural Networks

Authors: Lukas Fisch, Nils R. Winter, Janik Goltermann, Carlotta Barkhau, Daniel Emden, Jan Ernsting, Maximilian Konowski, Ramona Leenings, Tiana Borgers, Kira Flinkenfl\"ugel, Dominik Grotegerd, Anna Kraus, Elisabeth J. Leehr, Susanne Meinert, Frederike Stein, Lea Teutenberg, Florian Thomas-Odenthal, Paula Usemann, Marco Hermesdorf, Hamidreza Jamalabadi, Andreas Jansen, Igor Nenadic, Benjamin Straube, Tilo Kircher, Klaus Berger, Benjamin Risse, Udo Dannlowski, Tim Hahn

Abstract: Voxel-based Morphometry (VBM) has emerged as a powerful approach in neuroimaging research, utilized in over 7,000 studies since the year 2000. Using Magnetic Resonance Imaging (MRI) data, VBM assesses variations in the local density of brain tissue and examines its associations with biological and psychometric variables. Here, we present deepmriprep, a neural network-based pipeline that performs all necessary preprocessing steps for VBM analysis of T1-weighted MR images using deep neural networks. Utilizing the Graphics Processing Unit (GPU), deepmriprep is 37 times faster than CAT12, the leading VBM preprocessing toolbox. The proposed method matches CAT12 in accuracy for tissue segmentation and image registration across more than 100 datasets and shows strong correlations in VBM results. Tissue segmentation maps from deepmriprep have over 95% agreement with ground truth maps, and its non-linear registration, using supervised SYMNet, predicts smooth deformation fields comparable to CAT12. The high processing speed of deepmriprep enables rapid preprocessing of extensive datasets and thereby fosters the application of VBM analysis to large-scale neuroimaging studies and opens the door to real-time applications. Finally, deepmripreps straightforward, modular design enables researchers to easily understand, reuse, and advance the underlying methods, fostering further advancements in neuroimaging research. deepmriprep can be conveniently installed as a Python package and is publicly accessible at https://github.com/wwu-mmll/deepmriprep.

URLs: https://github.com/wwu-mmll/deepmriprep.

replace-cross Creativity and Visual Communication from Machine to Musician: Sharing a Score through a Robotic Camera

Authors: Ross Greer, Laura Fleig, Shlomo Dubnov

Abstract: This paper explores the integration of visual communication and musical interaction by implementing a robotic camera within a "Guided Harmony" musical game. We aim to examine co-creative behaviors between human musicians and robotic systems. Our research explores existing methodologies like improvisational game pieces and extends these concepts to include robotic participation using a PTZ camera. The robotic system interprets and responds to nonverbal cues from musicians, creating a collaborative and adaptive musical experience. This initial case study underscores the importance of intuitive visual communication channels. We also propose future research directions, including parameters for refining the visual cue toolkit and data collection methods to understand human-machine co-creativity further. Our findings contribute to the broader understanding of machine intelligence in augmenting human creativity, particularly in musical settings.

replace-cross Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning

Authors: Peyman Milanfar, Mauricio Delbracio

Abstract: Denoising, the process of reducing random fluctuations in a signal to emphasize essential patterns, has been a fundamental problem of interest since the dawn of modern scientific inquiry. Recent denoising techniques, particularly in imaging, have achieved remarkable success, nearing theoretical limits by some measures. Yet, despite tens of thousands of research papers, the wide-ranging applications of denoising beyond noise removal have not been fully recognized. This is partly due to the vast and diverse literature, making a clear overview challenging. This paper aims to address this gap. We present a clarifying perspective on denoisers, their structure, and desired properties. We emphasize the increasing importance of denoising and showcase its evolution into an essential building block for complex tasks in imaging, inverse problems, and machine learning. Despite its long history, the community continues to uncover unexpected and groundbreaking uses for denoising, further solidifying its place as a cornerstone of scientific and engineering practice.

replace-cross Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection

Authors: Qian Shao, Jiangrui Kang, Qiyuan Chen, Zepeng Li, Hongxia Xu, Yiwen Cao, Jiajuan Liang, Jian Wu

Abstract: Semi-Supervised Learning (SSL) has become a preferred paradigm in many deep learning tasks, which reduces the need for human labor. Previous studies primarily focus on effectively utilising the labelled and unlabeled data to improve performance. However, we observe that how to select samples for labelling also significantly impacts performance, particularly under extremely low-budget settings. The sample selection task in SSL has been under-explored for a long time. To fill in this gap, we propose a Representative and Diverse Sample Selection approach (RDSS). By adopting a modified Frank-Wolfe algorithm to minimise a novel criterion $\alpha$-Maximum Mean Discrepancy ($\alpha$-MMD), RDSS samples a representative and diverse subset for annotation from the unlabeled data. We demonstrate that minimizing $\alpha$-MMD enhances the generalization ability of low-budget learning. Experimental results show that RDSS consistently improves the performance of several popular SSL frameworks and outperforms the state-of-the-art sample selection approaches used in Active Learning (AL) and Semi-Supervised Active Learning (SSAL), even with constrained annotation budgets.

replace-cross NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomes

Authors: Ziquan Wei, Tingting Dan, Jiaqi Ding, Guorong Wu

Abstract: Although modern imaging technologies allow us to study connectivity between two distinct brain regions in-vivo, an in-depth understanding of how anatomical structure supports brain function and how spontaneous functional fluctuations emerge remarkable cognition is still elusive. Meanwhile, tremendous efforts have been made in the realm of machine learning to establish the nonlinear mapping between neuroimaging data and phenotypic traits. However, the absence of neuroscience insight in the current approaches poses significant challenges in understanding cognitive behavior from transient neural activities. To address this challenge, we put the spotlight on the coupling mechanism of structural connectivity (SC) and functional connectivity (FC) by formulating such network neuroscience question into an expressive graph representation learning problem for high-order topology. Specifically, we introduce the concept of topological detour to characterize how a ubiquitous instance of FC (direct link) is supported by neural pathways (detour) physically wired by SC, which forms a cyclic loop interacted by brain structure and function. In the clich\'e of machine learning, the multi-hop detour pathway underlying SC-FC coupling allows us to devise a novel multi-head self-attention mechanism within Transformer to capture multi-modal feature representation from paired graphs of SC and FC. Taken together, we propose a biological-inspired deep model, coined as NeuroPath, to find putative connectomic feature representations from the unprecedented amount of neuroimages, which can be plugged into various downstream applications such as task recognition and disease diagnosis. We have evaluated NeuroPath on large-scale public datasets including HCP and UK Biobank under supervised and zero-shot learning, where the state-of-the-art performance by our NeuroPath indicates great potential in network neuroscience.

replace-cross Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning

Authors: Grzegorz Rype\'s\'c, Sebastian Cygert, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski

Abstract: Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature extractor's latent space, enabling Bayes classification or training the classifier by replaying pseudo features. However, we identify two critical issues that compromise their efficacy when the feature extractor is updated on incremental tasks. First, they do not consider that classes' covariance matrices change and must be adapted after each task. Second, they are susceptible to a task-recency bias caused by dimensionality collapse occurring during training. In this work, we propose AdaGauss -- a novel method that adapts covariance matrices from task to task and mitigates the task-recency bias owing to the additional anti-collapse loss function. AdaGauss yields state-of-the-art results on popular EFCIL benchmarks and datasets when training from scratch or starting from a pre-trained backbone. The code is available at: https://github.com/grypesc/AdaGauss.

URLs: https://github.com/grypesc/AdaGauss.

replace-cross Mixture of Multicenter Experts in Multimodal Generative AI for Advanced Radiotherapy Target Delineation

Authors: Yujin Oh, Sangjoon Park, Xiang Li, Wang Yi, Jonathan Paly, Jason Efstathiou, Annie Chan, Jun Won Kim, Hwa Kyung Byun, Ik Jae Lee, Jaeho Cho, Chan Woo Wee, Peng Shu, Peilong Wang, Nathan Yu, Jason Holmes, Jong Chul Ye, Quanzheng Li, Wei Liu, Woong Sub Koom, Jin Sung Kim, Kyungsang Kim

Abstract: Clinical experts employ diverse philosophies and strategies in patient care, influenced by regional patient populations. However, existing medical artificial intelligence (AI) models are often trained on data distributions that disproportionately reflect highly prevalent patterns, reinforcing biases and overlooking the diverse expertise of clinicians. To overcome this limitation, we introduce the Mixture of Multicenter Experts (MoME) approach. This method strategically integrates specialized expertise from diverse clinical strategies, enhancing the AI model's ability to generalize and adapt across multiple medical centers. The MoME-based multimodal target volume delineation model, trained with few-shot samples including images and clinical notes from each medical center, outperformed baseline methods in prostate cancer radiotherapy target delineation. The advantages of MoME were most pronounced when data characteristics varied across centers or when data availability was limited, demonstrating its potential for broader clinical applications. Therefore, the MoME framework enables the deployment of AI-based target volume delineation models in resource-constrained medical facilities by adapting to specific preferences of each medical center only using a few sample data, without the need for data sharing between institutions. Expanding the number of multicenter experts within the MoME framework will significantly enhance the generalizability, while also improving the usability and adaptability of clinical AI applications in the field of precision radiation oncology.

replace-cross Multiscale Latent Diffusion Model for Enhanced Feature Extraction from Medical Images

Authors: Rabeya Tus Sadia, Jie Zhang, Jin Chen

Abstract: Various imaging modalities are used in patient diagnosis, each offering unique advantages and valuable insights into anatomy and pathology. Computed Tomography (CT) is crucial in diagnostics, providing high-resolution images for precise internal organ visualization. CT's ability to detect subtle tissue variations is vital for diagnosing diseases like lung cancer, enabling early detection and accurate tumor assessment. However, variations in CT scanner models and acquisition protocols introduce significant variability in the extracted radiomic features, even when imaging the same patient. This variability poses considerable challenges for downstream research and clinical analysis, which depend on consistent and reliable feature extraction. Current methods for medical image feature extraction, often based on supervised learning approaches, including GAN-based models, face limitations in generalizing across different imaging environments. In response to these challenges, we propose LTDiff++, a multiscale latent diffusion model designed to enhance feature extraction in medical imaging. The model addresses variability by standardizing non-uniform distributions in the latent space, improving feature consistency. LTDiff++ utilizes a UNet++ encoder-decoder architecture coupled with a conditional Denoising Diffusion Probabilistic Model (DDPM) at the latent bottleneck to achieve robust feature extraction and standardization. Extensive empirical evaluations on both patient and phantom CT datasets demonstrate significant improvements in image standardization, with higher Concordance Correlation Coefficients (CCC) across multiple radiomic feature categories. Through these advancements, LTDiff++ represents a promising solution for overcoming the inherent variability in medical imaging data, offering improved reliability and accuracy in feature extraction processes.

replace-cross LucidGrasp: Robotic Framework for Autonomous Manipulation of Laboratory Equipment with Different Degrees of Transparency via 6D Pose Estimation

Authors: Maria Makarova, Daria Trinitatova, Dzmitry Tsetserukou

Abstract: Many modern robotic systems operate autonomously, however they often lack the ability to accurately analyze the environment and adapt to changing external conditions, while teleoperation systems often require special operator skills. In the field of laboratory automation, the number of automated processes is growing, however such systems are usually developed to perform specific tasks. In addition, many of the objects used in this field are transparent, making it difficult to analyze them using visual channels. The contributions of this work include the development of a robotic framework with autonomous mode for manipulating liquid-filled objects with different degrees of transparency in complex pose combinations. The conducted experiments demonstrated the robustness of the designed visual perception system to accurately estimate object poses for autonomous manipulation, and confirmed the performance of the algorithms in dexterous operations such as liquid dispensing. The proposed robotic framework can be applied for laboratory automation, since it allows solving the problem of performing non-trivial manipulation tasks with the analysis of object poses of varying degrees of transparency and liquid levels, requiring high accuracy and repeatability.

replace-cross WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Authors: Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan, David Anugraha, Rifki Afina Putri, Yutong Wang, Adam Nohejl, Ubaidillah Ariq Prathama, Nedjma Ousidhoum, Afifa Amriani, Anar Rzayev, Anirban Das, Ashmari Pramodya, Aulia Adila, Bryan Wilie, Candy Olivia Mawalim, Ching Lam Cheng, Daud Abolade, Emmanuele Chersoni, Enrico Santus, Fariz Ikhwantri, Garry Kuwanto, Hanyang Zhao, Haryo Akbarianto Wibowo, Holy Lovenia, Jan Christian Blaise Cruz, Jan Wira Gotama Putra, Junho Myung, Lucky Susanto, Maria Angelica Riera Machin, Marina Zhukova, Michael Anugraha, Muhammad Farid Adilazuarda, Natasha Santosa, Peerat Limkonchotiwat, Raj Dabre, Rio Alexander Audino, Samuel Cahyawijaya, Shi-Xiong Zhang, Stephanie Yulia Salim, Yi Zhou, Yinxuan Gui, David Ifeoluwa Adelani, En-Shiun Annie Lee, Shogo Okada, Ayu Purwarianti, Alham Fikri Aji, Taro Watanabe, Derry Tanti Wijaya, Alice Oh, Chong-Wah Ngo

Abstract: Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data.

new Adaptive Real-Time Multi-Loss Function Optimization Using Dynamic Memory Fusion Framework: A Case Study on Breast Cancer Segmentation

new C^2DA: Contrastive and Context-aware Domain Adaptive Semantic Segmentation

new A SAM based Tool for Semi-Automatic Food Annotation

new PINNing Cerebral Blood Flow: Analysis of Perfusion MRI in Infants using Physics-Informed Neural Networks

new Movie Trailer Genre Classification Using Multimodal Pretrained Features

new Reliable, Routable, and Reproducible: Collection of Pedestrian Pathways at Statewide Scale

new Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition

new Developing Gridded Emission Inventory from High-Resolution Satellite Object Detection for Improved Air Quality Forecasts