Authors: Javon Hickmon
Abstract: In the rapidly advancing field of artificial intelligence, machine perception is becoming paramount to achieving increased performance. Image classification systems are becoming increasingly integral to various applications, ranging from medical diagnostics to image generation; however, these systems often exhibit harmful biases that can lead to unfair and discriminatory outcomes. Machine Learning systems that depend on a single data modality, i.e. only images or only text, can exaggerate hidden biases present in the training data, if the data is not carefully balanced and filtered. Even so, these models can still harm underrepresented populations when used in improper contexts, such as when government agencies reinforce racial bias using predictive policing. This thesis explores the intersection of technology and ethics in the development of fair image classification models. Specifically, I focus on improving fairness and methods of using multiple modalities to combat harmful demographic bias. Integrating multimodal approaches, which combine visual data with additional modalities such as text and metadata, allows this work to enhance the fairness and accuracy of image classification systems. The study critically examines existing biases in image datasets and classification algorithms, proposes innovative methods for mitigating these biases, and evaluates the ethical implications of deploying such systems in real-world scenarios. Through comprehensive experimentation and analysis, the thesis demonstrates how multimodal techniques can contribute to more equitable and ethical AI solutions, ultimately advocating for responsible AI practices that prioritize fairness.
Authors: Son Minh Nguyen, Linh Duy Tran, Duc Viet Le, Paul J. M Havinga
Abstract: Despite remarkable progress in knowledge transfer across visual and textual domains, extending these achievements to indoor localization, particularly for learning transferable representations among Received Signal Strength (RSS) fingerprint datasets, remains a challenge. This is due to inherent discrepancies among these RSS datasets, largely including variations in building structure, the input number and disposition of WiFi anchors. Accordingly, specialized networks, which were deprived of the ability to discern transferable representations, readily incorporate environment-sensitive clues into the learning process, hence limiting their potential when applied to specific RSS datasets. In this work, we propose a plug-and-play (PnP) framework of knowledge transfer, facilitating the exploitation of transferable representations for specialized networks directly on target RSS datasets through two main phases. Initially, we design an Expert Training phase, which features multiple surrogate generative teachers, all serving as a global adapter that homogenizes the input disparities among independent source RSS datasets while preserving their unique characteristics. In a subsequent Expert Distilling phase, we continue introducing a triplet of underlying constraints that requires minimizing the differences in essential knowledge between the specialized network and surrogate teachers through refining its representation learning on the target dataset. This process implicitly fosters a representational alignment in such a way that is less sensitive to specific environmental dynamics. Extensive experiments conducted on three benchmark WiFi RSS fingerprint datasets underscore the effectiveness of the framework that significantly exerts the full potential of specialized networks in localization.
Authors: Karthik Sivakoti
Abstract: Traditional automated toll collection systems depend on complex hardware configurations, that require huge investments in installation and maintenance. This research paper presents an innovative approach to revolutionize automated toll collection by using a single camera per plaza with the YOLOv11 computer vision architecture combined with an ensemble OCR technique. Our system has achieved a Mean Average Precision (mAP) of 0.895 over a wide range of conditions, demonstrating 98.5% accuracy in license plate recognition, 94.2% accuracy in axle detection, and 99.7% OCR confidence scoring. The architecture incorporates intelligent vehicle tracking across IOU regions, automatic axle counting by way of spatial wheel detection patterns, and real-time monitoring through an extended dashboard interface. Extensive training using 2,500 images under various environmental conditions, our solution shows improved performance while drastically reducing hardware resources compared to conventional systems. This research contributes toward intelligent transportation systems by introducing a scalable, precision-centric solution that improves operational efficiency and user experience in modern toll collections.
Authors: Erfan Entezami, Hui Guan
Abstract: Recent efforts to enhance immersive and interactive user experiences have driven the development of volumetric video, a form of 3D content that enables 6 DoF. Unlike traditional 2D content, volumetric content can be represented in various ways, such as point clouds, meshes, or neural representations. However, due to its complex structure and large amounts of data size, deploying this new form of 3D data presents significant challenges in transmission and rendering. These challenges have hindered the widespread adoption of volumetric video in daily applications. In recent years, researchers have proposed various AI-driven techniques to address these challenges and improve the efficiency and quality of volumetric content streaming. This paper provides a comprehensive overview of recent advances in AI-driven approaches to facilitate volumetric content streaming. Through this review, we aim to offer insights into the current state-of-the-art and suggest potential future directions for advancing the deployment of volumetric video streaming in real-world applications.
Authors: Hang Jin, Xin He, Lingyun Wang, Yujun Zhu, Weiwei Jiang, Xiaobo Zhou
Abstract: Poor sitting posture can lead to various work-related musculoskeletal disorders (WMSDs). Office employees spend approximately 81.8% of their working time seated, and sedentary behavior can result in chronic diseases such as cervical spondylosis and cardiovascular diseases. To address these health concerns, we present SitPose, a sitting posture and sedentary detection system utilizing the latest Kinect depth camera. The system tracks 3D coordinates of bone joint points in real-time and calculates the angle values of related joints. We established a dataset containing six different sitting postures and one standing posture, totaling 33,409 data points, by recruiting 36 participants. We applied several state-of-the-art machine learning algorithms to the dataset and compared their performance in recognizing the sitting poses. Our results show that the ensemble learning model based on the soft voting mechanism achieves the highest F1 score of 98.1%. Finally, we deployed the SitPose system based on this ensemble model to encourage better sitting posture and to reduce sedentary habits.
Authors: Xiao Teng, Long Lan, Dingyao Chen, Kele Xu, Nan Yin
Abstract: Unsupervised visible-infrared person re-identification (USL-VI-ReID) is of great research and practical significance yet remains challenging due to the absence of annotations. Existing approaches aim to learn modality-invariant representations in an unsupervised setting. However, these methods often encounter label noise within and across modalities due to suboptimal clustering results and considerable modality discrepancies, which impedes effective training. To address these challenges, we propose a straightforward yet effective solution for USL-VI-ReID by mitigating universal label noise using neighbor information. Specifically, we introduce the Neighbor-guided Universal Label Calibration (N-ULC) module, which replaces explicit hard pseudo labels in both homogeneous and heterogeneous spaces with soft labels derived from neighboring samples to reduce label noise. Additionally, we present the Neighbor-guided Dynamic Weighting (N-DW) module to enhance training stability by minimizing the influence of unreliable samples. Extensive experiments on the RegDB and SYSU-MM01 datasets demonstrate that our method outperforms existing USL-VI-ReID approaches, despite its simplicity. The source code is available at: https://github.com/tengxiao14/Neighbor-guided-USL-VI-ReID.
URLs: https://github.com/tengxiao14/Neighbor-guided-USL-VI-ReID.
Authors: Kunming Li, Mao Shan, Stephany Berrio Perez, Katie Luo, Stewart Worrall
Abstract: Traffic accidents are a global safety concern, resulting in numerous fatalities each year. A considerable number of these deaths are caused by animal-vehicle collisions (AVCs), which not only endanger human lives but also present serious risks to animal populations. This paper presents an innovative self-training methodology aimed at detecting rare animals, such as the cassowary in Australia, whose survival is threatened by road accidents. The proposed method addresses critical real-world challenges, including acquiring and labelling sensor data for rare animal species in resource-limited environments. It achieves this by leveraging cloud and edge computing, and automatic data labelling to improve the detection performance of the field-deployed model iteratively. Our approach introduces Label-Augmentation Non-Maximum Suppression (LA-NMS), which incorporates a vision-language model (VLM) to enable automated data labelling. During a five-month deployment, we confirmed the method's robustness and effectiveness, resulting in improved object detection accuracy and increased prediction confidence. The source code is available: https://github.com/acfr/CassDetect
Authors: Xiaozhe Li, Kai WU, Siyi Yang, YiZhan Qu, Guohua. Zhang, Zhiyu Chen, Jiayao Li, Jiangchuan Mu, Xiaobin Hu, Wen Fang, Mingliang Xiong, Hao Deng, Qingwen Liu, Gang Li, Bin He
Abstract: Recent advancements in text-to-video (T2V) generation have leveraged diffusion models to enhance the visual coherence of videos generated from textual descriptions. However, most research has primarily focused on object motion, with limited attention given to cinematic language in videos, which is crucial for cinematographers to convey emotion and narrative pacing. To address this limitation, we propose a threefold approach to enhance the ability of T2V models to generate controllable cinematic language. Specifically, we introduce a cinematic language dataset that encompasses shot framing, angle, and camera movement, enabling models to learn diverse cinematic styles. Building on this, to facilitate robust cinematic alignment evaluation, we present CameraCLIP, a model fine-tuned on the proposed dataset that excels in understanding complex cinematic language in generated videos and can further provide valuable guidance in the multi-shot composition process. Finally, we propose CLIPLoRA, a cost-guided dynamic LoRA composition method that facilitates smooth transitions and realistic blending of cinematic language by dynamically fusing multiple pre-trained cinematic LoRAs within a single video. Our experiments demonstrate that CameraCLIP outperforms existing models in assessing the alignment between cinematic language and video, achieving an R@1 score of 0.81. Additionally, CLIPLoRA improves the ability for multi-shot composition, potentially bridging the gap between automatically generated videos and those shot by professional cinematographers.
Authors: Zhi Zhou, Lan-Zhe Guo, Peng-Xiao Song, Yu-Feng Li
Abstract: Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model developers to upload models and users to download models. However, these model hubs lack advanced model management and identification mechanisms, resulting in users only searching for models through text matching, download sorting, etc., making it difficult to efficiently find the model that best meets user requirements. In this paper, we propose a novel setting called Generative Model Identification (GMI), which aims to enable the user to identify the most appropriate generative model(s) for the user's requirements from a large number of candidate models efficiently. To our best knowledge, it has not been studied yet. In this paper, we introduce a comprehensive solution consisting of three pivotal modules: a weighted Reduced Kernel Mean Embedding (RKME) framework for capturing the generated image distribution and the relationship between images and prompts, a pre-trained vision-language model aimed at addressing dimensionality challenges, and an image interrogator designed to tackle cross-modality issues. Extensive empirical results demonstrate the proposal is both efficient and effective. For example, users only need to submit a single example image to describe their requirements, and the model platform can achieve an average top-4 identification accuracy of more than 80%.
Authors: Yangyang Li, Daqing Liu, Wu Liu, Allen He, Xinchen Liu, Yongdong Zhang, Guoqing Jin
Abstract: Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation or are easily disrupted by irrelevant concepts in multi-aspect concept scenarios, leading to concept confusion and hindering creative generation. To address this, we propose OmniPrism, a visual concept disentangling approach for creative image generation. Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts. We utilize the rich semantic space of a multimodal extractor to achieve concept disentanglement from given images and concept guidance. To disentangle concepts with different semantics, we construct a paired concept disentangled dataset (PCD-200K), where each pair shares the same concept such as content, style, and composition. We learn disentangled concept representations through our contrastive orthogonal disentangled (COD) training pipeline, which are then injected into additional diffusion cross-attention layers for generation. A set of block embeddings is designed to adapt each block's concept domain in the diffusion models. Extensive experiments demonstrate that our method can generate high-quality, concept-disentangled results with high fidelity to text prompts and desired concepts.
Authors: Rohit Kundu, Hao Xiong, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury
Abstract: Existing DeepFake detection techniques primarily focus on facial manipulations, such as face-swapping or lip-syncing. However, advancements in text-to-video (T2V) and image-to-video (I2V) generative models now allow fully AI-generated synthetic content and seamless background alterations, challenging face-centric detection methods and demanding more versatile approaches. To address this, we introduce the \underline{U}niversal \underline{N}etwork for \underline{I}dentifying \underline{T}ampered and synth\underline{E}tic videos (\texttt{UNITE}) model, which, unlike traditional detectors, captures full-frame manipulations. \texttt{UNITE} extends detection capabilities to scenarios without faces, non-human subjects, and complex background modifications. It leverages a transformer-based architecture that processes domain-agnostic features extracted from videos via the SigLIP-So400M foundation model. Given limited datasets encompassing both facial/background alterations and T2V/I2V content, we integrate task-irrelevant data alongside standard DeepFake datasets in training. We further mitigate the model's tendency to over-focus on faces by incorporating an attention-diversity (AD) loss, which promotes diverse spatial attention across video frames. Combining AD loss with cross-entropy improves detection performance across varied contexts. Comparative evaluations demonstrate that \texttt{UNITE} outperforms state-of-the-art detectors on datasets (in cross-data settings) featuring face/background manipulations and fully synthetic T2V/I2V videos, showcasing its adaptability and generalizable detection capabilities.
Authors: Ph\'uc H. Le Khac, Graham Healy, Alan F. Smeaton
Abstract: This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric understanding and leverages pre-trained vision models to enhance object discovery. Our method introduces an efficient slot decoder specifically designed for object-centric learning, enabling effective representation of multi-object scenes without requiring explicit depth information. Results on synthetic video benchmarks with increasing complexity in terms of objects and their movement, object occlusion and camera motion demonstrate that our approach achieves comparable performance to supervised methods while maintaining computational efficiency. This advances the field towards more practical applications in complex real-world scenarios.
Authors: Madiyar Alimov, Temirlan Meiramkhanov
Abstract: This study investigates the domain generalization capabilities of three state-of-the-art object detection models - YOLOv8s, RT-DETR, and YOLO-NAS - within the unique driving environment of Kazakhstan. Utilizing the newly constructed ROAD-Almaty dataset, which encompasses diverse weather, lighting, and traffic conditions, we evaluated the models' performance without any retraining. Quantitative analysis revealed that RT-DETR achieved an average F1-score of 0.672 at IoU=0.5, outperforming YOLOv8s (0.458) and YOLO-NAS (0.526) by approximately 46% and 27%, respectively. Additionally, all models exhibited significant performance declines at higher IoU thresholds (e.g., a drop of approximately 20% when increasing IoU from 0.5 to 0.75) and under challenging environmental conditions, such as heavy snowfall and low-light scenarios. These findings underscore the necessity for geographically diverse training datasets and the implementation of specialized domain adaptation techniques to enhance the reliability of autonomous vehicle detection systems globally. This research contributes to the understanding of domain generalization challenges in autonomous driving, particularly in underrepresented regions.
Authors: Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma
Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced visual tasks by integrating visual representations into large language models (LLMs). The textual modality, inherited from LLMs, equips MLLMs with abilities like instruction following and in-context learning. In contrast, the visual modality enhances performance in downstream tasks by leveraging rich semantic content, spatial information, and grounding capabilities. These intrinsic modalities work synergistically across various visual tasks. Our research initially reveals a persistent imbalance between these modalities, with text often dominating output generation during visual instruction tuning. This imbalance occurs when using both full fine-tuning and parameter-efficient fine-tuning (PEFT) methods. We then found that re-balancing these modalities can significantly reduce the number of trainable parameters required, inspiring a direction for further optimizing visual instruction tuning. We introduce Modality Linear Representation-Steering (MoReS) to achieve the goal. MoReS effectively re-balances the intrinsic modalities throughout the model, where the key idea is to steer visual representations through linear transformations in the visual subspace across each model layer. To validate our solution, we composed LLaVA Steering, a suite of models integrated with the proposed MoReS method. Evaluation results show that the composed LLaVA Steering models require, on average, 500 times fewer trainable parameters than LoRA needs while still achieving comparable performance across three visual benchmarks and eight visual question-answering tasks. Last, we present the LLaVA Steering Factory, an in-house developed platform that enables researchers to quickly customize various MLLMs with component-based architecture for seamlessly integrating state-of-the-art models, and evaluate their intrinsic modality imbalance.
Authors: Hao Li, Shamit Lal, Zhiheng Li, Yusheng Xie, Ying Wang, Yang Zou, Orchid Majumder, R. Manmatha, Zhuowen Tu, Stefano Ermon, Stefano Soatto, Ashwin Swaminathan
Abstract: We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on datasets up to 600M images. We find that U-ViT, a pure self-attention based DiT model provides a simpler design and scales more effectively in comparison with cross-attention based DiT variants, which allows straightforward expansion for extra conditions and other modalities. We identify a 2.3B U-ViT model can get better performance than SDXL UNet and other DiT variants in controlled setting. On the data scaling side, we investigate how increasing dataset size and enhanced long caption improve the text-image alignment performance and the learning efficiency.
Authors: Riku Murai, Eric Dexheimer, Andrew J. Davison
Abstract: We present a real-time monocular dense SLAM system designed bottom-up from MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system is robust on in-the-wild video sequences despite making no assumption on a fixed or parametric camera model beyond a unique camera centre. We introduce efficient methods for pointmap matching, camera tracking and local fusion, graph construction and loop closure, and second-order global optimisation. With known calibration, a simple modification to the system achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.
Authors: Yash Patel, Giorgos Tolias, Jiri Matas
Abstract: This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization. In deep metric learning, optimizing the retrieval evaluation metric, recall@k, via gradient descent is desirable but challenging due to its non-differentiable nature. To overcome this, we propose a differentiable surrogate loss that is computed on large batches, nearly equivalent to the entire training set. This computationally intensive process is made feasible through an implementation that bypasses the GPU memory limitations. Additionally, we introduce an efficient mixup regularization technique that operates on pairwise scalar similarities, effectively increasing the batch size even further. The training process is further enhanced by initializing the vision encoder using foundational models, which are pre-trained on large-scale datasets. Through a systematic study of these components, we demonstrate that their synergy enables large models to nearly solve popular benchmarks.
Authors: Kun Guo, Qiang Ling
Abstract: Multi-camera 3D object detection aims to detect and localize objects in 3D space using multiple cameras, which has attracted more attention due to its cost-effectiveness trade-off. However, these methods often struggle with the lack of accurate depth estimation caused by the natural weakness of the camera in ranging. Recently, multi-modal fusion and knowledge distillation methods for 3D object detection have been proposed to solve this problem, which are time-consuming during the training phase and not friendly to memory cost. In light of this, we propose PromptDet, a lightweight yet effective 3D object detection framework motivated by the success of prompt learning in 2D foundation model. Our proposed framework, PromptDet, comprises two integral components: a general camera-based detection module, exemplified by models like BEVDet and BEVDepth, and a LiDAR-assisted prompter. The LiDAR-assisted prompter leverages the LiDAR points as a complementary signal, enriched with a minimal set of additional trainable parameters. Notably, our framework is flexible due to our prompt-like design, which can not only be used as a lightweight multi-modal fusion method but also as a camera-only method for 3D object detection during the inference phase. Extensive experiments on nuScenes validate the effectiveness of the proposed PromptDet. As a multi-modal detector, PromptDet improves the mAP and NDS by at most 22.8\% and 21.1\% with fewer than 2\% extra parameters compared with the camera-only baseline. Without LiDAR points, PromptDet still achieves an improvement of at most 2.4\% mAP and 4.0\% NDS with almost no impact on camera detection inference time.
Authors: Aditya Ganeshan, Thibault Groueix, Paul Guerrero, Radom\'ir M\v{e}ch, Matthew Fisher, Daniel Ritchie
Abstract: Pattern images are everywhere in the digital and physical worlds, and tools to edit them are valuable. But editing pattern images is tricky: desired edits are often programmatic: structure-aware edits that alter the underlying program which generates the pattern. One could attempt to infer this underlying program, but current methods for doing so struggle with complex images and produce unorganized programs that make editing tedious. In this work, we introduce a novel approach to perform programmatic edits on pattern images. By using a pattern analogy -- a pair of simple patterns to demonstrate the intended edit -- and a learning-based generative model to execute these edits, our method allows users to intuitively edit patterns. To enable this paradigm, we introduce SplitWeave, a domain-specific language that, combined with a framework for sampling synthetic pattern analogies, enables the creation of a large, high-quality synthetic training dataset. We also present TriFuser, a Latent Diffusion Model (LDM) designed to overcome critical issues that arise when naively deploying LDMs to this task. Extensive experiments on real-world, artist-sourced patterns reveals that our method faithfully performs the demonstrated edit while also generalizing to related pattern styles beyond its training distribution.
Authors: Qingtao Pan, Wenhao Qiao, Jingjiao Lou, Bing Ji, Shuo Li
Abstract: Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg).
Authors: Mingjia Shi, Yuhao Zhou, Ruiji Yu, Zekai Li, Zhiyuan Liang, Xuanlei Zhao, Xiaojiang Peng, Tanmay Rajpurohit, Shanmukha Ramakrishna Vedantam, Wangbo Zhao, Kai Wang, Yang You
Abstract: Vision Mamba (e.g., Vim) has successfully been integrated into computer vision, and token reduction has yielded promising outcomes in Vision Transformers (ViTs). However, token reduction performs less effectively on Vision Mamba compared to ViTs. Pruning informative tokens in Mamba leads to a high loss of key knowledge and bad performance. This makes it not a good solution for enhancing efficiency in Mamba. Token merging, which preserves more token information than pruning, has demonstrated commendable performance in ViTs. Nevertheless, vanilla merging performance decreases as the reduction ratio increases either, failing to maintain the key knowledge in Mamba. Re-training the token-reduced model enhances the performance of Mamba, by effectively rebuilding the key knowledge. Empirically, pruned Vims only drop up to 0.9% accuracy on ImageNet-1K, recovered by our proposed framework R-MeeTo in our main evaluation. We show how simple and effective the fast recovery can be achieved at minute-level, in particular, a 35.9% accuracy spike over 3 epochs of training on Vim-Ti. Moreover, Vim-Ti/S/B are re-trained within 5/7/17 minutes, and Vim-S only drop 1.3% with 1.2x (up to 1.5x) speed up in inference.
Authors: Yan Zhang, Gangyan Zeng, Huawen Shen, Daiqing Wu, Yu Zhou, Can Ma
Abstract: Video text-based visual question answering (Video TextVQA) is a practical task that aims to answer questions by jointly reasoning textual and visual information in a given video. Inspired by the development of TextVQA in image domain, existing Video TextVQA approaches leverage a language model (e.g. T5) to process text-rich multiple frames and generate answers auto-regressively. Nevertheless, the spatio-temporal relationships among visual entities (including scene text and objects) will be disrupted and models are susceptible to interference from unrelated information, resulting in irrational reasoning and inaccurate answering. To tackle these challenges, we propose the TEA (stands for ``\textbf{T}rack th\textbf{E} \textbf{A}nswer'') method that better extends the generative TextVQA framework from image to video. TEA recovers the spatio-temporal relationships in a complementary way and incorporates OCR-aware clues to enhance the quality of reasoning questions. Extensive experiments on several public Video TextVQA datasets validate the effectiveness and generalization of our framework. TEA outperforms existing TextVQA methods, video-language pretraining methods and video large language models by great margins.
Authors: Yakun Niu, Pei Chen, Lei Zhang, Hongjian Yin, Qi Chang
Abstract: Image Splicing Localization (ISL) is a fundamental yet challenging task in digital forensics. Although current approaches have achieved promising performance, the edge information is insufficiently exploited, resulting in poor integrality and high false alarms. To tackle this problem, we propose a multi-scale cross-fusion and edge-supervision network for ISL. Specifically, our framework consists of three key steps: multi-scale features cross-fusion, edge mask prediction and edge-supervision localization. Firstly, we input the RGB image and its noise image into a segmentation network to learn multi-scale features, which are then aggregated via a cross-scale fusion followed by a cross-domain fusion to enhance feature representation. Secondly, we design an edge mask prediction module to effectively mine the reliable boundary artifacts. Finally, the cross-fused features and the reliable edge mask information are seamlessly integrated via an attention mechanism to incrementally supervise and facilitate model training. Extensive experiments on publicly available datasets demonstrate that our proposed method is superior to state-of-the-art schemes.
Authors: Dongjun Hwang, Sungwon Woo, Tom Gao, Raymond Luo, Sunghwan Baek
Abstract: As Generative AI continues to become more accessible, the case for robust detection of generated images in order to combat misinformation is stronger than ever. Invisible watermarking methods act as identifiers of generated content, embedding image- and latent-space messages that are robust to many forms of perturbations. The majority of current research investigates full-image attacks against images with a single watermarking method applied. We introduce novel improvements to watermarking robustness as well as minimizing degradation on image quality during attack. Firstly, we examine the application of both image-space and latent-space watermarking methods on a single image, where we propose a custom watermark remover network which preserves one of the watermarking modalities while completely removing the other during decoding. Then, we investigate localized blurring attacks (LBA) on watermarked images based on the GradCAM heatmap acquired from the watermark decoder in order to reduce the amount of degradation to the target image. Our evaluation suggests that 1) implementing the watermark remover model to preserve one of the watermark modalities when decoding the other modality slightly improves on the baseline performance, and that 2) LBA degrades the image significantly less compared to uniform blurring of the entire image. Code is available at: https://github.com/tomputer-g/IDL_WAR
Authors: Ruixin Mao, Aoyu Shen, Lin Tang, Jun Zhou
Abstract: Event-based cameras feature high temporal resolution, wide dynamic range, and low power consumption, which is ideal for high-speed and low-light object detection. Spiking neural networks (SNNs) are promising for event-based object recognition and detection due to their spiking nature but lack efficient training methods, leading to gradient vanishing and high computational complexity, especially in deep SNNs. Additionally, existing SNN frameworks often fail to effectively handle multi-scale spatiotemporal features, leading to increased data redundancy and reduced accuracy. To address these issues, we propose CREST, a novel conjointly-trained spike-driven framework to exploit spatiotemporal dynamics in event-based object detection. We introduce the conjoint learning rule to accelerate SNN learning and alleviate gradient vanishing. It also supports dual operation modes for efficient and flexible implementation on different hardware types. Additionally, CREST features a fully spike-driven framework with a multi-scale spatiotemporal event integrator (MESTOR) and a spatiotemporal-IoU (ST-IoU) loss. Our approach achieves superior object recognition & detection performance and up to 100X energy efficiency compared with state-of-the-art SNN algorithms on three datasets, providing an efficient solution for event-based object detection algorithms suitable for SNN hardware implementation.
Authors: Iman Khazrak, Shakhnoza Takhirova, Mostafa M. Rezaee, Mehrdad Yadollahi, Robert C. Green II, Shuteng Niu
Abstract: The development of accurate medical image classification models is often constrained by privacy concerns and data scarcity for certain conditions, leading to small and imbalanced datasets. To address these limitations, this study explores the use of generative models, such as Denoising Diffusion Probabilistic Models (DDPM) and Progressive Growing Generative Adversarial Networks (PGGANs), for dataset augmentation. The research introduces a framework to assess the impact of synthetic images generated by DDPM and PGGANs on the performance of four models: a custom CNN, Untrained VGG16, Pretrained VGG16, and Pretrained ResNet50. Experiments were conducted using Random Sampling and Greedy K Sampling to create small, imbalanced datasets. The synthetic images were evaluated using Frechet Inception Distance (FID) and compared to original datasets through classification metrics. The results show that DDPM consistently generated more realistic images with lower FID scores and significantly outperformed PGGANs in improving classification metrics across all models and datasets. Incorporating DDPM-generated images into the original datasets increased accuracy by up to 6%, enhancing model robustness and stability, particularly in imbalanced scenarios. Random Sampling demonstrated superior stability, while Greedy K Sampling offered diversity at the cost of higher FID scores. This study highlights the efficacy of DDPM in augmenting small, imbalanced medical image datasets, improving model performance by balancing the dataset and expanding its size.
Authors: Xinlong Cheng, Tiantian Cao, Guoan Cheng, Bangxuan Huang, Xinghan Tian, Ye Wang, Xiaoyu He, Weixin Li, Tianfan Xue, Xuan Dong
Abstract: In this work, we address the limitations of denoising diffusion models (DDMs) in image restoration tasks, particularly the shape and color distortions that can compromise image quality. While DDMs have demonstrated a promising performance in many applications such as text-to-image synthesis, their effectiveness in image restoration is often hindered by shape and color distortions. We observe that these issues arise from inconsistencies between the training and testing data used by DDMs. Based on our observation, we propose a novel training method, named data-consistent training, which allows the DDMs to access images with accumulated errors during training, thereby ensuring the model to learn to correct these errors. Experimental results show that, across five image restoration tasks, our method has significant improvements over state-of-the-art methods while effectively minimizing distortions and preserving image fidelity.
Authors: Sparsh Pekhale, Rakshith Sathish, Sathisha Basavaraju, Divya Sharma
Abstract: Land-use and land cover (LULC) analysis is critical in remote sensing, with wide-ranging applications across diverse fields such as agriculture, utilities, and urban planning. However, automating LULC map generation using machine learning is rendered challenging due to noisy labels. Typically, the ground truths (e.g. ESRI LULC, MapBioMass) have noisy labels that hamper the model's ability to learn to accurately classify the pixels. Further, these erroneous labels can significantly distort the performance metrics of a model, leading to misleading evaluations. Traditionally, the ambiguous labels are rectified using unsupervised algorithms. These algorithms struggle not only with scalability but also with generalization across different geographies. To overcome these challenges, we propose a zero-shot approach using the foundation model, Segment Anything Model (SAM), to automatically delineate different land parcels/regions and leverage them to relabel the unsure pixels by using the local label statistics within each detected region. We achieve a significant reduction in label noise and an improvement in the performance of the downstream segmentation model by $\approx 5\%$ when trained with denoised labels.
Authors: Wenjun Huang, Yang Ni, Hanning Chen, Yirui He, Ian Bryant, Yezi Liu, Mohsen Imani
Abstract: Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on multi-modal data and precise target localization with temporal association. However, prior studies overlook the imbalanced data distribution between newborn targets and existing targets due to the nature of the task. In addition, they only indirectly fuse multi-modal features, struggling to deliver clear guidance on newborn target detection. To solve the above issues, we conduct a collaborative matching strategy to alleviate the impact of the imbalance, boosting the ability to detect newborn targets while maintaining tracking performance. In the encoder, we integrate and enhance the cross-modal and multi-scale fusion, overcoming the bottlenecks in previous work, where limited multi-modal information is shared and interacted between feature maps. In the decoder, we also develop a referring-infused adaptation that provides explicit referring guidance through the query tokens. The experiments showcase the superior performance of our model (+3.42%) compared to prior works, demonstrating the effectiveness of our designs.
Authors: Zhifei Shi, Zongyao Yin, Sheng Chang, Xiao Yi, Xianchuan Yu
Abstract: Achieving a balance between computational efficiency and detection accuracy in the realm of rotated bounding box object detection within aerial imagery is a significant challenge. While prior research has aimed at creating lightweight models that enhance computational performance and feature extraction, there remains a gap in the performance of these networks when it comes to the detection of small and multi-scale objects in remote sensing (RS) imagery. To address these challenges, we present a novel enhancement to the YOLOv8 model, tailored for oriented object detection tasks and optimized for environments with limited computational resources. Our model features a wavelet transform-based C2f module for capturing associative features and an Adaptive Scale Feature Pyramid (ASFP) module that leverages P2 layer details. Additionally, the incorporation of GhostDynamicConv significantly contributes to the model's lightweight nature, ensuring high efficiency in aerial imagery analysis. Featuring a parameter count of 21.6M, our approach provides a more efficient architectural design than DecoupleNet, which has 23.3M parameters, all while maintaining detection accuracy. On the DOTAv1.0 dataset, our model demonstrates a mean Average Precision (mAP) that is competitive with leading methods such as DecoupleNet. The model's efficiency, combined with its reduced parameter count, makes it a strong candidate for aerial object detection, particularly in resource-constrained environments.
Authors: Yuhyun Kim, Minwoo Kim, Hyobin Park, Jinwook Jung, Dong-Geol Choi
Abstract: The Multimodal Learning Workshop (PBVS 2024) aims to improve the performance of automatic target recognition (ATR) systems by leveraging both Synthetic Aperture Radar (SAR) data, which is difficult to interpret but remains unaffected by weather conditions and visible light, and Electro-Optical (EO) data for simultaneous learning. The subtask, known as the Multi-modal Aerial View Imagery Challenge - Classification, focuses on predicting the class label of a low-resolution aerial image based on a set of SAR-EO image pairs and their respective class labels. The provided dataset consists of SAR-EO pairs, characterized by a severe long-tail distribution with over a 1000-fold difference between the largest and smallest classes, making typical long-tail methods difficult to apply. Additionally, the domain disparity between the SAR and EO datasets complicates the effectiveness of standard multimodal methods. To address these significant challenges, we propose a two-stage learning approach that utilizes self-supervised techniques, combined with multimodal learning and inference through SAR-to-EO translation for effective EO utilization. In the final testing phase of the PBVS 2024 Multi-modal Aerial View Image Challenge - Classification (SAR Classification) task, our model achieved an accuracy of 21.45%, an AUC of 0.56, and a total score of 0.30, placing us 9th in the competition.
Authors: Haonan Xu, Yang Yang
Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliable deployment of deep models in real-world scenarios. Recently, from the perspective of over-parameterization, a series of methods leveraging weight sparsification techniques have shown promising performance. These methods typically focus on selecting important parameters for in-distribution (ID) data to reduce the negative impact of redundant parameters on OOD detection. However, we empirically find that these selected parameters may behave overconfidently toward OOD data and hurt OOD detection. To address this issue, we propose a simple yet effective post-hoc method called Instance-aware Test Pruning (ITP), which performs OOD detection by considering both coarse-grained and fine-grained levels of parameter pruning. Specifically, ITP first estimates the class-specific parameter contribution distribution by exploring the ID data. By using the contribution distribution, ITP conducts coarse-grained pruning to eliminate redundant parameters. More importantly, ITP further adopts a fine-grained test pruning process based on the right-tailed Z-score test, which can adaptively remove instance-level overconfident parameters. Finally, ITP derives OOD scores from the pruned model to achieve more reliable predictions. Extensive experiments on widely adopted benchmarks verify the effectiveness of ITP, demonstrating its competitive performance.
Authors: Lianghua Huang, Wei Wang, Zhi-Fan Wu, Yupeng Shi, Chen Liang, Tong Shen, Han Zhang, Huanzhang Dou, Yu Liu, Jingren Zhou
Abstract: Recent research arXiv:2410.15027 arXiv:2410.23775 has highlighted the inherent in-context generation capabilities of pretrained diffusion transformers (DiTs), enabling them to seamlessly adapt to diverse visual tasks with minimal or no architectural modifications. These capabilities are unlocked by concatenating self-attention tokens across multiple input and target images, combined with grouped and masked generation pipelines. Building upon this foundation, we present ChatDiT, a zero-shot, general-purpose, and interactive visual generation framework that leverages pretrained diffusion transformers in their original form, requiring no additional tuning, adapters, or modifications. Users can interact with ChatDiT to create interleaved text-image articles, multi-page picture books, edit images, design IP derivatives, or develop character design settings, all through free-form natural language across one or more conversational rounds. At its core, ChatDiT employs a multi-agent system comprising three key components: an Instruction-Parsing agent that interprets user-uploaded images and instructions, a Strategy-Planning agent that devises single-step or multi-step generation actions, and an Execution agent that performs these actions using an in-context toolkit of diffusion transformers. We thoroughly evaluate ChatDiT on IDEA-Bench arXiv:2412.11767, comprising 100 real-world design tasks and 275 cases with diverse instructions and varying numbers of input and target images. Despite its simplicity and training-free approach, ChatDiT surpasses all competitors, including those specifically designed and trained on extensive multi-task datasets. We further identify key limitations of pretrained DiTs in zero-shot adapting to tasks. We release all code, agents, results, and intermediate outputs to facilitate further research at https://github.com/ali-vilab/ChatDiT
Authors: Zahra Ebrahimi Vargoorani, Ching Yee Suen
Abstract: License plate detection (LPD) is essential for traffic management, vehicle tracking, and law enforcement but faces challenges like variable lighting and diverse font types, impacting accuracy. Traditionally reliant on image processing and machine learning, the field is now shifting towards deep learning for its robust performance in various conditions. Current methods, however, often require tailoring to specific regional datasets. This paper proposes a dual deep learning strategy using a Faster R-CNN for detection and a CNN-RNN model with Connectionist Temporal Classification (CTC) loss and a MobileNet V3 backbone for recognition. This approach aims to improve model performance using datasets from Ontario, Quebec, California, and New York State, achieving a recall rate of 92% on the Centre for Pattern Recognition and Machine Intelligence (CENPARMI) dataset and 90% on the UFPR-ALPR dataset. It includes a detailed error analysis to identify the causes of false positives. Additionally, the research examines the role of font features in license plate (LP) recognition, analyzing fonts like Driver Gothic, Dreadnought, California Clarendon, and Zurich Extra Condensed with the OpenALPR system. It discovers significant performance discrepancies influenced by font characteristics, offering insights for future LPD system enhancements. Keywords: Deep Learning, License Plate, Font Evaluation
Authors: Zipeng Qi, Buhua Liu, Shiyan Zhang, Bao Li, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
Abstract: Large diffusion models have become mainstream generative models in both academic studies and industrial AIGC applications. Recently, a number of works further explored how to employ the power of large diffusion models as zero-shot classifiers. While recent zero-shot diffusion-based classifiers have made performance advancement on benchmark datasets, they still suffered badly from extremely slow classification speed (e.g., ~1000 seconds per classifying single image on ImageNet). The extremely slow classification speed strongly prohibits existing zero-shot diffusion-based classifiers from practical applications. In this paper, we propose an embarrassingly simple and efficient zero-shot Gaussian Diffusion Classifiers (GDC) via pretrained text-to-image diffusion models and DINOv2. The proposed GDC can not only significantly surpass previous zero-shot diffusion-based classifiers by over 10 points (61.40% - 71.44%) on ImageNet, but also accelerate more than 30000 times (1000 - 0.03 seconds) classifying a single image on ImageNet. Additionally, it provides probability interpretation of the results. Our extensive experiments further demonstrate that GDC can achieve highly competitive zero-shot classification performance over various datasets and can promisingly self-improve with stronger diffusion models. To the best of our knowledge, the proposed GDC is the first zero-shot diffusionbased classifier that exhibits both competitive accuracy and practical efficiency.
Authors: Shide Du, Zihan Fang, Yanchao Tan, Changwei Wang, Shiping Wang, Wenzhong Guo
Abstract: Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained; 2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. The code is released at https://github.com/dushide/OpenViewer.
Authors: Guanwenjie Zou, Liang Yao, Fan Liu, Chuanyi Zhang, Xin Li, Ning Chen, Shengxiang Xu, Jun Zhou
Abstract: Since high resolution remote sensing image classification often requires a relatively high computation complexity, lightweight models tend to be practical and efficient. Model pruning is an effective method for model compression. However, existing methods rarely take into account the specificity of remote sensing images, resulting in significant accuracy loss after pruning. To this end, we propose an effective structural pruning approach for remote sensing image classification. Specifically, a pruning strategy that amplifies the differences in channel importance of the model is introduced. Then an adaptive mining loss function is designed for the fine-tuning process of the pruned model. Finally, we conducted experiments on two remote sensing classification datasets. The experimental results demonstrate that our method achieves minimal accuracy loss after compressing remote sensing classification models, achieving state-of-the-art (SoTA) performance.
Authors: Jianan Ye, Weiguang Zhao, Xi Yang, Guangliang Cheng, Kaizhu Huang
Abstract: Point cloud anomaly detection under the anomaly-free setting poses significant challenges as it requires accurately capturing the features of 3D normal data to identify deviations indicative of anomalies. Current efforts focus on devising reconstruction tasks, such as acquiring normal data representations by restoring normal samples from altered, pseudo-anomalous counterparts. Our findings reveal that distributing attention equally across normal and pseudo-anomalous data tends to dilute the model's focus on anomalous deviations. The challenge is further compounded by the inherently disordered and sparse nature of 3D point cloud data. In response to those predicaments, we introduce an innovative approach that emphasizes learning point offsets, targeting more informative pseudo-abnormal points, thus fostering more effective distillation of normal data representations. We also have crafted an augmentation technique that is steered by normal vectors, facilitating the creation of credible pseudo anomalies that enhance the efficiency of the training process. Our comprehensive experimental evaluation on the Anomaly-ShapeNet and Real3D-AD datasets evidences that our proposed method outperforms existing state-of-the-art approaches, achieving an average enhancement of 9.0% and 1.4% in the AUC-ROC detection metric across these datasets, respectively.
Authors: Junjie Wang, Yuze Gao, Dongying Li, Wenxian Yu
Abstract: Detecting small targets in sea clutter is challenging due to dynamic maritime conditions. Existing solutions either model sea clutter for detection or extract target features based on clutter-target echo differences, including statistical and deep features. While more common, the latter often excels in controlled scenarios but struggles with robust detection and generalization in diverse environments, limiting practical use. In this letter, we propose a multi-domain features guided supervised contrastive learning (MDFG_SCL) method, which integrates statistical features derived from multi-domain differences with deep features obtained through supervised contrastive learning, thereby capturing both low-level domain-specific variations and high-level semantic information. This comprehensive feature integration enables the model to effectively distinguish between small targets and sea clutter, even under challenging conditions. Experiments conducted on real-world datasets demonstrate that the proposed shallow-to-deep detector not only achieves effective identification of small maritime targets but also maintains superior detection performance across varying sea conditions, outperforming the mainstream unsupervised contrastive learning and supervised contrastive learning methods.
Authors: Shiyu Hu, Daizong Liu, Wei Hu
Abstract: Deep learning models for point clouds have shown to be vulnerable to adversarial attacks, which have received increasing attention in various safety-critical applications such as autonomous driving, robotics, and surveillance. Existing 3D attackers generally design various attack strategies in the white-box setting, requiring the prior knowledge of 3D model details. However, real-world 3D applications are in the black-box setting, where we can only acquire the outputs of the target classifier. Although few recent works try to explore the black-box attack, they still achieve limited attack success rates (ASR). To alleviate this issue, this paper focuses on attacking the 3D models in a transfer-based black-box setting, where we first carefully design adversarial examples in a white-box surrogate model and then transfer them to attack other black-box victim models. Specifically, we propose a novel Spectral-aware Admix with Augmented Optimization method (SAAO) to improve the adversarial transferability. In particular, since traditional Admix strategy are deployed in the 2D domain that adds pixel-wise images for perturbing, we can not directly follow it to merge point clouds in coordinate domain as it will destroy the geometric shapes. Therefore, we design spectral-aware fusion that performs Graph Fourier Transform (GFT) to get spectral features of the point clouds and add them in the spectral domain. Afterward, we run a few steps with spectral-aware weighted Admix to select better optimization paths as well as to adjust corresponding learning weights. At last, we run more steps to generate adversarial spectral feature along the optimization path and perform Inverse-GFT on the adversarial spectral feature to obtain the adversarial example in the data domain. Experiments show that our SAAO achieves better transferability compared to existing 3D attack methods.
Authors: Ziheng Zhou, Jinxing Zhou, Wei Qian, Shengeng Tang, Xiaojun Chang, Dan Guo
Abstract: In the field of audio-visual learning, most research tasks focus exclusively on short videos. This paper focuses on the more practical Dense Audio-Visual Event Localization (DAVEL) task, advancing audio-visual scene understanding for longer, {untrimmed} videos. This task seeks to identify and temporally pinpoint all events simultaneously occurring in both audio and visual streams. Typically, each video encompasses dense events of multiple classes, which may overlap on the timeline, each exhibiting varied durations. Given these challenges, effectively exploiting the audio-visual relations and the temporal features encoded at various granularities becomes crucial. To address these challenges, we introduce a novel \ul{CC}Net, comprising two core modules: the Cross-Modal Consistency \ul{C}ollaboration (CMCC) and the Multi-Temporal Granularity \ul{C}ollaboration (MTGC). Specifically, the CMCC module contains two branches: a cross-modal interaction branch and a temporal consistency-gated branch. The former branch facilitates the aggregation of consistent event semantics across modalities through the encoding of audio-visual relations, while the latter branch guides one modality's focus to pivotal event-relevant temporal areas as discerned in the other modality. The MTGC module includes a coarse-to-fine collaboration block and a fine-to-coarse collaboration block, providing bidirectional support among coarse- and fine-grained temporal features. Extensive experiments on the UnAV-100 dataset validate our module design, resulting in a new state-of-the-art performance in dense audio-visual event localization. The code is available at \url{https://github.com/zzhhfut/CCNet-AAAI2025}.
Authors: Chengyan Liu, Linglan Zhao, Fan Lyu, Kaile Du, Fuyuan Hu, Tao Zhou
Abstract: Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task where models are required to continuously learn novel concepts with only a few training samples. Due to data scarcity, existing FSCIL methods resort to training a backbone with abundant base data and then keeping it frozen afterward. However, the above operation often causes the backbone to overfit to base classes while overlooking the novel ones, leading to severe confusion between them. To address this issue, we propose Class-Aware Logit Adapter (CALA). Our method involves a lightweight adapter that learns to rectify biased predictions through a pseudo-incremental learning paradigm. In the real FSCIL process, we use the learned adapter to dynamically generate robust balancing factors. These factors can adjust confused novel instances back to their true label space based on their similarity to base classes. Specifically, when confusion is more likely to occur in novel instances that closely resemble base classes, greater rectification is required. Notably, CALA operates on the classifier level, preserving the original feature space, thus it can be flexibly plugged into most of the existing FSCIL works for improved performance. Experiments on three benchmark datasets consistently validate the effectiveness and flexibility of CALA. Codes will be available upon acceptance.
Authors: Shuangping Huang, Hao Liang, Qingfeng Wang, Chulong Zhong, Zijian Zhou, Miaojing Shi
Abstract: Recently, developing unified medical image segmentation models gains increasing attention, especially with the advent of the Segment Anything Model (SAM). SAM has shown promising binary segmentation performance in natural domains, however, transferring it to the medical domain remains challenging, as medical images often possess substantial inter-category overlaps. To address this, we propose the SEmantic-Guided SAM (SEG-SAM), a unified medical segmentation model that incorporates semantic medical knowledge to enhance medical segmentation performance. First, to avoid the potential conflict between binary and semantic predictions, we introduce a semantic-aware decoder independent of SAM's original decoder, specialized for both semantic segmentation on the prompted object and classification on unprompted objects in images. To further enhance the model's semantic understanding, we solicit key characteristics of medical categories from large language models and incorporate them into SEG-SAM through a text-to-vision semantic module, adaptively transferring the language information into the visual segmentation task. In the end, we introduce the cross-mask spatial alignment strategy to encourage greater overlap between the predicted masks from SEG-SAM's two decoders, thereby benefiting both predictions. Extensive experiments demonstrate that SEG-SAM outperforms state-of-the-art SAM-based methods in unified binary medical segmentation and task-specific methods in semantic medical segmentation, showcasing promising results and potential for broader medical applications.
Authors: Abderrezzaq Sendjasni, Seif-Eddine Benkabou, Mohamed-Chaker Larabi
Abstract: This article presents a novel approach to improving the accuracy of 360-degree perceptual image quality assessment (IQA) through a two-fold patch selection process. Our methodology combines visual patch selection with embedding similarity-based refinement. The first stage focuses on selecting patches from 360-degree images using three distinct sampling methods to ensure comprehensive coverage of visual content for IQA. The second stage, which is the core of our approach, employs an embedding similarity-based selection process to filter and prioritize the most informative patches based on their embeddings similarity distances. This dual selection mechanism ensures that the training data is both relevant and informative, enhancing the model's learning efficiency. Extensive experiments and statistical analyses using three distance metrics across three benchmark datasets validate the effectiveness of our selection algorithm. The results highlight its potential to deliver robust and accurate 360-degree IQA, with performance gains of up to 4.5% in accuracy and monotonicity of quality score prediction, while using only 40% to 50% of the training patches. These improvements are consistent across various configurations and evaluation metrics, demonstrating the strength of the proposed method. The code for the selection process is available at: https://github.com/sendjasni/patch-selection-360-image-quality.
URLs: https://github.com/sendjasni/patch-selection-360-image-quality.
Authors: Guilin Zhu, Dongyue Wu, Changxin Gao, Runmin Wang, Weidong Yang, Nong Sang
Abstract: Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catastrophic forgetting by replaying distributions of previously learned classes using stored prototypes or features. However, they overlook a critical issue: in CISS, the representation of class knowledge is updated continuously through incremental learning, whereas prototype replay methods maintain fixed prototypes. This mismatch between updated representation and fixed prototypes limits the effectiveness of the prototype replay strategy. To address this issue, we propose the Adaptive prototype replay (Adapter) for CISS in this paper. Adapter comprises an adaptive deviation compen sation (ADC) strategy and an uncertainty-aware constraint (UAC) loss. Specifically, the ADC strategy dynamically updates the stored prototypes based on the estimated representation shift distance to match the updated representation of old class. The UAC loss reduces prediction uncertainty, aggregating discriminative features to aid in generating compact prototypes. Additionally, we introduce a compensation-based prototype similarity discriminative (CPD) loss to ensure adequate differentiation between similar prototypes, thereby enhancing the efficiency of the adaptive prototype replay strategy. Extensive experiments on Pascal VOC and ADE20K datasets demonstrate that Adapter achieves state-of-the-art results and proves effective across various CISS tasks, particularly in challenging multi-step scenarios. The code and model is available at https://github.com/zhu-gl-ux/Adapter.
Authors: Dongyue Wu, Zilin Guo, Li Yu, Nong Sang, Changxin Gao
Abstract: In recent years, semantic segmentation has flourished in various applications. However, the high computational cost remains a significant challenge that hinders its further adoption. The filter pruning method for structured network slimming offers a direct and effective solution for the reduction of segmentation networks. Nevertheless, we argue that most existing pruning methods, originally designed for image classification, overlook the fact that segmentation is a location-sensitive task, which consequently leads to their suboptimal performance when applied to segmentation networks. To address this issue, this paper proposes a novel approach, denoted as Spatial-aware Information Redundancy Filter Pruning~(SIRFP), which aims to reduce feature redundancy between channels. First, we formulate the pruning process as a maximum edge weight clique problem~(MEWCP) in graph theory, thereby minimizing the redundancy among the remaining features after pruning. Within this framework, we introduce a spatial-aware redundancy metric based on feature maps, thus endowing the pruning process with location sensitivity to better adapt to pruning segmentation networks. Additionally, based on the MEWCP, we propose a low computational complexity greedy strategy to solve this NP-hard problem, making it feasible and efficient for structured pruning. To validate the effectiveness of our method, we conducted extensive comparative experiments on various challenging datasets. The results demonstrate the superior performance of SIRFP for semantic segmentation tasks.
Authors: Wangyu Xue, Chen Qian, Jiayi Wu, Yang Zhou, Wentao Liu, Ju Ren, Siming Fan, Yaoxue Zhang
Abstract: Existing works on human-centric video understanding typically focus on analyzing specific moment or entire videos. However, many applications require higher precision at the frame level. In this work, we propose a novel task, BestShot, which aims to locate highlight frames within human-centric videos via language queries. This task demands not only a deep semantic comprehension of human actions but also precise temporal localization. To support this task, we introduce the BestShot Benchmark. %The benchmark is meticulously constructed by combining human detection and tracking, potential frame selection based on human judgment, and detailed textual descriptions crafted by human input to ensure precision. The benchmark is meticulously constructed by combining human-annotated highlight frames, detailed textual descriptions and duration labeling. These descriptions encompass three critical elements: (1) Visual content; (2) Fine-grained action; and (3) Human Pose Description. Together, these elements provide the necessary precision to identify the exact highlight frames in videos. To tackle this problem, we have collected two distinct datasets: (i) ShotGPT4o Dataset, which is algorithmically generated by GPT-4o and (ii) Image-SMPLText Dataset, a dataset with large-scale and accurate per-frame pose description leveraging PoseScript and existing pose estimation datasets. Based on these datasets, we present a strong baseline model, ShotVL, fine-tuned from InternVL, specifically for BestShot. We highlight the impressive zero-shot capabilities of our model and offer comparative analyses with existing SOTA models. ShotVL demonstrates a significant 52% improvement over InternVL on the BestShot Benchmark and a notable 57% improvement on the THUMOS14 Benchmark, all while maintaining the SOTA performance in general image classification and retrieval.
Authors: Rixin Zhou, Honglin Pang, Qian Zhang, Ruihua Qi, Xi Yang, Chuntao Li
Abstract: In real-world applications across specialized domains, addressing complex out-of-distribution (OOD) challenges is a common and significant concern. In this study, we concentrate on the task of fine-grained bronze ware dating, a critical aspect in the study of ancient Chinese history, and developed a benchmark dataset named ShiftedBronzes. By extensively expanding the bronze Ding dataset, ShiftedBronzes incorporates two types of bronze ware data and seven types of OOD data, which exhibit distribution shifts commonly encountered in bronze ware dating scenarios. We conduct benchmarking experiments on ShiftedBronzes and five commonly used general OOD datasets, employing a variety of widely adopted post-hoc, pre-trained Vision Large Model (VLM)-based and generation-based OOD detection methods. Through analysis of the experimental results, we validate previous conclusions regarding post-hoc, VLM-based, and generation-based methods, while also highlighting their distinct behaviors on specialized datasets. These findings underscore the unique challenges of applying general OOD detection methods to domain-specific tasks such as bronze ware dating. We hope that the ShiftedBronzes benchmark provides valuable insights into both the field of bronze ware dating and the and the development of OOD detection methods. The dataset and associated code will be available later.
Authors: Chen Chen, Liangjin Zhao, Yuanchun He, Yingxuan Long, Kaiqiang Chen, Zhirui Wang, Yanfeng Hu, Xian Sun
Abstract: Semantic segmentation and 3D reconstruction are two fundamental tasks in remote sensing, typically treated as separate or loosely coupled tasks. Despite attempts to integrate them into a unified network, the constraints between the two heterogeneous tasks are not explicitly modeled, since the pioneering studies either utilize a loosely coupled parallel structure or engage in only implicit interactions, failing to capture the inherent connections. In this work, we explore the connections between the two tasks and propose a new network that imposes semantic constraints on the stereo matching task, both implicitly and explicitly. Implicitly, we transform the traditional parallel structure to a new cascade structure termed Semantic-Guided Cascade structure, where the deep features enriched with semantic information are utilized for the computation of initial disparity maps, enhancing semantic guidance. Explicitly, we propose a Semantic Selective Refinement (SSR) module and a Left-Right Semantic Consistency (LRSC) module. The SSR refines the initial disparity map under the guidance of the semantic map. The LRSC ensures semantic consistency between two views via reducing the semantic divergence after transforming the semantic map from one view to the other using the disparity map. Experiments on the US3D and WHU datasets demonstrate that our method achieves state-of-the-art performance for both semantic segmentation and stereo matching.
Authors: Wenyu Zhang, Wei En Ng, Lixin Ma, Yuwen Wang, Jungqi Zhao, Boyang Li, Lu Wang
Abstract: Current vision-language models may incorporate single-dimensional spatial cues, such as depth, object boundary, and basic spatial directions (e.g. left, right, front, back), yet often lack the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. To address this gap, we develop SPHERE (Spatial Perception and Hierarchical Evaluation of REasoning), a hierarchical evaluation framework with a new human-annotated dataset to pinpoint model strengths and weaknesses, advancing from single-skill tasks to multi-skill tasks, and ultimately to complex reasoning tasks that require the integration of multiple spatial and visual cues with logical reasoning. Benchmark evaluation of state-of-the-art open-source models reveal significant shortcomings, especially in the abilities to understand distance and proximity, to reason from both allocentric and egocentric viewpoints, and to perform complex reasoning in a physical context. This work underscores the need for more advanced approaches to spatial understanding and reasoning, paving the way for improvements in vision-language models and their alignment with human-like spatial capabilities. The dataset will be open-sourced upon publication.
Authors: Wenyao Ni, Jiangrong Shen, Qi Xu, Huajin Tang
Abstract: Inspired by the human brain's ability to adapt to new tasks without erasing prior knowledge, we develop spiking neural networks (SNNs) with dynamic structures for Class Incremental Learning (CIL). Our comparative experiments reveal that limited datasets introduce biases in logits distributions among tasks. Fixed features from frozen past-task extractors can cause overfitting and hinder the learning of new tasks. To address these challenges, we propose the ALADE-SNN framework, which includes adaptive logit alignment for balanced feature representation and OtoN suppression to manage weights mapping frozen old features to new classes during training, releasing them during fine-tuning. This approach dynamically adjusts the network architecture based on analytical observations, improving feature extraction and balancing performance between new and old tasks. Experiment results show that ALADE-SNN achieves an average incremental accuracy of 75.42 on the CIFAR100-B0 benchmark over 10 incremental steps. ALADE-SNN not only matches the performance of DNN-based methods but also surpasses state-of-the-art SNN-based continual learning algorithms. This advancement enhances continual learning in neuromorphic computing, offering a brain-inspired, energy-efficient solution for real-time data processing.
Authors: Dapeng Zhang, Dayu Chen, Peng Zhi, Yinda Chen, Zhenlong Yuan, Chenyang Li, Sunjing, Rui Zhou, Qingguo Zhou
Abstract: Constructing online High-Definition (HD) maps is crucial for the static environment perception of autonomous driving systems (ADS). Existing solutions typically attempt to detect vectorized HD map elements with unified models; however, these methods often overlook the distinct characteristics of different non-cubic map elements, making accurate distinction challenging. To address these issues, we introduce an expert-based online HD map method, termed MapExpert. MapExpert utilizes sparse experts, distributed by our routers, to describe various non-cubic map elements accurately. Additionally, we propose an auxiliary balance loss function to distribute the load evenly across experts. Furthermore, we theoretically analyze the limitations of prevalent bird's-eye view (BEV) feature temporal fusion methods and introduce an efficient temporal fusion module called Learnable Weighted Moving Descentage. This module effectively integrates relevant historical information into the final BEV features. Combined with an enhanced slice head branch, the proposed MapExpert achieves state-of-the-art performance and maintains good efficiency on both nuScenes and Argoverse2 datasets.
Authors: Hanfang Liang, Yizhuo Yang, Jinming Hu, Jianfei Yang, Fen Liu, Shenghai Yuan
Abstract: Compact UAV systems, while advancing delivery and surveillance, pose significant security challenges due to their small size, which hinders detection by traditional methods. This paper presents a cost-effective, unsupervised UAV detection method using spatial-temporal sequence processing to fuse multiple LiDAR scans for accurate UAV tracking in real-world scenarios. Our approach segments point clouds into foreground and background, analyzes spatial-temporal data, and employs a scoring mechanism to enhance detection accuracy. Tested on a public dataset, our solution placed 4th in the CVPR 2024 UG2+ Challenge, demonstrating its practical effectiveness. We plan to open-source all designs, code, and sample data for the research community github.com/lianghanfang/UnLiDAR-UAV-Est.
Authors: Zhenxing Zhang, Yaxiong Wang, Lechao Cheng, Zhun Zhong, Dan Guo, Meng Wang
Abstract: We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4).Upon thorough examination, we observe that accurate fine-grained cross-modal semantic alignment between the image and text is vital for accurately manipulation detection and grounding. While existing DGM4 methods pay rare attention to the cross-modal alignment, hampering the accuracy of manipulation detecting to step further. To remedy this issue, this work targets to advance the semantic alignment learning to promote this task. Particularly, we utilize the off-the-shelf Multimodal Large-Language Models (MLLMs) and Large Language Models (LLMs) to construct paired image-text pairs, especially for the manipulated instances. Subsequently, a cross-modal alignment learning is performed to enhance the semantic alignment. Besides the explicit auxiliary clues, we further design a Manipulation-Guided Cross Attention (MGCA) to provide implicit guidance for augmenting the manipulation perceiving. With the grounding truth available during training, MGCA encourages the model to concentrate more on manipulated components while downplaying normal ones, enhancing the model's ability to capture manipulations. Extensive experiments are conducted on the DGM4 dataset, the results demonstrate that our model can surpass the comparison method with a clear margin.
Authors: Qi Zhou, Tianlin Li, Qing Guo, Dongxia Wang, Yun Lin, Yang Liu, Jin Song Dong
Abstract: Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mislead their responses. Existing defense methods show that such vision attacks are sensitive to image modifications especially cropping, using majority voting across responses of modified images as corrected responses. However, these modifications often result in partial images and distort the semantics, which reduces response quality on clean images after voting. Instead of directly using responses from partial images for voting, we investigate using them to supervise the LVLM's responses to the original images. We propose a black-box, training-free method called DPS (Defense through Partial-Perception Supervision). In this approach, the model is prompted using the responses generated by a model that perceives only a partial image. With DPS, the model can adjust its response based on partial image understanding when under attack, while confidently maintaining its original response for clean input. Our findings show that the weak model can supervise the strong model: when faced with an attacked input, the strong model becomes less confident and adjusts its response based on the weak model's partial understanding, effectively defending against the attack. With clean input, it confidently maintains its original response. Empirical experiments show our method outperforms the baseline, cutting the average attack success rate by 76.3% across six datasets on three popular models.
Authors: Xiaomeng Chu, Jiajun Deng, Guoliang You, Yifan Duan, Houqiang Li, Yanyong Zhang
Abstract: We propose Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection by the following insight. The Radar-Camera fusion in outdoor 3D scene perception is capped by the image-to-BEV transformation--if the depth of pixels is not accurately estimated, the naive combination of BEV features actually integrates unaligned visual content. To avoid this problem, we propose a query-based framework that enables adaptively sample instance-relevant features from both the BEV and the original image view. Furthermore, we enhance system performance by two key designs: optimizing query initialization and strengthening the representational capacity of BEV. For the former, we introduce an adaptive circular distribution in polar coordinates to refine the initialization of object queries, allowing for a distance-based adjustment of query density. For the latter, we initially incorporate a radar-guided depth head to refine the transformation from image view to BEV. Subsequently, we focus on leveraging the Doppler effect of radar and introduce an implicit dynamic catcher to capture the temporal elements within the BEV. Extensive experiments on nuScenes and View-of-Delft (VoD) datasets validate the merits of our design. Remarkably, our method achieves superior results of 64.9% mAP and 70.2% NDS on nuScenes, even outperforming several LiDAR-based detectors. RaCFormer also secures the 1st ranking on the VoD dataset. The code will be released.
Authors: Sebastian Weiss, Derek Bradley
Abstract: Gaussian Splatting has recently emerged as the go-to representation for reconstructing and rendering 3D scenes. The transition from 3D to 2D Gaussian primitives has further improved multi-view consistency and surface reconstruction accuracy. In this work we highlight the similarity between 2D Gaussian Splatting (2DGS) and billboards from traditional computer graphics. Both use flat semi-transparent 2D geometry that is positioned, oriented and scaled in 3D space. However 2DGS uses a solid color per splat and an opacity modulated by a Gaussian distribution, where billboards are more expressive, modulating the color with a uv-parameterized texture. We propose to unify these concepts by presenting Gaussian Billboards, a modification of 2DGS to add spatially-varying color achieved using per-splat texture interpolation. The result is a mixture of the two representations, which benefits from both the robust scene optimization power of 2DGS and the expressiveness of texture mapping. We show that our method can improve the sharpness and quality of the scene representation in a wide range of qualitative and quantitative evaluations compared to the original 2DGS implementation.
Authors: Mukai Li, Lei Li, Shansan Gong, Qi Liu
Abstract: Visual Language Models (VLMs) demonstrate impressive capabilities in processing multimodal inputs, yet applications such as visual agents, which require handling multiple images and high-resolution videos, demand enhanced long-range modeling. Moreover, existing open-source VLMs lack systematic exploration into extending their context length, and commercial models often provide limited details. To tackle this, we aim to establish an effective solution that enhances long context performance of VLMs while preserving their capacities in short context scenarios. Towards this goal, we make the best design choice through extensive experiment settings from data curation to context window extending and utilizing: (1) we analyze data sources and length distributions to construct ETVLM - a data recipe to balance the performance across scenarios; (2) we examine existing position extending methods, identify their limitations and propose M-RoPE++ as an enhanced approach; we also choose to solely instruction-tune the backbone with mixed-source data; (3) we discuss how to better utilize extended context windows and propose hybrid-resolution training. Built on the Qwen-VL series model, we propose Giraffe, which is effectively extended to 128K lengths. Evaluated on extensive long context VLM benchmarks such as VideoMME and Viusal Haystacks, our Giraffe achieves state-of-the-art performance among similarly sized open-source long VLMs and is competitive with commercial model GPT-4V. We will open-source the code, data, and models.
Authors: Yuqing Wang, Zhongling Huang, Shuxin Yang, Hao Tang, Xiaolan Qiu, Junwei Han, Dingwen Zhang
Abstract: PolSAR data presents unique challenges due to its rich and complex characteristics. Existing data representations, such as complex-valued data, polarimetric features, and amplitude images, are widely used. However, these formats often face issues related to usability, interpretability, and data integrity. Most feature extraction networks for PolSAR are small, limiting their ability to capture features effectively. To address these issues, We propose the Polarimetric Scattering Mechanism-Informed SAM (PolSAM), an enhanced Segment Anything Model (SAM) that integrates domain-specific scattering characteristics and a novel prompt generation strategy. PolSAM introduces Microwave Vision Data (MVD), a lightweight and interpretable data representation derived from polarimetric decomposition and semantic correlations. We propose two key components: the Feature-Level Fusion Prompt (FFP), which fuses visual tokens from pseudo-colored SAR images and MVD to address modality incompatibility in the frozen SAM encoder, and the Semantic-Level Fusion Prompt (SFP), which refines sparse and dense segmentation prompts using semantic information. Experimental results on the PhySAR-Seg datasets demonstrate that PolSAM significantly outperforms existing SAM-based and multimodal fusion models, improving segmentation accuracy, reducing data storage, and accelerating inference time. The source code and datasets will be made publicly available at \url{https://github.com/XAI4SAR/PolSAM}.
Authors: Matteo Sodano, Federico Magistri, Jens Behley, Cyrill Stachniss
Abstract: Perception is a key building block of autonomously acting vision systems such as autonomous vehicles. It is crucial that these systems are able to understand their surroundings in order to operate safely and robustly. Additionally, autonomous systems deployed in unconstrained real-world scenarios must be able of dealing with novel situations and object that have never been seen before. In this article, we tackle the problem of open-world panoptic segmentation, i.e., the task of discovering new semantic categories and new object instances at test time, while enforcing consistency among the categories that we incrementally discover. We propose Con2MAV, an approach for open-world panoptic segmentation that extends our previous work, ContMAV, which was developed for open-world semantic segmentation. Through extensive experiments across multiple datasets, we show that our model achieves state-of-the-art results on open-world segmentation tasks, while still performing competitively on the known categories. We will open-source our implementation upon acceptance. Additionally, we propose PANIC (Panoptic ANomalies In Context), a benchmark for evaluating open-world panoptic segmentation in autonomous driving scenarios. This dataset, recorded with a multi-modal sensor suite mounted on a car, provides high-quality, pixel-wise annotations of anomalous objects at both semantic and instance level. Our dataset contains 800 images, with more than 50 unknown classes, i.e., classes that do not appear in the training set, and 4000 object instances, making it an extremely challenging dataset for open-world segmentation tasks in the autonomous driving scenario. We provide competitions for multiple open-world tasks on a hidden test set. Our dataset and competitions are available at https://www.ipb.uni-bonn.de/data/panic.
Authors: Yingyan Xu, Kate Gadola, Prashanth Chandran, Sebastian Weiss, Markus Gross, Gaspard Zoss, Derek Bradley
Abstract: We present a new method for reconstructing the appearance properties of human faces from a lightweight capture procedure in an unconstrained environment. Our method recovers the surface geometry, diffuse albedo, specular intensity and specular roughness from a monocular video containing a simple head rotation in-the-wild. Notably, we make no simplifying assumptions on the environment lighting, and we explicitly take visibility and occlusions into account. As a result, our method can produce facial appearance maps that approach the fidelity of studio-based multi-view captures, but with a far easier and cheaper procedure.
Authors: Vivek Madhavaram, Shivangana Rawat, Chaitanya Devaguptapu, Charu Sharma, Manohar Kaul
Abstract: Text driven diffusion models have shown remarkable capabilities in editing images. However, when editing 3D scenes, existing works mostly rely on training a NeRF for 3D editing. Recent NeRF editing methods leverages edit operations by deploying 2D diffusion models and project these edits into 3D space. They require strong positional priors alongside text prompt to identify the edit location. These methods are operational on small 3D scenes and are more generalized to particular scene. They require training for each specific edit and cannot be exploited in real-time edits. To address these limitations, we propose a novel method, FreeEdit, to make edits in training free manner using mesh representations as a substitute for NeRF. Training-free methods are now a possibility because of the advances in foundation model's space. We leverage these models to bring a training-free alternative and introduce solutions for insertion, replacement and deletion. We consider insertion, replacement and deletion as basic blocks for performing intricate edits with certain combinations of these operations. Given a text prompt and a 3D scene, our model is capable of identifying what object should be inserted/replaced or deleted and location where edit should be performed. We also introduce a novel algorithm as part of FreeEdit to find the optimal location on grounding object for placement. We evaluate our model by comparing it with baseline models on a wide range of scenes using quantitative and qualitative metrics and showcase the merits of our method with respect to others.
Authors: Shoukun Sun, Min Xian, Tiankai Yao, Fei Xu, Luca Capriotti
Abstract: Producing large images using small diffusion models is gaining increasing popularity, as the cost of training large models could be prohibitive. A common approach involves jointly generating a series of overlapped image patches and obtaining large images by merging adjacent patches. However, results from existing methods often exhibit obvious artifacts, e.g., seams and inconsistent objects and styles. To address the issues, we proposed Guided Fusion (GF), which mitigates the negative impact from distant image regions by applying a weighted average to the overlapping regions. Moreover, we proposed Variance-Corrected Fusion (VCF), which corrects data variance at post-averaging, generating more accurate fusion for the Denoising Diffusion Probabilistic Model. Furthermore, we proposed a one-shot Style Alignment (SA), which generates a coherent style for large images by adjusting the initial input noise without adding extra computational burden. Extensive experiments demonstrated that the proposed fusion methods improved the quality of the generated image significantly. As a plug-and-play module, the proposed method can be widely applied to enhance other fusion-based methods for large image generation.
Authors: Leo Segre, Shai Avidan
Abstract: Neural Radiance Fields (NeRF) have advanced photorealistic novel view synthesis, but their reliance on photometric reconstruction introduces artifacts, commonly known as "floaters". These artifacts degrade novel view quality, especially in areas unseen by the training cameras. We present a fast, post-hoc NeRF cleanup method that eliminates such artifacts by enforcing our Free Space Prior, effectively minimizing floaters without disrupting the NeRF's representation of observed regions. Unlike existing approaches that rely on either Maximum Likelihood (ML) estimation to fit the data or a complex, local data-driven prior, our method adopts a Maximum-a-Posteriori (MAP) approach, selecting the optimal model parameters under a simple global prior assumption that unseen regions should remain empty. This enables our method to clean artifacts in both seen and unseen areas, enhancing novel view quality even in challenging scene regions. Our method is comparable with existing NeRF cleanup models while being 2.5x faster in inference time, requires no additional memory beyond the original NeRF, and achieves cleanup training in less than 30 seconds. Our code will be made publically available.
Authors: Amalia Foka
Abstract: This paper proposes a novel interdisciplinary framework for the critical evaluation of text-to-image models, addressing the limitations of current technical metrics and bias studies. By integrating art historical analysis, artistic exploration, and critical prompt engineering, the framework offers a more nuanced understanding of these models' capabilities and societal implications. Art historical analysis provides a structured approach to examine visual and symbolic elements, revealing potential biases and misrepresentations. Artistic exploration, through creative experimentation, uncovers hidden potentials and limitations, prompting critical reflection on the algorithms' assumptions. Critical prompt engineering actively challenges the model's assumptions, exposing embedded biases. Case studies demonstrate the framework's practical application, showcasing how it can reveal biases related to gender, race, and cultural representation. This comprehensive approach not only enhances the evaluation of text-to-image models but also contributes to the development of more equitable, responsible, and culturally aware AI systems.
Authors: Chengzhou Yu (South China University of Technology), Huihui Fang (Pazhou Laboratory), Hongqiu Wang (The Hong Kong University of Science,Technology), Ting Deng (South China University of Technology), Qing Du (South China University of Technology), Yanwu Xu (South China University of Technology), Weihua Yang (Shenzhen Eye Hospital)
Abstract: Fundus imaging is a critical tool in ophthalmology, with different imaging modalities offering unique advantages. For instance, fundus fluorescein angiography (FFA) can accurately identify eye diseases. However, traditional invasive FFA involves the injection of sodium fluorescein, which can cause discomfort and risks. Generating corresponding FFA images from non-invasive fundus images holds significant practical value but also presents challenges. First, limited datasets constrain the performance and effectiveness of models. Second, previous studies have primarily focused on generating FFA for single diseases or single modalities, often resulting in poor performance for patients with various ophthalmic conditions. To address these issues, we propose a novel latent diffusion model-based framework, Diffusion, which introduces a fine-tuning protocol to overcome the challenge of limited medical data and unleash the generative capabilities of diffusion models. Furthermore, we designed a new approach to tackle the challenges of generating across different modalities and disease types. On limited datasets, our framework achieves state-of-the-art results compared to existing methods, offering significant potential to enhance ophthalmic diagnostics and patient care. Our code will be released soon to support further research in this field.
Authors: Zhiguang Lu, Qianqian Xu, Shilong Bao, Zhiyong Yang, Qingming Huang
Abstract: This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method.
Authors: Siyuan Wang, Dianyi Wang, Chengxing Zhou, Zejun Li, Zhihao Fan, Xuanjing Huang, Zhongyu Wei
Abstract: Large Vision-Language Models (LVLMs) typically learn visual capacity through visual instruction tuning, involving updates to both a projector and their LLM backbones. Drawing inspiration from the concept of visual region in the human brain, we investigate the existence of an analogous \textit{visual region} within LLMs that functions as a cognitive core, and explore the possibility of efficient training of LVLMs via selective layers tuning. We use Bunny-Llama-3-8B-V for detailed experiments and LLaVA-1.5-7B and LLaVA-1.5-13B for validation across a range of visual and textual tasks. Our findings reveal that selectively updating 25\% of LLMs layers, when sparsely and uniformly distributed, can preserve nearly 99\% of visual performance while maintaining or enhancing textual task results, and also effectively reducing training time. Based on this targeted training approach, we further propose a novel visual region-based pruning paradigm, removing non-critical layers outside the visual region, which can achieve minimal performance loss. This study offers an effective and efficient strategy for LVLM training and inference by activating a layer-wise visual region within LLMs, which is consistently effective across different models and parameter scales.
Authors: Kanghoon Yoon, Kibum Kim, Jaehyung Jeon, Yeonjun In, Donghyun Kim, Chanyoung Park
Abstract: Scene Graph Generation (SGG) research has suffered from two fundamental challenges: the long-tailed predicate distribution and semantic ambiguity between predicates. These challenges lead to a bias towards head predicates in SGG models, favoring dominant general predicates while overlooking fine-grained predicates. In this paper, we address the challenges of SGG by framing it as multi-label classification problem with partial annotation, where relevant labels of fine-grained predicates are missing. Under the new frame, we propose Retrieval-Augmented Scene Graph Generation (RA-SGG), which identifies potential instances to be multi-labeled and enriches the single-label with multi-labels that are semantically similar to the original label by retrieving relevant samples from our established memory bank. Based on augmented relations (i.e., discovered multi-labels), we apply multi-prototype learning to train our SGG model. Several comprehensive experiments have demonstrated that RA-SGG outperforms state-of-the-art baselines by up to 3.6% on VG and 5.9% on GQA, particularly in terms of F@K, showing that RA-SGG effectively alleviates the issue of biased prediction caused by the long-tailed distribution and semantic ambiguity of predicates.
Authors: Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin, Liu Qin, Ziyao Chen, Qing Gu
Abstract: Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locating the temporal location of event, as the relevant supervision is unavailable. Existing methods rely on explicit alignment constraints between event locations and captions, which involve complex event proposal procedures during both training and inference. To tackle this problem, we propose a novel implicit location-caption alignment paradigm by complementary masking, which simplifies the complex event proposal and localization process while maintaining effectiveness. Specifically, our model comprises two components: a dual-mode video captioning module and a mask generation module. The dual-mode video captioning module captures global event information and generates descriptive captions, while the mask generation module generates differentiable positive and negative masks for localizing the events. These masks enable the implicit alignment of event locations and captions by ensuring that captions generated from positively and negatively masked videos are complementary, thereby forming a complete video description. In this way, even under weak supervision, the event location and event caption can be aligned implicitly. Extensive experiments on the public datasets demonstrate that our method outperforms existing weakly-supervised methods and achieves competitive results compared to fully-supervised methods.
Authors: Shizhuo Deng, Bowen Han, Jiaqi Chen, Hao Wang, Dongyue Chen, Tong Jia
Abstract: Noisy labels threaten the robustness of few-shot learning (FSL) due to the inexact features in a new domain. CLIP, a large-scale vision-language model, performs well in FSL on image-text embedding similarities, but it is susceptible to misclassification caused by noisy labels. How to enhance domain generalization of CLIP on noisy data within FSL tasks is a critical challenge. In this paper, we provide a novel view to mitigate the influence of noisy labels, CLIP-based Robust Few-shot learning (CRoF). CRoF is a general plug-in module for CLIP-based models. To avoid misclassification and confused label embedding, we design the few-shot task-oriented prompt generator to give more discriminative descriptions of each category. The proposed prompt achieves larger distances of inter-class textual embedding. Furthermore, rather than fully trusting zero-shot classification by CLIP, we fine-tune CLIP on noisy few-shot data in a new domain with a weighting strategy like label-smooth. The weights for multiple potentially correct labels consider the relationship between CLIP's prior knowledge and original label information to ensure reliability. Our multiple label loss function further supports robust training under this paradigm. Comprehensive experiments show that CRoF, as a plug-in, outperforms fine-tuned and vanilla CLIP models on different noise types and noise ratios.
Authors: Shiqi Huang, Shuting He, Bihan Wen
Abstract: Instance segmentation algorithms in remote sensing are typically based on conventional methods, limiting their application to seen scenarios and closed-set predictions. In this work, we propose a novel task called zero-shot remote sensing instance segmentation, aimed at identifying aerial objects that are absent from training data. Challenges arise when classifying aerial categories with high inter-class similarity and intra-class variance. Besides, the domain gap between vision-language models' pretraining datasets and remote sensing datasets hinders the zero-shot capabilities of the pretrained model when it is directly applied to remote sensing images. To address these challenges, we propose a $\textbf{Z}$ero-Sh$\textbf{o}$t $\textbf{R}$emote Sensing $\textbf{I}$nstance Segmentation framework, dubbed $\textbf{ZoRI}$. Our approach features a discrimination-enhanced classifier that uses refined textual embeddings to increase the awareness of class disparities. Instead of direct fine-tuning, we propose a knowledge-maintained adaptation strategy that decouples semantic-related information to preserve the pretrained vision-language alignment while adjusting features to capture remote sensing domain-specific visual cues. Additionally, we introduce a prior-injected prediction with cache bank of aerial visual prototypes to supplement the semantic richness of text embeddings and seamlessly integrate aerial representations, adapting to the remote sensing domain. We establish new experimental protocols and benchmarks, and extensive experiments convincingly demonstrate that ZoRI achieves the state-of-art performance on the zero-shot remote sensing instance segmentation task. Our code is available at https://github.com/HuangShiqi128/ZoRI.
Authors: Yiheng Li, Yang Yang, Zhen Lei
Abstract: In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera Transformer (RCTrans). Specifically, we first design a Radar Dense Encoder to enrich the sparse valid radar tokens, and then concatenate them with the image tokens. By doing this, we can fully explore the 3D information of each interest region and reduce the interference of empty tokens during the fusing stage. We then design a Pruning Sequential Decoder to predict 3D boxes based on the obtained tokens and random initialized queries. To alleviate the effect of elevation ambiguity in radar point clouds, we gradually locate the position of the object via a sequential fusion structure. It helps to get more precise and flexible correspondences between tokens and queries. A pruning training strategy is adopted in the decoder, which can save much time during inference and inhibit queries from losing their distinctiveness. Extensive experiments on the large-scale nuScenes dataset prove the superiority of our method, and we also achieve new state-of-the-art radar-camera 3D detection results. Our implementation is available at https://github.com/liyih/RCTrans.
Authors: Yuhong Chen, Ailin Song, Huifeng Yin, Shuai Zhong, Fuhai Chen, Qi Xu, Shiping Wang, Mingkun Xu
Abstract: The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain's adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multi-view incremental framework named MVIL aimed at emulating the brain's fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating a fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network's capacity for generalization. Experimental results on six benchmark datasets show MVIL's effectiveness over state-of-the-art methods.
Authors: Yaohui Ma, Xiaopeng Hong, Shizhou Zhang, Huiyun Li, Zhilin Zhu, Wei Luo, Zhiheng Ma
Abstract: Large multimodal language models (MLLMs) have revolutionized natural language processing and visual understanding, but often contain outdated or inaccurate information. Current multimodal knowledge editing evaluations are limited in scope and potentially biased, focusing on narrow tasks and failing to assess the impact on in-domain samples. To address these issues, we introduce ComprehendEdit, a comprehensive benchmark comprising eight diverse tasks from multiple datasets. We propose two novel metrics: Knowledge Generalization Index (KGI) and Knowledge Preservation Index (KPI), which evaluate editing effects on in-domain samples without relying on AI-synthetic samples. Based on insights from our framework, we establish Hierarchical In-Context Editing (HICE), a baseline method employing a two-stage approach that balances performance across all metrics. This study provides a more comprehensive evaluation framework for multimodal knowledge editing, reveals unique challenges in this field, and offers a baseline method demonstrating improved performance. Our work opens new perspectives for future research and provides a foundation for developing more robust and effective editing techniques for MLLMs. The ComprehendEdit benchmark and implementation code are available at https://github.com/yaohui120/ComprehendEdit.
Authors: Abhishek Trivedi, Sourajit Mukherjee, Rajat Kumar Singh, Vani Agarwal, Sriranjani Ramakrishnan, Himanshu S. Bhatt
Abstract: Extraction of transaction information from bank statements is required to assess one's financial well-being for credit rating and underwriting decisions. Unlike other financial documents such as tax forms or financial statements, extracting the transaction descriptions from bank statements can provide a comprehensive and recent view into the cash flows and spending patterns. With multiple variations in layout and templates across several banks, extracting transactional level information from different table categories is an arduous task. Existing table structure recognition approaches produce sub optimal results for long, complex tables and are unable to capture all transactions accurately. This paper proposes TabSniper, a novel approach for efficient table detection, categorization and structure recognition from bank statements. The pipeline starts with detecting and categorizing tables of interest from the bank statements. The extracted table regions are then processed by the table structure recognition model followed by a post-processing module to transform the transactional data into a structured and standardised format. The detection and structure recognition architectures are based on DETR, fine-tuned with diverse bank statements along with additional feature enhancements. Results on challenging datasets demonstrate that TabSniper outperforms strong baselines and produces high-quality extraction of transaction information from bank and other financial documents across multiple layouts and templates.
Authors: Elena Bueno-Benito, Mariella Dimiccoli
Abstract: This paper presents a simple yet effective approach for the poorly investigated task of global action segmentation, aiming at grouping frames capturing the same action across videos of different activities. Unlike the case of videos depicting all the same activity, the temporal order of actions is not roughly shared among all videos, making the task even more challenging. We propose to use activity labels to learn, in a weakly-supervised fashion, action representations suitable for global action segmentation. For this purpose, we introduce a triadic learning approach for video pairs, to ensure intra-video action discrimination, as well as inter-video and inter-activity action association. For the backbone architecture, we use a Siamese network based on sparse transformers that takes as input video pairs and determine whether they belong to the same activity. The proposed approach is validated on two challenging benchmark datasets: Breakfast and YouTube Instructions, outperforming state-of-the-art methods.
Authors: Xinyu He (College of Intelligence and Computing, Tianjin University, Tianjin, China), Xinhui Li (College of Intelligence and Computing, Tianjin University, Tianjin, China), Xiaojie Guo (College of Intelligence and Computing, Tianjin University, Tianjin, China)
Abstract: Domain adaptive object detection (DAOD) aims to generalize an object detector trained on labeled source-domain data to a target domain without annotations, the core principle of which is \emph{source-target feature alignment}. Typically, existing approaches employ adversarial learning to align the distributions of the source and target domains as a whole, barely considering the varying significance of distinct regions, say instances under different circumstances and foreground \emph{vs} background areas, during feature alignment. To overcome the shortcoming, we investigates a differential feature alignment strategy. Specifically, a prediction-discrepancy feedback instance alignment module (dubbed PDFA) is designed to adaptively assign higher weights to instances of higher teacher-student detection discrepancy, effectively handling heavier domain-specific information. Additionally, an uncertainty-based foreground-oriented image alignment module (UFOA) is proposed to explicitly guide the model to focus more on regions of interest. Extensive experiments on widely-used DAOD datasets together with ablation studies are conducted to demonstrate the efficacy of our proposed method and reveal its superiority over other SOTA alternatives. Our code is available at https://github.com/EstrellaXyu/Differential-Alignment-for-DAOD.
URLs: https://github.com/EstrellaXyu/Differential-Alignment-for-DAOD.
Authors: Zheng Cheng, Rendong Wang, Zhicheng Wang
Abstract: Recently, multi-modal large language models have made significant progress. However, visual information lacking of guidance from the user's intention may lead to redundant computation and involve unnecessary visual noise, especially in long, untrimmed videos. To address this issue, we propose FocusChat, a text-guided multi-modal large language model (LLM) that emphasizes visual information correlated to the user's prompt. In detail, Our model first undergoes the semantic extraction module, which comprises a visual semantic branch and a text semantic branch to extract image and text semantics, respectively. The two branches are combined using the Spatial-Temporal Filtering Module (STFM). STFM enables explicit spatial-level information filtering and implicit temporal-level feature filtering, ensuring that the visual tokens are closely aligned with the user's query. It lowers the essential number of visual tokens inputted into the LLM. FocusChat significantly outperforms Video-LLaMA in zero-shot experiments, using an order of magnitude less training data with only 16 visual tokens occupied. It achieves results comparable to the state-of-the-art in few-shot experiments, with only 0.72M pre-training data.
Authors: Xiaxin Zhu, Fangming Guo, Xianlei Long, Qingyi Gu, Chao Chen, Fuqiang Gu
Abstract: Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at least 7.30% and 3.30% mIoU, respectively, with extremely 5.48x lower energy consumption and 1.14x faster inference speed.
Authors: Christopher Thirgood, Oscar Mendez, Erin Chao Ling, Jon Storey, Simon Hadfield
Abstract: We introduce HyperGS, a novel framework for Hyperspectral Novel View Synthesis (HNVS), based on a new latent 3D Gaussian Splatting (3DGS) technique. Our approach enables simultaneous spatial and spectral renderings by encoding material properties from multi-view 3D hyperspectral datasets. HyperGS reconstructs high-fidelity views from arbitrary perspectives with improved accuracy and speed, outperforming currently existing methods. To address the challenges of high-dimensional data, we perform view synthesis in a learned latent space, incorporating a pixel-wise adaptive density function and a pruning technique for increased training stability and efficiency. Additionally, we introduce the first HNVS benchmark, implementing a number of new baselines based on recent SOTA RGB-NVS techniques, alongside the small number of prior works on HNVS. We demonstrate HyperGS's robustness through extensive evaluation of real and simulated hyperspectral scenes with a 14db accuracy improvement upon previously published models.
Authors: Qingqing Fang, Qinliang Su, Wenxi Lv, Wenchao Xu, Jianxing Yu
Abstract: Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and generalization ability of neural networks, some anomalies can also be well reconstructed, resulting in unsatisfactory detection and localization accuracy. In this paper, a small coarsely-labeled anomaly dataset is first collected. Then, a coarse-knowledge-aware adversarial learning method is developed to align the distribution of reconstructed features with that of normal features. The alignment can effectively suppress the auto-encoder's reconstruction ability on anomalies and thus improve the detection accuracy. Considering that anomalies often only occupy very small areas in anomalous images, a patch-level adversarial learning strategy is further developed. Although no patch-level anomalous information is available, we rigorously prove that by simply viewing any patch features from anomalous images as anomalies, the proposed knowledge-aware method can also align the distribution of reconstructed patch features with the normal ones. Experimental results on four medical datasets and two industrial datasets demonstrate the effectiveness of our method in improving the detection and localization performance.
Authors: Zhengdi Yu, Stefanos Zafeiriou, Tolga Birdal
Abstract: We propose Dyn-HaMR, to the best of our knowledge, the first approach to reconstruct 4D global hand motion from monocular videos recorded by dynamic cameras in the wild. Reconstructing accurate 3D hand meshes from monocular videos is a crucial task for understanding human behaviour, with significant applications in augmented and virtual reality (AR/VR). However, existing methods for monocular hand reconstruction typically rely on a weak perspective camera model, which simulates hand motion within a limited camera frustum. As a result, these approaches struggle to recover the full 3D global trajectory and often produce noisy or incorrect depth estimations, particularly when the video is captured by dynamic or moving cameras, which is common in egocentric scenarios. Our Dyn-HaMR consists of a multi-stage, multi-objective optimization pipeline, that factors in (i) simultaneous localization and mapping (SLAM) to robustly estimate relative camera motion, (ii) an interacting-hand prior for generative infilling and to refine the interaction dynamics, ensuring plausible recovery under (self-)occlusions, and (iii) hierarchical initialization through a combination of state-of-the-art hand tracking methods. Through extensive evaluations on both in-the-wild and indoor datasets, we show that our approach significantly outperforms state-of-the-art methods in terms of 4D global mesh recovery. This establishes a new benchmark for hand motion reconstruction from monocular video with moving cameras. Our project page is at https://dyn-hamr.github.io/.
Authors: Samuel Teodoro, Agus Gunawan, Soo Ye Kim, Jihyong Oh, Munchurl Kim
Abstract: Recent AI-based video editing has enabled users to edit videos through simple text prompts, significantly simplifying the editing process. However, recent zero-shot video editing techniques primarily focus on global or single-object edits, which can lead to unintended changes in other parts of the video. When multiple objects require localized edits, existing methods face challenges, such as unfaithful editing, editing leakage, and lack of suitable evaluation datasets and metrics. To overcome these limitations, we propose a zero-shot $\textbf{M}$ulti-$\textbf{I}$nstance $\textbf{V}$ideo $\textbf{E}$diting framework, called MIVE. MIVE is a general-purpose mask-based framework, not dedicated to specific objects (e.g., people). MIVE introduces two key modules: (i) Disentangled Multi-instance Sampling (DMS) to prevent editing leakage and (ii) Instance-centric Probability Redistribution (IPR) to ensure precise localization and faithful editing. Additionally, we present our new MIVE Dataset featuring diverse video scenarios and introduce the Cross-Instance Accuracy (CIA) Score to evaluate editing leakage in multi-instance video editing tasks. Our extensive qualitative, quantitative, and user study evaluations demonstrate that MIVE significantly outperforms recent state-of-the-art methods in terms of editing faithfulness, accuracy, and leakage prevention, setting a new benchmark for multi-instance video editing. The project page is available at https://kaist-viclab.github.io/mive-site/
Authors: Hichem Sahbi
Abstract: Magnitude Pruning is a staple lightweight network design method which seeks to remove connections with the smallest magnitude. This process is either achieved in a structured or unstructured manner. While structured pruning allows reaching high efficiency, unstructured one is more flexible and leads to better accuracy, but this is achieved at the expense of low computational performance. In this paper, we devise a novel coarse-to-fine (CTF) method that gathers the advantages of structured and unstructured pruning while discarding their inconveniences to some extent. Our method relies on a novel CTF parametrization that models the mask of each connection as the Hadamard product involving four parametrizations which capture channel-wise, column-wise, row-wise and entry-wise pruning respectively. Hence, fine-grained pruning is enabled only when the coarse-grained one is disabled, and this leads to highly efficient networks while being effective. Extensive experiments conducted on the challenging task of skeleton-based recognition, using the standard SBU and FPHA datasets, show the clear advantage of our CTF approach against different baselines as well as the related work.
Authors: Zhongjie Duan, Qianyi Zhao, Cen Chen, Daoyuan Chen, Wenmeng Zhou, Yaliang Li, Yingda Chen
Abstract: The emergence of diffusion models has significantly advanced image synthesis. The recent studies of model interaction and self-corrective reasoning approach in large language models offer new insights for enhancing text-to-image models. Inspired by these studies, we propose a novel method called ArtAug for enhancing text-to-image models in this paper. To the best of our knowledge, ArtAug is the first one that improves image synthesis models via model interactions with understanding models. In the interactions, we leverage human preferences implicitly learned by image understanding models to provide fine-grained suggestions for image synthesis models. The interactions can modify the image content to make it aesthetically pleasing, such as adjusting exposure, changing shooting angles, and adding atmospheric effects. The enhancements brought by the interaction are iteratively fused into the synthesis model itself through an additional enhancement module. This enables the synthesis model to directly produce aesthetically pleasing images without any extra computational cost. In the experiments, we train the ArtAug enhancement module on existing text-to-image models. Various evaluation metrics consistently demonstrate that ArtAug enhances the generative capabilities of text-to-image models without incurring additional computational costs. The source code and models will be released publicly.
Authors: Shijing Wang, Yaping Huang
Abstract: Uncertainty in gaze estimation manifests in two aspects: 1) low-quality images caused by occlusion, blurriness, inconsistent eye movements, or even non-face images; 2) incorrect labels resulting from the misalignment between the labeled and actual gaze points during the annotation process. Allowing these uncertainties to participate in training hinders the improvement of gaze estimation. To tackle these challenges, in this paper, we propose an effective solution, named Suppressing Uncertainty in Gaze Estimation (SUGE), which introduces a novel triplet-label consistency measurement to estimate and reduce the uncertainties. Specifically, for each training sample, we propose to estimate a novel ``neighboring label'' calculated by a linearly weighted projection from the neighbors to capture the similarity relationship between image features and their corresponding labels, which can be incorporated with the predicted pseudo label and ground-truth label for uncertainty estimation. By modeling such triplet-label consistency, we can measure the qualities of both images and labels, and further largely reduce the negative effects of unqualified images and wrong labels through our designed sample weighting and label correction strategies. Experimental results on the gaze estimation benchmarks indicate that our proposed SUGE achieves state-of-the-art performance.
Authors: Xing Liufu, Chaolei Tan, Xiaotong Lin, Yonggang Qi, Jinxuan Li, Jian-Fang Hu
Abstract: Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse ``uncertainties'' in a data-driven fashion. Specifically, we inject a lightweight module (~ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model's superiority.
Authors: Nikitha SR, Tarun Ram Menta, Mausoom Sarkar
Abstract: The advent of multimodal learning has brought a significant improvement in document AI. Documents are now treated as multimodal entities, incorporating both textual and visual information for downstream analysis. However, works in this space are often focused on the textual aspect, using the visual space as auxiliary information. While some works have explored pure vision based techniques for document image understanding, they require OCR identified text as input during inference, or do not align with text in their learning procedure. Therefore, we present a novel image-text alignment technique specially designed for leveraging the textual information in document images to improve performance on visual tasks. Our document encoder model DoPTA - trained with this technique demonstrates strong performance on a wide range of document image understanding tasks, without requiring OCR during inference. Combined with an auxiliary reconstruction objective, DoPTA consistently outperforms larger models, while using significantly lesser pre-training compute. DoPTA also sets new state-of-the art results on D4LA, and FUNSD, two challenging document visual analysis benchmarks.
Authors: Wonseok Roh, Hwanhee Jung, Jong Wook Kim, Seunggwan Lee, Innfarn Yoo, Andreas Lugmayr, Seunggeun Chi, Karthik Ramani, Sangpil Kim
Abstract: Recently, generalizable feed-forward methods based on 3D Gaussian Splatting have gained significant attention for their potential to reconstruct 3D scenes using finite resources. These approaches create a 3D radiance field, parameterized by per-pixel 3D Gaussian primitives, from just a few images in a single forward pass. However, unlike multi-view methods that benefit from cross-view correspondences, 3D scene reconstruction with a single-view image remains an underexplored area. In this work, we introduce CATSplat, a novel generalizable transformer-based framework designed to break through the inherent constraints in monocular settings. First, we propose leveraging textual guidance from a visual-language model to complement insufficient information from a single image. By incorporating scene-specific contextual details from text embeddings through cross-attention, we pave the way for context-aware 3D scene reconstruction beyond relying solely on visual cues. Moreover, we advocate utilizing spatial guidance from 3D point features toward comprehensive geometric understanding under single-view settings. With 3D priors, image features can capture rich structural insights for predicting 3D Gaussians without multi-view techniques. Extensive experiments on large-scale datasets demonstrate the state-of-the-art performance of CATSplat in single-view 3D scene reconstruction with high-quality novel view synthesis.
Authors: Zixiang Li, Yue Song, Renshuai Tao, Xiaohong Jia, Yao Zhao, Wei Wang
Abstract: Although diffusion models have achieved remarkable success in the field of image generation, their latent space remains under-explored. Current methods for identifying semantics within latent space often rely on external supervision, such as textual information and segmentation masks. In this paper, we propose a method to identify semantic attributes in the latent space of pre-trained diffusion models without any further training. By projecting the Jacobian of the targeted semantic region into a low-dimensional subspace which is orthogonal to the non-masked regions, our approach facilitates precise semantic discovery and control over local masked areas, eliminating the need for annotations. We conducted extensive experiments across multiple datasets and various architectures of diffusion models, achieving state-of-the-art performance. In particular, for some specific face attributes, the performance of our proposed method even surpasses that of supervised approaches, demonstrating its superior ability in editing local image properties.
Authors: Zihui Cheng, Qiguang Chen, Jin Zhang, Hao Fei, Xiaocheng Feng, Wanxiang Che, Min Li, Libo Qin
Abstract: Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output, which leads to significant drawbacks such as missing visual operations and vague expressions. Motivated by this, we introduce a novel Chain of Multi-modal Thought (CoMT) benchmark to address these limitations. Different from the traditional MCoT benchmark, CoMT requires both multi-modal input and multi-modal reasoning output, aiming to mimic human-like reasoning that inherently integrates visual operation. Specifically, CoMT consists of four categories: (1) Visual Creation, (2) Visual Deletion, (3) Visual Update, and (4) Visual Selection to comprehensively explore complex visual operations and concise expression in real scenarios. We evaluate various LVLMs and strategies on CoMT, revealing some key insights into the capabilities and limitations of the current approaches. We hope that CoMT can inspire more research on introducing multi-modal generation into the reasoning process.
Authors: Ionut Marian Motoi, Valerio Belli, Alberto Carpineto, Daniele Nardi, Thomas Alessandro Ciarfuglia
Abstract: Early detection of illnesses and pest infestations in fruit cultivation is critical for maintaining yield quality and plant health. Computer vision and robotics are increasingly employed for the automatic detection of such issues, particularly using data-driven solutions. However, the rarity of these problems makes acquiring and processing the necessary data to train such algorithms a significant obstacle. One solution to this scarcity is the generation of synthetic high-quality anomalous samples. While numerous methods exist for this task, most require highly trained individuals for setup. This work addresses the challenge of generating synthetic anomalies in an automatic fashion that requires only an initial collection of normal and anomalous samples from the user - a task that is straightforward for farmers. We demonstrate the approach in the context of table grape cultivation. Specifically, based on the observation that normal berries present relatively smooth surfaces, while defects result in more complex textures, we introduce a Dual-Canny Edge Detection (DCED) filter. This filter emphasizes the additional texture indicative of diseases, pest infestations, or other defects. Using segmentation masks provided by the Segment Anything Model, we then select and seamlessly blend anomalous berries onto normal ones. We show that the proposed dataset augmentation technique improves the accuracy of an anomaly classifier for table grapes and that the approach can be generalized to other fruit types.
Authors: Tommy D. Beltran, Raul J. Villao, Luis E. Chuquimarca, Boris X. Vintimilla, Sergio A. Velastin
Abstract: The present study focuses on detecting the degree of deformity in fruits such as apples, mangoes, and strawberries during the process of inspecting their external quality, employing Single-Input and Multi-Input architectures based on convolutional neural network (CNN) models using sets of real and synthetic images. The datasets are segmented using the Segment Anything Model (SAM), which provides the silhouette of the fruits. Regarding the single-input architecture, the evaluation of the CNN models is performed only with real images, but a methodology is proposed to improve these results using a pre-trained model with synthetic images. In the Multi-Input architecture, branches with RGB images and fruit silhouettes are implemented as inputs for evaluating CNN models such as VGG16, MobileNetV2, and CIDIS. However, the results revealed that the Multi-Input architecture with the MobileNetV2 model was the most effective in identifying deformities in the fruits, achieving accuracies of 90\%, 94\%, and 92\% for apples, mangoes, and strawberries, respectively. In conclusion, the Multi-Input architecture with the MobileNetV2 model is the most accurate for classifying levels of deformity in fruits.
Authors: Wenhao Sun, Benlei Cui, Jingqun Tang, Xue-Mei Dong
Abstract: Recently, diffusion models have emerged as promising newcomers in the field of generative models, shining brightly in image generation. However, when employed for object removal tasks, they still encounter issues such as generating random artifacts and the incapacity to repaint foreground object areas with appropriate content after removal. To tackle these problems, we propose Attentive Eraser, a tuning-free method to empower pre-trained diffusion models for stable and effective object removal. Firstly, in light of the observation that the self-attention maps influence the structure and shape details of the generated images, we propose Attention Activation and Suppression (ASS), which re-engineers the self-attention mechanism within the pre-trained diffusion models based on the given mask, thereby prioritizing the background over the foreground object during the reverse generation process. Moreover, we introduce Self-Attention Redirection Guidance (SARG), which utilizes the self-attention redirected by ASS to guide the generation process, effectively removing foreground objects within the mask while simultaneously generating content that is both plausible and coherent. Experiments demonstrate the stability and effectiveness of Attentive Eraser in object removal across a variety of pre-trained diffusion models, outperforming even training-based methods. Furthermore, Attentive Eraser can be implemented in various diffusion model architectures and checkpoints, enabling excellent scalability. Code is available at https://github.com/Anonym0u3/AttentiveEraser.
Authors: Antonios Gasteratos, Stavros N. Moutsis, Konstantinos A. Tsintotas, Yiannis Aloimonos
Abstract: Visual-based human action recognition can be found in various application fields, e.g., surveillance systems, sports analytics, medical assistive technologies, or human-robot interaction frameworks, and it concerns the identification and classification of individuals' activities within a video. Since actions typically occur over a sequence of consecutive images, it is particularly challenging due to the inclusion of temporal analysis, which introduces an extra layer of complexity. However, although multiple approaches try to handle temporal analysis, there are still difficulties because of their computational cost and lack of adaptability. Therefore, different types of vision data, containing transition information between consecutive images, provided by next-generation hardware sensors will guide the robotics community in tackling the problem of human action recognition. On the other hand, while there is a plethora of still-image datasets, that researchers can adopt to train new artificial intelligence models, videos representing human activities are of limited capabilities, e.g., small and unbalanced datasets or selected without control from multiple sources. To this end, generating new and realistic synthetic videos is possible since labeling is performed throughout the data creation process, while reinforcement learning techniques can permit the avoidance of considerable dataset dependence. At the same time, human factors' involvement raises ethical issues for the research community, as doubts and concerns about new technologies already exist.
Authors: Athulya Sundaresan Geetha
Abstract: This work explores the YOLOv6 object detection model in depth, concentrating on its design framework, optimization techniques, and detection capabilities. YOLOv6's core elements consist of the EfficientRep Backbone for robust feature extraction and the Rep-PAN Neck for seamless feature aggregation, ensuring high-performance object detection. Evaluated on the COCO dataset, YOLOv6-N achieves 37.5\% AP at 1187 FPS on an NVIDIA Tesla T4 GPU. YOLOv6-S reaches 45.0\% AP at 484 FPS, outperforming models like PPYOLOE-S, YOLOv5-S, YOLOX-S, and YOLOv8-S in the same class. Moreover, YOLOv6-M and YOLOv6-L also show better accuracy (50.0\% and 52.8\%) while maintaining comparable inference speeds to other detectors. With an upgraded backbone and neck structure, YOLOv6-L6 delivers cutting-edge accuracy in real-time.
Authors: Shizuka Akahori, Shotaro Teruya, Pragyan Shrestha, Yuichi Yoshii, Ryuhei Michinobu, Satoshi Iizuka, Itaru Kitahara
Abstract: Ultrasound imaging of the medial elbow is crucial for the early identification of Ulnar Collateral Ligament (UCL) injuries. Specifically, measuring the elbow joint space in ultrasound images is used to assess the valgus instability of elbow. To automate this measurement, a precisely annotated dataset is necessary; however, no publicly available dataset has been proposed thus far. This study introduces a novel ultrasound medial elbow dataset for measuring joint space to diagnose Ulnar Collateral Ligament (UCL) injuries. The dataset comprises 4,201 medial elbow ultrasound images from 22 subjects, with landmark annotations on the humerus and ulna. The annotations are made precisely by the authors under the supervision of three orthopedic surgeons. We evaluated joint space measurement methods using our proposed dataset with several landmark detection approaches, including ViTPose, HRNet, PCT, YOLOv8, and U-Net. In addition, we propose using Shape Subspace (SS) for landmark refinement in heatmap-based landmark detection. The results show that the mean Euclidean distance error of joint space is 0.116 mm when using HRNet. Furthermore, the SS landmark refinement improves the mean absolute error of landmark positions by 0.010 mm with HRNet and by 0.103 mm with ViTPose on average. These highlight the potential for high-precision, real-time diagnosis of UCL injuries and associated risks, which could be leveraged in large-scale screening. Lastly, we demonstrate point-based segmentation of the humerus and ulna using the detected landmarks as input. The dataset will be made publicly available upon acceptance of this paper at: https://github.com/Akahori000/Ultrasound-Medial-Elbow-Dataset.
URLs: https://github.com/Akahori000/Ultrasound-Medial-Elbow-Dataset.
Authors: Shijun Zheng, Weiquan Liu, Yu Guo, Yu Zang, Siqi Shen, Cheng Wang
Abstract: Autonomous vehicles (AVs) rely on LiDAR sensors for environmental perception and decision-making in driving scenarios. However, ensuring the safety and reliability of AVs in complex environments remains a pressing challenge. To address this issue, we introduce a real-world dataset (ROLiD) comprising LiDAR-scanned point clouds of two random objects: water mist and smoke. In this paper, we introduce a novel adversarial perspective by proposing an attack framework that utilizes water mist and smoke to simulate environmental interference. Specifically, we propose a point cloud sequence generation method using a motion and content decomposition generative adversarial network named PCS-GAN to simulate the distribution of random objects. Furthermore, leveraging the simulated LiDAR scanning characteristics implemented with Range Image, we examine the effects of introducing random object perturbations at various positions on the target vehicle. Extensive experiments demonstrate that adversarial perturbations based on random objects effectively deceive vehicle detection and reduce the recognition rate of 3D object detection models.
Authors: Luca Savant Aira, Gabriele Facciolo, Thibaud Ehret
Abstract: Recently, Gaussian splatting has emerged as a strong alternative to NeRF, demonstrating impressive 3D modeling capabilities while requiring only a fraction of the training and rendering time. In this paper, we show how the standard Gaussian splatting framework can be adapted for remote sensing, retaining its high efficiency. This enables us to achieve state-of-the-art performance in just a few minutes, compared to the day-long optimization required by the best-performing NeRF-based Earth observation methods. The proposed framework incorporates remote-sensing improvements from EO-NeRF, such as radiometric correction and shadow modeling, while introducing novel components, including sparsity, view consistency, and opacity regularizations.
Authors: Br\'egier Romain, Baradel Fabien, Lucas Thomas, Galaaoui Salma, Armando Matthieu, Weinzaepfel Philippe, Rogez Gr\'egory
Abstract: Multi-person human mesh recovery (HMR) consists in detecting all individuals in a given input image, and predicting the body shape, pose, and 3D location for each detected person. The dominant approaches to this task rely on neural networks trained to output a single prediction for each detected individual. In contrast, we propose CondiMen, a method that outputs a joint parametric distribution over likely poses, body shapes, intrinsics and distances to the camera, using a Bayesian network. This approach offers several advantages. First, a probability distribution can handle some inherent ambiguities of this task -- such as the uncertainty between a person's size and their distance to the camera, or simply the loss of information when projecting 3D data onto the 2D image plane. Second, the output distribution can be combined with additional information to produce better predictions, by using e.g. known camera or body shape parameters, or by exploiting multi-view observations. Third, one can efficiently extract the most likely predictions from the output distribution, making our proposed approach suitable for real-time applications. Empirically we find that our model i) achieves performance on par with or better than the state-of-the-art, ii) captures uncertainties and correlations inherent in pose estimation and iii) can exploit additional information at test time, such as multi-view consistency or body shape priors. CondiMen spices up the modeling of ambiguity, using just the right ingredients on hand.
Authors: Anni Tang, Tianyu He, Junliang Guo, Xinle Cheng, Li Song, Jiang Bian
Abstract: Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporates several key advancements over existing approaches: 1) model architecture such as convolutional layers and up/downsampling modules; 2) to address the training instability and codebook collapse commonly associated with conventional Vector Quantization (VQ), we integrate Finite Scalar Quantization (FSQ) into discrete video tokenization; 3) improved training strategies, including a two-stage training process and the use of reduced frame rates. By integrating these advancements, VidTok achieves substantial improvements over existing methods, demonstrating superior performance across multiple metrics, including PSNR, SSIM, LPIPS, and FVD, under standardized evaluation settings.
Authors: Sai Teja Erukude, Akhil Joshi, Lior Shamir
Abstract: CNNs have become one of the most commonly used computational tool in the past two decades. One of the primary downsides of CNNs is that they work as a ``black box", where the user cannot necessarily know how the image data are analyzed, and therefore needs to rely on empirical evaluation to test the efficacy of a trained CNN. This can lead to hidden biases that affect the performance evaluation of neural networks, but are difficult to identify. Here we discuss examples of such hidden biases in common and widely used benchmark datasets, and propose techniques for identifying dataset biases that can affect the standard performance evaluation metrics. One effective approach to identify dataset bias is to perform image classification by using merely blank background parts of the original images. However, in some situations a blank background in the images is not available, making it more difficult to separate foreground or contextual information from the bias. To overcome this, we propose a method to identify dataset bias without the need to crop background information from the images. That method is based on applying several image transforms to the original images, including Fourier transform, wavelet transforms, median filter, and their combinations. These transforms were applied to recover background bias information that CNNs use to classify images. This transformations affect the contextual visual information in a different manner than it affects the systemic background bias. Therefore, the method can distinguish between contextual information and the bias, and alert on the presence of background bias even without the need to separate sub-images parts from the blank background of the original images. Code used in the experiments is publicly available.
Authors: Rumeysa Bodur, Binod Bhattarai, Tae-Kyun Kim
Abstract: Text-guided image editing finds applications in various creative and practical fields. While recent studies in image generation have advanced the field, they often struggle with the dual challenges of coherent image transformation and context preservation. In response, our work introduces prompt augmentation, a method amplifying a single input prompt into several target prompts, strengthening textual context and enabling localised image editing. Specifically, we use the augmented prompts to delineate the intended manipulation area. We propose a Contrastive Loss tailored to driving effective image editing by displacing edited areas and drawing preserved regions closer. Acknowledging the continuous nature of image manipulations, we further refine our approach by incorporating the similarity concept, creating a Soft Contrastive Loss. The new losses are incorporated to the diffusion model, demonstrating improved or competitive image editing results on public datasets and generated images over state-of-the-art approaches.
Authors: Huaijin Pi, Ruoxi Guo, Zehong Shen, Qing Shuai, Zechen Hu, Zhumei Wang, Yajiao Dong, Ruizhen Hu, Taku Komura, Sida Peng, Xiaowei Zhou
Abstract: Text-driven human motion synthesis is capturing significant attention for its ability to effortlessly generate intricate movements from abstract text cues, showcasing its potential for revolutionizing motion design not only in film narratives but also in virtual reality experiences and computer game development. Existing methods often rely on 3D motion capture data, which require special setups resulting in higher costs for data acquisition, ultimately limiting the diversity and scope of human motion. In contrast, 2D human videos offer a vast and accessible source of motion data, covering a wider range of styles and activities. In this paper, we explore leveraging 2D human motion extracted from videos as an alternative data source to improve text-driven 3D motion generation. Our approach introduces a novel framework that disentangles local joint motion from global movements, enabling efficient learning of local motion priors from 2D data. We first train a single-view 2D local motion generator on a large dataset of text-motion pairs. To enhance this model to synthesize 3D motion, we fine-tune the generator with 3D data, transforming it into a multi-view generator that predicts view-consistent local joint motion and root dynamics. Experiments on the HumanML3D dataset and novel text prompts demonstrate that our method efficiently utilizes 2D data, supporting realistic 3D human motion generation and broadening the range of motion types it supports. Our code will be made publicly available at https://zju3dv.github.io/Motion-2-to-3/.
Authors: Gordon Lim, Stefan Larson, Kevin Leach
Abstract: Tobacco3482 is a widely used document classification benchmark dataset. However, our manual inspection of the entire dataset uncovers widespread ontological issues, especially large amounts of annotation label problems in the dataset. We establish data label guidelines and find that 11.7% of the dataset is improperly annotated and should either have an unknown label or a corrected label, and 16.7% of samples in the dataset have multiple valid labels. We then analyze the mistakes of a top-performing model and find that 35% of the model's mistakes can be directly attributed to these label issues, highlighting the inherent problems with using a noisily labeled dataset as a benchmark. Supplementary material, including dataset annotations and code, is available at https://github.com/gordon-lim/tobacco3482-mistakes/.
Authors: Paolo Gabriel, Peter Rehani, Tyler Troy, Tiffany Wyatt, Michael Choma, Narinder Singh
Abstract: This study introduces an AI-driven platform for continuous and passive patient monitoring in hospital settings, developed by LookDeep Health. Leveraging advanced computer vision, the platform provides real-time insights into patient behavior and interactions through video analysis, securely storing inference results in the cloud for retrospective evaluation. The dataset, compiled in collaboration with 11 hospital partners, encompasses over 300 high-risk fall patients and over 1,000 days of inference, enabling applications such as fall detection and safety monitoring for vulnerable patient populations. To foster innovation and reproducibility, an anonymized subset of this dataset is publicly available. The AI system detects key components in hospital rooms, including individual presence and role, furniture location, motion magnitude, and boundary crossings. Performance evaluation demonstrates strong accuracy in object detection (macro F1-score = 0.92) and patient-role classification (F1-score = 0.98), as well as reliable trend analysis for the "patient alone" metric (mean logistic regression accuracy = 0.82 \pm 0.15). These capabilities enable automated detection of patient isolation, wandering, or unsupervised movement-key indicators for fall risk and other adverse events. This work establishes benchmarks for validating AI-driven patient monitoring systems, highlighting the platform's potential to enhance patient safety and care by providing continuous, data-driven insights into patient behavior and interactions.
Authors: Lu Liu, Huiyu Duan, Qiang Hu, Liu Yang, Chunlei Cai, Tianxiao Ye, Huayu Liu, Xiaoyun Zhang, Guangtao Zhai
Abstract: Artificial intelligence generative models exhibit remarkable capabilities in content creation, particularly in face image generation, customization, and restoration. However, current AI-generated faces (AIGFs) often fall short of human preferences due to unique distortions, unrealistic details, and unexpected identity shifts, underscoring the need for a comprehensive quality evaluation framework for AIGFs. To address this need, we introduce FaceQ, a large-scale, comprehensive database of AI-generated Face images with fine-grained Quality annotations reflecting human preferences. The FaceQ database comprises 12,255 images generated by 29 models across three tasks: (1) face generation, (2) face customization, and (3) face restoration. It includes 32,742 mean opinion scores (MOSs) from 180 annotators, assessed across multiple dimensions: quality, authenticity, identity (ID) fidelity, and text-image correspondence. Using the FaceQ database, we establish F-Bench, a benchmark for comparing and evaluating face generation, customization, and restoration models, highlighting strengths and weaknesses across various prompts and evaluation dimensions. Additionally, we assess the performance of existing image quality assessment (IQA), face quality assessment (FQA), AI-generated content image quality assessment (AIGCIQA), and preference evaluation metrics, manifesting that these standard metrics are relatively ineffective in evaluating authenticity, ID fidelity, and text-image correspondence. The FaceQ database will be publicly available upon publication.
Authors: Yimu Pan, Sitao Zhang, Alison D. Gernand, Jeffery A. Goldstein, James Z. Wang
Abstract: Robustness and generalizability in medical image segmentation are often hindered by scarcity and limited diversity of training data, which stands in contrast to the variability encountered during inference. While conventional strategies -- such as domain-specific augmentation, specialized architectures, and tailored training procedures -- can alleviate these issues, they depend on the availability and reliability of domain knowledge. When such knowledge is unavailable, misleading, or improperly applied, performance may deteriorate. In response, we introduce a novel, domain-agnostic, add-on, and data-driven strategy inspired by image stacking in image denoising. Termed ``semantic stacking,'' our method estimates a denoised semantic representation that complements the conventional segmentation loss during training. This method does not depend on domain-specific assumptions, making it broadly applicable across diverse image modalities, model architectures, and augmentation techniques. Through extensive experiments, we validate the superiority of our approach in improving segmentation performance under diverse conditions. Code is available at https://github.com/ymp5078/Semantic-Stacking.
Authors: Xingjian Wang, Li Chai
Abstract: In-the-wild Dynamic facial expression recognition (DFER) encounters a significant challenge in recognizing emotion-related expressions, which are often temporally and spatially diluted by emotion-irrelevant expressions and global context respectively. Most of the prior DFER methods model tightly coupled spatiotemporal representations which may incorporate weakly relevant features, leading to information redundancy and emotion-irrelevant context bias. Several DFER methods have highlighted the significance of dynamic information, but utilize explicit manners to extract dynamic features with overly strong prior knowledge. In this paper, we propose a novel Implicit Facial Dynamics Disentanglement framework (IFDD). Through expanding wavelet lifting scheme to fully learnable framework, IFDD disentangles emotion-related dynamic information from emotion-irrelevant global context in an implicit manner, i.e., without exploit operations and external guidance. The disentanglement process of IFDD contains two stages, i.e., Inter-frame Static-dynamic Splitting Module (ISSM) for rough disentanglement estimation and Lifting-based Aggregation-Disentanglement Module (LADM) for further refinement. Specifically, ISSM explores inter-frame correlation to generate content-aware splitting indexes on-the-fly. We preliminarily utilize these indexes to split frame features into two groups, one with greater global similarity, and the other with more unique dynamic features. Subsequently, LADM first aggregates these two groups of features to obtain fine-grained global context features by an updater, and then disentangles emotion-related facial dynamic features from the global context by a predictor. Extensive experiments on in-the-wild datasets have demonstrated that IFDD outperforms prior supervised DFER methods with higher recognition accuracy and comparable efficiency.
Authors: Siqi Li, Xiaoxue Chen, Haoyu Cheng, Guyue Zhou, Hao Zhao, Guanzhong Tian
Abstract: Detecting the openable parts of articulated objects is crucial for downstream applications in intelligent robotics, such as pulling a drawer. This task poses a multitasking challenge due to the necessity of understanding object categories and motion. Most existing methods are either category-specific or trained on specific datasets, lacking generalization to unseen environments and objects. In this paper, we propose a Transformer-based Openable Part Detection (OPD) framework named Multi-feature Openable Part Detection (MOPD) that incorporates perceptual grouping and geometric priors, outperforming previous methods in performance. In the first stage of the framework, we introduce a perceptual grouping feature model that provides perceptual grouping feature priors for openable part detection, enhancing detection results through a cross-attention mechanism. In the second stage, a geometric understanding feature model offers geometric feature priors for predicting motion parameters. Compared to existing methods, our proposed approach shows better performance in both detection and motion parameter prediction. Codes and models are publicly available at https://github.com/lisiqi-zju/MOPD
Authors: Jui-Che Chiang, Hou-Ning Hu, Bo-Syuan Hou, Chia-Yu Tseng, Yu-Lun Liu, Min-Hung Chen, Yen-Yu Lin
Abstract: Although facial landmark detection (FLD) has gained significant progress, existing FLD methods still suffer from performance drops on partially non-visible faces, such as faces with occlusions or under extreme lighting conditions or poses. To address this issue, we introduce ORFormer, a novel transformer-based method that can detect non-visible regions and recover their missing features from visible parts. Specifically, ORFormer associates each image patch token with one additional learnable token called the messenger token. The messenger token aggregates features from all but its patch. This way, the consensus between a patch and other patches can be assessed by referring to the similarity between its regular and messenger embeddings, enabling non-visible region identification. Our method then recovers occluded patches with features aggregated by the messenger tokens. Leveraging the recovered features, ORFormer compiles high-quality heatmaps for the downstream FLD task. Extensive experiments show that our method generates heatmaps resilient to partial occlusions. By integrating the resultant heatmaps into existing FLD methods, our method performs favorably against the state of the arts on challenging datasets such as WFLW and COFW.
Authors: Andrea Dunn Beltran, Daniel Rho, Marc Niethammer, Roni Sengupta
Abstract: Simultaneous Localization And Mapping (SLAM) from a monocular endoscopy video can enable autonomous navigation, guidance to unsurveyed regions, and 3D visualizations, which can significantly improve endoscopy experience for surgeons and patient outcomes. Existing dense SLAM algorithms often assume distant and static lighting and textured surfaces, and alternate between optimizing scene geometry and camera parameters by minimizing a photometric rendering loss, often called Photometric Bundle Adjustment. However, endoscopic environments exhibit dynamic near-field lighting due to the co-located light and camera moving extremely close to the surface, textureless surfaces, and strong specular reflections due to mucus layers. When not considered, these near-field lighting effects can cause significant performance reductions for existing SLAM algorithms from indoor/outdoor scenes when applied to endoscopy videos. To mitigate this problem, we introduce a new Near-Field Lighting Bundle Adjustment Loss $(L_{NFL-BA})$ that can also be alternatingly optimized, along with the Photometric Bundle Adjustment loss, such that the captured images' intensity variations match the relative distance and orientation between the surface and the co-located light and camera. We derive a general NFL-BA loss function for 3D Gaussian surface representations and demonstrate that adding $L_{NFL-BA}$ can significantly improve the tracking and mapping performance of two state-of-the-art 3DGS-SLAM systems, MonoGS (35% improvement in tracking, 48% improvement in mapping with predicted depth maps) and EndoGSLAM (22% improvement in tracking, marginal improvement in mapping with predicted depths), on the C3VD endoscopy dataset for colons. The project page is available at https://asdunnbe.github.io/NFL-BA/
Authors: Shirin Qiam, Saipraneeth Devunuri, Lewis J. Lehe
Abstract: Discussions of minimum parking requirement policies often include maps of parking lots, which are time consuming to construct manually. Open source datasets for such parking lots are scarce, particularly for US cities. This paper introduces the idea of using Near-Infrared (NIR) channels as input and several post-processing techniques to improve the prediction of off-street surface parking lots using satellite imagery. We constructed two datasets with 12,617 image-mask pairs each: one with 3-channel (RGB) and another with 4-channel (RGB + NIR). The datasets were used to train five deep learning models (OneFormer, Mask2Former, SegFormer, DeepLabV3, and FCN) for semantic segmentation, classifying images to differentiate between parking and non-parking pixels. Our results demonstrate that the NIR channel improved accuracy because parking lots are often surrounded by grass, even though the NIR channel needed to be upsampled from a lower resolution. Post-processing including eliminating erroneous holes, simplifying edges, and removing road and building footprints further improved the accuracy. Best model, OneFormer trained on 4-channel input and paired with post-processing techniques achieves a mean Intersection over Union (mIoU) of 84.9 percent and a pixel-wise accuracy of 96.3 percent.
Authors: Mark Endo, Xiaohan Wang, Serena Yeung-Levy
Abstract: Recent works on accelerating Vision-Language Models show that strong performance can be maintained across a variety of vision-language tasks despite highly compressing visual information. In this work, we examine the popular acceleration approach of early pruning of visual tokens inside the language model and find that its strong performance across many tasks is not due to an exceptional ability to compress visual information, but rather the benchmarks' limited ability to assess fine-grained visual capabilities. Namely, we demonstrate a core issue with the acceleration approach where most tokens towards the top of the image are pruned away. Yet, this issue is only reflected in performance for a small subset of tasks such as localization. For the other evaluated tasks, strong performance is maintained with the flawed pruning strategy. Noting the limited visual capabilities of the studied acceleration technique, we propose FEATHER (Fast and Effective Acceleration wiTH Ensemble cRiteria), a straightforward approach that (1) resolves the identified issue with early-layer pruning, (2) incorporates uniform sampling to ensure coverage across all image regions, and (3) applies pruning in two stages to allow the criteria to become more effective at a later layer while still achieving significant speedup through early-layer pruning. With comparable computational savings, we find that FEATHER has more than $5\times$ performance improvement on the vision-centric localization benchmarks compared to the original acceleration approach.
Authors: Guoxing Sun, Rishabh Dabral, Heming Zhu, Pascal Fua, Christian Theobalt, Marc Habermann
Abstract: Real-time free-view human rendering from sparse-view RGB inputs is a challenging task due to the sensor scarcity and the tight time budget. To ensure efficiency, recent methods leverage 2D CNNs operating in texture space to learn rendering primitives. However, they either jointly learn geometry and appearance, or completely ignore sparse image information for geometry estimation, significantly harming visual quality and robustness to unseen body poses. To address these issues, we present Double Unprojected Textures, which at the core disentangles coarse geometric deformation estimation from appearance synthesis, enabling robust and photorealistic 4K rendering in real-time. Specifically, we first introduce a novel image-conditioned template deformation network, which estimates the coarse deformation of the human template from a first unprojected texture. This updated geometry is then used to apply a second and more accurate texture unprojection. The resulting texture map has fewer artifacts and better alignment with input views, which benefits our learning of finer-level geometry and appearance represented by Gaussian splats. We validate the effectiveness and efficiency of the proposed method in quantitative and qualitative experiments, which significantly surpasses other state-of-the-art methods.
Authors: Hsin-Ping Huang, Yang Zhou, Jui-Hsien Wang, Difan Liu, Feng Liu, Ming-Hsuan Yang, Zhan Xu
Abstract: Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal. Existing approaches often use existing motion extracted from other videos, which restricts applications to specific motion types and global scene matching. We propose Move-in-2D, a novel approach to generate human motion sequences conditioned on a scene image, allowing for diverse motion that adapts to different scenes. Our approach utilizes a diffusion model that accepts both a scene image and text prompt as inputs, producing a motion sequence tailored to the scene. To train this model, we collect a large-scale video dataset featuring single-human activities, annotating each video with the corresponding human motion as the target output. Experiments demonstrate that our method effectively predicts human motion that aligns with the scene image after projection. Furthermore, we show that the generated motion sequence improves human motion quality in video synthesis tasks.
Authors: Chen Bao, Jiarui Xu, Xiaolong Wang, Abhinav Gupta, Homanga Bharadhwaj
Abstract: How can we predict future interaction trajectories of human hands in a scene given high-level colloquial task specifications in the form of natural language? In this paper, we extend the classic hand trajectory prediction task to two tasks involving explicit or implicit language queries. Our proposed tasks require extensive understanding of human daily activities and reasoning abilities about what should be happening next given cues from the current scene. We also develop new benchmarks to evaluate the proposed two tasks, Vanilla Hand Prediction (VHP) and Reasoning-Based Hand Prediction (RBHP). We enable solving these tasks by integrating high-level world knowledge and reasoning capabilities of Vision-Language Models (VLMs) with the auto-regressive nature of low-level ego-centric hand trajectories. Our model, HandsOnVLM is a novel VLM that can generate textual responses and produce future hand trajectories through natural-language conversations. Our experiments show that HandsOnVLM outperforms existing task-specific methods and other VLM baselines on proposed tasks, and demonstrates its ability to effectively utilize world knowledge for reasoning about low-level human hand trajectories based on the provided context. Our website contains code and detailed video results \url{https://www.chenbao.tech/handsonvlm/}
Authors: Yunzhi Yan, Zhen Xu, Haotong Lin, Haian Jin, Haoyu Guo, Yida Wang, Kun Zhan, Xianpeng Lang, Hujun Bao, Xiaowei Zhou, Sida Peng
Abstract: This paper aims to tackle the problem of photorealistic view synthesis from vehicle sensor data. Recent advancements in neural scene representation have achieved notable success in rendering high-quality autonomous driving scenes, but the performance significantly degrades as the viewpoint deviates from the training trajectory. To mitigate this problem, we introduce StreetCrafter, a novel controllable video diffusion model that utilizes LiDAR point cloud renderings as pixel-level conditions, which fully exploits the generative prior for novel view synthesis, while preserving precise camera control. Moreover, the utilization of pixel-level LiDAR conditions allows us to make accurate pixel-level edits to target scenes. In addition, the generative prior of StreetCrafter can be effectively incorporated into dynamic scene representations to achieve real-time rendering. Experiments on Waymo Open Dataset and PandaSet demonstrate that our model enables flexible control over viewpoint changes, enlarging the view synthesis regions for satisfying rendering, which outperforms existing methods.
Authors: Maham Tanveer, Yang Zhou, Simon Niklaus, Ali Mahdavi Amiri, Hao Zhang, Krishna Kumar Singh, Nanxuan Zhao
Abstract: By generating plausible and smooth transitions between two image frames, video inbetweening is an essential tool for video editing and long video synthesis. Traditional works lack the capability to generate complex large motions. While recent video generation techniques are powerful in creating high-quality results, they often lack fine control over the details of intermediate frames, which can lead to results that do not align with the creative mind. We introduce MotionBridge, a unified video inbetweening framework that allows flexible controls, including trajectory strokes, keyframes, masks, guide pixels, and text. However, learning such multi-modal controls in a unified framework is a challenging task. We thus design two generators to extract the control signal faithfully and encode feature through dual-branch embedders to resolve ambiguities. We further introduce a curriculum training strategy to smoothly learn various controls. Extensive qualitative and quantitative experiments have demonstrated that such multi-modal controls enable a more dynamic, customizable, and contextually accurate visual narrative.
Authors: Haoyi Jiang, Liu Liu, Tianheng Cheng, Xinjie Wang, Tianwei Lin, Zhizhong Su, Wenyu Liu, Xinggang Wang
Abstract: 3D Semantic Occupancy Prediction is fundamental for spatial understanding as it provides a comprehensive semantic cognition of surrounding environments. However, prevalent approaches primarily rely on extensive labeled data and computationally intensive voxel-based modeling, restricting the scalability and generalizability of 3D representation learning. In this paper, we introduce GaussTR, a novel Gaussian Transformer that leverages alignment with foundation models to advance self-supervised 3D spatial understanding. GaussTR adopts a Transformer architecture to predict sparse sets of 3D Gaussians that represent scenes in a feed-forward manner. Through aligning rendered Gaussian features with diverse knowledge from pre-trained foundation models, GaussTR facilitates the learning of versatile 3D representations and enables open-vocabulary occupancy prediction without explicit annotations. Empirical evaluations on the Occ3D-nuScenes dataset showcase GaussTR's state-of-the-art zero-shot performance, achieving 11.70 mIoU while reducing training duration by approximately 50%. These experimental results highlight the significant potential of GaussTR for scalable and holistic 3D spatial understanding, with promising implications for autonomous driving and embodied agents. Code is available at https://github.com/hustvl/GaussTR.
Authors: Gaoyang Zhang, Bingtao Fu, Qingnan Fan, Qi Zhang, Runxing Liu, Hong Gu, Huaqi Zhang, Xinguo Liu
Abstract: Text-to-image diffusion models excel at generating photorealistic images, but commonly struggle to render accurate spatial relationships described in text prompts. We identify two core issues underlying this common failure: 1) the ambiguous nature of spatial-related data in existing datasets, and 2) the inability of current text encoders to accurately interpret the spatial semantics of input descriptions. We address these issues with CoMPaSS, a versatile training framework that enhances spatial understanding of any T2I diffusion model. CoMPaSS solves the ambiguity of spatial-related data with the Spatial Constraints-Oriented Pairing (SCOP) data engine, which curates spatially-accurate training data through a set of principled spatial constraints. To better exploit the curated high-quality spatial priors, CoMPaSS further introduces a Token ENcoding ORdering (TENOR) module to allow better exploitation of high-quality spatial priors, effectively compensating for the shortcoming of text encoders. Extensive experiments on four popular open-weight T2I diffusion models covering both UNet- and MMDiT-based architectures demonstrate the effectiveness of CoMPaSS by setting new state-of-the-arts with substantial relative gains across well-known benchmarks on spatial relationships generation, including VISOR (+98%), T2I-CompBench Spatial (+67%), and GenEval Position (+131%). Code will be available at https://github.com/blurgyy/CoMPaSS.
Authors: Christoph Leiter, Jonas Belouadi, Yanran Chen, Ran Zhang, Daniil Larionov, Aida Kostikova, Steffen Eger
Abstract: The NLLG (Natural Language Learning & Generation) arXiv reports assist in navigating the rapidly evolving landscape of NLP and AI research across cs.CL, cs.CV, cs.AI, and cs.LG categories. This fourth installment captures a transformative period in AI history - from January 1, 2023, following ChatGPT's debut, through September 30, 2024. Our analysis reveals substantial new developments in the field - with 45% of the top 40 most-cited papers being new entries since our last report eight months ago and offers insights into emerging trends and major breakthroughs, such as novel multimodal architectures, including diffusion and state space models. Natural Language Processing (NLP; cs.CL) remains the dominant main category in the list of our top-40 papers but its dominance is on the decline in favor of Computer vision (cs.CV) and general machine learning (cs.LG). This report also presents novel findings on the integration of generative AI in academic writing, documenting its increasing adoption since 2022 while revealing an intriguing pattern: top-cited papers show notably fewer markers of AI-generated content compared to random samples. Furthermore, we track the evolution of AI-associated language, identifying declining trends in previously common indicators such as "delve".
Authors: Sizhe Xing, Aolong Sun, Chengxi Wang, Yizhi Wang, Boyu Dong, Junhui Hu, Xuyu Deng, An Yan, Yingjun Liu, Fangchen Hu, Zhongya Li, Ouhan Huang, Junhao Zhao, Yingjun Zhou, Ziwei Li, Jianyang Shi, Xi Xiao, Richard Penty, Qixiang Cheng, Nan Chi, Junwen Zhang
Abstract: The rapid advancement of generative artificial intelligence (AI) in recent years has profoundly reshaped modern lifestyles, necessitating a revolutionary architecture to support the growing demands for computational power. Cloud computing has become the driving force behind this transformation. However, it consumes significant power and faces computation security risks due to the reliance on extensive data centers and servers in the cloud. Reducing power consumption while enhancing computational scale remains persistent challenges in cloud computing. Here, we propose and experimentally demonstrate an optical cloud computing system that can be seamlessly deployed across edge-metro network. By modulating inputs and models into light, a wide range of edge nodes can directly access the optical computing center via the edge-metro network. The experimental validations show an energy efficiency of 118.6 mW/TOPs (tera operations per second), reducing energy consumption by two orders of magnitude compared to traditional electronic-based cloud computing solutions. Furthermore, it is experimentally validated that this architecture can perform various complex generative AI models through parallel computing to achieve image generation tasks.
Authors: Chiyu Max Jiang, Yijing Bai, Andre Cornman, Christopher Davis, Xiukun Huang, Hong Jeon, Sakshum Kulshrestha, John Lambert, Shuangyu Li, Xuanyu Zhou, Carlos Fuertes, Chang Yuan, Mingxing Tan, Yin Zhou, Dragomir Anguelov
Abstract: Realistic and interactive scene simulation is a key prerequisite for autonomous vehicle (AV) development. In this work, we present SceneDiffuser, a scene-level diffusion prior designed for traffic simulation. It offers a unified framework that addresses two key stages of simulation: scene initialization, which involves generating initial traffic layouts, and scene rollout, which encompasses the closed-loop simulation of agent behaviors. While diffusion models have been proven effective in learning realistic and multimodal agent distributions, several challenges remain, including controllability, maintaining realism in closed-loop simulations, and ensuring inference efficiency. To address these issues, we introduce amortized diffusion for simulation. This novel diffusion denoising paradigm amortizes the computational cost of denoising over future simulation steps, significantly reducing the cost per rollout step (16x less inference steps) while also mitigating closed-loop errors. We further enhance controllability through the introduction of generalized hard constraints, a simple yet effective inference-time constraint mechanism, as well as language-based constrained scene generation via few-shot prompting of a large language model (LLM). Our investigations into model scaling reveal that increased computational resources significantly improve overall simulation realism. We demonstrate the effectiveness of our approach on the Waymo Open Sim Agents Challenge, achieving top open-loop performance and the best closed-loop performance among diffusion models.
Authors: Manman Yuan, Weiming Jia, Xiong Luo, Jiazhen Ye, Peican Zhu, Junlin Li
Abstract: The precise detection of mild cognitive impairment (MCI) is of significant importance in preventing the deterioration of patients in a timely manner. Although hypergraphs have enhanced performance by learning and analyzing brain networks, they often only depend on vector distances between features at a single scale to infer interactions. In this paper, we deal with a more arduous challenge, hypergraph modelling with synchronization between brain regions, and design a novel framework, i.e., A Multi-scale Hypergraph Network for MCI Detection via Synchronous and Attentive Fusion (MHSA), to tackle this challenge. Specifically, our approach employs the Phase-Locking Value (PLV) to calculate the phase synchronization relationship in the spectrum domain of regions of interest (ROIs) and designs a multi-scale feature fusion mechanism to integrate dynamic connectivity features of functional magnetic resonance imaging (fMRI) from both the temporal and spectrum domains. To evaluate and optimize the direct contribution of each ROI to phase synchronization in the temporal domain, we structure the PLV coefficients dynamically adjust strategy, and the dynamic hypergraph is modelled based on a comprehensive temporal-spectrum fusion matrix. Experiments on the real-world dataset indicate the effectiveness of our strategy. The code is available at https://github.com/Jia-Weiming/MHSA.
Authors: Kelsey Doerksen, Casper Fibaek, Rochelle Schneider, Do-Hyung Kim, Isabelle Tingzon
Abstract: Internet connectivity in schools is critical to provide students with the digital literary skills necessary to compete in modern economies. In order for governments to effectively implement digital infrastructure development in schools, accurate internet connectivity information is required. However, traditional survey-based methods can exceed the financial and capacity limits of governments. Open-source Earth Observation (EO) datasets have unlocked our ability to observe and understand socio-economic conditions on Earth from space, and in combination with Machine Learning (ML), can provide the tools to circumvent costly ground-based survey methods to support infrastructure development. In this paper, we present our work on school internet connectivity prediction using EO and ML. We detail the creation of our multi-modal, freely-available satellite imagery and survey information dataset, leverage the latest geographically-aware location encoders, and introduce the first results of using the new European Space Agency phi-lab geographically-aware foundational model to predict internet connectivity in Botswana and Rwanda. We find that ML with EO and ground-based auxiliary data yields the best performance in both countries, for accuracy, F1 score, and False Positive rates, and highlight the challenges of internet connectivity prediction from space with a case study in Kigali, Rwanda. Our work showcases a practical approach to support data-driven digital infrastructure development in low-resource settings, leveraging freely available information, and provide cleaned and labelled datasets for future studies to the community through a unique collaboration between UNICEF and the European Space Agency phi-lab.
Authors: Yuang Qi, Kejiang Chen, Na Zhao, Zijin Yang, Weiming Zhang
Abstract: The rapid development of image generation models has facilitated the widespread dissemination of generated images on social networks, creating favorable conditions for provably secure image steganography. However, existing methods face issues such as low quality of generated images and lack of semantic control in the generation process. To leverage provably secure steganography with more effective and high-performance image generation models, and to ensure that stego images can accurately extract secret messages even after being uploaded to social networks and subjected to lossy processing such as JPEG compression, we propose a high-quality, provably secure, and robust image steganography method based on state-of-the-art autoregressive (AR) image generation models using Vector-Quantized (VQ) tokenizers. Additionally, we employ a cross-modal error-correction framework that generates stego text from stego images to aid in restoring lossy images, ultimately enabling the extraction of secret messages embedded within the images. Extensive experiments have demonstrated that the proposed method provides advantages in stego quality, embedding capacity, and robustness, while ensuring provable undetectability.
Authors: Wenbin An, Haonan Lin, Jiahao Nie, Feng Tian, Wenkai Shi, Yaqiang Wu, Qianying Wang, Ping Chen
Abstract: Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another labeled dataset containing only known categories. The primary challenges stem from model bias induced by pre-training on only known categories and the lack of precise supervision for novel ones, leading to category bias towards known categories and category confusion among different novel categories, which hinders models' ability to identify novel categories effectively. To address these challenges, we propose a novel framework named Self-Debiasing Calibration (SDC). Unlike prior methods that regard model bias towards known categories as an obstacle to novel category identification, SDC provides a novel insight into unleashing the potential of the bias to facilitate novel category learning. Specifically, the output of the biased model serves two key purposes. First, it provides an accurate modeling of category bias, which can be utilized to measure the degree of bias and debias the output of the current training model. Second, it offers valuable insights for distinguishing different novel categories by transferring knowledge between similar categories. Based on these insights, SDC dynamically adjusts the output logits of the current training model using the output of the biased model. This approach produces less biased logits to effectively address the issue of category bias towards known categories, and generates more accurate pseudo labels for unlabeled data, thereby mitigating category confusion for novel categories. Experiments on three benchmark datasets show that SDC outperforms SOTA methods, especially in the identification of novel categories. Our code and data are available at \url{https://github.com/Lackel/SDC}.
Authors: Qi Wu, Janick Martinez Esturo, Ashkan Mirzaei, Nicolas Moenne-Loccoz, Zan Gojcic
Abstract: 3D Gaussian Splatting (3DGS) has shown great potential for efficient reconstruction and high-fidelity real-time rendering of complex scenes on consumer hardware. However, due to its rasterization-based formulation, 3DGS is constrained to ideal pinhole cameras and lacks support for secondary lighting effects. Recent methods address these limitations by tracing volumetric particles instead, however, this comes at the cost of significantly slower rendering speeds. In this work, we propose 3D Gaussian Unscented Transform (3DGUT), replacing the EWA splatting formulation in 3DGS with the Unscented Transform that approximates the particles through sigma points, which can be projected exactly under any nonlinear projection function. This modification enables trivial support of distorted cameras with time dependent effects such as rolling shutter, while retaining the efficiency of rasterization. Additionally, we align our rendering formulation with that of tracing-based methods, enabling secondary ray tracing required to represent phenomena such as reflections and refraction within the same 3D representation.
Authors: YiFan Zhang, Shanglin Lei, Runqi Qiao, Zhuoma GongQue, Xiaoshuai Song, Guanting Dong, Qiuna Tan, Zhe Wei, Peiqing Yang, Ye Tian, Yadong Xue, Xiaofei Wang, Honggang Zhang
Abstract: The rapidly developing field of large multimodal models (LMMs) has led to the emergence of diverse models with remarkable capabilities. However, existing benchmarks fail to comprehensively, objectively and accurately evaluate whether LMMs align with the diverse needs of humans in real-world scenarios. To bridge this gap, we propose the Multi-Dimensional Insights (MDI) benchmark, which includes over 500 images covering six common scenarios of human life. Notably, the MDI-Benchmark offers two significant advantages over existing evaluations: (1) Each image is accompanied by two types of questions: simple questions to assess the model's understanding of the image, and complex questions to evaluate the model's ability to analyze and reason beyond basic content. (2) Recognizing that people of different age groups have varying needs and perspectives when faced with the same scenario, our benchmark stratifies questions into three age categories: young people, middle-aged people, and older people. This design allows for a detailed assessment of LMMs' capabilities in meeting the preferences and needs of different age groups. With MDI-Benchmark, the strong model like GPT-4o achieve 79% accuracy on age-related tasks, indicating that existing LMMs still have considerable room for improvement in addressing real-world applications. Looking ahead, we anticipate that the MDI-Benchmark will open new pathways for aligning real-world personalization in LMMs. The MDI-Benchmark data and evaluation code are available at https://mdi-benchmark.github.io/
Authors: Pranav Rajpurkar, Julian N. Acosta, Siddhant Dogra, Jaehwan Jeong, Deepanshu Jindal, Michael Moritz, Samir Rajpurkar
Abstract: We present a comprehensive evaluation of a2z-1, an artificial intelligence (AI) model designed to analyze abdomen-pelvis CT scans for 21 time-sensitive and actionable findings. Our study focuses on rigorous assessment of the model's performance and generalizability. Large-scale retrospective analysis demonstrates an average AUC of 0.931 across 21 conditions. External validation across two distinct health systems confirms consistent performance (AUC 0.923), establishing generalizability to different evaluation scenarios, with notable performance in critical findings such as small bowel obstruction (AUC 0.958) and acute pancreatitis (AUC 0.961). Subgroup analysis shows consistent accuracy across patient sex, age groups, and varied imaging protocols, including different slice thicknesses and contrast administration types. Comparison of high-confidence model outputs to radiologist reports reveals instances where a2z-1 identified overlooked findings, suggesting potential for quality assurance applications.
Authors: Hritik Bansal, Daniel Israel, Siyan Zhao, Shufan Li, Tung Nguyen, Aditya Grover
Abstract: Recent advancements in mixed-modal generative models have enabled flexible integration of information across image-text content. These models have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and predicting the impact of medical procedures on a patient's health. However, existing resources face challenges such as limited data availability, narrow domain coverage, and restricted sources (e.g., medical papers). To address these gaps, we present MedMax, the first large-scale multimodal biomedical instruction-tuning dataset for mixed-modal foundation models. With 1.47 million instances, MedMax encompasses a diverse range of tasks, including multimodal content generation (interleaved image-text data), biomedical image captioning and generation, visual chatting, and report understanding. These tasks span diverse medical domains such as radiology and histopathology. Subsequently, we fine-tune a mixed-modal foundation model on the MedMax dataset, achieving significant performance improvements: a 26% gain over the Chameleon model and an 18.3% improvement over GPT-4o across 12 downstream biomedical visual question-answering tasks. Additionally, we introduce a unified evaluation suite for biomedical tasks, providing a robust framework to guide the development of next-generation mixed-modal biomedical AI assistants.
Authors: Irham T. Andika, Stefan Schuldt, Sherry H. Suyu, Satadru Bag, Raoul Ca\~nameras, Alejandra Melo, Claudio Grillo, James H. H. Chan
Abstract: Strongly lensed quasars provide valuable insights into the rate of cosmic expansion, the distribution of dark matter in foreground deflectors, and the characteristics of quasar hosts. However, detecting them in astronomical images is difficult due to the prevalence of non-lensing objects. To address this challenge, we developed a generative deep learning model called VariLens, built upon a physics-informed variational autoencoder. This model seamlessly integrates three essential modules: image reconstruction, object classification, and lens modeling, offering a fast and comprehensive approach to strong lens analysis. VariLens is capable of rapidly determining both (1) the probability that an object is a lens system and (2) key parameters of a singular isothermal ellipsoid (SIE) mass model -- including the Einstein radius ($\theta_\mathrm{E}$), lens center, and ellipticity -- in just milliseconds using a single CPU. A direct comparison of VariLens estimates with traditional lens modeling for 20 known lensed quasars within the Subaru Hyper Suprime-Cam (HSC) footprint shows good agreement, with both results consistent within $2\sigma$ for systems with $\theta_\mathrm{E}<3$ arcsecs. To identify new lensed quasar candidates, we begin with an initial sample of approximately 80 million sources, combining HSC data with multiwavelength information from various surveys. After applying a photometric preselection aimed at locating $z>1.5$ sources, the number of candidates is reduced to 710,966. Subsequently, VariLens highlights 13,831 sources, each showing a high likelihood of being a lens. A visual assessment of these objects results in 42 promising candidates that await spectroscopic confirmation. These results underscore the potential of automated deep learning pipelines to efficiently detect and model strong lenses in large datasets.
Authors: Khen Cohen, Liav Hen, Ariel Lellouch
Abstract: Distributed Acoustic Sensing (DAS) has emerged as a promising tool for real-time traffic monitoring in densely populated areas. In this paper, we present a novel concept that integrates DAS data with co-located visual information. We use YOLO-derived vehicle location and classification from camera inputs as labeled data to train a detection and classification neural network utilizing DAS data only. Our model achieves a performance exceeding 94% for detection and classification, and about 1.2% false alarm rate. We illustrate the model's application in monitoring traffic over a week, yielding statistical insights that could benefit future smart city developments. Our approach highlights the potential of combining fiber-optic sensors with visual information, focusing on practicality and scalability, protecting privacy, and minimizing infrastructure costs. To encourage future research, we share our dataset.
Authors: Vidya Prasad, Anna Vilanova, Nicola Pezzotti
Abstract: While deep generative models (DGMs) have gained popularity, their susceptibility to biases and other inefficiencies that lead to undesirable outcomes remains an issue. With their growing complexity, there is a critical need for early detection of issues to achieve desired results and optimize resources. Hence, we introduce a progressive analysis framework to monitor the training process of DGMs. Our method utilizes dimensionality reduction techniques to facilitate the inspection of latent representations, the generated and real distributions, and their evolution across training iterations. This monitoring allows us to pause and fix the training method if the representations or distributions progress undesirably. This approach allows for the analysis of a models' training dynamics and the timely identification of biases and failures, minimizing computational loads. We demonstrate how our method supports identifying and mitigating biases early in training a Generative Adversarial Network (GAN) and improving the quality of the generated data distribution.
Authors: Yuyu Guo, Lei Bi, Zhengbin Zhu, David Dagan Feng, Ruiyan Zhang, Qian Wang, Jinman Kim
Abstract: Automated segmentation of left ventricular cavity (LVC) in temporal cardiac image sequences (multiple time points) is a fundamental requirement for quantitative analysis of its structural and functional changes. Deep learning based methods for the segmentation of LVC are the state of the art; however, these methods are generally formulated to work on single time points, and fails to exploit the complementary information from the temporal image sequences that can aid in segmentation accuracy and consistency among the images across the time points. Furthermore, these segmentation methods perform poorly in segmenting the end-systole (ES) phase images, where the left ventricle deforms to the smallest irregular shape, and the boundary between the blood chamber and myocardium becomes inconspicuous. To overcome these limitations, we propose a new method to automatically segment temporal cardiac images where we introduce a spatial sequential (SS) network to learn the deformation and motion characteristics of the LVC in an unsupervised manner; these characteristics were then integrated with sequential context information derived from bi-directional learning (BL) where both chronological and reverse-chronological directions of the image sequence were used. Our experimental results on a cardiac computed tomography (CT) dataset demonstrated that our spatial-sequential network with bi-directional learning (SS-BL) method outperformed existing methods for LVC segmentation. Our method was also applied to MRI cardiac dataset and the results demonstrated the generalizability of our method.
Authors: Zhentao Liu, Ruyi Zha, Huangxuan Zhao, Hongdong Li, Zhiming Cui
Abstract: Reconstructing 3D vessel structures from sparse-view dynamic digital subtraction angiography (DSA) images enables accurate medical assessment while reducing radiation exposure. Existing methods often produce suboptimal results or require excessive computation time. In this work, we propose 4D radiative Gaussian splatting (4DRGS) to achieve high-quality reconstruction efficiently. In detail, we represent the vessels with 4D radiative Gaussian kernels. Each kernel has time-invariant geometry parameters, including position, rotation, and scale, to model static vessel structures. The time-dependent central attenuation of each kernel is predicted from a compact neural network to capture the temporal varying response of contrast agent flow. We splat these Gaussian kernels to synthesize DSA images via X-ray rasterization and optimize the model with real captured ones. The final 3D vessel volume is voxelized from the well-trained kernels. Moreover, we introduce accumulated attenuation pruning and bounded scaling activation to improve reconstruction quality. Extensive experiments on real-world patient data demonstrate that 4DRGS achieves impressive results in 5 minutes training, which is 32x faster than the state-of-the-art method. This underscores the potential of 4DRGS for real-world clinics.
Authors: Neil Dizon, Jyrki Jauhiainen, Tuomo Valkonen
Abstract: Online optimisation studies the convergence of optimisation methods as the data embedded in the problem changes. Based on this idea, we propose a primal dual online method for nonlinear time-discrete inverse problems. We analyse the method through regret theory and demonstrate its performance in real-time monitoring of moving bodies in a fluid with Electrical Impedance Tomography (EIT). To do so, we also prove the second-order differentiability of the Complete Electrode Model (CEM) solution operator on $L^\infty$.
Authors: Ruijie Chen, Qi Mao, Zhengxue Cheng
Abstract: Recent advances in Artificial Intelligence Generated Content (AIGC) have garnered significant interest, accompanied by an increasing need to transmit and compress the vast number of AI-generated images (AIGIs). However, there is a noticeable deficiency in research focused on compression methods for AIGIs. To address this critical gap, we introduce a scalable cross-modal compression framework that incorporates multiple human-comprehensible modalities, designed to efficiently capture and relay essential visual information for AIGIs. In particular, our framework encodes images into a layered bitstream consisting of a semantic layer that delivers high-level semantic information through text prompts; a structural layer that captures spatial details using edge or skeleton maps; and a texture layer that preserves local textures via a colormap. Utilizing Stable Diffusion as the backend, the framework effectively leverages these multimodal priors for image generation, effectively functioning as a decoder when these priors are encoded. Qualitative and quantitative results show that our method proficiently restores both semantic and visual details, competing against baseline approaches at extremely low bitrates ( <0.02 bpp). Additionally, our framework facilitates downstream editing applications without requiring full decoding, thereby paving a new direction for future research in AIGI compression.
Authors: Karan Wanchoo, Xiaoye Zuo, Hannah Gonzalez, Soham Dan, Georgios Georgakis, Dan Roth, Kostas Daniilidis, Eleni Miltsakaki
Abstract: We present NAVCON, a large-scale annotated Vision-Language Navigation (VLN) corpus built on top of two popular datasets (R2R and RxR). The paper introduces four core, cognitively motivated and linguistically grounded, navigation concepts and an algorithm for generating large-scale silver annotations of naturally occurring linguistic realizations of these concepts in navigation instructions. We pair the annotated instructions with video clips of an agent acting on these instructions. NAVCON contains 236, 316 concept annotations for approximately 30, 0000 instructions and 2.7 million aligned images (from approximately 19, 000 instructions) showing what the agent sees when executing an instruction. To our knowledge, this is the first comprehensive resource of navigation concepts. We evaluated the quality of the silver annotations by conducting human evaluation studies on NAVCON samples. As further validation of the quality and usefulness of the resource, we trained a model for detecting navigation concepts and their linguistic realizations in unseen instructions. Additionally, we show that few-shot learning with GPT-4o performs well on this task using large-scale silver annotations of NAVCON.
Authors: Weiguo Pian, Shijian Deng, Shentong Mo, Yunhui Guo, Yapeng Tian
Abstract: In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with inconsistent modalities (image, audio, or video) and varying task types (captioning or question-answering). Unlike existing vision-only or modality-incremental settings, MICL combines modality and task type shifts, both of which drive catastrophic forgetting. To address these challenges, we propose MoInCL, which employs a Pseudo Targets Generation Module to mitigate forgetting caused by task type shifts in previously seen modalities. It also incorporates Instruction-based Knowledge Distillation to preserve the model's ability to handle previously learned modalities when new ones are introduced. We benchmark MICL using a total of six tasks and conduct experiments to validate the effectiveness of our proposed MoInCL. The experimental results highlight the superiority of MoInCL, showing significant improvements over representative and state-of-the-art continual learning baselines.
Authors: Haoshen Wang, Zhentao Liu, Kaicong Sun, Xiaodong Wang, Dinggang Shen, Zhiming Cui
Abstract: The generation of medical images presents significant challenges due to their high-resolution and three-dimensional nature. Existing methods often yield suboptimal performance in generating high-quality 3D medical images, and there is currently no universal generative framework for medical imaging. In this paper, we introduce the 3D Medical Diffusion (3D MedDiffusion) model for controllable, high-quality 3D medical image generation. 3D MedDiffusion incorporates a novel, highly efficient Patch-Volume Autoencoder that compresses medical images into latent space through patch-wise encoding and recovers back into image space through volume-wise decoding. Additionally, we design a new noise estimator to capture both local details and global structure information during diffusion denoising process. 3D MedDiffusion can generate fine-detailed, high-resolution images (up to 512x512x512) and effectively adapt to various downstream tasks as it is trained on large-scale datasets covering CT and MRI modalities and different anatomical regions (from head to leg). Experimental results demonstrate that 3D MedDiffusion surpasses state-of-the-art methods in generative quality and exhibits strong generalizability across tasks such as sparse-view CT reconstruction, fast MRI reconstruction, and data augmentation.
Authors: Stanislas Ducotterd, Sebastian Neumayer, Michael Unser
Abstract: We aim at the solution of inverse problems in imaging, by combining a penalized sparse representation of image patches with an unconstrained smooth one. This allows for a straightforward interpretation of the reconstruction. We formulate the optimization as a bilevel problem. The inner problem deploys classical algorithms while the outer problem optimizes the dictionary and the regularizer parameters through supervised learning. The process is carried out via implicit differentiation and gradient-based optimization. We evaluate our method for denoising, super-resolution, and compressed-sensing magnetic-resonance imaging. We compare it to other classical models as well as deep-learning-based methods and show that it always outperforms the former and also the latter in some instances.
Authors: Junda Wang, Minghui Hu, Ning Li, Abdulaziz Al-Ali, Ponnuthurai Nagaratnam Suganthan
Abstract: Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization.
Authors: Axel Durbet, Paul-Marie Grollemund, Pascal Lafourcade, Kevin Thiry-Atighehchi
Abstract: Biometric systems are widely used for identity verification and identification, including authentication (i.e., one-to-one matching to verify a claimed identity) and identification (i.e., one-to-many matching to find a subject in a database). The matching process relies on measuring similarities or dissimilarities between a fresh biometric template and enrolled templates. The False Match Rate FMR is a key metric for assessing the accuracy and reliability of such systems. This paper analyzes biometric systems based on their FMR, with two main contributions. First, we explore untargeted attacks, where an adversary aims to impersonate any user within a database. We determine the number of trials required for an attacker to successfully impersonate a user and derive the critical population size (i.e., the maximum number of users in the database) required to maintain a given level of security. Furthermore, we compute the critical FMR value needed to ensure resistance against untargeted attacks as the database size increases. Second, we revisit the biometric birthday problem to evaluate the approximate and exact probabilities that two users in a database collide (i.e., can impersonate each other). Based on this analysis, we derive both the approximate critical population size and the critical FMR value needed to bound the likelihood of such collisions occurring with a given probability. These thresholds offer insights for designing systems that mitigate the risk of impersonation and collisions, particularly in large-scale biometric databases. Our findings indicate that current biometric systems fail to deliver sufficient accuracy to achieve an adequate security level against untargeted attacks, even in small-scale databases. Moreover, state-of-the-art systems face significant challenges in addressing the biometric birthday problem, especially as database sizes grow.
Authors: Xiao Zhou, Luoyi Sun, Dexuan He, Wenbin Guan, Ruifen Wang, Lifeng Wang, Xin Sun, Kun Sun, Ya Zhang, Yanfeng Wang, Weidi Xie
Abstract: Deep learning has enabled the development of highly robust foundation models for various pathological tasks across diverse diseases and patient cohorts. Among these models, vision-language pre-training, which leverages large-scale paired data to align pathology image and text embedding spaces, and provides a novel zero-shot paradigm for downstream tasks. However, existing models have been primarily data-driven and lack the incorporation of domain-specific knowledge, which limits their performance in cancer diagnosis, especially for rare tumor subtypes. To address this limitation, we establish a Knowledge-enhanced Pathology (KEEP) foundation model that harnesses disease knowledge to facilitate vision-language pre-training. Specifically, we first construct a disease knowledge graph (KG) that covers 11,454 human diseases with 139,143 disease attributes, including synonyms, definitions, and hypernym relations. We then systematically reorganize the millions of publicly available noisy pathology image-text pairs, into 143K well-structured semantic groups linked through the hierarchical relations of the disease KG. To derive more nuanced image and text representations, we propose a novel knowledge-enhanced vision-language pre-training approach that integrates disease knowledge into the alignment within hierarchical semantic groups instead of unstructured image-text pairs. Validated on 18 diverse benchmarks with more than 14,000 whole slide images (WSIs), KEEP achieves state-of-the-art performance in zero-shot cancer diagnostic tasks. Notably, for cancer detection, KEEP demonstrates an average sensitivity of 89.8% at a specificity of 95.0% across 7 cancer types. For cancer subtyping, KEEP achieves a median balanced accuracy of 0.456 in subtyping 30 rare brain cancers, indicating strong generalizability for diagnosing rare tumors.
Authors: Maximilian Fischer, Peter Neher, Peter Sch\"uffler, Sebastian Ziegler, Shuhan Xiao, Robin Peretzke, David Clunie, Constantin Ulrich, Michael Baumgartner, Alexander Muckenhuber, Silvia Dias Almeida, Michael G\"otz, Jens Kleesiek, Marco Nolden, Rickmer Braren, Klaus Maier-Hein
Abstract: Digital pathology offers a groundbreaking opportunity to transform clinical practice in histopathological image analysis, yet faces a significant hurdle: the substantial file sizes of pathological Whole Slide Images (WSI). While current digital pathology solutions rely on lossy JPEG compression to address this issue, lossy compression can introduce color and texture disparities, potentially impacting clinical decision-making. While prior research addresses perceptual image quality and downstream performance independently of each other, we jointly evaluate compression schemes for perceptual and downstream task quality on four different datasets. In addition, we collect an initially uncompressed dataset for an unbiased perceptual evaluation of compression schemes. Our results show that deep learning models fine-tuned for perceptual quality outperform conventional compression schemes like JPEG-XL or WebP for further compression of WSI. However, they exhibit a significant bias towards the compression artifacts present in the training data and struggle to generalize across various compression schemes. We introduce a novel evaluation metric based on feature similarity between original files and compressed files that aligns very well with the actual downstream performance on the compressed WSI. Our metric allows for a general and standardized evaluation of lossy compression schemes and mitigates the requirement to independently assess different downstream tasks. Our study provides novel insights for the assessment of lossy compression schemes for WSI and encourages a unified evaluation of lossy compression schemes to accelerate the clinical uptake of digital pathology.
Authors: Mohammad Nazmush Shamael, Sabila Nawshin, Swakkhar Shatabda, Salekul Islam
Abstract: This work presents the BanglishRev Dataset, the largest e-commerce product review dataset to date for reviews written in Bengali, English, a mixture of both and Banglish, Bengali words written with English alphabets. The dataset comprises of 1.74 million written reviews from 3.2 million ratings information collected from a total of 128k products being sold in online e-commerce platforms targeting the Bengali population. It includes an extensive array of related metadata for each of the reviews including the rating given by the reviewer, date the review was posted and date of purchase, number of likes, dislikes, response from the seller, images associated with the review etc. With sentiment analysis being the most prominent usage of review datasets, experimentation with a binary sentiment analysis model with the review rating serving as an indicator of positive or negative sentiment was conducted to evaluate the effectiveness of the large amount of data presented in BanglishRev for sentiment analysis tasks. A BanglishBERT model is trained on the data from BanglishRev with reviews being considered labeled positive if the rating is greater than 3 and negative if the rating is less than or equal to 3. The model is evaluated by being testing against a previously published manually annotated dataset for e-commerce reviews written in a mixture of Bangla, English and Banglish. The experimental model achieved an exceptional accuracy of 94\% and F1 score of 0.94, demonstrating the dataset's efficacy for sentiment analysis. Some of the intriguing patterns and observations seen within the dataset and future research directions where the dataset can be utilized is also discussed and explored. The dataset can be accessed through https://huggingface.co/datasets/BanglishRev/bangla-english-and-code-mixed-ecommerce-review-dataset.
URLs: https://huggingface.co/datasets/BanglishRev/bangla-english-and-code-mixed-ecommerce-review-dataset.
Authors: Yifei Zhou, Qianlan Yang, Kaixiang Lin, Min Bai, Xiong Zhou, Yu-Xiong Wang, Sergey Levine, Erran Li
Abstract: The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation models. Such a generalist agent needs to have a large and diverse skill repertoire, such as finding directions between two travel locations and buying specific items from the Internet. If each skill needs to be specified manually through a fixed set of human-annotated instructions, the agent's skill repertoire will necessarily be limited due to the quantity and diversity of human-annotated instructions. In this work, we address this challenge by proposing Proposer-Agent-Evaluator, an effective learning system that enables foundation model agents to autonomously discover and practice skills in the wild. At the heart of PAE is a context-aware task proposer that autonomously proposes tasks for the agent to practice with context information of the environment such as user demos or even just the name of the website itself for Internet-browsing agents. Then, the agent policy attempts those tasks with thoughts and actual grounded operations in the real world with resulting trajectories evaluated by an autonomous VLM-based success evaluator. The success evaluation serves as the reward signal for the agent to refine its policies through RL. We validate PAE on challenging vision-based web navigation, using both real-world and self-hosted websites from WebVoyager and WebArena.To the best of our knowledge, this work represents the first effective learning system to apply autonomous task proposal with RL for agents that generalizes real-world human-annotated benchmarks with SOTA performances. Our open-source checkpoints and code can be found in https://yanqval.github.io/PAE/
Authors: Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, Yikang Li
Abstract: Multi-modal fusion is a fundamental task for the perception of an autonomous driving system, which has recently intrigued many researchers. However, achieving a rather good performance is not an easy task due to the noisy raw data, underutilized information, and the misalignment of multi-modal sensors. In this paper, we provide a literature review of the existing multi-modal-based methods for perception tasks in autonomous driving. Generally, we make a detailed analysis including over 50 papers leveraging perception sensors including LiDAR and camera trying to solve object detection and semantic segmentation tasks. Different from traditional fusion methodology for categorizing fusion models, we propose an innovative way that divides them into two major classes, four minor classes by a more reasonable taxonomy in the view of the fusion stage. Moreover, we dive deep into the current fusion methods, focusing on the remaining problems and open-up discussions on the potential research opportunities. In conclusion, what we expect to do in this paper is to present a new taxonomy of multi-modal fusion methods for the autonomous driving perception tasks and provoke thoughts of the fusion-based techniques in the future.
Authors: Mingde Yao, Ruikang Xu, Yuanshen Guan, Jie Huang, Zhiwei Xiong
Abstract: Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR decomposes different types of degradations adaptively, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively recognize and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalization capability of our method.
Authors: Lily Erickson
Abstract: Despite lagging behind their modal cousins in many respects, Vision Transformers have provided an interesting opportunity to bridge the gap between sequence modeling and image modeling. Up until now however, vision transformers have largely been held back, due to both computational inefficiency, and lack of proper handling of spatial dimensions. In this paper, we introduce the Cross-Axis Transformer. CAT is a model inspired by both Axial Transformers, and Microsoft's recent Retentive Network, that drastically reduces the required number of floating point operations required to process an image, while simultaneously converging faster and more accurately than the Vision Transformers it replaces.
Authors: Moulik Choraria, Xinbo Wu, Sourya Basu, Nitesh Sekhar, Yue Wu, Xu Zhang, Prateek Singhal, Lav R. Varshney
Abstract: General purpose Vision Language Models (VLMs) have received tremendous interest in recent years, owing to their ability to learn rich vision-language correlations as well as their broad zero-shot competencies. One immensely popular line of work utilizes frozen unimodal models, by bridging vision representations to language using a trainable module called the QFormer. However, this method relies heavily on large-scale multimodal pretraining with huge computational overheads. To that end, we propose a more efficient framework for QFormer-based vision-language alignment. Our key idea relies on the observation that QFormer latents correspond more strongly to the frozen LLM's intermediate latent space. Consequently, instead of using QFormer latents as inputs to the LLM, we alter the framework by using the latents to directly condition the LLM latent space for image-to-text generation. We demonstrate the effectiveness of our approach against existing baselines in improving the efficiency of vision-language pretraining.
Authors: Der-Hau Lee
Abstract: The accurate prediction of smooth steering inputs is crucial for automotive applications because control actions with jitter might cause the vehicle system to become unstable. To address this problem in automobile lane-keeping control without the use of additional smoothing algorithms, we developed a novel soft-constrained iterative linear quadratic regulator (soft-CILQR) algorithm by integrating CILQR algorithm and a model predictive control (MPC) constraint relaxation method. We incorporated slack variables into the state and control barrier functions of the soft-CILQR solver to soften the constraints in the optimization process such that control input stabilization can be achieved in a computationally simple manner. Two types of automotive lane-keeping experiments (numerical simulations and experiments involving challenging vision-based maneuvers) were conducted with a linear system dynamics model to test the performance of the proposed soft-CILQR algorithm, and its performance was compared with that of the CILQR algorithm. In the numerical simulations, the soft-CILQR and CILQR solvers managed to drive the system toward the reference state asymptotically; however, the soft-CILQR solver obtained smooth steering input trajectories more easily than did the CILQR solver under conditions involving additive disturbances. The results of the vision-based experiments in which an ego vehicle drove in perturbed TORCS environments with various road friction settings were consistent with those of the numerical tests. The proposed soft-CILQR algorithm achieved an average runtime of 2.55 ms and is thus applicable for real-time autonomous driving scenarios.
Authors: Ci-Siang Lin, Chien-Yi Wang, Yu-Chiang Frank Wang, Min-Hung Chen
Abstract: Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models using image data with only image-level supervision. Since precise pixel-level annotations are not accessible, existing methods typically focus on producing pseudo masks for training segmentation models by refining CAM-like heatmaps. However, the produced heatmaps may capture only the discriminative image regions of object categories or the associated co-occurring backgrounds. To address the issues, we propose a Semantic Prompt Learning for WSSS (SemPLeS) framework, which learns to effectively prompt the CLIP latent space to enhance the semantic alignment between the segmented regions and the target object categories. More specifically, we propose Contrastive Prompt Learning and Prompt-guided Semantic Refinement to learn the prompts that adequately describe and suppress the co-occurring backgrounds associated with each object category. In this way, SemPLeS can perform better semantic alignment between object regions and class labels, resulting in desired pseudo masks for training segmentation models. The proposed SemPLeS framework achieves competitive performance on standard WSSS benchmarks, PASCAL VOC 2012 and MS COCO2014, and shows compatibility with other WSSS methods.
Authors: Miao Zhang, Zee fryer, Ben Colman, Ali Shahriyari, Gaurav Bharaj
Abstract: Machine learning model bias can arise from dataset composition: correlated sensitive features can disturb the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing works tackle most prominent bias features, like colors of digits or background of animals. However, a real-world dataset often includes a large number of feature correlations, that manifest intrinsically in the data as common sense information. Such spurious visual cues can further reduce model robustness. Thus, practitioners desire the whole picture of correlations and flexibility to treat concerned bias for specific domain tasks. With this goal, we propose a novel framework to extract comprehensive bias information in image datasets based on textual descriptions, a common sense-rich modality. Specifically, features are constructed by clustering noun phrase embeddings of similar semantics. Each feature's appearance across a dataset is inferred and their co-occurrence statistics are measured, with spurious correlations optionally examined by a human-in-the-loop interface. Downstream experiments show that our method discovers novel model biases on multiple image benchmark datasets. Furthermore, the discovered bias can be mitigated by a simple data re-weighting strategy that de-correlates the features, and outperforms state-of-the-art unsupervised bias mitigation methods.
Authors: Sana Ayromlou, Vahid Reza Khazaie, Fereshteh Forghani, Arash Afkanpour
Abstract: The rapid advancement in self-supervised representation learning has highlighted its potential to leverage unlabeled data for learning rich visual representations. However, the existing techniques, particularly those employing different augmentations of the same image, often rely on a limited set of simple transformations that cannot fully capture variations in the real world. This constrains the diversity and quality of samples, which leads to sub-optimal representations. In this paper, we introduce a framework that enriches the self-supervised learning (SSL) paradigm by utilizing generative models to produce semantically consistent image augmentations. By directly conditioning generative models on a source image, our method enables the generation of diverse augmentations while maintaining the semantics of the source image, thus offering a richer set of data for SSL. Our extensive experimental results on various joint-embedding SSL techniques demonstrate that our framework significantly enhances the quality of learned visual representations by up to 10\% Top-1 accuracy in downstream tasks. This research demonstrates that incorporating generative models into the joint-embedding SSL workflow opens new avenues for exploring the potential of synthetic data. This development paves the way for more robust and versatile representation learning techniques.
Authors: Mengqi Zhou, Yuxi Wang, Jun Hou, Shougao Zhang, Yiwei Li, Chuanchen Luo, Junran Peng, Zhaoxiang Zhang
Abstract: Developing comprehensive explicit world models is crucial for understanding and simulating real-world scenarios. Recently, Procedural Controllable Generation (PCG) has gained significant attention in large-scale scene generation by enabling the creation of scalable, high-quality assets. However, PCG faces challenges such as limited modular diversity, high expertise requirements, and challenges in managing the diverse elements and structures in complex scenes. In this paper, we introduce a large-scale scene generation framework, SceneX, which can automatically produce high-quality procedural models according to designers' textual descriptions. Specifically, the proposed method comprises two components, PCGHub and PCGPlanner. The former encompasses an extensive collection of accessible procedural assets and thousands of hand-craft API documents to perform as a standard protocol for PCG controller. The latter aims to generate executable actions for Blender to produce controllable and precise 3D assets guided by the user's instructions. Extensive experiments demonstrated the capability of our method in controllable large-scale scene generation, including nature scenes and unbounded cities, as well as scene editing such as asset placement and season translation.
Authors: Hao Xiang, Zhaoliang Zheng, Xin Xia, Runsheng Xu, Letian Gao, Zewei Zhou, Xu Han, Xinkai Ji, Mingxi Li, Zonglin Meng, Li Jin, Mingyue Lei, Zhaoyang Ma, Zihang He, Haoxuan Ma, Yunshuang Yuan, Yingqian Zhao, Jiaqi Ma
Abstract: Recent advancements in Vehicle-to-Everything (V2X) technologies have enabled autonomous vehicles to share sensing information to see through occlusions, greatly boosting the perception capability. However, there are no real-world datasets to facilitate the real V2X cooperative perception research -- existing datasets either only support Vehicle-to-Infrastructure cooperation or Vehicle-to-Vehicle cooperation. In this paper, we present V2X-Real, a large-scale dataset that includes a mixture of multiple vehicles and smart infrastructure to facilitate the V2X cooperative perception development with multi-modality sensing data. Our V2X-Real is collected using two connected automated vehicles and two smart infrastructure, which are all equipped with multi-modal sensors including LiDAR sensors and multi-view cameras. The whole dataset contains 33K LiDAR frames and 171K camera data with over 1.2M annotated bounding boxes of 10 categories in very challenging urban scenarios. According to the collaboration mode and ego perspective, we derive four types of datasets for Vehicle-Centric, Infrastructure-Centric, Vehicle-to-Vehicle, and Infrastructure-to-Infrastructure cooperative perception. Comprehensive multi-class multi-agent benchmarks of SOTA cooperative perception methods are provided. The V2X-Real dataset and codebase are available at https://mobility-lab.seas.ucla.edu/v2x-real.
Authors: Zhiwen Fan, Kairun Wen, Wenyan Cong, Kevin Wang, Jian Zhang, Xinghao Ding, Danfei Xu, Boris Ivanovic, Marco Pavone, Georgios Pavlakos, Zhangyang Wang, Yue Wang
Abstract: While neural 3D reconstruction has advanced substantially, it typically requires densely captured multi-view data with carefully initialized poses (e.g., using COLMAP). However, this requirement limits its broader applicability, as Structure-from-Motion (SfM) is often unreliable in sparse-view scenarios where feature matches are limited, resulting in cumulative errors. In this paper, we introduce InstantSplat, a novel and lightning-fast neural reconstruction system that builds accurate 3D representations from as few as 2-3 images. InstantSplat adopts a self-supervised framework that bridges the gap between 2D images and 3D representations using Gaussian Bundle Adjustment (GauBA) and can be optimized in an end-to-end manner. InstantSplat integrates dense stereo priors and co-visibility relationships between frames to initialize pixel-aligned geometry by progressively expanding the scene avoiding redundancy. Gaussian Bundle Adjustment is used to adapt both the scene representation and camera parameters quickly by minimizing gradient-based photometric error. Overall, InstantSplat achieves large-scale 3D reconstruction in mere seconds by reducing the required number of input views. It achieves an acceleration of over 20 times in reconstruction, improves visual quality (SSIM) from 0.3755 to 0.7624 than COLMAP with 3D-GS, and is compatible with multiple 3D representations (3D-GS, 2D-GS, and Mip-Splatting).
Authors: Junyi Li, Zhilu Zhang, Wangmeng Zuo
Abstract: Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potential to overcome the limitations of convolutions in many image restoration tasks, the attention mechanisms may violate the blind-spot requirement, thereby restricting their applicability in BSN. To this end, we propose to analyze and redesign the channel and spatial attentions to meet the blind-spot requirement. Specifically, channel self-attention may leak the blind-spot information in multi-scale architectures, since the downsampling shuffles the spatial feature into channel dimensions. To alleviate this problem, we divide the channel into several groups and perform channel attention separately. For spatial selfattention, we apply an elaborate mask to the attention matrix to restrict and mimic the receptive field of dilated convolution. Based on the redesigned channel and window attentions, we build a Transformer-based Blind-Spot Network (TBSN), which shows strong local fitting and global perspective abilities. Furthermore, we introduce a knowledge distillation strategy that distills TBSN into smaller denoisers to improve computational efficiency while maintaining performance. Extensive experiments on real-world image denoising datasets show that TBSN largely extends the receptive field and exhibits favorable performance against state-of-theart SSID methods.
Authors: Chenyang Zhu, Kai Li, Yue Ma, Chunming He, Xiu Li
Abstract: This paper introduces MultiBooth, a novel and efficient technique for multi-concept customization in image generation from text. Despite the significant advancements in customized generation methods, particularly with the success of diffusion models, existing methods often struggle with multi-concept scenarios due to low concept fidelity and high inference cost. MultiBooth addresses these issues by dividing the multi-concept generation process into two phases: a single-concept learning phase and a multi-concept integration phase. During the single-concept learning phase, we employ a multi-modal image encoder and an efficient concept encoding technique to learn a concise and discriminative representation for each concept. In the multi-concept integration phase, we use bounding boxes to define the generation area for each concept within the cross-attention map. This method enables the creation of individual concepts within their specified regions, thereby facilitating the formation of multi-concept images. This strategy not only improves concept fidelity but also reduces additional inference cost. MultiBooth surpasses various baselines in both qualitative and quantitative evaluations, showcasing its superior performance and computational efficiency. Project Page: https://multibooth.github.io/
Authors: Yexin Liu, Zhengyang Liang, Yueze Wang, Xianfeng Wu, Feilong Tang, Muyang He, Jian Li, Zheng Liu, Harry Yang, Sernam Lim, Bo Zhao
Abstract: Multimodal Large Language Models (MLLMs) have displayed remarkable performance in multi-modal tasks, particularly in visual comprehension. However, we reveal that MLLMs often generate incorrect answers even when they understand the visual content. To this end, we manually construct a benchmark with 12 categories and design evaluation metrics that assess the degree of error in MLLM responses even when the visual content is seemingly understood. Based on this benchmark, we test 15 leading MLLMs and analyze the distribution of attention maps and logits of some MLLMs. Our investigation identifies two primary issues: 1) most instruction tuning datasets predominantly feature questions that 'directly' relate to the visual content, leading to a bias in MLLMs' responses to other indirect questions, and 2) MLLMs' attention to visual tokens is notably lower than to system and question tokens. We further observe that attention scores between questions and visual tokens as well as the model's confidence in the answers are lower in response to misleading questions than to straightforward ones. To address the first challenge, we introduce a paired positive and negative data construction pipeline to diversify the dataset. For the second challenge, we propose to enhance the model's focus on visual content during decoding by refining the text and visual prompt. For the text prompt, we propose a content guided refinement strategy that performs preliminary visual content analysis to generate structured information before answering the question. Additionally, we employ a visual attention refinement strategy that highlights question-relevant visual tokens to increase the model's attention to visual content that aligns with the question. Extensive experiments demonstrate that these challenges can be significantly mitigated with our proposed dataset and techniques.
Authors: Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu
Abstract: Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV.
Authors: Ali Khaleghi Rahimian, Manish Kumar Govind, Subhajit Maity, Dominick Reilly, Christian K\"ummerle, Srijan Das, Aritra Dutta
Abstract: Transformer architectures such as Vision Transformers (ViT) have proven effective for solving visual perception tasks. However, they suffer from two major limitations; first, the quadratic complexity of self-attention limits the number of tokens that can be processed, and second, Transformers often require large amounts of training data to attain state-of-the-art performance. In this paper, we propose a new multi-head self-attention (MHSA) variant named Fibottention, which can replace MHSA in Transformer architectures. Fibottention is data-efficient and computationally more suitable for processing large numbers of tokens than the standard MHSA. It employs structured sparse attention based on dilated Fibonacci sequences, which, uniquely, differ across attention heads, resulting in inception-like diverse features across heads. The spacing of the Fibonacci sequences follows the Wythoff array, which minimizes the redundancy of token interactions aggregated across different attention heads, while still capturing sufficient complementary information through token pair interactions. These sparse attention patterns are unique among the existing sparse attention and lead to an $O(N \log N)$ complexity, where $N$ is the number of tokens. Leveraging only 2-6% of the elements in the self-attention heads, Fibottention embedded into popular, state-of-the-art Transformer architectures can achieve significantly improved predictive performance for domains with limited data such as image classification, video understanding, and robot learning tasks, and render reduced computational complexity. We further validated the improved diversity of feature representations resulting from different self-attention heads, and our model design against other sparse attention mechanisms.
Authors: Shengjia Chen, Gabriele Campanella, Abdulkadir Elmas, Aryeh Stock, Jennifer Zeng, Alexandros D. Polydorides, Adam J. Schoenfeld, Kuan-lin Huang, Jane Houldsworth, Chad Vanderbilt, Thomas J. Fuchs
Abstract: Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation. Due to the prevalent use of datasets created for genomic research, such as TCGA, for method development, the performance of these techniques on diagnostic slides from clinical practice has been inadequately explored. This study conducts a thorough benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks, including diagnostic assessment, biomarker classification, and outcome prediction. The results yield following key insights: (1) Embeddings derived from domain-specific (histological images) FMs outperform those from generic ImageNet-based models across aggregation methods. (2) Spatial-aware aggregators enhance the performance significantly when using ImageNet pre-trained models but not when using FMs. (3) No single model excels in all tasks and spatially-aware models do not show general superiority as it would be expected. These findings underscore the need for more adaptable and universally applicable aggregation techniques, guiding future research towards tools that better meet the evolving needs of clinical-AI in pathology. The code used in this work is available at \url{https://github.com/fuchs-lab-public/CPath_SABenchmark}.
Authors: Kai Liu, Zhihang Fu, Sheng Jin, Ze Chen, Fan Zhou, Rongxin Jiang, Yaowu Chen, Jieping Ye
Abstract: Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code is available at https://github.com/alibaba/esod.
Authors: Yanqi Bao, Tianyu Ding, Jing Huo, Yaoli Liu, Yuxin Li, Wenbin Li, Yang Gao, Jiebo Luo
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to become a mainstream method for 3D representations. It can effectively transform multi-view images into explicit 3D Gaussian through efficient training, and achieve real-time rendering of novel views. This survey aims to analyze existing 3DGS-related works from multiple intersecting perspectives, including related tasks, technologies, challenges, and opportunities. The primary objective is to provide newcomers with a rapid understanding of the field and to assist researchers in methodically organizing existing technologies and challenges. Specifically, we delve into the optimization, application, and extension of 3DGS, categorizing them based on their focuses or motivations. Additionally, we summarize and classify nine types of technical modules and corresponding improvements identified in existing works. Based on these analyses, we further examine the common challenges and technologies across various tasks, proposing potential research opportunities.
Authors: Xiaowei Chi, Yatian Wang, Aosong Cheng, Pengjun Fang, Zeyue Tian, Yingqing He, Zhaoyang Liu, Xingqun Qi, Jiahao Pan, Rongyu Zhang, Mengfei Li, Ruibin Yuan, Yanbing Jiang, Wei Xue, Wenhan Luo, Qifeng Chen, Shanghang Zhang, Qifeng Liu, Yike Guo
Abstract: Massive multi-modality datasets play a significant role in facilitating the success of large video-language models. However, current video-language datasets primarily provide text descriptions for visual frames, considering audio to be weakly related information. They usually overlook exploring the potential of inherent audio-visual correlation, leading to monotonous annotation within each modality instead of comprehensive and precise descriptions. Such ignorance results in the difficulty of multiple cross-modality studies. To fulfill this gap, we present MMTrail, a large-scale multi-modality video-language dataset incorporating more than 20M trailer clips with visual captions, and 2M high-quality clips with multimodal captions. Trailers preview full-length video works and integrate context, visual frames, and background music. In particular, the trailer has two main advantages: (1) the topics are diverse, and the content characters are of various types, e.g., film, news, and gaming. (2) the corresponding background music is custom-designed, making it more coherent with the visual context. Upon these insights, we propose a systemic captioning framework, achieving various modality annotations with more than 27.1k hours of trailer videos. Here, to ensure the caption retains music perspective while preserving the authority of visual context, we leverage the advanced LLM to merge all annotations adaptively. In this fashion, our MMtrail dataset potentially paves the path for fine-grained large multimodal-language model training. In experiments, we provide evaluation metrics and benchmark results on our dataset, demonstrating the high quality of our annotation and its effectiveness for model training.
Authors: Amirhosein Chahe, Lifeng Zhou
Abstract: This paper introduces a novel method for open-vocabulary 3D scene querying in autonomous driving by combining Language Embedded 3D Gaussians with Large Language Models (LLMs). We propose utilizing LLMs to generate both contextually canonical phrases and helping positive words for enhanced segmentation and scene interpretation. Our method leverages GPT-3.5 Turbo as an expert model to create a high-quality text dataset, which we then use to fine-tune smaller, more efficient LLMs for on-device deployment. Our comprehensive evaluation on the WayveScenes101 dataset demonstrates that LLM-guided segmentation significantly outperforms traditional approaches based on predefined canonical phrases. Notably, our fine-tuned smaller models achieve performance comparable to larger expert models while maintaining faster inference times. Through ablation studies, we discover that the effectiveness of helping positive words correlates with model scale, with larger models better equipped to leverage additional semantic information. This work represents a significant advancement towards more efficient, context-aware autonomous driving systems, effectively bridging 3D scene representation with high-level semantic querying while maintaining practical deployment considerations.
Authors: Mohammadreza Samadi, Fred X. Han, Mohammad Salameh, Hao Wu, Fengyu Sun, Chunhua Zhou, Di Niu
Abstract: Diffusion models have demonstrated outstanding performance in generative tasks, making them ideal candidates for image editing. Recent studies highlight their ability to apply desired edits effectively by following textual instructions, yet with two key challenges remaining. First, these models struggle to apply multiple edits simultaneously, resulting in computational inefficiencies due to their reliance on sequential processing. Second, relying on textual prompts to determine the editing region can lead to unintended alterations to the image. We introduce FunEditor, an efficient diffusion model designed to learn atomic editing functions and perform complex edits by aggregating simpler functions. This approach enables complex editing tasks, such as object movement, by aggregating multiple functions and applying them simultaneously to specific areas. Our experiments demonstrate that FunEditor significantly outperforms recent inference-time optimization methods and fine-tuned models, either quantitatively across various metrics or through visual comparisons or both, on complex tasks like object movement and object pasting. In the meantime, with only 4 steps of inference, FunEditor achieves 5-24x inference speedups over existing popular methods. The code is available at: mhmdsmdi.github.io/funeditor/.
Authors: Diandian Guo, Weixin Si, Zhixi Li, Jialun Pei, Pheng-Ann Heng
Abstract: Pringle maneuver (PM) in laparoscopic liver resection aims to reduce blood loss and provide a clear surgical view by intermittently blocking blood inflow of the liver, whereas prolonged PM may cause ischemic injury. To comprehensively monitor this surgical procedure and provide timely warnings of ineffective and prolonged blocking, we suggest two complementary AI-assisted surgical monitoring tasks: workflow recognition and blocking effectiveness detection in liver resections. The former presents challenges in real-time capturing of short-term PM, while the latter involves the intraoperative discrimination of long-term liver ischemia states. To address these challenges, we meticulously collect a novel dataset, called PmLR50, consisting of 25,037 video frames covering various surgical phases from 50 laparoscopic liver resection procedures. Additionally, we develop an online baseline for PmLR50, termed PmNet. This model embraces Masked Temporal Encoding (MTE) and Compressed Sequence Modeling (CSM) for efficient short-term and long-term temporal information modeling, and embeds Contrastive Prototype Separation (CPS) to enhance action discrimination between similar intraoperative operations. Experimental results demonstrate that PmNet outperforms existing state-of-the-art surgical workflow recognition methods on the PmLR50 benchmark. Our research offers potential clinical applications for the laparoscopic liver surgery community. Codes are available at https://github.com/RascalGdd/PmNet.
Authors: Chao Zhang, Jiamin Tang, Jing Xiao
Abstract: Significant advancements in Large Multimodal Models (LMMs) have enabled them to tackle complex problems involving visual-mathematical reasoning. However, their ability to identify geometric elements remains underexplored. To address this gap, we introduce Tangram, a novel benchmark designed to evaluate the performance of LMMs on geometric element recognition. Tangram comprises 1,080 diverse geometric diagrams sourced from primary and secondary school exams, competitions, and textbooks, ranging from simple geometric shapes to complex combinations. Each diagram is paired with four questions, resulting in 4,320 visual-question-answer pairs. Unlike existing benchmarks that emphasize higher-level cognition and reasoning, Tangram focuses on understanding geometric elements, requiring models to perform a ``simple yet challenging" counting task. Systematic evaluation of 13 prominent LMMs, such as GPT-4o and Claude 3.5 Sonnet, reveals that these models face significant challenges even in seemingly straightforward tasks. The top-performing model achieves an accuracy of only 53.0%, highlighting a substantial gap compared to human performance. These findings underscore the limitations of current multimodal AI systems in handling basic perception tasks and serve to inspire the development of the next generation of expert-level multimodal foundational models. The data and code will be released soon.
Authors: Xiujian Liang, Gaozhi Liu, Yichao Si, Xiaoxiao Hu, Zhenxing Qian
Abstract: Digital watermarking has shown its effectiveness in protecting multimedia content. However, existing watermarking is predominantly tailored for specific media types, rendering them less effective for the protection of content displayed on computer screens, which is often multi-modal and dynamic. Visual Screen Content (VSC), is particularly susceptible to theft and leakage through screenshots, a vulnerability that current watermarking methods fail to adequately address.To address these challenges, we propose ScreenMark, a robust and practical watermarking method designed specifically for arbitrary VSC protection. ScreenMark utilizes a three-stage progressive watermarking framework. Initially, inspired by diffusion principles, we initialize the mutual transformation between regular watermark information and irregular watermark patterns. Subsequently, these patterns are integrated with screen content using a pre-multiplication alpha blending technique, supported by a pre-trained screen decoder for accurate watermark retrieval. The progressively complex distorter enhances the robustness of the watermark in real-world screenshot scenarios. Finally, the model undergoes fine-tuning guided by a joint-level distorter to ensure optimal performance. To validate the effectiveness of ScreenMark, we compiled a dataset comprising 100,000 screenshots from various devices and resolutions. Extensive experiments on different datasets confirm the superior robustness, imperceptibility, and practical applicability of the method.
Authors: Haisheng Su, Wei Wu, Junchi Yan
Abstract: Current end-to-end autonomous driving methods resort to unifying modular designs for various tasks (e.g. perception, prediction and planning). Although optimized in a planning-oriented spirit with a fully differentiable framework, existing end-to-end driving systems without ego-centric designs still suffer from unsatisfactory performance and inferior efficiency, owing to the rasterized scene representation learning and redundant information transmission. In this paper, we revisit the human driving behavior and propose an ego-centric fully sparse paradigm, named DiFSD, for end-to-end self-driving. Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner. The sparse perception module performs detection, tracking and online mapping based on sparse representation of the driving scene. The hierarchical interaction module aims to select the Closest In-Path Vehicle / Stationary (CIPV / CIPS) from coarse to fine, benefiting from an additional geometric prior. As for the iterative motion planner, both selected interactive agents and ego-vehicle are considered for joint motion prediction, where the output multi-modal ego-trajectories are optimized in an iterative fashion. Besides, both position-level motion diffusion and trajectory-level planning denoising are introduced for uncertainty modeling, thus facilitating the training stability and convergence of the whole framework. Extensive experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superior planning performance and great efficiency of DiFSD.
Authors: Brent Yi, Vickie Ye, Maya Zheng, Yunqi Li, Lea M\"uller, Georgios Pavlakos, Yi Ma, Jitendra Malik, Angjoo Kanazawa
Abstract: We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%. Project page: https://egoallo.github.io/
Authors: Dongxu Li, Yudong Liu, Haoning Wu, Yue Wang, Zhiqi Shen, Bowen Qu, Xinyao Niu, Fan Zhou, Chengen Huang, Yanpeng Li, Chongyan Zhu, Xiaoyi Ren, Chao Li, Yifan Ye, Lihuan Zhang, Hanshu Yan, Guoyin Wang, Bei Chen, Junnan Li
Abstract: Information comes in diverse modalities. Multimodal native AI models are essential to integrate real-world information and deliver comprehensive understanding. While proprietary multimodal native models exist, their lack of openness imposes obstacles for adoptions, let alone adaptations. To fill this gap, we introduce Aria, an open multimodal native model with best-in-class performance across a wide range of multimodal, language, and coding tasks. Aria is a mixture-of-expert model with 3.9B and 3.5B activated parameters per visual token and text token, respectively. It outperforms Pixtral-12B and Llama3.2-11B, and is competitive against the best proprietary models on various multimodal tasks. We pre-train Aria from scratch following a 4-stage pipeline, which progressively equips the model with strong capabilities in language understanding, multimodal understanding, long context window, and instruction following. We open-source the model weights along with a codebase that facilitates easy adoptions and adaptations of Aria in real-world applications.
Authors: Shaozhe Hao, Xuantong Liu, Xianbiao Qi, Shihao Zhao, Bojia Zi, Rong Xiao, Kai Han, Kwan-Yee K. Wong
Abstract: We introduce BiGR, a novel conditional image generation model using compact binary latent codes for generative training, focusing on enhancing both generation and representation capabilities. BiGR is the first conditional generative model that unifies generation and discrimination within the same framework. BiGR features a binary tokenizer, a masked modeling mechanism, and a binary transcoder for binary code prediction. Additionally, we introduce a novel entropy-ordered sampling method to enable efficient image generation. Extensive experiments validate BiGR's superior performance in generation quality, as measured by FID-50k, and representation capabilities, as evidenced by linear-probe accuracy. Moreover, BiGR showcases zero-shot generalization across various vision tasks, enabling applications such as image inpainting, outpainting, editing, interpolation, and enrichment, without the need for structural modifications. Our findings suggest that BiGR unifies generative and discriminative tasks effectively, paving the way for further advancements in the field. We further enable BiGR to perform text-to-image generation, showcasing its potential for broader applications.
Authors: Shuangrui Ding, Rui Qian, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Yuhang Cao, Yuwei Guo, Dahua Lin, Jiaqi Wang
Abstract: The Segment Anything Model 2 (SAM 2) has emerged as a powerful foundation model for object segmentation in both images and videos, paving the way for various downstream video applications. The crucial design of SAM 2 for video segmentation is its memory module, which prompts object-aware memories from previous frames for current frame prediction. However, its greedy-selection memory design suffers from the "error accumulation" problem, where an errored or missed mask will cascade and influence the segmentation of the subsequent frames, which limits the performance of SAM 2 toward complex long-term videos. To this end, we introduce SAM2Long, an improved training-free video object segmentation strategy, which considers the segmentation uncertainty within each frame and chooses the video-level optimal results from multiple segmentation pathways in a constrained tree search manner. In practice, we maintain a fixed number of segmentation pathways throughout the video. For each frame, multiple masks are proposed based on the existing pathways, creating various candidate branches. We then select the same fixed number of branches with higher cumulative scores as the new pathways for the next frame. After processing the final frame, the pathway with the highest cumulative score is chosen as the final segmentation result. Benefiting from its heuristic search design, SAM2Long is robust toward occlusions and object reappearances, and can effectively segment and track objects for complex long-term videos. Notably, SAM2Long achieves an average improvement of 3.0 points across all 24 head-to-head comparisons, with gains of up to 5.3 points in J&F on long-term video object segmentation benchmarks such as SA-V and LVOS. The code is released at https://github.com/Mark12Ding/SAM2Long.
Authors: Zun Wang, Jialu Li, Han Lin, Jaehong Yoon, Mohit Bansal
Abstract: Storytelling video generation (SVG) has recently emerged as a task to create long, multi-motion, multi-scene videos that consistently represent the story described in the input text script. SVG holds great potential for diverse content creation in media and entertainment; however, it also presents significant challenges: (1) objects must exhibit a range of fine-grained, complex motions, (2) multiple objects need to appear consistently across scenes, and (3) subjects may require multiple motions with seamless transitions within a single scene. To address these challenges, we propose DreamRunner, a novel story-to-video generation method: First, we structure the input script using a large language model (LLM) to facilitate both coarse-grained scene planning as well as fine-grained object-level layout and motion planning. Next, DreamRunner presents retrieval-augmented test-time adaptation to capture target motion priors for objects in each scene, supporting diverse motion customization based on retrieved videos, thus facilitating the generation of new videos with complex, scripted motions. Lastly, we propose a novel spatial-temporal region-based 3D attention and prior injection module SR3AI for fine-grained object-motion binding and frame-by-frame semantic control. We compare DreamRunner with various SVG baselines, demonstrating state-of-the-art performance in character consistency, text alignment, and smooth transitions. Additionally, DreamRunner exhibits strong fine-grained condition-following ability in compositional text-to-video generation, significantly outperforming baselines on T2V-ComBench. Finally, we validate DreamRunner's robust ability to generate multi-object interactions with qualitative examples.
Authors: Chengxing Xie, Xiaoming Zhang, Linze Li, Yuqian Fu, Biao Gong, Tianrui Li, Kai Zhang
Abstract: Recent advances in image super-resolution (SR) have significantly benefited from the incorporation of Transformer architectures. However, conventional techniques aimed at enlarging the self-attention window to capture broader contexts come with inherent drawbacks, especially the significantly increased computational demands. Moreover, the feature perception within a fixed-size window of existing models restricts the effective receptive fields and the intermediate feature diversity. This study demonstrates that a flexible integration of attention across diverse spatial extents can yield significant performance enhancements. In line with this insight, we introduce Multi-Range Attention Transformer (MAT) tailored for SR tasks. MAT leverages the computational advantages inherent in dilation operation, in conjunction with self-attention mechanism, to facilitate both multi-range attention (MA) and sparse multi-range attention (SMA), enabling efficient capture of both regional and sparse global features. Further coupled with local feature extraction, MAT adeptly capture dependencies across various spatial ranges, improving the diversity and efficacy of its feature representations. We also introduce the MSConvStar module, which augments the model's ability for multi-range representation learning. Comprehensive experiments show that our MAT exhibits superior performance to existing state-of-the-art SR models with remarkable efficiency (~3.3 faster than SRFormer-light).
Authors: Meng Wang, Zach Noonan, Pnina Gershon, Bruce Mehler, Bryan Reimer, Shannon C. Roberts
Abstract: Understanding the context of crash occurrence in complex driving environments is essential for improving traffic safety and advancing automated driving. Previous studies have used statistical models and deep learning to predict crashes based on semantic, contextual, or vehicle kinematic features, but none have examined the combined influence of these factors. In this study, we term the integration of these features ``roadway complexity''. This paper introduces a two-stage framework that integrates roadway complexity features for crash prediction. In the first stage, an encoder extracts hidden contextual information from these features, generating complexity-infused features. The second stage uses both original and complexity-infused features to predict crash likelihood, achieving an accuracy of 87.98\% with original features alone and 90.15\% with the added complexity-infused features. Ablation studies confirm that a combination of semantic, kinematic, and contextual features yields the best results, which emphasize their role in capturing roadway complexity. Additionally, complexity index annotations generated by the Large Language Model outperform those by Amazon Mechanical Turk, highlighting the potential of AI-based tools for accurate, scalable crash prediction systems.
Authors: Linwei Dong, Qingnan Fan, Yihong Guo, Zhonghao Wang, Qi Zhang, Jinwei Chen, Yawei Luo, Changqing Zou
Abstract: Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive. While methods such as SinSR and OSEDiff have emerged to condense inference steps via distillation, their performance in image restoration or details recovery is not satisfied. To address this, we propose TSD-SR, a novel distillation framework specifically designed for real-world image super-resolution, aiming to construct an efficient and effective one-step model. We first introduce the Target Score Distillation, which leverages the priors of diffusion models and real image references to achieve more realistic image restoration. Secondly, we propose a Distribution-Aware Sampling Module to make detail-oriented gradients more readily accessible, addressing the challenge of recovering fine details. Extensive experiments demonstrate that our TSD-SR has superior restoration results (most of the metrics perform the best) and the fastest inference speed (e.g. 40 times faster than SeeSR) compared to the past Real-ISR approaches based on pre-trained diffusion priors.
Authors: Yu Wang, Xiaofei Zhou, Yichen Wang, Geyuan Zhang, Tianxing He
Abstract: With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that violates ethical and legal standards. However, existing methods struggle against state-of-the-art VLMs like GPT-4o, due to the over-exposure of harmful content and lack of stealthy malicious guidance. In this work, we propose a novel jailbreak attack framework: Multi-Modal Linkage (MML) Attack. Drawing inspiration from cryptography, MML utilizes an encryption-decryption process across text and image modalities to mitigate over-exposure of malicious information. To align the model's output with malicious intent covertly, MML employs a technique called "evil alignment", framing the attack within a video game production scenario. Comprehensive experiments demonstrate MML's effectiveness. Specifically, MML jailbreaks GPT-4o with attack success rates of 97.80% on SafeBench, 98.81% on MM-SafeBench and 99.07% on HADES-Dataset. Our code is available at https://github.com/wangyu-ovo/MML
Authors: Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Shaohui Lin
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava .
Authors: Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, Lixin Gu, Xuehui Wang, Qingyun Li, Yimin Ren, Zixuan Chen, Jiapeng Luo, Jiahao Wang, Tan Jiang, Bo Wang, Conghui He, Botian Shi, Xingcheng Zhang, Han Lv, Yi Wang, Wenqi Shao, Pei Chu, Zhongying Tu, Tong He, Zhiyong Wu, Huipeng Deng, Jiaye Ge, Kai Chen, Min Dou, Lewei Lu, Xizhou Zhu, Tong Lu, Dahua Lin, Yu Qiao, Jifeng Dai, Wenhai Wang
Abstract: We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing significant enhancements in training and testing strategies as well as data quality. In this work, we delve into the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations. Through extensive evaluations on a wide range of benchmarks, including multi-discipline reasoning, document understanding, multi-image / video understanding, real-world comprehension, multimodal hallucination detection, visual grounding, multilingual capabilities, and pure language processing, InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet. Notably, our model is the first open-source MLLMs to surpass 70% on the MMMU benchmark, achieving a 3.7-point improvement through Chain-of-Thought (CoT) reasoning and showcasing strong potential for test-time scaling. We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems. HuggingFace demo see https://huggingface.co/spaces/OpenGVLab/InternVL
Authors: Jinglong Yang, Yichen Wu, Jun Cen, Wenjian Huang, Hong Wang, Jianguo Zhang
Abstract: Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In real-world scenarios, we are generally confronted with the dynamic scenario where the data comes in a streaming manner. Driven by the practical need, in this paper, we first propose a novel Continual SAM adaptation (CoSAM) benchmark with 8 different task domains and carefully analyze the limitations of the existing SAM one-step adaptation methods in the continual segmentation scenario. Then we propose a novel simple-yet-effective Mixture of Domain Adapters (MoDA) algorithm which utilizes the Global Feature Tokens (GFT) and Global Assistant Tokens (GAT) modules to help the SAM encoder extract well-separated features for different task domains, and then provide the accurate task-specific information for continual learning. Extensive experiments demonstrate that our proposed MoDA obviously surpasses the existing classic continual learning methods, as well as prompt-based and adapter-based approaches for continual segmentation. Moreover, after sequential learning on the CoSAM benchmark with diverse data distributions, our MoDA maintains highly competitive results in the natural image domain, approaching the zero-shot performance of the original SAM, demonstrating its superior capability in knowledge preservation. Notably, the proposed MoDA can be seamlessly integrated into various one-step adaptation methods of SAM, which can consistently bring obvious performance gains. Code is available at \url{https://github.com/yangjl1215/CoSAM}
Authors: Jinlu Zhang, Jiji Tang, Rongsheng Zhang, Tangjie Lv, Xiaoshuai Sun
Abstract: Story visualization has gained increasing attention in artificial intelligence. However, existing methods still struggle with maintaining a balance between character identity preservation and text-semantics alignment, largely due to a lack of detailed semantic modeling of the story scene. To tackle this challenge, we propose a novel knowledge graph, namely Character Graph (\textbf{CG}), which comprehensively represents various story-related knowledge, including the characters, the attributes related to characters, and the relationship between characters. We then introduce StoryWeaver, an image generator that achieve Customization via Character Graph (\textbf{C-CG}), capable of consistent story visualization with rich text semantics. To further improve the multi-character generation performance, we incorporate knowledge-enhanced spatial guidance (\textbf{KE-SG}) into StoryWeaver to precisely inject character semantics into generation. To validate the effectiveness of our proposed method, extensive experiments are conducted using a new benchmark called TBC-Bench. The experiments confirm that our StoryWeaver excels not only in creating vivid visual story plots but also in accurately conveying character identities across various scenarios with considerable storage efficiency, \emph{e.g.}, achieving an average increase of +9.03\% DINO-I and +13.44\% CLIP-T. Furthermore, ablation experiments are conducted to verify the superiority of the proposed module. Codes and datasets are released at https://github.com/Aria-Zhangjl/StoryWeaver.
Authors: Yunshuai Zhou, Junbo Qiao, Jincheng Liao, Wei Li, Simiao Li, Jiao Xie, Yunhang Shen, Jie Hu, Shaohui Lin
Abstract: Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state and dynamically adjust the distilled solution space using contrastive learning. Additionally, we also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models. Note that the proposed DCKD is a structure-agnostic distillation framework, which can adapt to different backbones and can be combined with methods that optimize upper-bound constraints to further enhance model performance. Extensive experiments demonstrate that DCKD significantly outperforms the state-of-the-art KD methods across various image restoration tasks and backbones.
Authors: Sora Kim, Sungho Suh, Minsik Lee
Abstract: Diffusion models have achieved remarkable success in image generation, with applications broadening across various domains. Inpainting is one such application that can benefit significantly from diffusion models. Existing methods either hijack the reverse process of a pretrained diffusion model or cast the problem into a larger framework, \ie, conditioned generation. However, these approaches often require nested loops in the generation process or additional components for conditioning. In this paper, we present region-aware diffusion models (RAD) for inpainting with a simple yet effective reformulation of the vanilla diffusion models. RAD utilizes a different noise schedule for each pixel, which allows local regions to be generated asynchronously while considering the global image context. A plain reverse process requires no additional components, enabling RAD to achieve inference time up to 100 times faster than the state-of-the-art approaches. Moreover, we employ low-rank adaptation (LoRA) to fine-tune RAD based on other pretrained diffusion models, reducing computational burdens in training as well. Experiments demonstrated that RAD provides state-of-the-art results both qualitatively and quantitatively, on the FFHQ, LSUN Bedroom, and ImageNet datasets.
Authors: Kunlun Xu, Chenghao Jiang, Peixi Xiong, Yuxin Peng, Jiahuan Zhou
Abstract: Lifelong person re-identification (LReID) is an important but challenging task that suffers from catastrophic forgetting due to significant domain gaps between training steps. Existing LReID approaches typically rely on data replay and knowledge distillation to mitigate this issue. However, data replay methods compromise data privacy by storing historical exemplars, while knowledge distillation methods suffer from limited performance due to the cumulative forgetting of undistilled knowledge. To overcome these challenges, we propose a novel paradigm that models and rehearses the distribution of the old domains to enhance knowledge consolidation during the new data learning, possessing a strong anti-forgetting capacity without storing any exemplars. Specifically, we introduce an exemplar-free LReID method called Distribution Rehearsing via Adaptive Style Kernel Learning (DASK). DASK includes a Distribution Rehearser Learning (DRL) mechanism that learns to transform arbitrary distribution data into the current data style at each learning step. To enhance the style transfer capacity of DRL, an Adaptive Kernel Prediction Network (AKPNet) is explored to achieve an instance-specific distribution adjustment. Additionally, we design a Distribution Rehearsing-driven LReID Training (DRRT) module, which rehearses old distribution based on the new data via the old AKPNet model, achieving effective new-old knowledge accumulation under a joint knowledge consolidation scheme. Experimental results show our DASK outperforms the existing methods by 3.6%-6.8% and 4.5%-6.5% on anti-forgetting and generalization capacity, respectively. Our code is available at https://github.com/zhoujiahuan1991/AAAI2025-LReID-DASK
URLs: https://github.com/zhoujiahuan1991/AAAI2025-LReID-DASK
Authors: Taiming Lu, Tianmin Shu, Junfei Xiao, Luoxin Ye, Jiahao Wang, Cheng Peng, Chen Wei, Daniel Khashabi, Rama Chellappa, Alan Yuille, Jieneng Chen
Abstract: Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms priors (expectations) about the surrounding environments. GenEx generates an entire 3D-consistent imaginative environment from as little as a single RGB image, bringing it to life through panoramic video streams. Leveraging scalable 3D world data curated from Unreal Engine, our generative model is rounded in the physical world. It captures a continuous 360-degree environment with little effort, offering a boundless landscape for AI agents to explore and interact with. GenEx achieves high-quality world generation, robust loop consistency over long trajectories, and demonstrates strong 3D capabilities such as consistency and active 3D mapping. Powered by generative imagination of the world, GPT-assisted agents are equipped to perform complex embodied tasks, including both goal-agnostic exploration and goal-driven navigation. These agents utilize predictive expectation regarding unseen parts of the physical world to refine their beliefs, simulate different outcomes based on potential decisions, and make more informed choices. In summary, we demonstrate that GenEx provides a transformative platform for advancing embodied AI in imaginative spaces and brings potential for extending these capabilities to real-world exploration.
Authors: Songyan Zhang, Wenhui Huang, Zihui Gao, Hao Chen, Chen Lv
Abstract: The emergence of general human knowledge and impressive logical reasoning capacity in rapidly progressed vision-language models (VLMs) have driven increasing interest in applying VLMs to high-level autonomous driving tasks, such as scene understanding and decision-making. However, an in-depth study on the relationship between knowledge proficiency, especially essential driving expertise, and closed-loop autonomous driving performance requires further exploration. In this paper, we investigate the effects of the depth and breadth of fundamental driving knowledge on closed-loop trajectory planning and introduce WiseAD, a specialized VLM tailored for end-to-end autonomous driving capable of driving reasoning, action justification, object recognition, risk analysis, driving suggestions, and trajectory planning across diverse scenarios. We employ joint training on driving knowledge and planning datasets, enabling the model to perform knowledge-aligned trajectory planning accordingly. Extensive experiments indicate that as the diversity of driving knowledge extends, critical accidents are notably reduced, contributing 11.9% and 12.4% improvements in the driving score and route completion on the Carla closed-loop evaluations, achieving state-of-the-art performance. Moreover, WiseAD also demonstrates remarkable performance in knowledge evaluations on both in-domain and out-of-domain datasets.
Authors: Zhentao Tan, Ben Xue, Jian Jia, Junhao Wang, Wencai Ye, Shaoyun Shi, Mingjie Sun, Wenjin Wu, Quan Chen, Peng Jiang
Abstract: This paper presents the \textbf{S}emantic-a\textbf{W}ar\textbf{E} spatial-t\textbf{E}mporal \textbf{T}okenizer (SweetTokenizer), a compact yet effective discretization approach for vision data. Our goal is to boost tokenizers' compression ratio while maintaining reconstruction fidelity in the VQ-VAE paradigm. Firstly, to obtain compact latent representations, we decouple images or videos into spatial-temporal dimensions, translating visual information into learnable querying spatial and temporal tokens through a \textbf{C}ross-attention \textbf{Q}uery \textbf{A}uto\textbf{E}ncoder (CQAE). Secondly, to complement visual information during compression, we quantize these tokens via a specialized codebook derived from off-the-shelf LLM embeddings to leverage the rich semantics from language modality. Finally, to enhance training stability and convergence, we also introduce a curriculum learning strategy, which proves critical for effective discrete visual representation learning. SweetTokenizer achieves comparable video reconstruction fidelity with only \textbf{25\%} of the tokens used in previous state-of-the-art video tokenizers, and boost video generation results by \textbf{32.9\%} w.r.t gFVD. When using the same token number, we significantly improves video and image reconstruction results by \textbf{57.1\%} w.r.t rFVD on UCF-101 and \textbf{37.2\%} w.r.t rFID on ImageNet-1K. Additionally, the compressed tokens are imbued with semantic information, enabling few-shot recognition capabilities powered by LLMs in downstream applications.
Authors: Zehao Chen, Rong Pan
Abstract: Scalable Vector Graphics (SVG) are essential XML-based formats for versatile graphics, offering resolution independence and scalability. Unlike raster images, SVGs use geometric shapes and support interactivity, animation, and manipulation via CSS and JavaScript. Current SVG generation methods face challenges related to high computational costs and complexity. In contrast, human designers use component-based tools for efficient SVG creation. Inspired by this, SVGBuilder introduces a component-based, autoregressive model for generating high-quality colored SVGs from textual input. It significantly reduces computational overhead and improves efficiency compared to traditional methods. Our model generates SVGs up to 604 times faster than optimization-based approaches. To address the limitations of existing SVG datasets and support our research, we introduce ColorSVG-100K, the first large-scale dataset of colored SVGs, comprising 100,000 graphics. This dataset fills the gap in color information for SVG generation models and enhances diversity in model training. Evaluation against state-of-the-art models demonstrates SVGBuilder's superior performance in practical applications, highlighting its efficiency and quality in generating complex SVG graphics.
Authors: Yiheng Lin, Yihan Hu, Chenyi Zhang, Ting Liu, Xiaochao Qu, Luoqi Liu, Yao Zhao, Yunchao Wei
Abstract: Transformer-based models have recently achieved outstanding performance in image matting. However, their application to high-resolution images remains challenging due to the quadratic complexity of global self-attention. To address this issue, we propose MEMatte, a \textbf{m}emory-\textbf{e}fficient \textbf{m}atting framework for processing high-resolution images. MEMatte incorporates a router before each global attention block, directing informative tokens to the global attention while routing other tokens to a Lightweight Token Refinement Module (LTRM). Specifically, the router employs a local-global strategy to predict the routing probability of each token, and the LTRM utilizes efficient modules to simulate global attention. Additionally, we introduce a Batch-constrained Adaptive Token Routing (BATR) mechanism, which allows each router to dynamically route tokens based on image content and the stages of attention block in the network. Furthermore, we construct an ultra high-resolution image matting dataset, UHR-395, comprising 35,500 training images and 1,000 test images, with an average resolution of $4872\times6017$. This dataset is created by compositing 395 different alpha mattes across 11 categories onto various backgrounds, all with high-quality manual annotation. Extensive experiments demonstrate that MEMatte outperforms existing methods on both high-resolution and real-world datasets, significantly reducing memory usage by approximately 88% and latency by 50% on the Composition-1K benchmark. Our code is available at https://github.com/linyiheng123/MEMatte.
Authors: Tulashi Prasad Joshi, Amrendra Kumar Yadav, Arjun Chhetri, Suraj Agrahari, Umesh Kanta Ghimire
Abstract: Online shopping has revolutionized the retail industry, providing customers with convenience and accessibility. However, customers often hesitate to purchase wearable products such as watches, jewelry, glasses, shoes, and clothes due to the lack of certainty regarding fit and suitability. This leads to significant return rates, causing problems for both customers and vendors. To address this issue, a platform called the Virtual Trial Room with Computer Vision and Machine Learning is designed which enables customers to easily check whether a product will fit and suit them or not. To achieve this, an AI-generated 3D model of the human head was created from a single 2D image using the DECA model. This 3D model was then superimposed with a custom-made 3D model of glass which is based on real-world measurements and fitted over the human head. To replicate the real-world look and feel, the model was retouched with textures, lightness, and smoothness. Furthermore, a full-stack application was developed utilizing various fornt-end and back-end technologies. This application enables users to view 3D-generated results on the website, providing an immersive and interactive experience.
Authors: Cong Wan, Xiangyang Luo, Zijian Cai, Yiren Song, Yunlong Zhao, Yifan Bai, Yuhang He, Yihong Gong
Abstract: In this paper, we introduce GRID, a novel paradigm that reframes a broad range of visual generation tasks as the problem of arranging grids, akin to film strips. At its core, GRID transforms temporal sequences into grid layouts, enabling image generation models to process visual sequences holistically. To achieve both layout consistency and motion coherence, we develop a parallel flow-matching training strategy that combines layout matching and temporal losses, guided by a coarse-to-fine schedule that evolves from basic layouts to precise motion control. Our approach demonstrates remarkable efficiency, achieving up to 35 faster inference speeds while using 1/1000 of the computational resources compared to specialized models. Extensive experiments show that GRID exhibits exceptional versatility across diverse visual generation tasks, from Text-to-Video to 3D Editing, while maintaining its foundational image generation capabilities. This dual strength in both expanded applications and preserved core competencies establishes GRID as an efficient and versatile omni-solution for visual generation.
Authors: Sida Huang, Hongyuan Zhang, Xuelong Li
Abstract: With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical challenge. Different from existing fine-tuning methods that add extra modules to these two modalities, we investigate whether the frozen model can be fine-tuned by customized noise. Our approach is motivated by the scientific study of beneficial noise, namely Positive-incentive Noise (Pi-noise or $\pi$-noise) , which quantitatively analyzes the impact of noise. It therefore implies a new scheme to learn beneficial noise distribution that can be employed to fine-tune VL models. Focusing on few-shot classification tasks based on CLIP, we reformulate the inference process of CLIP and apply variational inference, demonstrating how to generate $\pi$-noise towards visual and linguistic modalities. Then, we propose Positive-incentive Noise Injector (PiNI), which can fine-tune CLIP via injecting noise into both visual and text encoders. Since the proposed method can learn the distribution of beneficial noise, we can obtain more diverse embeddings of vision and language to better align these two modalities for specific downstream tasks within limited computational resources. We evaluate different noise incorporation approaches and network architectures of PiNI. The evaluation across 11 datasets demonstrates its effectiveness.
Authors: Lichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
Abstract: Diffusion models, the most popular generative paradigm so far, can inject conditional information into the generation path to guide the latent towards desired directions. However, existing text-to-image diffusion models often fail to maintain high image quality and high prompt-image alignment for those challenging prompts. To mitigate this issue and enhance existing pretrained diffusion models, we mainly made three contributions in this paper. First, we propose diffusion self-reflection that alternately performs denoising and inversion and demonstrate that such diffusion self-reflection can leverage the guidance gap between denoising and inversion to capture prompt-related semantic information with theoretical and empirical evidence. Second, motivated by theoretical analysis, we derive Zigzag Diffusion Sampling (Z-Sampling), a novel self-reflection-based diffusion sampling method that leverages the guidance gap between denosing and inversion to accumulate semantic information step by step along the sampling path, leading to improved sampling results. Moreover, as a plug-and-play method, Z-Sampling can be generally applied to various diffusion models (e.g., accelerated ones and Transformer-based ones) with very limited coding and computational costs. Third, our extensive experiments demonstrate that Z-Sampling can generally and significantly enhance generation quality across various benchmark datasets, diffusion models, and performance evaluation metrics. For example, DreamShaper with Z-Sampling can self-improve with the HPSv2 winning rate up to 94% over the original results. Moreover, Z-Sampling can further enhance existing diffusion models combined with other orthogonal methods, including Diffusion-DPO.
Authors: Sagi Eppel
Abstract: Large vision language models (LVLM) are the leading A.I approach for achieving a general visual understanding of the world. Models such as GPT, Claude, Gemini, and LLama can use images to understand and analyze complex visual scenes. 3D objects and shapes are the basic building blocks of the world, recognizing them is a fundamental part of human perception. The goal of this work is to test whether LVLMs truly understand 3D shapes by testing the models ability to identify and match objects of the exact same 3D shapes but with different orientations and materials/textures. Test images were created using CGI with a huge number of highly diverse objects, materials, and scenes. The results of this test show that the ability of such models to match 3D shapes is significantly below humans but much higher than random guesses. Suggesting that the models have gained some abstract understanding of 3D shapes but still trail far beyond humans in this task. Mainly it seems that the models can easily identify the same object with a different orientation as well as matching identical 3D shapes of the same orientation but with different material textures. However, when both the object material and orientation are changed, all models perform poorly relative to humans.
Authors: Liyuan Cui, Xiaogang Xu, Wenqi Dong, Zesong Yang, Hujun Bao, Zhaopeng Cui
Abstract: Human video synthesis aims to create lifelike characters in various environments, with wide applications in VR, storytelling, and content creation. While 2D diffusion-based methods have made significant progress, they struggle to generalize to complex 3D poses and varying scene backgrounds. To address these limitations, we introduce CFSynthesis, a novel framework for generating high-quality human videos with customizable attributes, including identity, motion, and scene configurations. Our method leverages a texture-SMPL-based representation to ensure consistent and stable character appearances across free viewpoints. Additionally, we introduce a novel foreground-background separation strategy that effectively decomposes the scene as foreground and background, enabling seamless integration of user-defined backgrounds. Experimental results on multiple datasets show that CFSynthesis not only achieves state-of-the-art performance in complex human animations but also adapts effectively to 3D motions in free-view and user-specified scenarios.
Authors: Pengcheng Zhao, Jinxing Zhou, Yang Zhao, Dan Guo, Yanxiang Chen
Abstract: The Audio-Visual Video Parsing task aims to recognize and temporally localize all events occurring in either the audio or visual stream, or both. Capturing accurate event semantics for each audio/visual segment is vital. Prior works directly utilize the extracted holistic audio and visual features for intra- and cross-modal temporal interactions. However, each segment may contain multiple events, resulting in semantically mixed holistic features that can lead to semantic interference during intra- or cross-modal interactions: the event semantics of one segment may incorporate semantics of unrelated events from other segments. To address this issue, our method begins with a Class-Aware Feature Decoupling (CAFD) module, which explicitly decouples the semantically mixed features into distinct class-wise features, including multiple event-specific features and a dedicated background feature. The decoupled class-wise features enable our model to selectively aggregate useful semantics for each segment from clearly matched classes contained in other segments, preventing semantic interference from irrelevant classes. Specifically, we further design a Fine-Grained Semantic Enhancement module for encoding intra- and cross-modal relations. It comprises a Segment-wise Event Co-occurrence Modeling (SECM) block and a Local-Global Semantic Fusion (LGSF) block. The SECM exploits inter-class dependencies of concurrent events within the same timestamp with the aid of a new event co-occurrence loss. The LGSF further enhances the event semantics of each segment by incorporating relevant semantics from more informative global video features. Extensive experiments validate the effectiveness of the proposed modules and loss functions, resulting in a new state-of-the-art parsing performance.
Authors: Rui Liu, Shuwei He, Yifan Hu, Haizhou Li
Abstract: Visual Text-to-Speech (VTTS) aims to take the environmental image as the prompt to synthesize the reverberant speech for the spoken content. The challenge of this task lies in understanding the spatial environment from the image. Many attempts have been made to extract global spatial visual information from the RGB space of an spatial image. However, local and depth image information are crucial for understanding the spatial environment, which previous works have ignored. To address the issues, we propose a novel multi-modal and multi-scale spatial environment understanding scheme to achieve immersive VTTS, termed M2SE-VTTS. The multi-modal aims to take both the RGB and Depth spaces of the spatial image to learn more comprehensive spatial information, and the multi-scale seeks to model the local and global spatial knowledge simultaneously. Specifically, we first split the RGB and Depth images into patches and adopt the Gemini-generated environment captions to guide the local spatial understanding. After that, the multi-modal and multi-scale features are integrated by the local-aware global spatial understanding. In this way, M2SE-VTTS effectively models the interactions between local and global spatial contexts in the multi-modal spatial environment. Objective and subjective evaluations suggest that our model outperforms the advanced baselines in environmental speech generation. The code and audio samples are available at: https://github.com/AI-S2-Lab/M2SE-VTTS.
Authors: Zhipeng Chen, Lan Yang, Yonggang Qi, Honggang Zhang, Kaiyue Pang, Ke Li, Yi-Zhe Song
Abstract: Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative control over generated images. However, our pilot study reveals that the expressive power of humans far surpasses the capabilities of current methods. Users desire a more versatile approach that can accommodate their diverse creative intents, ranging from controlling individual subjects to manipulating the entire scene composition. We present VersaGen, a generative AI agent that enables versatile visual control in T2I synthesis. VersaGen admits four types of visual controls: i) single visual subject; ii) multiple visual subjects; iii) scene background; iv) any combination of the three above or merely no control at all. We train an adaptor upon a frozen T2I model to accommodate the visual information into the text-dominated diffusion process. We introduce three optimization strategies during the inference phase of VersaGen to improve generation results and enhance user experience. Comprehensive experiments on COCO and Sketchy validate the effectiveness and flexibility of VersaGen, as evidenced by both qualitative and quantitative results.
Authors: Wenxiao Fan, Kan Li
Abstract: Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these methods may introduce problematic semantic associations, a phenomenon that we identify as Semantic Contamination. Through an analysis of Robust LR, a representative label refurbishment method, we found that utilizing the logits of views for refurbishment does not adequately balance the semantic information of individual classes. Conversely, using the logits of models fails to maintain consistent semantic relationships across models, which explains why label refurbishment methods frequently encounter issues related to Semantic Contamination. To address this issue, we propose a novel method called Collaborative Cross Learning, which utilizes semi-supervised learning on refurbished labels to extract appropriate semantic associations from embeddings across views and models. Experimental results show that our method outperforms existing approaches on both synthetic and real-world noisy datasets, effectively mitigating the impact of label noise and Semantic Contamination.
Authors: Xilin Wang, Jia Zheng, Yuanchao Hu, Hao Zhu, Qian Yu, Zihan Zhou
Abstract: In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-language models (VLMs), and departs from traditional methods which rely on task-specific data representations and/or algorithms. Specifically, on the input side, we simply treat the 2D CAD drawing as a raster image, regardless of its original format, and encode the image with a standard ViT model. We show that such an encoding scheme achieves competitive performance against existing methods that operate on vector-graphics inputs, while imposing substantially fewer restrictions on the 2D drawings. On the output side, our method auto-regressively predicts a general-purpose language describing 3D parametric models in text form. Compared to other sequence modeling methods for CAD which use domain-specific sequence representations with fixed-size slots, our text-based representation is more flexible, and can be easily extended to arbitrary geometric entities and semantic or functional properties. Experimental results on a large-scale dataset of cabinet models demonstrate the effectiveness of our method.
Authors: Chaorui Deng, Deyao Zhu, Kunchang Li, Shi Guang, Haoqi Fan
Abstract: We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existing next-token prediction models like LLaMA and GPT. While recent works attempt to combine diffusion with AR models, we show that introducing sequential factorization to a diffusion model can substantially improve its performance and enables a smooth transition between AR and diffusion generation modes. Hence, we propose CausalFusion - a decoder-only transformer that dual-factorizes data across sequential tokens and diffusion noise levels, leading to state-of-the-art results on the ImageNet generation benchmark while also enjoying the AR advantage of generating an arbitrary number of tokens for in-context reasoning. We further demonstrate CausalFusion's multimodal capabilities through a joint image generation and captioning model, and showcase CausalFusion's ability for zero-shot in-context image manipulations. We hope that this work could provide the community with a fresh perspective on training multimodal models over discrete and continuous data.
Authors: Vidit Gautam
Abstract: Advance in medical imaging is an important part in deep learning research. One of the goals of computer vision is development of a holistic, comprehensive model which can identify tumors from histology slides obtained via biopsies. A major problem that stands in the way is lack of data for a few cancer-types. In this paper, we ascertain that data augmentation using GANs can be a viable solution to reduce the unevenness in the distribution of different cancer types in our dataset. Our demonstration showed that a dataset augmented to a 50% increase causes an increase in tumor detection from 80% to 87.5%
Authors: Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xuefeng Du, Yixuan Li, Ziwei Liu, Yiran Chen, Hai Li
Abstract: Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field. OpenOOD v1 initiated the unification of the OOD detection evaluation but faced limitations in scalability and scope. In response, this paper presents OpenOOD v1.5, a significant improvement from its predecessor that ensures accurate and standardized evaluation of OOD detection methodologies at large scale. Notably, OpenOOD v1.5 extends its evaluation capabilities to large-scale data sets (ImageNet) and foundation models (e.g., CLIP and DINOv2), and expands its scope to investigate full-spectrum OOD detection which considers semantic and covariate distribution shifts at the same time. This work also contributes in-depth analysis and insights derived from comprehensive experimental results, thereby enriching the knowledge pool of OOD detection methodologies. With these enhancements, OpenOOD v1.5 aims to drive advancements and offer a more robust and comprehensive evaluation benchmark for OOD detection research.
Authors: Yao Yao, Peike Li, Boyu Chen, Alex Wang
Abstract: With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation. Nevertheless, achieving precise control over multi-track generation remains an open challenge. While existing models excel in directly generating multi-track mix, their limitations become evident when it comes to composing individual tracks and integrating them in a controllable manner. This departure from the typical workflows of professional composers hinders the ability to refine details in specific tracks. To address this gap, we propose JEN-1 Composer, a unified framework designed to efficiently model marginal, conditional, and joint distributions over multi-track music using a single model. Building upon an audio latent diffusion model, JEN-1 Composer extends the versatility of multi-track music generation. We introduce a progressive curriculum training strategy, which gradually escalates the difficulty of training tasks while ensuring the model's generalization ability and facilitating smooth transitions between different scenarios. During inference, users can iteratively generate and select music tracks, thus incrementally composing entire musical pieces in accordance with the Human-AI co-composition workflow. Our approach demonstrates state-of-the-art performance in controllable and high-fidelity multi-track music synthesis, marking a significant advancement in interactive AI-assisted music creation. Our demo pages are available at www.jenmusic.ai/research.
Authors: Tony Lindeberg
Abstract: This paper presents an analysis of properties of two hybrid discretization methods for Gaussian derivatives, based on convolutions with either the normalized sampled Gaussian kernel or the integrated Gaussian kernel followed by central differences. The motivation for studying these discretization methods is that in situations when multiple spatial derivatives of different order are needed at the same scale level, they can be computed significantly more efficiently compared to more direct derivative approximations based on explicit convolutions with either sampled Gaussian kernels or integrated Gaussian kernels. While these computational benefits do also hold for the genuinely discrete approach for computing discrete analogues of Gaussian derivatives, based on convolution with the discrete analogue of the Gaussian kernel followed by central differences, the underlying mathematical primitives for the discrete analogue of the Gaussian kernel, in terms of modified Bessel functions of integer order, may not be available in certain frameworks for image processing, such as when performing deep learning based on scale-parameterized filters in terms of Gaussian derivatives, with learning of the scale levels. In this paper, we present a characterization of the properties of these hybrid discretization methods, in terms of quantitative performance measures concerning the amount of spatial smoothing that they imply, as well as the relative consistency of scale estimates obtained from scale-invariant feature detectors with automatic scale selection, with an emphasis on the behaviour for very small values of the scale parameter, which may differ significantly from corresponding results obtained from the fully continuous scale-space theory, as well as between different types of discretization methods.
Authors: Yujin Baek, ChaeHun Park, Jaeseok Kim, Yu-Jung Heo, Du-Seong Chang, Jaegul Choo
Abstract: To create culturally inclusive vision-language models (VLMs), developing a benchmark that tests their ability to address culturally relevant questions is essential. Existing approaches typically rely on human annotators, making the process labor-intensive and creating a cognitive burden in generating diverse questions. To address this, we propose a semi-automated framework for constructing cultural VLM benchmarks, specifically targeting multiple-choice QA. This framework combines human-VLM collaboration, where VLMs generate questions based on guidelines, a small set of annotated examples, and relevant knowledge, followed by a verification process by native speakers. We demonstrate the effectiveness of this framework through the creation of K-Viscuit, a dataset focused on Korean culture. Our experiments on this dataset reveal that open-source models lag behind proprietary ones in understanding Korean culture, highlighting key areas for improvement. We also present a series of further analyses, including human evaluation, augmenting VLMs with external knowledge, and the evaluation beyond multiple-choice QA. Our dataset is available at https://huggingface.co/datasets/ddehun/k-viscuit.
Authors: Nhat Minh Le, Ciyue Shen, Neel Patel, Chintan Shah, Darpan Sanghavi, Blake Martin, Alfred Eng, Daniel Shenker, Harshith Padigela, Raymond Biju, Syed Ashar Javed, Jennifer Hipp, John Abel, Harsha Pokkalla, Sean Grullon, Dinkar Juyal
Abstract: Pathology plays an important role in disease diagnosis, treatment decision-making and drug development. Previous works on interpretability for machine learning models on pathology images have revolved around methods such as attention value visualization and deriving human-interpretable features from model heatmaps. Mechanistic interpretability is an emerging area of model interpretability that focuses on reverse-engineering neural networks. Sparse Autoencoders (SAEs) have emerged as a promising direction in terms of extracting monosemantic features from polysemantic model activations. In this work, we trained a Sparse Autoencoder on the embeddings of a pathology pretrained foundation model. We found that Sparse Autoencoder features represent interpretable and monosemantic biological concepts. In particular, individual SAE dimensions showed strong correlations with cell type counts such as plasma cells and lymphocytes. These biological representations were unique to the pathology pretrained model and were not found in a self-supervised model pretrained on natural images. We demonstrated that such biologically-grounded monosemantic representations evolved across the model's depth, and the pathology foundation model eventually gained robustness to non-biological factors such as scanner type. The emergence of biologically relevant SAE features was generalizable to an out-of-domain dataset. Our work paves the way for further exploration around interpretable feature dimensions and their utility for medical and clinical applications.
Authors: Hanqiu Chen, Xuebin Yao, Pradeep Subedi, Cong Hao
Abstract: Edge computing is a distributed computing paradigm that collects and processes data at or near the source of data generation. The on-device learning at edge relies on device-to-device wireless communication to facilitate real-time data sharing and collaborative decision-making among multiple devices. This significantly improves the adaptability of the edge computing system to the changing environments. However, as the scale of the edge computing system is getting larger, communication among devices is becoming the bottleneck because of the limited bandwidth of wireless communication leads to large data transfer latency. To reduce the amount of device-to-device data transmission and accelerate on-device learning, in this paper, we propose Residual-INR, a fog computing-based communication-efficient on-device learning framework by utilizing implicit neural representation (INR) to compress images/videos into neural network weights. Residual-INR enhances data transfer efficiency by collecting JPEG images from edge devices, compressing them into INR format at the fog node, and redistributing them for on-device learning. By using a smaller INR for full image encoding and a separate object INR for high-quality object region reconstruction through residual encoding, our technique can reduce the encoding redundancy while maintaining the object quality. Residual-INR is a promising solution for edge on-device learning because it reduces data transmission by up to 5.16 x across a network of 10 edge devices. It also facilitates CPU-free accelerated on-device learning, achieving up to 2.9 x speedup without sacrificing accuracy. Our code is available at: https://github.com/sharc-lab/Residual-INR.
Authors: Kening Zheng, Junkai Chen, Yibo Yan, Xin Zou, Xuming Hu
Abstract: Hallucination issues continue to affect multimodal large language models (MLLMs), with existing research mainly addressing object-level or attribute-level hallucinations, neglecting the more complex relation hallucinations that require advanced reasoning. Current benchmarks for relation hallucinations lack detailed evaluation and effective mitigation, and their datasets often suffer from biases due to systematic annotation processes. To address these challenges, we introduce Reefknot, a comprehensive benchmark targeting relation hallucinations, comprising over 20,000 real-world samples. We provide a systematic definition of relation hallucinations, integrating perceptive and cognitive perspectives, and construct a relation-based corpus using the Visual Genome scene graph dataset. Our comparative evaluation reveals significant limitations in current MLLMs' ability to handle relation hallucinations. Additionally, we propose a novel confidence-based mitigation strategy, which reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot. Our work offers valuable insights for achieving trustworthy multimodal intelligence.
Authors: Subhankar Ghosh, Arun Sharma, Jayant Gupta, Aneesh Subramanian, Shashi Shekhar
Abstract: Given coarser-resolution projections from global climate models or satellite data, the downscaling problem aims to estimate finer-resolution regional climate data, capturing fine-scale spatial patterns and variability. Downscaling is any method to derive high-resolution data from low-resolution variables, often to provide more detailed and local predictions and analyses. This problem is societally crucial for effective adaptation, mitigation, and resilience against significant risks from climate change. The challenge arises from spatial heterogeneity and the need to recover finer-scale features while ensuring model generalization. Most downscaling methods \cite{Li2020} fail to capture the spatial dependencies at finer scales and underperform on real-world climate datasets, such as sea-level rise. We propose a novel Kriging-informed Conditional Diffusion Probabilistic Model (Ki-CDPM) to capture spatial variability while preserving fine-scale features. Experimental results on climate data show that our proposed method is more accurate than state-of-the-art downscaling techniques.
Authors: Haoran Lu, Ruihai Wu, Yitong Li, Sijie Li, Ziyu Zhu, Chuanruo Ning, Yan Shen, Longzan Luo, Yuanpei Chen, Hao Dong
Abstract: Manipulating garments and fabrics has long been a critical endeavor in the development of home-assistant robots. However, due to complex dynamics and topological structures, garment manipulations pose significant challenges. Recent successes in reinforcement learning and vision-based methods offer promising avenues for learning garment manipulation. Nevertheless, these approaches are severely constrained by current benchmarks, which offer limited diversity of tasks and unrealistic simulation behavior. Therefore, we present GarmentLab, a content-rich benchmark and realistic simulation designed for deformable object and garment manipulation. Our benchmark encompasses a diverse range of garment types, robotic systems and manipulators. The abundant tasks in the benchmark further explores of the interactions between garments, deformable objects, rigid bodies, fluids, and human body. Moreover, by incorporating multiple simulation methods such as FEM and PBD, along with our proposed sim-to-real algorithms and real-world benchmark, we aim to significantly narrow the sim-to-real gap. We evaluate state-of-the-art vision methods, reinforcement learning, and imitation learning approaches on these tasks, highlighting the challenges faced by current algorithms, notably their limited generalization capabilities. Our proposed open-source environments and comprehensive analysis show promising boost to future research in garment manipulation by unlocking the full potential of these methods. We guarantee that we will open-source our code as soon as possible. You can watch the videos in supplementary files to learn more about the details of our work. Our project page is available at: https://garmentlab.github.io/
Authors: Arjun P S, Andrew Melnik, Gora Chand Nandi
Abstract: Experience Goal Visual Rearrangement task stands as a foundational challenge within Embodied AI, requiring an agent to construct a robust world model that accurately captures the goal state. The agent uses this world model to restore a shuffled scene to its original configuration, making an accurate representation of the world essential for successfully completing the task. In this work, we present a novel framework that leverages on 3D Gaussian Splatting as a 3D scene representation for experience goal visual rearrangement task. Recent advances in volumetric scene representation like 3D Gaussian Splatting, offer fast rendering of high quality and photo-realistic novel views. Our approach enables the agent to have consistent views of the current and the goal setting of the rearrangement task, which enables the agent to directly compare the goal state and the shuffled state of the world in image space. To compare these views, we propose to use a dense feature matching method with visual features extracted from a foundation model, leveraging its advantages of a more universal feature representation, which facilitates robustness, and generalization. We validate our approach on the AI2-THOR rearrangement challenge benchmark and demonstrate improvements over the current state of the art methods
Authors: Marziyeh Bamdad, Hans-Peter Hutter, Alireza Darvishy
Abstract: Simultaneous localization and mapping (SLAM) techniques can be used to navigate the visually impaired, but the development of robust SLAM solutions for crowded spaces is limited by the lack of realistic datasets. To address this, we introduce InCrowd-VI, a novel visual-inertial dataset specifically designed for human navigation in indoor pedestrian-rich environments. Recorded using Meta Aria Project glasses, it captures realistic scenarios without environmental control. InCrowd-VI features 58 sequences totaling a 5 km trajectory length and 1.5 hours of recording time, including RGB, stereo images, and IMU measurements. The dataset captures important challenges such as pedestrian occlusions, varying crowd densities, complex layouts, and lighting changes. Ground-truth trajectories, accurate to approximately 2 cm, are provided in the dataset, originating from the Meta Aria project machine perception SLAM service. In addition, a semi-dense 3D point cloud of scenes is provided for each sequence. The evaluation of state-of-the-art visual odometry (VO) and SLAM algorithms on InCrowd-VI revealed severe performance limitations in these realistic scenarios. Under challenging conditions, systems exceeded the required localization accuracy of 0.5 meters and the 1\% drift threshold, with classical methods showing drift up to 5-10\%. While deep learning-based approaches maintained high pose estimation coverage (>90\%), they failed to achieve real-time processing speeds necessary for walking pace navigation. These results demonstrate the need and value of a new dataset to advance SLAM research for visually impaired navigation in complex indoor environments. The dataset and associated tools are publicly available at https://incrowd-vi.cloudlab.zhaw.ch/.
Authors: Pengfei Fang, Yongchun Qin, Hui Xue
Abstract: Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL, knowledge distillation is employed as a way to maintain the knowledge from learned data distribution. Recognizing the limitations of generating discriminative feature representations in a few-shot context, our approach incorporates structural information between samples into knowledge distillation. This structural information serves as a remedy for the low quality of features. Diverging from traditional structured distillation methods that compute sample similarity, we introduce the Displacement Knowledge Distillation (DKD) method. DKD utilizes displacement rather than similarity between samples, incorporating both distance and angular information to significantly enhance the information density retained through knowledge distillation. Observing performance disparities in feature distribution between base and novel classes, we propose the Dual Distillation Network (DDNet). This network applies traditional knowledge distillation to base classes and DKD to novel classes, challenging the conventional integration of novel classes with base classes. Additionally, we implement an instance-aware sample selector during inference to dynamically adjust dual branch weights, thereby leveraging the complementary strengths of each approach. Extensive testing on three benchmarks demonstrates that DDNet achieves state-of-the-art results. Moreover, through rigorous experimentation and comparison, we establish the robustness and general applicability of our proposed DKD method.
Authors: Zeeshan Patel, James DeLoye, Lance Mathias
Abstract: In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified framework of Generator Matching. By recasting both diffusion and flow matching under the same generative Markov framework, we provide theoretical insights into why flow matching models can be more robust empirically and how novel model classes can be constructed by mixing deterministic and stochastic components. Our analysis offers a fresh perspective on the relationships between state-of-the-art generative modeling paradigms.
Authors: Qi Sun, Pengfei Hong, Tej Deep Pala, Vernon Toh, U-Xuan Tan, Deepanway Ghosal, Soujanya Poria
Abstract: Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to specific robotic embodiments. To address this, Visual-Language-Action (VLA) models have emerged, yet they face challenges in long-horizon spatial reasoning and grounded task planning. In this work, we propose the Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning, Emma-X. Emma-X leverages our constructed hierarchical embodiment dataset based on BridgeV2, containing 60,000 robot manipulation trajectories auto-annotated with grounded task reasoning and spatial guidance. Additionally, we introduce a trajectory segmentation strategy based on gripper states and motion trajectories, which can help mitigate hallucination in grounding subtask reasoning generation. Experimental results demonstrate that Emma-X achieves superior performance over competitive baselines, particularly in real-world robotic tasks requiring spatial reasoning.