Authors: Boyang Zhang, Daning Cheng, Yunquan Zhang, Fangmin Liu, Wenguang Chen
Abstract: This work focus on how to stabilize and lossless model compression, aiming to reduce model complexity and enhance efficiency without sacrificing performance due to compression errors. A key challenge is effectively leveraging compression errors and defining the boundaries for lossless compression to minimize model loss. i.e., compression for better. Currently, there is no systematic approach to determining this error boundary or understanding its specific impact on model performance. We propose a general \textbf{L}oss\textbf{L}ess \textbf{C}ompression theoretical framework (\textbf{LLC}), which further delineates the compression neighborhood and higher-order analysis boundaries through the total differential, thereby specifying the error range within which a model can be compressed without loss. To verify the effectiveness of LLC, we apply various compression techniques, including quantization and decomposition. Specifically, for quantization, we reformulate the classic quantization search problem as a grouped knapsack problem within the lossless neighborhood, achieving lossless quantization while improving computational efficiency. For decomposition, LLC addresses the approximation problem under low-rank constraints, automatically determining the rank for each layer and producing lossless low-rank models. We conduct extensive experiments on multiple neural network architectures on different datasets. The results show that without fancy tricks, LLC can effectively achieve lossless model compression. Our code will be made publicly.
Authors: Zhaorun Chen, Francesco Pinto, Minzhou Pan, Bo Li
Abstract: With the rise of generative AI and rapid growth of high-quality video generation, video guardrails have become more crucial than ever to ensure safety and security across platforms. Current video guardrails, however, are either overly simplistic, relying on pure classification models trained on simple policies with limited unsafe categories, which lack detailed explanations, or prompting multimodal large language models (MLLMs) with long safety guidelines, which are inefficient and impractical for guardrailing real-world content. To bridge this gap, we propose SafeWatch, an efficient MLLM-based video guardrail model designed to follow customized safety policies and provide multi-label video guardrail outputs with content-specific explanations in a zero-shot manner. In particular, unlike traditional MLLM-based guardrails that encode all safety policies autoregressively, causing inefficiency and bias, SafeWatch uniquely encodes each policy chunk in parallel and eliminates their position bias such that all policies are attended simultaneously with equal importance. In addition, to improve efficiency and accuracy, SafeWatch incorporates a policy-aware visual token pruning algorithm that adaptively selects the most relevant video tokens for each policy, discarding noisy or irrelevant information. This allows for more focused, policy-compliant guardrail with significantly reduced computational overhead. Considering the limitations of existing video guardrail benchmarks, we propose SafeWatch-Bench, a large-scale video guardrail benchmark comprising over 2M videos spanning six safety categories which covers over 30 tasks to ensure a comprehensive coverage of all potential safety scenarios. SafeWatch outperforms SOTA by 28.2% on SafeWatch-Bench, 13.6% on benchmarks, cuts costs by 10%, and delivers top-tier explanations validated by LLM and human reviews.
Authors: Yaniv Benny, Lior Wolf
Abstract: This paper proposes a novel method for omnidirectional 360$\degree$ perception. Most common previous methods relied on equirectangular projection. This representation is easily applicable to 2D operation layers but introduces distortions into the image. Other methods attempted to remove the distortions by maintaining a sphere representation but relied on complicated convolution kernels that failed to show competitive results. In this work, we introduce a transformer-based architecture that, by incorporating a novel ``Spherical Local Self-Attention'' and other spherically-oriented modules, successfully operates in the spherical domain and outperforms the state-of-the-art in 360$\degree$ perception benchmarks for depth estimation and semantic segmentation.
Authors: Zhenggang Tang, Yuchen Fan, Dilin Wang, Hongyu Xu, Rakesh Ranjan, Alexander Schwing, Zhicheng Yan
Abstract: Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When dealing with more than two views, a combinatorial number of error prone pairwise reconstructions are usually followed by an expensive global optimization, which often fails to rectify the pairwise reconstruction errors. To handle more views, reduce errors, and improve inference time, we propose the fast single-stage feed-forward network MV-DUSt3R. At its core are multi-view decoder blocks which exchange information across any number of views while considering one reference view. To make our method robust to reference view selection, we further propose MV-DUSt3R+, which employs cross-reference-view blocks to fuse information across different reference view choices. To further enable novel view synthesis, we extend both by adding and jointly training Gaussian splatting heads. Experiments on multi-view stereo reconstruction, multi-view pose estimation, and novel view synthesis confirm that our methods improve significantly upon prior art. Code will be released.
Authors: Mehdi Noroozi, Isma Hadji, Victor Escorcia, Anestis Zaganidis, Brais Martinez, Georgios Tzimiropoulos
Abstract: There has been immense progress recently in the visual quality of Stable Diffusion-based Super Resolution (SD-SR). However, deploying large diffusion models on computationally restricted devices such as mobile phones remains impractical due to the large model size and high latency. This is compounded for SR as it often operates at high res (e.g. 4Kx3K). In this work, we introduce Edge-SD-SR, the first parameter efficient and low latency diffusion model for image super-resolution. Edge-SD-SR consists of ~169M parameters, including UNet, encoder and decoder, and has a complexity of only ~142 GFLOPs. To maintain a high visual quality on such low compute budget, we introduce a number of training strategies: (i) A novel conditioning mechanism on the low resolution input, coined bidirectional conditioning, which tailors the SD model for the SR task. (ii) Joint training of the UNet and encoder, while decoupling the encodings of the HR and LR images and using a dedicated schedule. (iii) Finetuning the decoder using the UNet's output to directly tailor the decoder to the latents obtained at inference time. Edge-SD-SR runs efficiently on device, e.g. it can upscale a 128x128 patch to 512x512 in 38 msec while running on a Samsung S24 DSP, and of a 512x512 to 2048x2048 (requiring 25 model evaluations) in just ~1.1 sec. Furthermore, we show that Edge-SD-SR matches or even outperforms state-of-the-art SR approaches on the most established SR benchmarks.
Authors: Yash Savani, Marc Finzi, J. Zico Kolter
Abstract: We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models. Rather than merely mode-seeking, our method achieves sampling by "pulling back" the dynamics of the reverse-time process--from the image space to the diffrep parameter space--and updating the parameters according to this pulled-back process. We identify an implicit constraint on the samples induced by the diffrep and demonstrate that addressing this constraint significantly improves the consistency and detail of the generated objects. Our method yields diffreps with substantially improved quality and diversity for images, panoramas, and 3D NeRFs compared to existing techniques. Our approach is a general-purpose method for sampling diffreps, expanding the scope of problems that diffusion models can tackle.
Authors: Bin Li, Li Li, Zhenwei Zhang, Yuping Duan
Abstract: Underwater optical images inevitably suffer from various degradation factors such as blurring, low contrast, and color distortion, which hinder the accuracy of object detection tasks. Due to the lack of paired underwater/clean images, most research methods adopt a strategy of first enhancing and then detecting, resulting in a lack of feature communication between the two learning tasks. On the other hand, due to the contradiction between the diverse degradation factors of underwater images and the limited number of samples, existing underwater enhancement methods are difficult to effectively enhance degraded images of unknown water bodies, thereby limiting the improvement of object detection accuracy. Therefore, most underwater target detection results are still displayed on degraded images, making it difficult to visually judge the correctness of the detection results. To address the above issues, this paper proposes a multi-task learning method that simultaneously enhances underwater images and improves detection accuracy. Compared with single-task learning, the integrated model allows for the dynamic adjustment of information communication and sharing between different tasks. Due to the fact that real underwater images can only provide annotated object labels, this paper introduces physical constraints to ensure that object detection tasks do not interfere with image enhancement tasks. Therefore, this article introduces a physical module to decompose underwater images into clean images, background light, and transmission images and uses a physical model to calculate underwater images for self-supervision. Numerical experiments demonstrate that the proposed model achieves satisfactory results in visual performance, object detection accuracy, and detection efficiency compared to state-of-the-art comparative methods.
Authors: Jieyu Zhang, Le Xue, Linxin Song, Jun Wang, Weikai Huang, Manli Shu, An Yan, Zixian Ma, Juan Carlos Niebles, silvio savarese, Caiming Xiong, Zeyuan Chen, Ranjay Krishna, Ran Xu
Abstract: With the rise of multimodal applications, instruction data has become critical for training multimodal language models capable of understanding complex image-based queries. Existing practices rely on powerful but costly large language models (LLMs) or multimodal language models (MLMs) to produce instruction data. These are often prone to hallucinations, licensing issues and the generation process is often hard to scale and interpret. In this work, we present a programmatic approach that employs scene graphs as symbolic representations of images and human-written programs to systematically synthesize vision-centric instruction data. Our approach ensures the interpretability and controllability of the data generation process and scales efficiently while maintaining factual accuracy. By implementing a suite of 24 single-image, 14 multi-image instruction generators, and a scene graph generation pipeline, we build a scalable, cost-effective system: ProVision which produces diverse question-answer pairs concerning objects, attributes, relations, depth, etc., for any given image. Applied to Visual Genome and DataComp datasets, we generate over 10 million instruction data points, ProVision-10M, and leverage them in both pretraining and instruction tuning stages of MLMs. When adopted in the instruction tuning stage, our single-image instruction data yields up to a 7% improvement on the 2D split and 8% on the 3D split of CVBench, along with a 3% increase in performance on QBench2, RealWorldQA, and MMMU. Our multi-image instruction data leads to an 8% improvement on Mantis-Eval. Incorporation of our data in both pre-training and fine-tuning stages of xGen-MM-4B leads to an averaged improvement of 1.6% across 11 benchmarks.
Authors: Longwei Wang, Xueqian Li, Zheng Zhang
Abstract: The resilience of convolutional neural networks against input variations and adversarial attacks remains a significant challenge in image recognition tasks. Motivated by the need for more robust and reliable image recognition systems, we propose the Dense Cross-Connected Ensemble Convolutional Neural Network (DCC-ECNN). This novel architecture integrates the dense connectivity principle of DenseNet with the ensemble learning strategy, incorporating intermediate cross-connections between different DenseNet paths to facilitate extensive feature sharing and integration. The DCC-ECNN architecture leverages DenseNet's efficient parameter usage and depth while benefiting from the robustness of ensemble learning, ensuring a richer and more resilient feature representation.
Authors: Zizhao Hu, Xiaolin Zhou, Mohammad Rostami
Abstract: The success of vision transformers is widely attributed to the expressive power of their dynamically parameterized multi-head self-attention mechanism. We examine the impact of substituting the dynamic parameterized key with a static key within the standard attention mechanism in Vision Transformers. Our findings reveal that static key attention mechanisms can match or even exceed the performance of standard self-attention. Integrating static key attention modules into a Metaformer backbone, we find that it serves as a better intermediate stage in hierarchical hybrid architectures, balancing the strengths of depth-wise convolution and self-attention. Experiments on several vision tasks underscore the effectiveness of the static key mechanism, indicating that the typical two-step dynamic parameterization in attention can be streamlined to a single step without impacting performance under certain circumstances.
Authors: Akash Kumar, Sirshapan Mitra, Yogesh Singh Rawat
Abstract: In this work, we focus on semi-supervised learning for video action detection. Video action detection requires spatiotemporal localization in addition to classification, and a limited amount of labels makes the model prone to unreliable predictions. We present Stable Mean Teacher, a simple end-to-end teacher-based framework that benefits from improved and temporally consistent pseudo labels. It relies on a novel Error Recovery (EoR) module, which learns from students' mistakes on labeled samples and transfers this knowledge to the teacher to improve pseudo labels for unlabeled samples. Moreover, existing spatiotemporal losses do not take temporal coherency into account and are prone to temporal inconsistencies. To address this, we present Difference of Pixels (DoP), a simple and novel constraint focused on temporal consistency, leading to coherent temporal detections. We evaluate our approach on four different spatiotemporal detection benchmarks: UCF101-24, JHMDB21, AVA, and YouTube-VOS. Our approach outperforms the supervised baselines for action detection by an average margin of 23.5% on UCF101-24, 16% on JHMDB21, and 3.3% on AVA. Using merely 10% and 20% of data, it provides competitive performance compared to the supervised baseline trained on 100% annotations on UCF101-24 and JHMDB21, respectively. We further evaluate its effectiveness on AVA for scaling to large-scale datasets and YouTube-VOS for video object segmentation, demonstrating its generalization capability to other tasks in the video domain. Code and models are publicly available.
Authors: Donggeun Kim, Yujin Jo, Myungjoo Lee, Taesup Kim
Abstract: The advancement of vision-language models, particularly the Contrastive Language-Image Pre-training (CLIP) model, has revolutionized the field of machine learning by enabling robust zero-shot learning capabilities. These capabilities allow models to understand and respond to previously unseen data without task-specific training. However, adapting CLIP to integrate specialized knowledge from various domains while retaining its zero-shot capabilities remains a significant challenge. To address this, we introduce a novel prompt ensemble learning approach called Group-wise Prompt Ensemble (GPE). This method aims to enhance CLIP's zero-shot capabilities by incorporating new domain knowledge while improving its adaptability and robustness against data distribution shifts. Our approach hinges on three main strategies: prompt grouping with masked attention to optimize CLIP's adaptability while safeguarding its zero-shot capabilities; the incorporation of auxiliary prompts for the seamless integration of new domain insights without disrupting the original model's representation; and an ensemble learning strategy that effectively merges original and new knowledge. Through rigorous experimentation, including more challenging cross-dataset transfer evaluations, our GPE method redefines the benchmarks for the adaptability and efficiency of vision-language models, surpassing existing models across various scenarios.
Authors: Qiang Qu, Xiaoming Chen, Yuk Ying Chung, Yiran Shen
Abstract: Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach's superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.
Authors: Sebastian Hereu, Qianfei Hu
Abstract: Convolutional neural networks (CNNs) have been combined with generative adversarial networks (GANs) to create deep convolutional generative adversarial networks (DCGANs) with great success. DCGANs have been used for generating images and videos from creative domains such as fashion design and painting. A common critique of the use of DCGANs in creative applications is that they are limited in their ability to generate creative products because the generator simply learns to copy the training distribution. We explore an extension of DCGANs, creative adversarial networks (CANs). Using CANs, we generate novel, creative portraits, using the WikiArt dataset to train the network. Moreover, we introduce our extension of CANs, conditional creative adversarial networks (CCANs), and demonstrate their potential to generate creative portraits conditioned on a style label. We argue that generating products that are conditioned, or inspired, on a style label closely emulates real creative processes in which humans produce imaginative work that is still rooted in previous styles.
Authors: Nahid Alam, Karthik Reddy Kanjula, Surya Guthikonda, Timothy Chung, Bala Krishna S Vegesna, Abhipsha Das, Anthony Susevski, Ryan Sze-Yin Chan, S M Iftekhar Uddin, Shayekh Bin Islam, Roshan Santhosh, Snegha A, Drishti Sharma, Chen Liu, Isha Chaturvedi, Genta Indra Winata, Ashvanth. S, Snehanshu Mukherjee, Alham Fikri Aji
Abstract: The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.
Authors: Haihang Wu, Wei Wang, Tamasha Malepathirana, Sachith Seneviratne, Denny Oetomo, Saman Halgamuge
Abstract: Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fine-tuning. However, access to the training data can be limited due to concerns such as data privacy and commercial confidentiality. Furthermore, with covariate shift (disparities between test and training data distributions), pruning and finetuning with training datasets can hinder the generalization of the pruned model to test data. To address these issues, pruning and finetuning the model with test time samples becomes essential. However, test-time model pruning and fine-tuning incur additional computation costs and slow down the model's prediction speed, thus posing efficiency issues. Existing pruning methods are not efficient enough for test time model pruning setting, since finetuning the pruned model is needed to evaluate the importance of removable components. To address this, we propose two variables to approximate the fine-tuned accuracy. We then introduce an efficient pruning method that considers the approximated finetuned accuracy and potential inference latency saving. To enhance fine-tuning efficiency, we propose an efficient knowledge distillation method that only needs to generate pseudo labels for a small set of finetuning samples one time, thereby reducing the expensive pseudo-label generation cost. Experimental results demonstrate that our method achieves a comparable or superior tradeoff between test accuracy and inference latency, with a 32% relative reduction in pruning and finetuning time compared to the best existing method.
Authors: Jiaqing Zhang, Mingxiang Cao, Xue Yang, Kai Jiang, Yunsong Li
Abstract: Visual language models like Contrastive Language-Image Pretraining (CLIP) have shown impressive performance in analyzing natural images with language information. However, these models often encounter challenges when applied to specialized domains such as remote sensing due to the limited availability of image-text pairs for training. To tackle this issue, we introduce DiffCLIP, a novel framework that extends CLIP to effectively convey comprehensive language-driven semantic information for accurate classification of high-dimensional multimodal remote sensing images. DiffCLIP is a few-shot learning method that leverages unlabeled images for pretraining. It employs unsupervised mask diffusion learning to capture the distribution of diverse modalities without requiring labels. The modality-shared image encoder maps multimodal data into a unified subspace, extracting shared features with consistent parameters across modalities. A well-trained image encoder further enhances learning by aligning visual representations with class-label text information from CLIP. By integrating these approaches, DiffCLIP significantly boosts CLIP performance using a minimal number of image-text pairs. We evaluate DiffCLIP on widely used high-dimensional multimodal datasets, demonstrating its effectiveness in addressing few-shot annotated classification tasks. DiffCLIP achieves an overall accuracy improvement of 10.65% across three remote sensing datasets compared with CLIP, while utilizing only 2-shot image-text pairs. The code has been released at https://github.com/icey-zhang/DiffCLIP.
Authors: Yunming Zhang, Dengpan Ye, Sipeng Shen, Jun Wang
Abstract: Arbitrary Style Transfer (AST) achieves the rendering of real natural images into the painting styles of arbitrary art style images, promoting art communication. However, misuse of unauthorized art style images for AST may infringe on artists' copyrights. One countermeasure is robust watermarking, which tracks image propagation by embedding copyright watermarks into carriers. Unfortunately, AST-generated images lose the structural and semantic information of the original style image, hindering end-to-end robust tracking by watermarks. To fill this gap, we propose StyleMark, the first robust watermarking method for black-box AST, which can be seamlessly applied to art style images achieving precise attribution of artistic styles after AST. Specifically, we propose a new style watermark network that adjusts the mean activations of style features through multi-scale watermark embedding, thereby planting watermark traces into the shared style feature space of style images. Furthermore, we design a distribution squeeze loss, which constrain content statistical feature distortion, forcing the reconstruction network to focus on integrating style features with watermarks, thus optimizing the intrinsic watermark distribution. Finally, based on solid end-to-end training, StyleMark mitigates the optimization conflict between robustness and watermark invisibility through decoder fine-tuning under random noise. Experimental results demonstrate that StyleMark exhibits significant robustness against black-box AST and common pixel-level distortions, while also securely defending against malicious adaptive attacks.
Authors: Wei-Lun Huang, Minghao Xue, Zhiyou Liu, Davood Tashayyod, Jun Kang, Amir Gandjbakhche, Misha Kazhdan, Mehran Armand
Abstract: Melanoma is the most deadly form of skin cancer. Tracking the evolution of nevi and detecting new lesions across the body is essential for the early detection of melanoma. Despite prior work on longitudinal tracking of skin lesions in 3D total body photography, there are still several challenges, including 1) low accuracy for finding correct lesion pairs across scans, 2) sensitivity to noisy lesion detection, and 3) lack of large-scale datasets with numerous annotated lesion pairs. We propose a framework that takes in a pair of 3D textured meshes, matches lesions in the context of total body photography, and identifies unmatchable lesions. We start by computing correspondence maps bringing the source and target meshes to a template mesh. Using these maps to define source/target signals over the template domain, we construct a flow field aligning the mapped signals. The initial correspondence maps are then refined by advecting forward/backward along the vector field. Finally, lesion assignment is performed using the refined correspondence maps. We propose the first large-scale dataset for skin lesion tracking with 25K lesion pairs across 198 subjects. The proposed method achieves a success rate of 89.9% (at 10 mm criterion) for all pairs of annotated lesions and a matching accuracy of 98.2% for subjects with more than 200 lesions.
Authors: Meixu Chen, Kai Wang, Payal Kapur, James Brugarolas, Raquibul Hannan, Jing Wang
Abstract: Purpose: A reliable cancer prognosis model for clear cell renal cell carcinoma (ccRCC) can enhance personalized treatment. We developed a multi-modal ensemble model (MMEM) that integrates pretreatment clinical data, multi-omics data, and histopathology whole slide image (WSI) data to predict overall survival (OS) and disease-free survival (DFS) for ccRCC patients. Methods: We analyzed 226 patients from The Cancer Genome Atlas Kidney Renal Clear Cell Carcinoma (TCGA-KIRC) dataset, which includes OS, DFS follow-up data, and five data modalities: clinical data, WSIs, and three multi-omics datasets (mRNA, miRNA, and DNA methylation). Separate survival models were built for OS and DFS. Cox-proportional hazards (CPH) model with forward feature selection is used for clinical and multi-omics data. Features from WSIs were extracted using ResNet and three general-purpose foundation models. A deep learning-based CPH model predicted survival using encoded WSI features. Risk scores from all models were combined based on training performance. Results: Performance was assessed using concordance index (C-index) and AUROC. The clinical feature-based CPH model received the highest weight for both OS and DFS tasks. Among WSI-based models, the general-purpose foundation model (UNI) achieved the best performance. The final MMEM model surpassed single-modality models, achieving C-indices of 0.820 (OS) and 0.833 (DFS), and AUROC values of 0.831 (3-year patient death) and 0.862 (cancer recurrence). Using predicted risk medians to stratify high- and low-risk groups, log-rank tests showed improved performance in both OS and DFS compared to single-modality models. Conclusion: MMEM is the first multi-modal model for ccRCC patients, integrating five data modalities. It outperformed single-modality models in prognostic ability and has the potential to assist in ccRCC patient management if independently validated.
Authors: Beilin Chu, Xuan Xu, Xin Wang, Yufei Zhang, Weike You, Linna Zhou
Abstract: The rapid advancement of diffusion models has significantly improved high-quality image generation, making generated content increasingly challenging to distinguish from real images and raising concerns about potential misuse. In this paper, we observe that diffusion models struggle to accurately reconstruct mid-band frequency information in real images, suggesting the limitation could serve as a cue for detecting diffusion model generated images. Motivated by this observation, we propose a novel method called Frequency-guided Reconstruction Error (FIRE), which, to the best of our knowledge, is the first to investigate the influence of frequency decomposition on reconstruction error. FIRE assesses the variation in reconstruction error before and after the frequency decomposition, offering a robust method for identifying diffusion model generated images. Extensive experiments show that FIRE generalizes effectively to unseen diffusion models and maintains robustness against diverse perturbations.
Authors: Qianhao Han, Junyi Liu, Zengchang Qin, Zheng Zheng
Abstract: Automating radiology report generation can significantly reduce the workload of radiologists and enhance the accuracy, consistency, and efficiency of clinical documentation.We propose a novel cross-modal framework that uses MedCLIP as both a vision extractor and a retrieval mechanism to improve the process of medical report generation.By extracting retrieved report features and image features through an attention-based extract module, and integrating them with a fusion module, our method improves the coherence and clinical relevance of generated reports.Experimental results on the widely used IU-Xray dataset demonstrate the effectiveness of our approach, showing improvements over commonly used methods in both report quality and relevance.Additionally, ablation studies provide further validation of the framework, highlighting the importance of accurate report retrieval and feature integration in generating comprehensive medical reports.
Authors: Bo Li, Shaolin Zhu, Lijie Wen
Abstract: Image Translation (IT) holds immense potential across diverse domains, enabling the translation of textual content within images into various languages. However, existing datasets often suffer from limitations in scale, diversity, and quality, hindering the development and evaluation of IT models. To address this issue, we introduce MIT-10M, a large-scale parallel corpus of multilingual image translation with over 10M image-text pairs derived from real-world data, which has undergone extensive data cleaning and multilingual translation validation. It contains 840K images in three sizes, 28 categories, tasks with three levels of difficulty and 14 languages image-text pairs, which is a considerable improvement on existing datasets. We conduct extensive experiments to evaluate and train models on MIT-10M. The experimental results clearly indicate that our dataset has higher adaptability when it comes to evaluating the performance of the models in tackling challenging and complex image translation tasks in the real world. Moreover, the performance of the model fine-tuned with MIT-10M has tripled compared to the baseline model, further confirming its superiority.
Authors: Sayak Chakrabarty, Souradip Pal
Abstract: This paper introduces Multiple Choice Reasoning via. Process of Elimination using Multi-Modal models, herein referred to as Multi-Modal Process of Elimination (MM-PoE). This novel methodology is engineered to augment the efficacy of Vision-Language Models (VLMs) in multiple-choice visual reasoning tasks. Diverging from conventional approaches that evaluate each option independently, MM-PoE employs a dual-step scoring paradigm that initially identifies and excludes implausible choices, subsequently concentrating on the most probable remaining options. This method emulates human test-taking strategies, where individuals typically eliminate clearly incorrect answers prior to selecting the optimal response. Our empirical evaluations, conducted across three benchmark datasets, reveal that MM-PoE significantly improves both zero-shot and few-shot performance of contemporary state-of-the-art VLMs. Critically, this approach not only broadens the application of the elimination process to multi-modal contexts but also allows few-shot experiments, thereby addressing two principal limitations concerning usage of PoE only in zero-shot settings and only with a language-only framework. As a result, MM-PoE not only refines the reasoning capabilities of VLMs but also broadens their applicability to complex visual question-answering scenarios. All code and documentation supporting our work are available at https://pypi.org/project/mm-poe/, enabling researchers and practitioners to easily integrate and further develop these techniques.
Authors: Jiangang Wang, Qingnan Fan, Jinwei Chen, Hong Gu, Feng Huang, Wenqi Ren
Abstract: Benefiting from their powerful generative capabilities, pretrained diffusion models have garnered significant attention for real-world image super-resolution (Real-SR). Existing diffusion-based SR approaches typically utilize semantic information from degraded images and restoration prompts to activate prior for producing realistic high-resolution images. However, general-purpose pretrained diffusion models, not designed for restoration tasks, often have suboptimal prior, and manually defined prompts may fail to fully exploit the generated potential. To address these limitations, we introduce RAP-SR, a novel restoration prior enhancement approach in pretrained diffusion models for Real-SR. First, we develop the High-Fidelity Aesthetic Image Dataset (HFAID), curated through a Quality-Driven Aesthetic Image Selection Pipeline (QDAISP). Our dataset not only surpasses existing ones in fidelity but also excels in aesthetic quality. Second, we propose the Restoration Priors Enhancement Framework, which includes Restoration Priors Refinement (RPR) and Restoration-Oriented Prompt Optimization (ROPO) modules. RPR refines the restoration prior using the HFAID, while ROPO optimizes the unique restoration identifier, improving the quality of the resulting images. RAP-SR effectively bridges the gap between general-purpose models and the demands of Real-SR by enhancing restoration prior. Leveraging the plug-and-play nature of RAP-SR, our approach can be seamlessly integrated into existing diffusion-based SR methods, boosting their performance. Extensive experiments demonstrate its broad applicability and state-of-the-art results. Codes and datasets will be available upon acceptance.
Authors: Jiangang Wang, Qingnan Fan, Qi Zhang, Haigen Liu, Yuhang Yu, Jinwei Chen, Wenqi Ren
Abstract: Owing to the robust priors of diffusion models, recent approaches have shown promise in addressing real-world super-resolution (Real-SR). However, achieving semantic consistency and perceptual naturalness to meet human perception demands remains difficult, especially under conditions of heavy degradation and varied input complexities. To tackle this, we propose Hero-SR, a one-step diffusion-based SR framework explicitly designed with human perception priors. Hero-SR consists of two novel modules: the Dynamic Time-Step Module (DTSM), which adaptively selects optimal diffusion steps for flexibly meeting human perceptual standards, and the Open-World Multi-modality Supervision (OWMS), which integrates guidance from both image and text domains through CLIP to improve semantic consistency and perceptual naturalness. Through these modules, Hero-SR generates high-resolution images that not only preserve intricate details but also reflect human perceptual preferences. Extensive experiments validate that Hero-SR achieves state-of-the-art performance in Real-SR. The code will be publicly available upon paper acceptance.
Authors: Anthony Miyaguchi, Jed Moutahir, Tanmay Sutar
Abstract: This paper presents a semi-supervised approach to extracting and analyzing combat phases in judo tournaments using live-streamed footage. The objective is to automate the annotation and summarization of live streamed judo matches. We train models that extract relevant entities and classify combat phases from fixed-perspective judo recordings. We employ semi-supervised methods to address limited labeled data in the domain. We build a model of combat phases via transfer learning from a fine-tuned object detector to classify the presence, activity, and standing state of the match. We evaluate our approach on a dataset of 19 thirty-second judo clips, achieving an F1 score on a $20\%$ test hold-out of 0.66, 0.78, and 0.87 for the three classes, respectively. Our results show initial promise for automating more complex information retrieval tasks using rigorous methods with limited labeled data.
Authors: Thong Thanh Nguyen, Yi Bin, Xiaobao Wu, Zhiyuan Hu, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu
Abstract: Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level structure known as a feature pyramid. In this structure, lower levels concentrate on short-range video moments, while higher levels address long-range moments. Because higher levels experience downsampling to accommodate increasing moment length, their capacity to capture information is reduced and consequently leads to degraded information in moment representations. To resolve this problem, we propose a contrastive learning framework to capture salient semantics among video moments. Our key methodology is to leverage samples from the feature space emanating from multiple stages of the video encoder itself requiring neither data augmentation nor online memory banks to obtain positive and negative samples. To enable such an extension, we introduce a sampling process to draw multiple video moments corresponding to a common query. Subsequently, by utilizing these moments' representations across video encoder layers, we instantiate a novel form of multi-scale and cross-scale contrastive learning that links local short-range video moments with global long-range video moments. Extensive experiments demonstrate the effectiveness of our framework for not only long-form but also short-form video grounding.
Authors: Thong Thanh Nguyen, Xiaobao Wu, Yi Bin, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu
Abstract: To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations. Existing methods encode entity masks tracked across temporal dimensions (mask tubes), then predict their relations with temporal pooling operation, which does not fully utilize the motion indicative of the entities' relation. To overcome this limitation, we introduce a contrastive representation learning framework that focuses on motion pattern for temporal scene graph generation. Firstly, our framework encourages the model to learn close representations for mask tubes of similar subject-relation-object triplets. Secondly, we seek to push apart mask tubes from their temporally shuffled versions. Moreover, we also learn distant representations for mask tubes belonging to the same video but different triplets. Extensive experiments show that our motion-aware contrastive framework significantly improves state-of-the-art methods on both video and 4D datasets.
Authors: Yun Li, Zhe Liu, Lina Yao
Abstract: Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of seen attributes and objects. Current CLIP-based methods in CZSL, despite their advancements, often fail to effectively understand and link the attributes and objects due to inherent limitations in CLIP's pretraining mechanisms. To address these shortcomings, this paper introduces a novel framework, Understanding and Linking Attributes and Objects (ULAO) in CZSL, which comprises two innovative modules. The Understanding Attributes and Objects (UAO) module improves primitive understanding by sequential primitive prediction and leveraging recognized objects as contextual hints for attribute classification. Concurrently, the Linking Attributes and Objects (LAO) module improves the attribute-object linkage understanding through a new contrastive learning strategy that incorporates tailored hard negative generation and adaptive loss adjustments. We demonstrate our model's superiority by showcasing its state-of-the-art performance across three benchmark datasets in both Closed-World (CW) and Open-World (OW) scenarios.
Authors: Mingjie Lu, Yuanxian Huang, Ji Liu, Xingliang Huang, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum
Abstract: Occupancy Network has recently attracted much attention in autonomous driving. Instead of monocular 3D detection and recent bird's eye view(BEV) models predicting 3D bounding box of obstacles, Occupancy Network predicts the category of voxel in specified 3D space around the ego vehicle via transforming 3D detection task into 3D voxel segmentation task, which has much superiority in tackling category outlier obstacles and providing fine-grained 3D representation. However, existing methods usually require huge computation resources than previous methods, which hinder the Occupancy Network solution applying in intelligent driving systems. To address this problem, we make an analysis of the bottleneck of Occupancy Network inference cost, and present a simple and fast Occupancy Network model, which adopts a deformable 2D convolutional layer to lift BEV feature to 3D voxel feature and presents an efficient voxel feature pyramid network (FPN) module to improve performance with few computational cost. Further, we present a cost-free 2D segmentation branch in perspective view after feature extractors for Occupancy Network during inference phase to improve accuracy. Experimental results demonstrate that our method consistently outperforms existing methods in both accuracy and inference speed, which surpasses recent state-of-the-art (SOTA) OCCNet by 1.7% with ResNet50 backbone with about 3X inference speedup. Furthermore, our method can be easily applied to existing BEV models to transform them into Occupancy Network models.
Authors: Xuecheng Wu, Junxiao Xue, Liangyu Fu, Jiayu Nie, Danlei Huang, Xinyi Yin
Abstract: Recent research on real-time object detectors (e.g., YOLO series) has demonstrated the effectiveness of attention mechanisms for elevating model performance. Nevertheless, existing methods neglect to unifiedly deploy hierarchical attention mechanisms to construct a more discriminative YOLO head which is enriched with more useful intermediate features. To tackle this gap, this work aims to leverage multiple attention mechanisms to hierarchically enhance the triple discriminative awareness of the YOLO detection head and complementarily learn the coordinated intermediate representations, resulting in a new series detectors denoted 3A-YOLO. Specifically, we first propose a new head denoted TDA-YOLO Module, which unifiedly enhance the representations learning of scale-awareness, spatial-awareness, and task-awareness. Secondly, we steer the intermediate features to coordinately learn the inter-channel relationships and precise positional information. Finally, we perform neck network improvements followed by introducing various tricks to boost the adaptability of 3A-YOLO. Extensive experiments across COCO and VOC benchmarks indicate the effectiveness of our detectors.
Authors: Kayne Uriel K. Rodrigo, Jerriane Hillary Heart S. Marcial, Samuel C. Brillo, Khatalyn E. Mata, Jonathan C. Morano
Abstract: This study focuses on enhancing rice leaf disease image classification algorithms, which have traditionally relied on Convolutional Neural Network (CNN) models. We employed transfer learning with MobileViTV2_050 using ImageNet-1k weights, a lightweight model that integrates CNN's local feature extraction with Vision Transformers' global context learning through a separable self-attention mechanism. Our approach resulted in a significant 15.66% improvement in classification accuracy for MobileViTV2_050-A, our first enhanced model trained on the baseline dataset, achieving 93.14%. Furthermore, MobileViTV2_050-B, our second enhanced model trained on a broader rice leaf dataset, demonstrated a 22.12% improvement, reaching 99.6% test accuracy. Additionally, MobileViTV2-A attained an F1-score of 93% across four rice labels and a Receiver Operating Characteristic (ROC) curve ranging from 87% to 97%. In terms of resource consumption, our enhanced models reduced the total parameters of the baseline CNN model by up to 92.50%, from 14 million to 1.1 million. These results indicate that MobileViTV2_050 not only improves computational efficiency through its separable self-attention mechanism but also enhances global context learning. Consequently, it offers a lightweight and robust solution suitable for mobile deployment, advancing the interpretability and practicality of models in precision agriculture.
Authors: Hang Du, Guoshun Nan, Jiawen Qian, Wangchenhui Wu, Wendi Deng, Hanqing Mu, Zhenyan Chen, Pengxuan Mao, Xiaofeng Tao, Jun Liu
Abstract: Recent advancements in video anomaly understanding (VAU) have opened the door to groundbreaking applications in various fields, such as traffic monitoring and industrial automation. While the current benchmarks in VAU predominantly emphasize the detection and localization of anomalies. Here, we endeavor to delve deeper into the practical aspects of VAU by addressing the essential questions: "what anomaly occurred?", "why did it happen?", and "how severe is this abnormal event?". In pursuit of these answers, we introduce a comprehensive benchmark for Exploring the Causation of Video Anomalies (ECVA). Our benchmark is meticulously designed, with each video accompanied by detailed human annotations. Specifically, each instance of our ECVA involves three sets of human annotations to indicate "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality. Building upon this foundation, we propose a novel prompt-based methodology that serves as a baseline for tackling the intricate challenges posed by ECVA. We utilize "hard prompt" to guide the model to focus on the critical parts related to video anomaly segments, and "soft prompt" to establish temporal and spatial relationships within these anomaly segments. Furthermore, we propose AnomEval, a specialized evaluation metric crafted to align closely with human judgment criteria for ECVA. This metric leverages the unique features of the ECVA dataset to provide a more comprehensive and reliable assessment of various video large language models. We demonstrate the efficacy of our approach through rigorous experimental analysis and delineate possible avenues for further investigation into the comprehension of video anomaly causation.
Authors: David G Hobson, Majid Komeili
Abstract: Blindness and visual impairments affect many people worldwide. For help with navigation, people with visual impairments often rely on tactile maps that utilize raised surfaces and edges to convey information through touch. Although these maps are helpful, they are often not widely available and current tools to automate their production have similar limitations including only working at certain scales, for particular world regions, or adhering to specific tactile map standards. To address these shortcomings, we train a proof-of-concept model as a first step towards applying computer vision techniques to help automate the generation of tactile maps. We create a first-of-its-kind tactile maps dataset of street-views from Google Maps spanning 6500 locations and including different tactile line- and area-like features. Generative adversarial network (GAN) models trained on a single zoom successfully identify key map elements, remove extraneous ones, and perform inpainting with median F1 and intersection-over-union (IoU) scores of better than 0.97 across all features. Models trained on two zooms experience only minor drops in performance, and generalize well both to unseen map scales and world regions. Finally, we discuss future directions towards a full implementation of a tactile map solution that builds on our results.
Authors: Yujie Feng, Yin Yang, Xiaohong Fan, Zhengpeng Zhang, Lijing Bu, Jianping Zhang
Abstract: Recently, deep learning methods have gained remarkable achievements in the field of image restoration for remote sensing (RS). However, most existing RS image restoration methods focus mainly on conventional first-order degradation models, which may not effectively capture the imaging mechanisms of remote sensing images. Furthermore, many RS image restoration approaches that use deep learning are often criticized for their lacks of architecture transparency and model interpretability. To address these problems, we propose a novel progressive restoration network for high-order degradation imaging (HDI-PRNet), to progressively restore different image degradation. HDI-PRNet is developed based on the theoretical framework of degradation imaging, offering the benefit of mathematical interpretability within the unfolding network. The framework is composed of three main components: a module for image denoising that relies on proximal mapping prior learning, a module for image deblurring that integrates Neumann series expansion with dual-domain degradation learning, and a module for super-resolution. Extensive experiments demonstrate that our method achieves superior performance on both synthetic and real remote sensing images.
Authors: Xu Ouyang, Ying Chen, Kaiyue Zhu, Gady Agam
Abstract: Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different subclasses, and there may be linguistic discrepancy among texts describing the same image. Recent Generative Adversarial Networks (GAN), such as the Recurrent Affine Transformation (RAT) GAN model, are able to synthesize clear and realistic images from texts. However, GAN models ignore fine-grained level information. In this paper we propose an approach that incorporates an auxiliary classifier in the discriminator and a contrastive learning method to improve the accuracy of fine-grained details in images synthesized by RAT GAN. The auxiliary classifier helps the discriminator classify the class of images, and helps the generator synthesize more accurate fine-grained images. The contrastive learning method minimizes the similarity between images from different subclasses and maximizes the similarity between images from the same subclass. We evaluate on several state-of-the-art methods on the commonly used CUB-200-2011 bird dataset and Oxford-102 flower dataset, and demonstrated superior performance.
Authors: Debasmita Pal, Redwan Sony, Arun Ross
Abstract: Iris-based biometric systems are vulnerable to presentation attacks (PAs), where adversaries present physical artifacts (e.g., printed iris images, textured contact lenses) to defeat the system. This has led to the development of various presentation attack detection (PAD) algorithms, which typically perform well in intra-domain settings. However, they often struggle to generalize effectively in cross-domain scenarios, where training and testing employ different sensors, PA instruments, and datasets. In this work, we use adversarial training samples of both bonafide irides and PAs to improve the cross-domain performance of a PAD classifier. The novelty of our approach lies in leveraging transformation parameters from classical data augmentation schemes (e.g., translation, rotation) to generate adversarial samples. We achieve this through a convolutional autoencoder, ADV-GEN, that inputs original training samples along with a set of geometric and photometric transformations. The transformation parameters act as regularization variables, guiding ADV-GEN to generate adversarial samples in a constrained search space. Experiments conducted on the LivDet-Iris 2017 database, comprising four datasets, and the LivDet-Iris 2020 dataset, demonstrate the efficacy of our proposed method. The code is available at https://github.com/iPRoBe-lab/ADV-GEN-IrisPAD.
Authors: Hangyan Zhu, Ming Liu, Chao Zhou, Zifei Yan, Kuanquan Wang, Wangmeng Zuo
Abstract: Image colorization methods have shown prominent performance on natural images. However, since humans are more sensitive to faces, existing methods are insufficient to meet the demands when applied to facial images, typically showing unnatural and uneven colorization results. In this paper, we investigate the facial image colorization task and find that the problems with facial images can be attributed to an insufficient understanding of facial components. As a remedy, by introducing facial component priors, we present a novel facial image colorization framework dubbed FCNet. Specifically, we learn a decoupled color representation for each face component (e.g., lips, skin, eyes, and hair) under the guidance of face parsing maps. A chromatic and spatial augmentation strategy is presented to facilitate the learning procedure, which requires only grayscale and color facial image pairs. After training, the presented FCNet can be naturally applied to facial image colorization with single or multiple reference images. To expand the application paradigms to scenarios with no reference images, we further train two alternative modules, which predict the color representations from the grayscale input or a random seed, respectively. Extensive experiments show that our method can perform favorably against existing methods in various application scenarios (i.e., no-, single-, and multi-reference facial image colorization). The source code and pre-trained models will be publicly available.
Authors: Yingchu Wang, Ji He, Shijie Yu
Abstract: Structural health monitoring (SHM) is essential for the early detection of infrastructure defects, such as cracks in concrete bridge pier. but often faces challenges in efficiency and accuracy in complex environments. Although the Segment Anything Model (SAM) achieves excellent segmentation performance, its computational demands limit its suitability for real-time applications on edge devices. To address these challenges, this paper proposes Crack-EdgeSAM, a self-prompting crack segmentation system that integrates YOLOv8 for generating prompt boxes and a fine-tuned EdgeSAM model for crack segmentation. To ensure computational efficiency, the method employs ConvLoRA, a Parameter-Efficient Fine-Tuning (PEFT) technique, along with DiceFocalLoss to fine-tune the EdgeSAM model. Our experimental results on public datasets and the climbing robot automatic inspections demonstrate that the system achieves high segmentation accuracy and significantly enhanced inference speed compared to the most recent methods. Notably, the system processes 1024 x 1024 pixels images at 46 FPS on our PC and 8 FPS on Jetson Orin Nano.
Authors: Kohei Fukuda, Hiroaki Aizawa
Abstract: Out-of-distribution (OOD) detection is the task of identifying data sampled from distributions that were not used during training. This task is essential for reliable machine learning and a better understanding of their generalization capabilities. Among OOD detection methods, Outlier Exposure (OE) significantly enhances OOD detection performance and generalization ability by exposing auxiliary OOD data to the model. However, constructing clean auxiliary OOD datasets, uncontaminated by in-distribution (ID) samples, is essential for OE; generally, a noisy OOD dataset contaminated with ID samples negatively impacts OE training dynamics and final detection performance. Furthermore, as dataset scale increases, constructing clean OOD data becomes increasingly challenging and costly. To address these challenges, we propose Taylor Outlier Exposure (TaylorOE), an OE-based approach with regularization that allows training on noisy OOD datasets contaminated with ID samples. Specifically, we represent the OE regularization term as a polynomial function via a Taylor expansion, allowing us to control the regularization strength for ID data in the auxiliary OOD dataset by adjusting the order of Taylor expansion. In our experiments on the OOD detection task with clean and noisy OOD datasets, we demonstrate that the proposed method consistently outperforms conventional methods and analyze our regularization term to show its effectiveness. Our implementation code of TaylorOE is available at \url{https://github.com/fukuchan41/TaylorOE}.
Authors: Yuchun He, Yuhan He
Abstract: Single image super-resolution (SR) has long posed a challenge in the field of computer vision. While the advent of deep learning has led to the emergence of numerous methods aimed at tackling this persistent issue, the current methodologies still encounter challenges in modeling long sequence information, leading to limitations in effectively capturing the global pixel interactions. To tackle this challenge and achieve superior SR outcomes, we propose the Mamba pixel-wise sequential interaction network (MPSI), aimed at enhancing the establishment of long-range connections of information, particularly focusing on pixel-wise sequential interaction. We propose the Channel-Mamba Block (CMB) to capture comprehensive pixel interaction information by effectively modeling long sequence information. Moreover, in the existing SR methodologies, there persists the issue of the neglect of features extracted by preceding layers, leading to the loss of valuable feature information. While certain existing models strive to preserve these features, they frequently encounter difficulty in establishing connections across all layers. To overcome this limitation, MPSI introduces the Mamba channel recursion module (MCRM), which maximizes the retention of valuable feature information from early layers, thereby facilitating the acquisition of pixel sequence interaction information from multiple-level layers. Through extensive experimentation, we demonstrate that MPSI outperforms existing super-resolution methods in terms of image reconstruction results, attaining state-of-the-art performance.
Authors: Yuhan He, Yuchun He
Abstract: Image restoration represents a fundamental challenge in low-level vision, focusing on reconstructing high-quality images from their degraded counterparts. With the rapid advancement of deep learning technologies, transformer-based methods with pyramid structures have advanced the field by capturing long-range cross-scale spatial interaction. Despite its popularity, the degradation of essential features during the upsampling process notably compromised the restoration performance, resulting in suboptimal reconstruction outcomes. We introduce the EchoIR, an UNet-like image restoration network with a bilateral learnable upsampling mechanism to bridge this gap. Specifically, we proposed the Echo-Upsampler that optimizes the upsampling process by learning from the bilateral intermediate features of U-Net, the "Echo", aiming for a more refined restoration by minimizing the degradation during upsampling. In pursuit of modeling a hierarchical model of image restoration and upsampling tasks, we propose the Approximated Sequential Bi-level Optimization (AS-BLO), an advanced bi-level optimization model establishing a relationship between upsampling learning and image restoration tasks. Extensive experiments against the state-of-the-art (SOTA) methods demonstrate the proposed EchoIR surpasses the existing methods, achieving SOTA performance in image restoration tasks.
Authors: Yingfan Wang, Guoliang Kang
Abstract: Domain Generalization (DG) aims to learn a model from multiple source domains to achieve satisfactory performance on unseen target domains. Recent works introduce CLIP to DG tasks due to its superior image-text alignment and zeros-shot performance. Previous methods either utilize full fine-tuning or prompt-learning paradigms to harness CLIP for DG tasks. Those works focus on avoiding catastrophic forgetting of the original knowledge encoded in CLIP but ignore that the knowledge encoded in CLIP in nature may contain domain-specific cues that constrain its domain generalization performance. In this paper, we propose a new perspective to harness CLIP for DG, i.e., attention head purification. We observe that different attention heads may encode different properties of an image and selecting heads appropriately may yield remarkable performance improvement across domains. Based on such observations, we purify the attention heads of CLIP from two levels, including task-level purification and domain-level purification. For task-level purification, we design head-aware LoRA to make each head more adapted to the task we considered. For domain-level purification, we perform head selection via a simple gating strategy. We utilize MMD loss to encourage masked head features to be more domain-invariant to emphasize more generalizable properties/heads. During training, we jointly perform task-level purification and domain-level purification. We conduct experiments on various representative DG benchmarks. Though simple, extensive experiments demonstrate that our method performs favorably against previous state-of-the-arts.
Authors: Hui Deng, Jiawei Shi, Zhen Qin, Yiran Zhong, Yuchao Dai
Abstract: Non-Rigid Structure-from-Motion (NRSfM) is a classic 3D vision problem, where a 2D sequence is taken as input to estimate the corresponding 3D sequence. Recently, the deep neural networks have greatly advanced the task of NRSfM. However, existing deep NRSfM methods still have limitations in handling the inherent sequence property and motion ambiguity associated with the NRSfM problem. In this paper, we revisit deep NRSfM from two perspectives to address the limitations of current deep NRSfM methods : (1) canonicalization and (2) sequence modeling. We propose an easy-to-implement per-sequence canonicalization method as opposed to the previous per-dataset canonicalization approaches. With this in mind, we propose a sequence modeling method that combines temporal information and subspace constraint. As a result, we have achieved a more optimal NRSfM reconstruction pipeline compared to previous efforts. The effectiveness of our method is verified by testing the sequence-to-sequence deep NRSfM pipeline with corresponding regularization modules on several commonly used datasets.
Authors: Kun Li, Xinge Peng, Dan Guo, Xun Yang, Meng Wang
Abstract: Repetitive Action Counting (RAC) aims to count the number of repetitive actions occurring in videos. In the real world, repetitive actions have great diversity and bring numerous challenges (e.g., viewpoint changes, non-uniform periods, and action interruptions). Existing methods based on the temporal self-similarity matrix (TSSM) for RAC are trapped in the bottleneck of insufficient capturing action periods when applied to complicated daily videos. To tackle this issue, we propose a novel method named Hybrid Temporal Relation Modeling Network (HTRM-Net) to build diverse TSSM for RAC. The HTRM-Net mainly consists of three key components: bi-modal temporal self-similarity matrix modeling, random matrix dropping, and local temporal context modeling. Specifically, we construct temporal self-similarity matrices by bi-modal (self-attention and dual-softmax) operations, yielding diverse matrix representations from the combination of row-wise and column-wise correlations. To further enhance matrix representations, we propose incorporating a random matrix dropping module to guide channel-wise learning of the matrix explicitly. After that, we inject the local temporal context of video frames and the learned matrix into temporal correlation modeling, which can make the model robust enough to cope with error-prone situations, such as action interruption. Finally, a multi-scale matrix fusion module is designed to aggregate temporal correlations adaptively in multi-scale matrices. Extensive experiments across intra- and cross-datasets demonstrate that the proposed method not only outperforms current state-of-the-art methods but also exhibits robust capabilities in accurately counting repetitive actions in unseen action categories. Notably, our method surpasses the classical TransRAC method by 20.04\% in MAE and 22.76\% in OBO.
Authors: Jiayi Su, Youhe Feng, Zheng Li, Jinhua Song, Yangfan He, Botao Ren, Botian Xu
Abstract: This paper presents a novel framework for modeling and conditional generation of 3D articulated objects. Troubled by flexibility-quality tradeoffs, existing methods are often limited to using predefined structures or retrieving shapes from static datasets. To address these challenges, we parameterize an articulated object as a tree of tokens and employ a transformer to generate both the object's high-level geometry code and its kinematic relations. Subsequently, each sub-part's geometry is further decoded using a signed-distance-function (SDF) shape prior, facilitating the synthesis of high-quality 3D shapes. Our approach enables the generation of diverse objects with high-quality geometry and varying number of parts. Comprehensive experiments on conditional generation from text descriptions demonstrate the effectiveness and flexibility of our method.
Authors: Jiahan Li, Zhiqi Li, Tong Lu
Abstract: This technical report describes the methods we employed for the Driving with Language track of the CVPR 2024 Autonomous Grand Challenge. We utilized a powerful open-source multimodal model, InternVL-1.5, and conducted a full-parameter fine-tuning on the competition dataset, DriveLM-nuScenes. To effectively handle the multi-view images of nuScenes and seamlessly inherit InternVL's outstanding multimodal understanding capabilities, we formatted and concatenated the multi-view images in a specific manner. This ensured that the final model could meet the specific requirements of the competition task while leveraging InternVL's powerful image understanding capabilities. Meanwhile, we designed a simple automatic annotation strategy that converts the center points of objects in DriveLM-nuScenes into corresponding bounding boxes. As a result, our single model achieved a score of 0.6002 on the final leadboard.
Authors: Xin Zhao, Xiaojun Chen, Yuexin Xuan, Zhendong Zhao
Abstract: In the digital age, the proliferation of deep learning models has led to significant concerns about the generation of Not Safe for Work (NSFW) content. Existing defense methods primarily involve model fine-tuning and post-hoc content moderation. However, these approaches often lack scalability in eliminating harmful content, degrade the quality of benign image generation, or incur high inference costs. To tackle these challenges, we propose an innovative framework called \textbf{Buster}, which injects backdoor attacks into the text encoder to prevent NSFW content generation. Specifically, Buster leverages deep semantic information rather than explicit prompts as triggers, redirecting NSFW prompts towards targeted benign prompts. This approach demonstrates exceptional resilience and scalability in mitigating NSFW content. Remarkably, Buster fine-tunes the text encoder of Text-to-Image models within just five minutes, showcasing high efficiency. Our extensive experiments reveal that Buster outperforms all other baselines, achieving superior NSFW content removal rate while preserving the quality of harmless images.
Authors: Chaoqun Li, Zhuodong Liu, Huanqian Yan, Hang Su
Abstract: Adversarial patches, often used to provide physical stealth protection for critical assets and assess perception algorithm robustness, usually neglect the need for visual harmony with the background environment, making them easily noticeable. Moreover, existing methods primarily concentrate on improving attack performance, disregarding the intricate dynamics of adversarial patch elements. In this work, we introduce the Camouflaged Adversarial Pattern Generator (CAPGen), a novel approach that leverages specific base colors from the surrounding environment to produce patches that seamlessly blend with their background for superior visual stealthiness while maintaining robust adversarial performance. We delve into the influence of both patterns (i.e., color-agnostic texture information) and colors on the effectiveness of attacks facilitated by patches, discovering that patterns exert a more pronounced effect on performance than colors. Based on these findings, we propose a rapid generation strategy for adversarial patches. This involves updating the colors of high-performance adversarial patches to align with those of the new environment, ensuring visual stealthiness without compromising adversarial impact. This paper is the first to comprehensively examine the roles played by patterns and colors in the context of adversarial patches.
Authors: Peipeng Yu, Hui Gao, Zhitao Huang, Zhihua Xia, Chip-Hong Chang
Abstract: Recent advances in deepfake forensics have primarily focused on improving the classification accuracy and generalization performance. Despite enormous progress in detection accuracy across a wide variety of forgery algorithms, existing algorithms lack intuitive interpretability and identity traceability to help with forensic investigation. In this paper, we introduce a novel DeepFake Identity Recovery scheme (DFREC) to fill this gap. DFREC aims to recover the pair of source and target faces from a deepfake image to facilitate deepfake identity tracing and reduce the risk of deepfake attack. It comprises three key components: an Identity Segmentation Module (ISM), a Source Identity Reconstruction Module (SIRM), and a Target Identity Reconstruction Module (TIRM). The ISM segments the input face into distinct source and target face information, and the SIRM reconstructs the source face and extracts latent target identity features with the segmented source information. The background context and latent target identity features are synergetically fused by a Masked Autoencoder in the TIRM to reconstruct the target face. We evaluate DFREC on six different high-fidelity face-swapping attacks on FaceForensics++, CelebaMegaFS and FFHQ-E4S datasets, which demonstrate its superior recovery performance over state-of-the-art deepfake recovery algorithms. In addition, DFREC is the only scheme that can recover both pristine source and target faces directly from the forgery image with high fadelity.
Authors: Ziyao Yi, Diego Valsesia, Tiziano Bianchi, Enrico Magli
Abstract: The rise of portable Lidar instruments, including their adoption in smartphones, opens the door to novel computational imaging techniques. Being an active sensing instrument, Lidar can provide complementary data to passive optical sensors, particularly in situations like low-light imaging where motion blur can affect photos. In this paper, we study if the depth information provided by mobile Lidar sensors is useful for the task of image deblurring and how to integrate it with a general approach that transforms any state-of-the-art neural deblurring model into a depth-aware one. To achieve this, we developed a universal adapter structure that efficiently preprocesses the depth information to modulate image features with depth features. Additionally, we applied a continual learning strategy to pretrained encoder-decoder models, enabling them to incorporate depth information as an additional input with minimal extra data requirements. We demonstrate that utilizing true depth information can significantly boost the effectiveness of deblurring algorithms, as validated on a dataset with real-world depth data captured by a smartphone Lidar.
Authors: Aixuan Li, Jing Zhang, Jiawei Shi, Yiran Zhong, Yuchao Dai
Abstract: We find that the well-trained victim models (VMs), against which the attacks are generated, serve as fundamental prerequisites for adversarial attacks, i.e. a segmentation VM is needed to generate attacks for segmentation. In this context, the victim model is assumed to be robust to achieve effective adversarial perturbation generation. Instead of focusing on improving the robustness of the task-specific victim models, we shift our attention to image generation. From an image generation perspective, we derive a novel VM for segmentation, aiming to generate adversarial perturbations for segmentation tasks without requiring models explicitly designed for image segmentation. Our approach to adversarial attack generation diverges from conventional white-box or black-box attacks, offering a fresh outlook on adversarial attack strategies. Experiments show that our attack method is able to generate effective adversarial attacks with good transferability.
Authors: Yi Yu, Song Xia, Xun Lin, Wenhan Yang, Shijian Lu, Yap-peng Tan, Alex Kot
Abstract: No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and optimizing computer vision systems, e.g., low-light enhancement. Recent research indicates that NR-IQA models are susceptible to adversarial attacks, which can significantly alter predicted scores with visually imperceptible perturbations. Despite revealing vulnerabilities, these attack methods have limitations, including high computational demands, untargeted manipulation, limited practical utility in white-box scenarios, and reduced effectiveness in black-box scenarios. To address these challenges, we shift our focus to another significant threat and present a novel poisoning-based backdoor attack against NR-IQA (BAIQA), allowing the attacker to manipulate the IQA model's output to any desired target value by simply adjusting a scaling coefficient $\alpha$ for the trigger. We propose to inject the trigger in the discrete cosine transform (DCT) domain to improve the local invariance of the trigger for countering trigger diminishment in NR-IQA models due to widely adopted data augmentations. Furthermore, the universal adversarial perturbations (UAP) in the DCT space are designed as the trigger, to increase IQA model susceptibility to manipulation and improve attack effectiveness. In addition to the heuristic method for poison-label BAIQA (P-BAIQA), we explore the design of clean-label BAIQA (C-BAIQA), focusing on $\alpha$ sampling and image data refinement, driven by theoretical insights we reveal. Extensive experiments on diverse datasets and various NR-IQA models demonstrate the effectiveness of our attacks. Code will be released at https://github.com/yuyi-sd/BAIQA.
Authors: Isabela M. Yepes, Manasvi Goyal
Abstract: This study investigates the applicability of Singular Value Decomposition for the image classification of specific breeds of cats and dogs using fur color as the primary identifying feature. Sequential Quadratic Programming (SQP) is employed to construct optimally weighted templates. The proposed method achieves 69% accuracy using the Frobenius norm at rank 10. The results partially validate the assumption that dominant features, such as fur color, can be effectively captured through low-rank approximations. However, the accuracy suggests that additional features or methods may be required for more robust classification, highlighting the trade-off between simplicity and performance in resource-constrained environments.
Authors: Toshiya Yura, Ashkan Mirzaei, Igor Gilitschenski
Abstract: We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address the novel view synthesis challenge in the presence of fast camera motion. For initialization of the optimization process, our approach uses prior knowledge encoded in an event-to-video model. We also use spline interpolation for obtaining high quality poses along the event camera trajectory. This enhances the reconstruction quality from fast-moving cameras while overcoming the computational limitations traditionally associated with event-based Neural Radiance Field (NeRF) methods. Our experimental evaluation demonstrates that our results achieve higher visual fidelity and better performance than existing event-based NeRF approaches while being an order of magnitude faster to render.
Authors: Jae-Young Yim, Jae-Young Sim
Abstract: Large-scale 3D point clouds (LS3DPC) obtained by LiDAR scanners require huge storage space and transmission bandwidth due to a large amount of data. The existing methods of LS3DPC compression separately perform rule-based point sampling and learnable feature extraction, and hence achieve limited compression performance. In this paper, we propose a fully end-to-end training framework for LS3DPC compression where the point sampling and the feature extraction are jointly optimized in terms of the rate and distortion losses. To this end, we first make the point sampling module to be trainable such that an optimal position of the downsampled point is estimated via aggregation with learnable weights. We also develop a reliable point reconstruction scheme that adaptively aggregates the expanded candidate points to refine the positions of upsampled points. Experimental results evaluated on the SemanticKITTI and nuScenes datasets show that the proposed method achieves significantly higher compression ratios compared with the existing state-of-the-art methods.
Authors: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Abstract: EXplainable Artificial Intelligence (XAI) approaches are widely applied for identifying fairness issues in Artificial Intelligence (AI) systems. However, in the context of facial analysis, existing XAI approaches, such as pixel attribution methods, offer explanations for individual images, posing challenges in assessing the overall behavior of a model, which would require labor-intensive manual inspection of a very large number of instances and leaving to the human the task of drawing a general impression of the model behavior from the individual outputs. Addressing this limitation, we introduce FaceX, the first method that provides a comprehensive understanding of face attribute classifiers through summary model explanations. Specifically, FaceX leverages the presence of distinct regions across all facial images to compute a region-level aggregation of model activations, allowing for the visualization of the model's region attribution across 19 predefined regions of interest in facial images, such as hair, ears, or skin. Beyond spatial explanations, FaceX enhances interpretability by visualizing specific image patches with the highest impact on the model's decisions for each facial region within a test benchmark. Through extensive evaluation in various experimental setups, including scenarios with or without intentional biases and mitigation efforts on four benchmarks, namely CelebA, FairFace, CelebAMask-HQ, and Racial Faces in the Wild, FaceX demonstrates high effectiveness in identifying the models' biases.
Authors: Shanlin Sun, Gabriel De Araujo, Jiaqi Xu, Shenghan Zhou, Hanwen Zhang, Ziheng Huang, Chenyu You, Xiaohui Xie
Abstract: 3D human motion generation has seen substantial advancement in recent years. While state-of-the-art approaches have improved performance significantly, they still struggle with complex and detailed motions unseen in training data, largely due to the scarcity of motion datasets and the prohibitive cost of generating new training examples. To address these challenges, we introduce CoMA, an agent-based solution for complex human motion generation, editing, and comprehension. CoMA leverages multiple collaborative agents powered by large language and vision models, alongside a mask transformer-based motion generator featuring body part-specific encoders and codebooks for fine-grained control. Our framework enables generation of both short and long motion sequences with detailed instructions, text-guided motion editing, and self-correction for improved quality. Evaluations on the HumanML3D dataset demonstrate competitive performance against state-of-the-art methods. Additionally, we create a set of context-rich, compositional, and long text prompts, where user studies show our method significantly outperforms existing approaches.
Authors: Donghwna Lee, Kyungha Min, Kirok Kim, Seyoung Jeong, Jiwoo Jeong, Wooju Kim
Abstract: Pose-Guided Person Image Synthesis (PGPIS) aims to synthesize high-quality person images corresponding to target poses while preserving the appearance of the source image. Recently, PGPIS methods that use diffusion models have achieved competitive performance. Most approaches involve extracting representations of the target pose and source image and learning their relationships in the generative model's training process. This approach makes it difficult to learn the semantic relationships between the input and target images and complicates the model structure needed to enhance generation results. To address these issues, we propose Fusion embedding for PGPIS using a Diffusion Model (FPDM). Inspired by the successful application of pre-trained CLIP models in text-to-image diffusion models, our method consists of two stages. The first stage involves training the fusion embedding of the source image and target pose to align with the target image's embedding. In the second stage, the generative model uses this fusion embedding as a condition to generate the target image. We applied the proposed method to the benchmark datasets DeepFashion and RWTH-PHOENIX-Weather 2014T, and conducted both quantitative and qualitative evaluations, demonstrating state-of-the-art (SOTA) performance. An ablation study of the model structure showed that even a model using only the second stage achieved performance close to the other PGPIS SOTA models. The code is available at https://github.com/dhlee-work/FPDM.
Authors: Xuerui Qiu, Man Yao, Jieyuan Zhang, Yuhong Chou, Ning Qiao, Shibo Zhou, Bo Xu, Guoqi Li
Abstract: Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs should be well-suited for processing them. However, when applying SNNs to point clouds, they often exhibit limited performance and fewer application scenarios. We attribute this to inappropriate preprocessing and feature extraction methods. To address this issue, we first introduce the Spike Voxel Coding (SVC) scheme, which encodes the 3D point clouds into a sparse spike train space, reducing the storage requirements and saving time on point cloud preprocessing. Then, we propose a Spike Sparse Convolution (SSC) model for efficiently extracting 3D sparse point cloud features. Combining SVC and SSC, we design an efficient 3D SNN backbone (E-3DSNN), which is friendly with neuromorphic hardware. For instance, SSC can be implemented on neuromorphic chips with only minor modifications to the addressing function of vanilla spike convolution. Experiments on ModelNet40, KITTI, and Semantic KITTI datasets demonstrate that E-3DSNN achieves state-of-the-art (SOTA) results with remarkable efficiency. Notably, our E-3DSNN (1.87M) obtained 91.7\% top-1 accuracy on ModelNet40, surpassing the current best SNN baselines (14.3M) by 3.0\%. To our best knowledge, it is the first direct training 3D SNN backbone that can simultaneously handle various 3D computer vision tasks (e.g., classification, detection, and segmentation) with an event-driven nature. Code is available: https://github.com/bollossom/E-3DSNN/.
Authors: Rongqing Li, Changsheng Li, Yuhang Li, Hanjie Li, Yi Chen, Dongchun Ren, Ye Yuan, Guoren Wang
Abstract: Trajectory prediction of agents is crucial for the safety of autonomous vehicles, whereas previous approaches usually rely on sufficiently long-observed trajectory to predict the future trajectory of the agents. However, in real-world scenarios, it is not realistic to collect adequate observed locations for moving agents, leading to the collapse of most prediction models. For instance, when a moving car suddenly appears and is very close to an autonomous vehicle because of the obstruction, it is quite necessary for the autonomous vehicle to quickly and accurately predict the future trajectories of the car with limited observed trajectory locations. In light of this, we focus on investigating the task of instantaneous trajectory prediction, i.e., two observed locations are available during inference. To this end, we propose a general and plug-and-play instantaneous trajectory prediction approach, called ITPNet. Specifically, we propose a backward forecasting mechanism to reversely predict the latent feature representations of unobserved historical trajectories of the agent based on its two observed locations and then leverage them as complementary information for future trajectory prediction. Meanwhile, due to the inevitable existence of noise and redundancy in the predicted latent feature representations, we further devise a Noise Redundancy Reduction Former, aiming at to filter out noise and redundancy from unobserved trajectories and integrate the filtered features and observed features into a compact query for future trajectory predictions. In essence, ITPNet can be naturally compatible with existing trajectory prediction models, enabling them to gracefully handle the case of instantaneous trajectory prediction. Extensive experiments on the Argoverse and nuScenes datasets demonstrate ITPNet outperforms the baselines, and its efficacy with different trajectory prediction models.
Authors: Wenhang Ge, Jiantao Lin, Guibao Shen, Jiawei Feng, Tao Hu, Xinli Xu, Ying-Cong Chen
Abstract: We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained local details. Unlike previous large reconstruction models that prepare images under fixed and simple lighting as both input and supervision, PRM renders photometric stereo images by varying materials and lighting for the purposes, which not only improves the precise local details by providing rich photometric cues but also increases the model robustness to variations in the appearance of input images. To offer enhanced flexibility of images rendering, we incorporate a real-time physically-based rendering (PBR) method and mesh rasterization for online images rendering. Moreover, in employing an explicit mesh as our 3D representation, PRM ensures the application of differentiable PBR, which supports the utilization of multiple photometric supervisions and better models the specular color for high-quality geometry optimization. Our PRM leverages photometric stereo images to achieve high-quality reconstructions with fine-grained local details, even amidst sophisticated image appearances. Extensive experiments demonstrate that PRM significantly outperforms other models.
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: Jiazuo Mu, Fuyi Yang, Yanshun Zhang, Junxiong Zhang, Yongjian Luo, Lan Xu, Yujiao Shi, Jingyi Yu, Yingliang Zhang
Abstract: We introduce CADSpotting, an efficient method for panoptic symbol spotting in large-scale architectural CAD drawings. Existing approaches struggle with the diversity of symbols, scale variations, and overlapping elements in CAD designs. CADSpotting overcomes these challenges by representing each primitive with dense points instead of a single primitive point, described by essential attributes like coordinates and color. Building upon a unified 3D point cloud model for joint semantic, instance, and panoptic segmentation, CADSpotting learns robust feature representations. To enable accurate segmentation in large, complex drawings, we further propose a novel Sliding Window Aggregation (SWA) technique, combining weighted voting and Non-Maximum Suppression (NMS). Moreover, we introduce a large-scale CAD dataset named LS-CAD to support our experiments. Each floorplan in LS-CAD has an average coverage of 1,000 square meter(versus 100 square meter in the existing dataset), providing a valuable benchmark for symbol spotting research. Experimental results on FloorPlanCAD and LS-CAD datasets demonstrate that CADSpotting outperforms existing methods, showcasing its robustness and scalability for real-world CAD applications.
Authors: Ellington Kirby, Mickael Chen, Renaud Marlet, Nermin Samet
Abstract: A common strategy to improve lidar segmentation results on rare semantic classes consists of pasting objects from one lidar scene into another. While this augments the quantity of instances seen at training time and varies their context, the instances fundamentally remain the same. In this work, we explore how to enhance instance diversity using a lidar object generator. We introduce a novel diffusion-based method to produce lidar point clouds of dataset objects, including reflectance, and with an extensive control of the generation via conditioning information. Our experiments on nuScenes show the quality of our object generations measured with new 3D metrics developed to suit lidar objects.
Authors: Ahmed Luqman, Khuzemah Qazi, Imdadullah Khan
Abstract: Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource constrained devices. Quantization is one technique that aims to alleviate these large storage requirements and speed up the inference process by reducing the precision of model parameters to lower-bit representations. In this paper, we introduce a novel post-training quantization method for model weights. Our method finds optimal clipping thresholds and scaling factors along with mathematical guarantees that our method minimizes quantization noise. Empirical results on Real World Datasets demonstrate that our quantization scheme significantly reduces model size and computational requirements while preserving model accuracy.
Authors: Muhayy Ud Din, Ahsan B. Bakht, Waseem Akram, Yihao Dong, Lakmal Seneviratne, Irfan Hussain
Abstract: Vision-based target tracking is crucial for unmanned surface vehicles (USVs) to perform tasks such as inspection, monitoring, and surveillance. However, real-time tracking in complex maritime environments is challenging due to dynamic camera movement, low visibility, and scale variation. Typically, object detection methods combined with filtering techniques are commonly used for tracking, but they often lack robustness, particularly in the presence of camera motion and missed detections. Although advanced tracking methods have been proposed recently, their application in maritime scenarios is limited. To address this gap, this study proposes a vision-guided object-tracking framework for USVs, integrating state-of-the-art tracking algorithms with low-level control systems to enable precise tracking in dynamic maritime environments. We benchmarked the performance of seven distinct trackers, developed using advanced deep learning techniques such as Siamese Networks and Transformers, by evaluating them on both simulated and real-world maritime datasets. In addition, we evaluated the robustness of various control algorithms in conjunction with these tracking systems. The proposed framework was validated through simulations and real-world sea experiments, demonstrating its effectiveness in handling dynamic maritime conditions. The results show that SeqTrack, a Transformer-based tracker, performed best in adverse conditions, such as dust storms. Among the control algorithms evaluated, the linear quadratic regulator controller (LQR) demonstrated the most robust and smooth control, allowing for stable tracking of the USV.
Authors: Sudha Krishnamurthy
Abstract: We propose a novel self-supervised approach for learning audio and visual representations from unlabeled videos, based on their correspondence. The approach uses an attention mechanism to learn the relative importance of convolutional features extracted at different resolutions from the audio and visual streams and uses the attention features to encode the audio and visual input based on their correspondence. We evaluated the representations learned by the model to classify audio-visual correlation as well as to recommend sound effects for visual scenes. Our results show that the representations generated by the attention model improves the correlation accuracy compared to the baseline, by 18% and the recommendation accuracy by 10% for VGG-Sound, which is a public video dataset. Additionally, audio-visual representations learned by training the attention model with cross-modal contrastive learning further improves the recommendation performance, based on our evaluation using VGG-Sound and a more challenging dataset consisting of gameplay video recordings.
Authors: Jihen Amara, Birgitta K\"onig-Ries, Sheeba Samuel
Abstract: While deep learning has significantly advanced automatic plant disease detection through image-based classification, improving model explainability remains crucial for reliable disease detection. In this study, we apply the Automated Concept-based Explanation (ACE) method to plant disease classification using the widely adopted InceptionV3 model and the PlantVillage dataset. ACE automatically identifies the visual concepts found in the image data and provides insights about the critical features influencing the model predictions. This approach reveals both effective disease-related patterns and incidental biases, such as those from background or lighting that can compromise model robustness. Through systematic experiments, ACE helped us to identify relevant features and pinpoint areas for targeted model improvement. Our findings demonstrate the potential of ACE to improve the explainability of plant disease classification based on deep learning, which is essential for producing transparent tools for plant disease management in agriculture.
Authors: Gayathri Dandugula, Santhosh Boddana, Sudesh Mirashi
Abstract: Deploying radar object detection models on resource-constrained edge devices like the Raspberry Pi poses significant challenges due to the large size of the model and the limited computational power and the memory of the Pi. In this work, we explore the efficiency of Depthwise Separable Convolutions in radar object detection networks and integrate them into our model. Additionally, we introduce a novel Feature Enhancement and Compression (FEC) module to the PointPillars feature encoder to further improve the model performance. With these innovations, we propose the DSFEC-L model and its two versions, which outperform the baseline (23.9 mAP of Car class, 20.72 GFLOPs) on nuScenes dataset: 1). An efficient DSFEC-M model with a 14.6% performance improvement and a 60% reduction in GFLOPs. 2). A deployable DSFEC-S model with a 3.76% performance improvement and a remarkable 78.5% reduction in GFLOPs. Despite marginal performance gains, our deployable model achieves an impressive 74.5% reduction in runtime on the Raspberry Pi compared to the baseline.
Authors: Weihua Liu, Jianhua Qiu, Said Boumaraf, Chaochao lin, Pan liyuan, Lin Li, Mohammed Bennamoun, Naoufel Werghi
Abstract: In response to the growing threat of deepfake technology, we introduce BENet, a Cross-Domain Robust Bias Expansion Network. BENet enhances the detection of fake faces by addressing limitations in current detectors related to variations across different types of fake face generation techniques, where ``cross-domain" refers to the diverse range of these deepfakes, each considered a separate domain. BENet's core feature is a bias expansion module based on autoencoders. This module maintains genuine facial features while enhancing differences in fake reconstructions, creating a reliable bias for detecting fake faces across various deepfake domains. We also introduce a Latent-Space Attention (LSA) module to capture inconsistencies related to fake faces at different scales, ensuring robust defense against advanced deepfake techniques. The enriched LSA feature maps are multiplied with the expanded bias to create a versatile feature space optimized for subtle forgeries detection. To improve its ability to detect fake faces from unknown sources, BENet integrates a cross-domain detector module that enhances recognition accuracy by verifying the facial domain during inference. We train our network end-to-end with a novel bias expansion loss, adopted for the first time, in face forgery detection. Extensive experiments covering both intra and cross-dataset demonstrate BENet's superiority over current state-of-the-art solutions.
Authors: Wenbo Huang, Jinghui Zhang, Guang Li, Lei Zhang, Shuoyuan Wang, Fang Dong, Jiahui Jin, Takahiro Ogawa, Miki Haseyama
Abstract: In few-shot action recognition~(FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba demonstrates efficiency in modeling long sequences, but directly applying Mamba to FSAR overlooks the importance of local feature modeling and alignment. Moreover, long sub-sequences within the same class accumulate intra-class variance, which adversely impacts FSAR performance. To solve these challenges, we propose a \underline{\textbf{M}}atryoshka M\underline{\textbf{A}}mba and Co\underline{\textbf{N}}tras\underline{\textbf{T}}ive Le\underline{\textbf{A}}rning framework~(\textbf{Manta}). Firstly, the Matryoshka Mamba introduces multiple Inner Modules to enhance local feature representation, rather than directly modeling global features. An Outer Module captures dependencies of timeline between these local features for implicit temporal alignment. Secondly, a hybrid contrastive learning paradigm, combining both supervised and unsupervised methods, is designed to mitigate the negative effects of intra-class variance accumulation. The Matryoshka Mamba and the hybrid contrastive learning paradigm operate in parallel branches within Manta, enhancing Mamba for FSAR of long sub-sequence. Manta achieves new state-of-the-art performance on prominent benchmarks, including SSv2, Kinetics, UCF101, and HMDB51. Extensive empirical studies prove that Manta significantly improves FSAR of long sub-sequence from multiple perspectives. The code is released at https://github.com/wenbohuang1002/Manta.
Authors: Yanzhe Lyu, Kai Cheng, Xin Kang, Xuejin Chen
Abstract: Recently, 3D Gaussian Splatting (3D-GS) has prevailed in novel view synthesis, achieving high fidelity and efficiency. However, it often struggles to capture rich details and complete geometry. Our analysis highlights a key limitation of 3D-GS caused by the fixed threshold in densification, which balances geometry coverage against detail recovery as the threshold varies. To address this, we introduce a novel densification method, residual split, which adds a downscaled Gaussian as a residual. Our approach is capable of adaptively retrieving details and complementing missing geometry while enabling progressive refinement. To further support this method, we propose a pipeline named ResGS. Specifically, we integrate a Gaussian image pyramid for progressive supervision and implement a selection scheme that prioritizes the densification of coarse Gaussians over time. Extensive experiments demonstrate that our method achieves SOTA rendering quality. Consistent performance improvements can be achieved by applying our residual split on various 3D-GS variants, underscoring its versatility and potential for broader application in 3D-GS-based applications.
Authors: Yuchen Sun, Qianqian Xu, Zitai Wang, Zhiyong Yang, Junwei He
Abstract: Multi-label Out-Of-Distribution (OOD) detection aims to discriminate the OOD samples from the multi-label In-Distribution (ID) ones. Compared with its multiclass counterpart, it is crucial to model the joint information among classes. To this end, JointEnergy, which is a representative multi-label OOD inference criterion, summarizes the logits of all the classes. However, we find that JointEnergy can produce an imbalance problem in OOD detection, especially when the model lacks enough discrimination ability. Specifically, we find that the samples only related to minority classes tend to be classified as OOD samples due to the ambiguous energy decision boundary. Besides, imbalanced multi-label learning methods, originally designed for ID ones, would not be suitable for OOD detection scenarios, even producing a serious negative transfer effect. In this paper, we resort to auxiliary outlier exposure (OE) and propose an unknown-aware multi-label learning framework to reshape the uncertainty energy space layout. In this framework, the energy score is separately optimized for tail ID samples and unknown samples, and the energy distribution gap between them is expanded, such that the tail ID samples can have a significantly larger energy score than the OOD ones. What's more, a simple yet effective measure is designed to select more informative OE datasets. Finally, comprehensive experimental results on multiple multi-label and OOD datasets reveal the effectiveness of the proposed method.
Authors: Vladislav Li, Ilias Siniosoglou, Thomai Karamitsou, Anastasios Lytos, Ioannis D. Moscholios, Sotirios K. Goudos, Jyoti S. Banerjee, Panagiotis Sarigiannidi, Vasileios Argyriou
Abstract: Autonomous Vehicles (AVs) use natural images and videos as input to understand the real world by overlaying and inferring digital elements, facilitating proactive detection in an effort to assure safety. A crucial aspect of this process is real-time, accurate object recognition through automatic scene analysis. While traditional methods primarily concentrate on 2D object detection, exploring 3D object detection, which involves projecting 3D bounding boxes into the three-dimensional environment, holds significance and can be notably enhanced using the AR ecosystem. This study examines an AI model's ability to deduce 3D bounding boxes in the context of real-time scene analysis while producing and evaluating the model's performance and processing time, in the virtual domain, which is then applied to AVs. This work also employs a synthetic dataset that includes artificially generated images mimicking various environmental, lighting, and spatiotemporal states. This evaluation is oriented in handling images featuring objects in diverse weather conditions, captured with varying camera settings. These variations pose more challenging detection and recognition scenarios, which the outcomes of this work can help achieve competitive results under most of the tested conditions.
Authors: Xiaoyang Ning, Qing Xie, Jinyu Xu, Wenbo Jiang, Jiachen Li, Yanchun Ma
Abstract: Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the existing 3D backdoor attacks achieved high attack performance, they remain vulnerable to preprocessing-based defenses (e.g., outlier removal and rotation augmentation) and are prone to detection by human inspection. In pursuit of a more challenging-to-defend and stealthy 3D backdoor attack, this paper introduces the Stealthy and Robust Backdoor Attack (SRBA), which ensures robustness and stealthiness through intentional design considerations. The key insight of our attack involves applying a uniform shift to the additional point features of point clouds (e.g., reflection intensity) widely utilized as part of inputs for 3D DNNs as the trigger. Without altering the geometric information of the point clouds, our attack ensures visual consistency between poisoned and benign samples, and demonstrate robustness against preprocessing-based defenses. In addition, to automate our attack, we employ Bayesian Optimization (BO) to identify the suitable trigger. Extensive experiments suggest that SRBA achieves an attack success rate (ASR) exceeding 94% in all cases, and significantly outperforms previous SOTA methods when multiple preprocessing operations are applied during training.
Authors: Yingying Deng, Xiangyu He, Changwang Mei, Peisong Wang, Fan Tang
Abstract: Though Rectified Flows (ReFlows) with distillation offers a promising way for fast sampling, its fast inversion transforms images back to structured noise for recovery and following editing remains unsolved. This paper introduces FireFlow, a simple yet effective zero-shot approach that inherits the startling capacity of ReFlow-based models (such as FLUX) in generation while extending its capabilities to accurate inversion and editing in $8$ steps. We first demonstrate that a carefully designed numerical solver is pivotal for ReFlow inversion, enabling accurate inversion and reconstruction with the precision of a second-order solver while maintaining the practical efficiency of a first-order Euler method. This solver achieves a $3\times$ runtime speedup compared to state-of-the-art ReFlow inversion and editing techniques, while delivering smaller reconstruction errors and superior editing results in a training-free mode. The code is available at $\href{https://github.com/HolmesShuan/FireFlow}{this URL}$.
Authors: Jiaqi Fan, Jianhua Wu, Hongqing Chu, Quanbo Ge, Bingzhao Gao
Abstract: Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation tasks. However, these models occasionally generate hallucinatory texts, resulting in descriptions that seem reasonable but do not correspond to the image. This phenomenon can lead to wrong driving decisions of the autonomous driving system. To address this challenge, this paper proposes HCOENet, a plug-and-play chain-of-thought correction method designed to eliminate object hallucinations and generate enhanced descriptions for critical objects overlooked in the initial response. Specifically, HCOENet employs a cross-checking mechanism to filter entities and directly extracts critical objects from the given image, enriching the descriptive text. Experimental results on the POPE benchmark demonstrate that HCOENet improves the F1-score of the Mini-InternVL-4B and mPLUG-Owl3 models by 12.58% and 4.28%, respectively. Additionally, qualitative results using images collected in open campus scene further highlight the practical applicability of the proposed method. Compared with the GPT-4o model, HCOENet achieves comparable descriptive performance while significantly reducing costs. Finally, two novel semantic understanding datasets, CODA_desc and nuScenes_desc, are created for traffic scenarios to support future research. The codes and datasets are publicly available at https://github.com/fjq-tongji/HCOENet.
Authors: Tu Vo, Chan Y. Park
Abstract: Low-light and blurring issues are prevalent when capturing photos at night, often due to the use of long exposure to address dim environments. Addressing these joint problems can be challenging and error-prone if an end-to-end model is trained without incorporating an appropriate physical model. In this paper, we introduce JUDE, a Deep Joint Unrolling for Deblurring and Low-Light Image Enhancement, inspired by the image physical model. Based on Retinex theory and the blurring model, the low-light blurry input is iteratively deblurred and decomposed, producing sharp low-light reflectance and illuminance through an unrolling mechanism. Additionally, we incorporate various modules to estimate the initial blur kernel, enhance brightness, and eliminate noise in the final image. Comprehensive experiments on LOL-Blur and Real-LOL-Blur demonstrate that our method outperforms existing techniques both quantitatively and qualitatively.
Authors: Jingzhi Li, Zongwei Wu, Eduard Zamfir, Radu Timofte
Abstract: Accurate 3D objects relighting in diverse unseen environments is crucial for realistic virtual object placement. Due to the albedo-lighting ambiguity, existing methods often fall short in producing faithful relights. Without proper constraints, observed training views can be explained by numerous combinations of lighting and material attributes, lacking physical correspondence with the actual environment maps used for relighting. In this work, we present ReCap, treating cross-environment captures as multi-task target to provide the missing supervision that cuts through the entanglement. Specifically, ReCap jointly optimizes multiple lighting representations that share a common set of material attributes. This naturally harmonizes a coherent set of lighting representations around the mutual material attributes, exploiting commonalities and differences across varied object appearances. Such coherence enables physically sound lighting reconstruction and robust material estimation - both essential for accurate relighting. Together with a streamlined shading function and effective post-processing, ReCap outperforms the leading competitor by 3.4 dB in PSNR on an expanded relighting benchmark.
Authors: Simon Kristoffersson Lind, Rudolph Triebel, Volker Kr\"uger
Abstract: Modern robotic perception is highly dependent on neural networks. It is well known that neural network-based perception can be unreliable in real-world deployment, especially in difficult imaging conditions. Out-of-distribution detection is commonly proposed as a solution for ensuring reliability in real-world deployment. Previous work has shown that normalizing flow models can be used for out-of-distribution detection to improve reliability of robotic perception tasks. Specifically, camera parameters can be optimized with respect to the likelihood output from a normalizing flow, which allows a perception system to adapt to difficult vision scenarios. With this work we propose to use the absolute gradient values from a normalizing flow, which allows the perception system to optimize local regions rather than the whole image. By setting up a table top picking experiment with exceptionally difficult lighting conditions, we show that our method achieves a 60% higher success rate for an object detection task compared to previous methods.
Authors: Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang
Abstract: Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous regions, leading to detection failures. To addresses this problem, the widely accepted Reverse Distillation (RD) paradigm designs the asymmetry teacher and student, using an encoder as teacher and a decoder as student. Yet, the design of RD does not ensure that the teacher encoder effectively distinguishes between normal and abnormal features or that the student decoder generates anomaly-free features. Additionally, the absence of skip connections results in a loss of fine details during feature reconstruction. To address these issues, we propose RD with Expert, which introduces a novel Expert-Teacher-Student network for simultaneous distillation of both the teacher encoder and student decoder. The added expert network enhances the student's ability to generate normal features and optimizes the teacher's differentiation between normal and abnormal features, reducing missed detections. Additionally, Guided Information Injection is designed to filter and transfer features from teacher to student, improving detail reconstruction and minimizing false positives. Experiments on several benchmarks prove that our method outperforms existing unsupervised AD methods under RD paradigm, fully unlocking RD's potential.
Authors: Haitam Ben Yahia, Denis Korzhenkov, Ioannis Lelekas, Amir Ghodrati, Amirhossein Habibian
Abstract: Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper introduces the first mobile-optimized video diffusion model. Starting from a spatio-temporal UNet from Stable Video Diffusion (SVD), we reduce memory and computational cost by reducing the frame resolution, incorporating multi-scale temporal representations, and introducing two novel pruning schema to reduce the number of channels and temporal blocks. Furthermore, we employ adversarial finetuning to reduce the denoising to a single step. Our model, coined as MobileVD, is 523x more efficient (1817.2 vs. 4.34 TFLOPs) with a slight quality drop (FVD 149 vs. 171), generating latents for a 14x512x256 px clip in 1.7 seconds on a Xiaomi-14 Pro. Our results are available at https://qualcomm-ai-research.github.io/mobile-video-diffusion/
URLs: https://qualcomm-ai-research.github.io/mobile-video-diffusion/
Authors: Quoc-Bao Nguyen-Le, Thanh-Huy Le-Nguyen
Abstract: Current video retrieval systems, especially those used in competitions, primarily focus on querying individual keyframes or images rather than encoding an entire clip or video segment. However, queries often describe an action or event over a series of frames, not a specific image. This results in insufficient information when analyzing a single frame, leading to less accurate query results. Moreover, extracting embeddings solely from images (keyframes) does not provide enough information for models to encode higher-level, more abstract insights inferred from the video. These models tend to only describe the objects present in the frame, lacking a deeper understanding. In this work, we propose a system that integrates the latest methodologies, introducing a novel pipeline that extracts multimodal data, and incorporate information from multiple frames within a video, enabling the model to abstract higher-level information that captures latent meanings, focusing on what can be inferred from the video clip, rather than just focusing on object detection in one single image.
Authors: Jianzong Wu, Chao Tang, Jingbo Wang, Yanhong Zeng, Xiangtai Li, Yunhai Tong
Abstract: Story visualization, the task of creating visual narratives from textual descriptions, has seen progress with text-to-image generation models. However, these models often lack effective control over character appearances and interactions, particularly in multi-character scenes. To address these limitations, we propose a new task: \textbf{customized manga generation} and introduce \textbf{DiffSensei}, an innovative framework specifically designed for generating manga with dynamic multi-character control. DiffSensei integrates a diffusion-based image generator with a multimodal large language model (MLLM) that acts as a text-compatible identity adapter. Our approach employs masked cross-attention to seamlessly incorporate character features, enabling precise layout control without direct pixel transfer. Additionally, the MLLM-based adapter adjusts character features to align with panel-specific text cues, allowing flexible adjustments in character expressions, poses, and actions. We also introduce \textbf{MangaZero}, a large-scale dataset tailored to this task, containing 43,264 manga pages and 427,147 annotated panels, supporting the visualization of varied character interactions and movements across sequential frames. Extensive experiments demonstrate that DiffSensei outperforms existing models, marking a significant advancement in manga generation by enabling text-adaptable character customization. The project page is https://jianzongwu.github.io/projects/diffsensei/.
Authors: Qikai Chang, Mingjun Chen, Changpeng Pi, Pengfei Hu, Zhenrong Zhang, Jiefeng Ma, Jun Du, Baocai Yin, Jinshui Hu
Abstract: The primary objective of Optical Chemical Structure Recognition is to identify chemical structure images into corresponding markup sequences. However, the complex two-dimensional structures of molecules, particularly those with rings and multiple branches, present significant challenges for current end-to-end methods to learn one-dimensional markup directly. To overcome this limitation, we propose a novel Ring-Free Language (RFL), which utilizes a divide-and-conquer strategy to describe chemical structures in a hierarchical form. RFL allows complex molecular structures to be decomposed into multiple parts, ensuring both uniqueness and conciseness while enhancing readability. This approach significantly reduces the learning difficulty for recognition models. Leveraging RFL, we propose a universal Molecular Skeleton Decoder (MSD), which comprises a skeleton generation module that progressively predicts the molecular skeleton and individual rings, along with a branch classification module for predicting branch information. Experimental results demonstrate that the proposed RFL and MSD can be applied to various mainstream methods, achieving superior performance compared to state-of-the-art approaches in both printed and handwritten scenarios. The code is available at https://github.com/JingMog/RFL-MSD.
Authors: Chengbo Wang, Guozheng Ma, Yifei Xue, Yizhen Lao
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, demonstrating remarkable capability in high-fidelity scene reconstruction through its Gaussian primitive representations. However, the computational overhead induced by the massive number of primitives poses a significant bottleneck to training efficiency. To overcome this challenge, we propose Group Training, a simple yet effective strategy that organizes Gaussian primitives into manageable groups, optimizing training efficiency and improving rendering quality. This approach shows universal compatibility with existing 3DGS frameworks, including vanilla 3DGS and Mip-Splatting, consistently achieving accelerated training while maintaining superior synthesis quality. Extensive experiments reveal that our straightforward Group Training strategy achieves up to 30% faster convergence and improved rendering quality across diverse scenarios.
Authors: Subin Varghese, Joshua Gao, Vedhus Hoskere
Abstract: Detecting changes between images is a fundamental problem in computer vision with broad applications in situational awareness, infrastructure assessment, environment monitoring, and industrial automation. Existing supervised models are typically limited to detecting specific types of changes, necessitating retraining for new tasks. To address these limitations with a single approach, we propose a novel change detection method that is the first to utilize unaligned images and textual prompts to output a binary segmentation of changes relevant to user-provided text. Our architecture not only enables flexible detection across diverse change detection use cases, but also yields state-of-the art performance on established benchmarks. Additionally, we release an accompanying dataset comprising of 100,311 pairs of images with text prompts and the corresponding change detection labels. We demonstrate the effectiveness of our method both quantitatively and qualitatively on datasets with a wide variety of viewpoints in indoor, outdoor, street level, synthetic, and satellite images.
Authors: Yujing Xue, Jiaxiang Liu, Jiawei Du, Joey Tianyi Zhou
Abstract: Recently, polar coordinate-based representations have shown promise for 3D perceptual tasks. Compared to Cartesian methods, polar grids provide a viable alternative, offering better detail preservation in nearby spaces while covering larger areas. However, they face feature distortion due to non-uniform division. To address these issues, we introduce the Polar Voxel Occupancy Predictor (PVP), a novel 3D multi-modal predictor that operates in polar coordinates. PVP features two key design elements to overcome distortion: a Global Represent Propagation (GRP) module that integrates global spatial data into 3D volumes, and a Plane Decomposed Convolution (PD-Conv) that simplifies 3D distortions into 2D convolutions. These innovations enable PVP to outperform existing methods, achieving significant improvements in mIoU and IoU metrics on the OpenOccupancy dataset.
Authors: Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, Jin Shi, Fan Wu, Pei Chu, Minghao Liu, Zhenxiang Li, Chao Xu, Bo Zhang, Botian Shi, Zhongying Tu, Conghui He
Abstract: Document content extraction is crucial in computer vision, especially for meeting the high-quality data needs of large language models (LLMs) and retrieval-augmented generation (RAG) technologies. However, current document parsing methods suffer from significant limitations in terms of diversity and comprehensive evaluation. To address these challenges, we introduce OmniDocBench, a novel multi-source benchmark designed to advance automated document content extraction. OmniDocBench includes a meticulously curated and annotated high-quality evaluation dataset comprising nine diverse document types, such as academic papers, textbooks, slides, among others. Our benchmark provides a flexible and comprehensive evaluation framework with 19 layout category labels and 14 attribute labels, enabling multi-level assessments across entire datasets, individual modules, or specific data types. Using OmniDocBench, we perform an exhaustive comparative analysis of existing modular pipelines and multimodal end-to-end methods, highlighting their limitations in handling document diversity and ensuring fair evaluation. OmniDocBench establishes a robust, diverse, and fair evaluation standard for the document content extraction field, offering crucial insights for future advancements and fostering the development of document parsing technologies. The codes and dataset is available in https://github.com/opendatalab/OmniDocBench.
Authors: Anubhav Jain, Yuya Kobayashi, Takashi Shibuya, Yuhta Takida, Nasir Memon, Julian Togelius, Yuki Mitsufuji
Abstract: Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as not-safe-for-work (NSFW) images. While approaches have been proposed to erase such abstract concepts from the models, jail-breaking techniques have succeeded in bypassing such safety measures. In this paper, we propose TraSCE, an approach to guide the diffusion trajectory away from generating harmful content. Our approach is based on negative prompting, but as we show in this paper, conventional negative prompting is not a complete solution and can easily be bypassed in some corner cases. To address this issue, we first propose a modification of conventional negative prompting. Furthermore, we introduce a localized loss-based guidance that enhances the modified negative prompting technique by steering the diffusion trajectory. We demonstrate that our proposed method achieves state-of-the-art results on various benchmarks in removing harmful content including ones proposed by red teams; and erasing artistic styles and objects. Our proposed approach does not require any training, weight modifications, or training data (both image or prompt), making it easier for model owners to erase new concepts.
Authors: Axel Martinez, Emilio Hernandez, Matthieu Olague, Gustavo Olague
Abstract: Low-light image enhancement remains an open problem, and the new wave of artificial intelligence is at the center of this problem. This work describes the use of genetic algorithms for optimizing analytical models that can improve the visualization of images with poor light. Genetic algorithms are part of metaheuristic approaches, which proved helpful in solving challenging optimization tasks. We propose two analytical methods combined with optimization reasoning to approach a solution to the physical and computational aspects of transforming dark images into visible ones. The experiments demonstrate that the proposed approach ranks at the top among 26 state-of-the-art algorithms in the LOL benchmark. The results show evidence that a simple genetic algorithm combined with analytical reasoning can defeat the current mainstream in a challenging computer vision task through controlled experiments and objective comparisons. This work opens interesting new research avenues for the swarm and evolutionary computation community and others interested in analytical and heuristic reasoning.
Authors: Yixuan Li, Xingjian Ran, Linning Xu, Tao Lu, Mulin Yu, Zhenzhi Wang, Yuanbo Xiangli, Dahua Lin, Bo Dai
Abstract: Buildings are primary components of cities, often featuring repeated elements such as windows and doors. Traditional 3D building asset creation is labor-intensive and requires specialized skills to develop design rules. Recent generative models for building creation often overlook these patterns, leading to low visual fidelity and limited scalability. Drawing inspiration from procedural modeling techniques used in the gaming and visual effects industry, our method, Proc-GS, integrates procedural code into the 3D Gaussian Splatting (3D-GS) framework, leveraging their advantages in high-fidelity rendering and efficient asset management from both worlds. By manipulating procedural code, we can streamline this process and generate an infinite variety of buildings. This integration significantly reduces model size by utilizing shared foundational assets, enabling scalable generation with precise control over building assembly. We showcase the potential for expansive cityscape generation while maintaining high rendering fidelity and precise control on both real and synthetic cases.
Authors: Tong Wu, Yinghao Xu, Ryan Po, Mengchen Zhang, Guandao Yang, Jiaqi Wang, Ziwei Liu, Dahua Lin, Gordon Wetzstein
Abstract: Recent advances in text-to-image generation have enabled the creation of high-quality images with diverse applications. However, accurately describing desired visual attributes can be challenging, especially for non-experts in art and photography. An intuitive solution involves adopting favorable attributes from the source images. Current methods attempt to distill identity and style from source images. However, "style" is a broad concept that includes texture, color, and artistic elements, but does not cover other important attributes such as lighting and dynamics. Additionally, a simplified "style" adaptation prevents combining multiple attributes from different sources into one generated image. In this work, we formulate a more effective approach to decompose the aesthetics of a picture into specific visual attributes, allowing users to apply characteristics such as lighting, texture, and dynamics from different images. To achieve this goal, we constructed the first fine-grained visual attributes dataset (FiVA) to the best of our knowledge. This FiVA dataset features a well-organized taxonomy for visual attributes and includes around 1 M high-quality generated images with visual attribute annotations. Leveraging this dataset, we propose a fine-grained visual attribute adaptation framework (FiVA-Adapter), which decouples and adapts visual attributes from one or more source images into a generated one. This approach enhances user-friendly customization, allowing users to selectively apply desired attributes to create images that meet their unique preferences and specific content requirements.
Authors: Greg Heinrich (Danny), Mike Ranzinger (Danny), Hongxu (Danny), Yin, Yao Lu, Jan Kautz, Andrew Tao, Bryan Catanzaro, Pavlo Molchanov
Abstract: Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables the efficient creation of robust models, combining the strengths of individual teachers while significantly reducing computational and resource demands. In this paper, we thoroughly analyze state-of-the-art agglomerative models, identifying critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens. To address these issues, we propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions. Specifically, in the context of Vision Language Models, we introduce a token compression technique to maintain high-resolution information within a fixed token count. We release our top-performing models, available in multiple scales (-B, -L, -H, and -g), alongside inference code and pretrained weights.
Authors: Zhijian Huang, Chengjian Feng, Feng Yan, Baihui Xiao, Zequn Jie, Yujie Zhong, Xiaodan Liang, Lin Ma
Abstract: Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despite the advancements, current data-driven AD approaches tend to concentrate on a single dataset and specific tasks, neglecting their overall capabilities and ability to generalize. To bridge these gaps, we propose DriveMM, a general large multimodal model designed to process diverse data inputs, such as images and multi-view videos, while performing a broad spectrum of AD tasks, including perception, prediction, and planning. Initially, the model undergoes curriculum pre-training to process varied visual signals and perform basic visual comprehension and perception tasks. Subsequently, we augment and standardize various AD-related datasets to fine-tune the model, resulting in an all-in-one LMM for autonomous driving. To assess the general capabilities and generalization ability, we conduct evaluations on six public benchmarks and undertake zero-shot transfer on an unseen dataset, where DriveMM achieves state-of-the-art performance across all tasks. We hope DriveMM as a promising solution for future end-toend autonomous driving applications in the real world.
Authors: Igor Morawski, Kai He, Shusil Dangi, Winston H. Hsu
Abstract: Low-light conditions have an adverse impact on machine cognition, limiting the performance of computer vision systems in real life. Since low-light data is limited and difficult to annotate, we focus on image processing to enhance low-light images and improve the performance of any downstream task model, instead of fine-tuning each of the models which can be prohibitively expensive. We propose to improve the existing zero-reference low-light enhancement by leveraging the CLIP model to capture image prior and for semantic guidance. Specifically, we propose a data augmentation strategy to learn an image prior via prompt learning, based on image sampling, to learn the image prior without any need for paired or unpaired normal-light data. Next, we propose a semantic guidance strategy that maximally takes advantage of existing low-light annotation by introducing both content and context cues about the image training patches. We experimentally show, in a qualitative study, that the proposed prior and semantic guidance help to improve the overall image contrast and hue, as well as improve background-foreground discrimination, resulting in reduced over-saturation and noise over-amplification, common in related zero-reference methods. As we target machine cognition, rather than rely on assuming the correlation between human perception and downstream task performance, we conduct and present an ablation study and comparison with related zero-reference methods in terms of task-based performance across many low-light datasets, including image classification, object and face detection, showing the effectiveness of our proposed method.
Authors: Alex Trevithick, Roni Paiss, Philipp Henzler, Dor Verbin, Rundi Wu, Hadi Alzayer, Ruiqi Gao, Ben Poole, Jonathan T. Barron, Aleksander Holynski, Ravi Ramamoorthi, Pratul P. Srinivasan
Abstract: Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are difficult to model explicitly. We present an approach for leveraging generative video models to simulate the inconsistencies in the world that can occur during capture. We use this process, along with existing multi-view datasets, to create synthetic data for training a multi-view harmonization network that is able to reconcile inconsistent observations into a consistent 3D scene. We demonstrate that our world-simulation strategy significantly outperforms traditional augmentation methods in handling real-world scene variations, thereby enabling highly accurate static 3D reconstructions in the presence of a variety of challenging inconsistencies. Project page: https://alextrevithick.github.io/simvs
Authors: Yicheng Wang, Zhikang Zhang, Jue Wang, David Fan, Zhenlin Xu, Linda Liu, Xiang Hao, Vimal Bhat, Xinyu Li
Abstract: In various video-language learning tasks, the challenge of achieving cross-modality alignment with multi-grained data persists. We propose a method to tackle this challenge from two crucial perspectives: data and modeling. Given the absence of a multi-grained video-text pretraining dataset, we introduce a Granularity EXpansion (GEX) method with Integration and Compression operations to expand the granularity of a single-grained dataset. To better model multi-grained data, we introduce an Iterative Approximation Module (IAM), which embeds multi-grained videos and texts into a unified, low-dimensional semantic space while preserving essential information for cross-modal alignment. Furthermore, GEXIA is highly scalable with no restrictions on the number of video-text granularities for alignment. We evaluate our work on three categories of video tasks across seven benchmark datasets, showcasing state-of-the-art or comparable performance. Remarkably, our model excels in tasks involving long-form video understanding, even though the pretraining dataset only contains short video clips.
Authors: Jinyi Hu, Shengding Hu, Yuxuan Song, Yufei Huang, Mingxuan Wang, Hao Zhou, Zhiyuan Liu, Wei-Ying Ma, Maosong Sun
Abstract: The recent surge of interest in comprehensive multimodal models has necessitated the unification of diverse modalities. However, the unification suffers from disparate methodologies. Continuous visual generation necessitates the full-sequence diffusion-based approach, despite its divergence from the autoregressive modeling in the text domain. We posit that autoregressive modeling, i.e., predicting the future based on past deterministic experience, remains crucial in developing both a visual generation model and a potential unified multimodal model. In this paper, we explore an interpolation between the autoregressive modeling and full-parameters diffusion to model visual information. At its core, we present ACDiT, an Autoregressive blockwise Conditional Diffusion Transformer, where the block size of diffusion, i.e., the size of autoregressive units, can be flexibly adjusted to interpolate between token-wise autoregression and full-sequence diffusion. ACDiT is easy to implement, as simple as creating a Skip-Causal Attention Mask (SCAM) during training. During inference, the process iterates between diffusion denoising and autoregressive decoding that can make full use of KV-Cache. We verify the effectiveness of ACDiT on image and video generation tasks. We also demonstrate that benefitted from autoregressive modeling, ACDiT can be seamlessly used in visual understanding tasks despite being trained on the diffusion objective. The analysis of the trade-off between autoregressive modeling and diffusion demonstrates the potential of ACDiT to be used in long-horizon visual generation tasks. These strengths make it promising as the backbone of future unified models.
Authors: Zhouxia Wang, Yushi Lan, Shangchen Zhou, Chen Change Loy
Abstract: This study aims to achieve more precise and versatile object control in image-to-video (I2V) generation. Current methods typically represent the spatial movement of target objects with 2D trajectories, which often fail to capture user intention and frequently produce unnatural results. To enhance control, we present ObjCtrl-2.5D, a training-free object control approach that uses a 3D trajectory, extended from a 2D trajectory with depth information, as a control signal. By modeling object movement as camera movement, ObjCtrl-2.5D represents the 3D trajectory as a sequence of camera poses, enabling object motion control using an existing camera motion control I2V generation model (CMC-I2V) without training. To adapt the CMC-I2V model originally designed for global motion control to handle local object motion, we introduce a module to isolate the target object from the background, enabling independent local control. In addition, we devise an effective way to achieve more accurate object control by sharing low-frequency warped latent within the object's region across frames. Extensive experiments demonstrate that ObjCtrl-2.5D significantly improves object control accuracy compared to training-free methods and offers more diverse control capabilities than training-based approaches using 2D trajectories, enabling complex effects like object rotation. Code and results are available at https://wzhouxiff.github.io/projects/ObjCtrl-2.5D/.
Authors: Zongyu Lin, Wei Liu, Chen Chen, Jiasen Lu, Wenze Hu, Tsu-Jui Fu, Jesse Allardice, Zhengfeng Lai, Liangchen Song, Bowen Zhang, Cha Chen, Yiran Fei, Yifan Jiang, Lezhi Li, Yizhou Sun, Kai-Wei Chang, Yinfei Yang
Abstract: The field of video generation has made remarkable advancements, yet there remains a pressing need for a clear, systematic recipe that can guide the development of robust and scalable models. In this work, we present a comprehensive study that systematically explores the interplay of model architectures, training recipes, and data curation strategies, culminating in a simple and scalable text-image-conditioned video generation method, named STIV. Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning via a joint image-text conditional classifier-free guidance. This design enables STIV to perform both text-to-video (T2V) and text-image-to-video (TI2V) tasks simultaneously. Additionally, STIV can be easily extended to various applications, such as video prediction, frame interpolation, multi-view generation, and long video generation, etc. With comprehensive ablation studies on T2I, T2V, and TI2V, STIV demonstrate strong performance, despite its simple design. An 8.7B model with 512 resolution achieves 83.1 on VBench T2V, surpassing both leading open and closed-source models like CogVideoX-5B, Pika, Kling, and Gen-3. The same-sized model also achieves a state-of-the-art result of 90.1 on VBench I2V task at 512 resolution. By providing a transparent and extensible recipe for building cutting-edge video generation models, we aim to empower future research and accelerate progress toward more versatile and reliable video generation solutions.
Authors: Jack Saunders, Charlie Hewitt, Yanan Jian, Marek Kowalski, Tadas Baltrusaitis, Yiye Chen, Darren Cosker, Virginia Estellers, Nicholas Gyde, Vinay P. Namboodiri, Benjamin E Lundell
Abstract: Gaussian Splatting has changed the game for real-time photo-realistic rendering. One of the most popular applications of Gaussian Splatting is to create animatable avatars, known as Gaussian Avatars. Recent works have pushed the boundaries of quality and rendering efficiency but suffer from two main limitations. Either they require expensive multi-camera rigs to produce avatars with free-view rendering, or they can be trained with a single camera but only rendered at high quality from this fixed viewpoint. An ideal model would be trained using a short monocular video or image from available hardware, such as a webcam, and rendered from any view. To this end, we propose GASP: Gaussian Avatars with Synthetic Priors. To overcome the limitations of existing datasets, we exploit the pixel-perfect nature of synthetic data to train a Gaussian Avatar prior. By fitting this prior model to a single photo or video and fine-tuning it, we get a high-quality Gaussian Avatar, which supports 360$^\circ$ rendering. Our prior is only required for fitting, not inference, enabling real-time application. Through our method, we obtain high-quality, animatable Avatars from limited data which can be animated and rendered at 70fps on commercial hardware. See our project page (https://microsoft.github.io/GASP/) for results.
Authors: Wanwen Chen, Adam Schmidt, Eitan Prisman, Septimiu E. Salcudean
Abstract: Purpose: Intraoperative ultrasound (US) can enhance real-time visualization in transoral robotic surgery. The surgeon creates a mental map with a pre-operative scan. Then, a surgical assistant performs freehand US scanning during the surgery while the surgeon operates at the remote surgical console. Communicating the target scanning plane in the surgeon's mental map is difficult. Automatic image retrieval can help match intraoperative images to preoperative scans, guiding the assistant to adjust the US probe toward the target plane. Methods: We propose a self-supervised contrastive learning approach to match intraoperative US views to a preoperative image database. We introduce a novel contrastive learning strategy that leverages intra-sweep similarity and US probe location to improve feature encoding. Additionally, our model incorporates a flexible threshold to reject unsatisfactory matches. Results: Our method achieves 92.30% retrieval accuracy on simulated data and outperforms state-of-the-art temporal-based contrastive learning approaches. Our ablation study demonstrates that using probe location in the optimization goal improves image representation, suggesting that semantic information can be extracted from probe location. We also present our approach on real patient data to show the feasibility of the proposed US probe localization system despite tissue deformation from tongue retraction. Conclusion: Our contrastive learning method, which utilizes intra-sweep similarity and US probe location, enhances US image representation learning. We also demonstrate the feasibility of using our image retrieval method to provide neck US localization on real patient US after tongue retraction.
Authors: Zixuan Ye, Huijuan Huang, Xintao Wang, Pengfei Wan, Di Zhang, Wenhan Luo
Abstract: Style control has been popular in video generation models. Existing methods often generate videos far from the given style, cause content leakage, and struggle to transfer one video to the desired style. Our first observation is that the style extraction stage matters, whereas existing methods emphasize global style but ignore local textures. In order to bring texture features while preventing content leakage, we filter content-related patches while retaining style ones based on prompt-patch similarity; for global style extraction, we generate a paired style dataset through model illusion to facilitate contrastive learning, which greatly enhances the absolute style consistency. Moreover, to fill in the image-to-video gap, we train a lightweight motion adapter on still videos, which implicitly enhances stylization extent, and enables our image-trained model to be seamlessly applied to videos. Benefited from these efforts, our approach, StyleMaster, not only achieves significant improvement in both style resemblance and temporal coherence, but also can easily generalize to video style transfer with a gray tile ControlNet. Extensive experiments and visualizations demonstrate that StyleMaster significantly outperforms competitors, effectively generating high-quality stylized videos that align with textual content and closely resemble the style of reference images. Our project page is at https://zixuan-ye.github.io/stylemaster
Authors: Ziqi Lu, Heng Yang, Danfei Xu, Boyi Li, Boris Ivanovic, Marco Pavone, Yue Wang
Abstract: Emerging 3D geometric foundation models, such as DUSt3R, offer a promising approach for in-the-wild 3D vision tasks. However, due to the high-dimensional nature of the problem space and scarcity of high-quality 3D data, these pre-trained models still struggle to generalize to many challenging circumstances, such as limited view overlap or low lighting. To address this, we propose LoRA3D, an efficient self-calibration pipeline to $\textit{specialize}$ the pre-trained models to target scenes using their own multi-view predictions. Taking sparse RGB images as input, we leverage robust optimization techniques to refine multi-view predictions and align them into a global coordinate frame. In particular, we incorporate prediction confidence into the geometric optimization process, automatically re-weighting the confidence to better reflect point estimation accuracy. We use the calibrated confidence to generate high-quality pseudo labels for the calibrating views and use low-rank adaptation (LoRA) to fine-tune the models on the pseudo-labeled data. Our method does not require any external priors or manual labels. It completes the self-calibration process on a $\textbf{single standard GPU within just 5 minutes}$. Each low-rank adapter requires only $\textbf{18MB}$ of storage. We evaluated our method on $\textbf{more than 160 scenes}$ from the Replica, TUM and Waymo Open datasets, achieving up to $\textbf{88% performance improvement}$ on 3D reconstruction, multi-view pose estimation and novel-view rendering.
Authors: Yuval Atzmon, Rinon Gal, Yoad Tewel, Yoni Kasten, Gal Chechik
Abstract: Text-to-video models have made significant strides in generating short video clips from textual descriptions. Yet, a significant challenge remains: generating several video shots of the same characters, preserving their identity without hurting video quality, dynamics, and responsiveness to text prompts. We present Video Storyboarding, a training-free method to enable pretrained text-to-video models to generate multiple shots with consistent characters, by sharing features between them. Our key insight is that self-attention query features (Q) encode both motion and identity. This creates a hard-to-avoid trade-off between preserving character identity and making videos dynamic, when features are shared. To address this issue, we introduce a novel query injection strategy that balances identity preservation and natural motion retention. This approach improves upon naive consistency techniques applied to videos, which often struggle to maintain this delicate equilibrium. Our experiments demonstrate significant improvements in character consistency across scenes while maintaining high-quality motion and text alignment. These results offer insights into critical stages of video generation and the interplay of structure and motion in video diffusion models.
Authors: Timur Ismagilov, Bruno Ferrarini, Michael Milford, Tan Viet Tuyen Nguyen, SD Ramchurn, Shoaib Ehsan
Abstract: Visual Place Recognition (VPR) in mobile robotics enables robots to localize themselves by recognizing previously visited locations using visual data. While the reliability of VPR methods has been extensively studied under conditions such as changes in illumination, season, weather and viewpoint, the impact of motion blur is relatively unexplored despite its relevance not only in rapid motion scenarios but also in low-light conditions where longer exposure times are necessary. Similarly, the role of image deblurring in enhancing VPR performance under motion blur has received limited attention so far. This paper bridges these gaps by introducing a new benchmark designed to evaluate VPR performance under the influence of motion blur and image deblurring. The benchmark includes three datasets that encompass a wide range of motion blur intensities, providing a comprehensive platform for analysis. Experimental results with several well-established VPR and image deblurring methods provide new insights into the effects of motion blur and the potential improvements achieved through deblurring. Building on these findings, the paper proposes adaptive deblurring strategies for VPR, designed to effectively manage motion blur in dynamic, real-world scenarios.
Authors: Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Muhammad Awais, Josef Kittler
Abstract: Audio-driven talking face generation is a challenging task in digital communication. Despite significant progress in the area, most existing methods concentrate on audio-lip synchronization, often overlooking aspects such as visual quality, customization, and generalization that are crucial to producing realistic talking faces. To address these limitations, we introduce a novel, customizable one-shot audio-driven talking face generation framework, named PortraitTalk. Our proposed method utilizes a latent diffusion framework consisting of two main components: IdentityNet and AnimateNet. IdentityNet is designed to preserve identity features consistently across the generated video frames, while AnimateNet aims to enhance temporal coherence and motion consistency. This framework also integrates an audio input with the reference images, thereby reducing the reliance on reference-style videos prevalent in existing approaches. A key innovation of PortraitTalk is the incorporation of text prompts through decoupled cross-attention mechanisms, which significantly expands creative control over the generated videos. Through extensive experiments, including a newly developed evaluation metric, our model demonstrates superior performance over the state-of-the-art methods, setting a new standard for the generation of customizable realistic talking faces suitable for real-world applications.
Authors: Arijit Ray, Jiafei Duan, Reuben Tan, Dina Bashkirova, Rose Hendrix, Kiana Ehsani, Aniruddha Kembhavi, Bryan A. Plummer, Ranjay Krishna, Kuo-Hao Zeng, Kate Saenko
Abstract: Spatial perception is a fundamental component of intelligence. While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only test for static spatial reasoning, such as categorizing the relative positions of objects. Meanwhile, real-world deployment requires dynamic capabilities like perspective-taking and egocentric action recognition. As a roadmap to improving spatial intelligence, we introduce SAT, Spatial Aptitude Training, which goes beyond static relative object position questions to the more dynamic tasks. SAT contains 218K question-answer pairs for 22K synthetic scenes across a training and testing set. Generated using a photo-realistic physics engine, our dataset can be arbitrarily scaled and easily extended to new actions, scenes, and 3D assets. We find that even MLMs that perform relatively well on static questions struggle to accurately answer dynamic spatial questions. Further, we show that SAT instruction-tuning data improves not only dynamic spatial reasoning on SAT, but also zero-shot performance on existing real-image spatial benchmarks: $23\%$ on CVBench, $8\%$ on the harder BLINK benchmark, and $18\%$ on VSR. When instruction-tuned on SAT, our 13B model matches larger proprietary MLMs like GPT4-V and Gemini-3-1.0 in spatial reasoning. Our data/code is available at http://arijitray1993.github.io/SAT/ .
Authors: Xiao Fu, Xian Liu, Xintao Wang, Sida Peng, Menghan Xia, Xiaoyu Shi, Ziyang Yuan, Pengfei Wan, Di Zhang, Dahua Lin
Abstract: This paper aims to manipulate multi-entity 3D motions in video generation. Previous methods on controllable video generation primarily leverage 2D control signals to manipulate object motions and have achieved remarkable synthesis results. However, 2D control signals are inherently limited in expressing the 3D nature of object motions. To overcome this problem, we introduce 3DTrajMaster, a robust controller that regulates multi-entity dynamics in 3D space, given user-desired 6DoF pose (location and rotation) sequences of entities. At the core of our approach is a plug-and-play 3D-motion grounded object injector that fuses multiple input entities with their respective 3D trajectories through a gated self-attention mechanism. In addition, we exploit an injector architecture to preserve the video diffusion prior, which is crucial for generalization ability. To mitigate video quality degradation, we introduce a domain adaptor during training and employ an annealed sampling strategy during inference. To address the lack of suitable training data, we construct a 360-Motion Dataset, which first correlates collected 3D human and animal assets with GPT-generated trajectory and then captures their motion with 12 evenly-surround cameras on diverse 3D UE platforms. Extensive experiments show that 3DTrajMaster sets a new state-of-the-art in both accuracy and generalization for controlling multi-entity 3D motions. Project page: http://fuxiao0719.github.io/projects/3dtrajmaster
Authors: Jianhong Bai, Menghan Xia, Xintao Wang, Ziyang Yuan, Xiao Fu, Zuozhu Liu, Haoji Hu, Pengfei Wan, Di Zhang
Abstract: Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency. This progress inspires us to investigate the potential of these models to ensure dynamic consistency across various viewpoints, a highly desirable feature for applications such as virtual filming. Unlike existing methods focused on multi-view generation of single objects for 4D reconstruction, our interest lies in generating open-world videos from arbitrary viewpoints, incorporating 6 DoF camera poses. To achieve this, we propose a plug-and-play module that enhances a pre-trained text-to-video model for multi-camera video generation, ensuring consistent content across different viewpoints. Specifically, we introduce a multi-view synchronization module to maintain appearance and geometry consistency across these viewpoints. Given the scarcity of high-quality training data, we design a hybrid training scheme that leverages multi-camera images and monocular videos to supplement Unreal Engine-rendered multi-camera videos. Furthermore, our method enables intriguing extensions, such as re-rendering a video from novel viewpoints. We also release a multi-view synchronized video dataset, named SynCamVideo-Dataset. Project page: https://jianhongbai.github.io/SynCamMaster/.
Authors: Jingxi Chen, Brandon Y. Feng, Haoming Cai, Tianfu Wang, Levi Burner, Dehao Yuan, Cornelia Fermuller, Christopher A. Metzler, Yiannis Aloimonos
Abstract: Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, the large motion between frames makes this problem ill-posed. Event-based Video Frame Interpolation (EVFI) addresses this challenge by using sparse, high-temporal-resolution event measurements as motion guidance. This guidance allows EVFI methods to significantly outperform frame-only methods. However, to date, EVFI methods have relied on a limited set of paired event-frame training data, severely limiting their performance and generalization capabilities. In this work, we overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI. We experimentally validate our approach on real-world EVFI datasets, including a new one that we introduce. Our method outperforms existing methods and generalizes across cameras far better than existing approaches.
Authors: Xiaoyu Xiang, Liat Sless Gorelik, Yuchen Fan, Omri Armstrong, Forrest Iandola, Yilei Li, Ita Lifshitz, Rakesh Ranjan
Abstract: We present Make-A-Texture, a new framework that efficiently synthesizes high-resolution texture maps from textual prompts for given 3D geometries. Our approach progressively generates textures that are consistent across multiple viewpoints with a depth-aware inpainting diffusion model, in an optimized sequence of viewpoints determined by an automatic view selection algorithm. A significant feature of our method is its remarkable efficiency, achieving a full texture generation within an end-to-end runtime of just 3.07 seconds on a single NVIDIA H100 GPU, significantly outperforming existing methods. Such an acceleration is achieved by optimizations in the diffusion model and a specialized backprojection method. Moreover, our method reduces the artifacts in the backprojection phase, by selectively masking out non-frontal faces, and internal faces of open-surfaced objects. Experimental results demonstrate that Make-A-Texture matches or exceeds the quality of other state-of-the-art methods. Our work significantly improves the applicability and practicality of texture generation models for real-world 3D content creation, including interactive creation and text-guided texture editing.
Authors: Shuailei Ma, Kecheng Zheng, Ying Wei, Wei Wu, Fan Lu, Yifei Zhang, Chen-wei Xie, Jiapeng Zhu, Yujun Shen
Abstract: Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive. We argue that grasping the cross-modality alignment is not a necessity for a sound visual generative prior, whose focus should be on texture modeling. Such a philosophy inspires us to study image-to-image (I2I) generation, where models can learn from in-the-wild images in a self-supervised manner. We first develop a pure vision-based training framework, Lumos, and confirm the feasibility and the scalability of learning I2I models. We then find that, as an upstream task of T2I, our I2I model serves as a more foundational visual prior and achieves on-par or better performance than existing T2I models using only 1/10 text-image pairs for fine-tuning. We further demonstrate the superiority of I2I priors over T2I priors on some text-irrelevant visual generative tasks, like image-to-3D and image-to-video.
Authors: Zetong Yang, Hanxue Zhang, Yanan Sun, Li Chen, Fei Xia, Fatma Guney, Hongyang Li
Abstract: This paper introduces Test-time Correction (TTC) system, a novel online 3D detection system designated for online correction of test-time errors via human feedback, to guarantee the safety of deployed autonomous driving systems. Unlike well-studied offline 3D detectors frozen at inference, TTC explores the capability of instant online error rectification. By leveraging user feedback with interactive prompts at a frame, e.g., a simple click or draw of boxes, TTC could immediately update the corresponding detection results for future streaming inputs, even though the model is deployed with fixed parameters. This enables autonomous driving systems to adapt to new scenarios immediately and decrease deployment risks reliably without additional expensive training. To achieve such TTC system, we equip existing 3D detectors with Online Adapter (OA) module, a prompt-driven query generator for online correction. At the core of OA module are visual prompts, images of missed object-of-interest for guiding the corresponding detection and subsequent tracking. Those visual prompts, belonging to missed objects through online inference, are maintained by the visual prompt buffer for continuous error correction in subsequent frames. By doing so, TTC consistently detects online missed objects and immediately lowers driving risks. It achieves reliable, versatile, and adaptive driving autonomy. Extensive experiments demonstrate significant gain on instant error rectification over pre-trained 3D detectors, even in challenging scenarios with limited labels, zero-shot detection, and adverse conditions. We hope this work would inspire the community to investigate online rectification systems for autonomous driving post-deployment. Code would be publicly shared.
Authors: Sahal Shaji Mullappilly, Mohammed Irfan Kurpath, Sara Pieri, Saeed Yahya Alseiari, Shanavas Cholakkal, Khaled Aldahmani, Fahad Khan, Rao Anwer, Salman Khan, Timothy Baldwin, Hisham Cholakkal
Abstract: This paper introduces BiMediX2, a bilingual (Arabic-English) Bio-Medical EXpert Large Multimodal Model (LMM) with a unified architecture that integrates text and visual modalities, enabling advanced image understanding and medical applications. BiMediX2 leverages the Llama3.1 architecture and integrates text and visual capabilities to facilitate seamless interactions in both English and Arabic, supporting text-based inputs and multi-turn conversations involving medical images. The model is trained on an extensive bilingual healthcare dataset consisting of 1.6M samples of diverse medical interactions for both text and image modalities, mixed in Arabic and English. We also propose the first bilingual GPT-4o based medical LMM benchmark named BiMed-MBench. BiMediX2 is benchmarked on both text-based and image-based tasks, achieving state-of-the-art performance across several medical benchmarks. It outperforms recent state-of-the-art models in medical LLM evaluation benchmarks. Our model also sets a new benchmark in multimodal medical evaluations with over 9% improvement in English and over 20% in Arabic evaluations. Additionally, it surpasses GPT-4 by around 9% in UPHILL factual accuracy evaluations and excels in various medical Visual Question Answering, Report Generation, and Report Summarization tasks. The project page including source code and the trained model, is available at https://github.com/mbzuai-oryx/BiMediX2.
Authors: Matthew Wallingford, Anand Bhattad, Aditya Kusupati, Vivek Ramanujan, Matt Deitke, Sham Kakade, Aniruddha Kembhavi, Roozbeh Mottaghi, Wei-Chiu Ma, Ali Farhadi
Abstract: Three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision, graphics, and robotics. Large scale synthetic and object-centric 3D datasets have shown to be effective in training models that have 3D understanding of objects. However, applying a similar approach to real-world objects and scenes is difficult due to a lack of large-scale data. Videos are a potential source for real-world 3D data, but finding diverse yet corresponding views of the same content has shown to be difficult at scale. Furthermore, standard videos come with fixed viewpoints, determined at the time of capture. This restricts the ability to access scenes from a variety of more diverse and potentially useful perspectives. We argue that large scale 360 videos can address these limitations to provide: scalable corresponding frames from diverse views. In this paper, we introduce 360-1M, a 360 video dataset, and a process for efficiently finding corresponding frames from diverse viewpoints at scale. We train our diffusion-based model, Odin, on 360-1M. Empowered by the largest real-world, multi-view dataset to date, Odin is able to freely generate novel views of real-world scenes. Unlike previous methods, Odin can move the camera through the environment, enabling the model to infer the geometry and layout of the scene. Additionally, we show improved performance on standard novel view synthesis and 3D reconstruction benchmarks.
Authors: Kartik Narayan, Nithin Gopalakrishnan Nair, Jennifer Xu, Rama Chellappa, Vishal M. Patel
Abstract: Pre-training on large-scale datasets and utilizing margin-based loss functions have been highly successful in training models for high-resolution face recognition. However, these models struggle with low-resolution face datasets, in which the faces lack the facial attributes necessary for distinguishing different faces. Full fine-tuning on low-resolution datasets, a naive method for adapting the model, yields inferior performance due to catastrophic forgetting of pre-trained knowledge. Additionally the domain difference between high-resolution (HR) gallery images and low-resolution (LR) probe images in low resolution datasets leads to poor convergence for a single model to adapt to both gallery and probe after fine-tuning. To this end, we propose PETALface, a Parameter-Efficient Transfer Learning approach for low-resolution face recognition. Through PETALface, we attempt to solve both the aforementioned problems. (1) We solve catastrophic forgetting by leveraging the power of parameter efficient fine-tuning(PEFT). (2) We introduce two low-rank adaptation modules to the backbone, with weights adjusted based on the input image quality to account for the difference in quality for the gallery and probe images. To the best of our knowledge, PETALface is the first work leveraging the powers of PEFT for low resolution face recognition. Extensive experiments demonstrate that the proposed method outperforms full fine-tuning on low-resolution datasets while preserving performance on high-resolution and mixed-quality datasets, all while using only 0.48% of the parameters. Code: https://kartik-3004.github.io/PETALface/
Authors: Tianwei Yin, Qiang Zhang, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, Xun Huang
Abstract: Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to a causal transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator. To enable stable and high-quality distillation, we introduce a student initialization scheme based on teacher's ODE trajectories, as well as an asymmetric distillation strategy that supervises a causal student model with a bidirectional teacher. This approach effectively mitigates error accumulation in autoregressive generation, allowing long-duration video synthesis despite training on short clips. Our model supports fast streaming generation of high quality videos at 9.4 FPS on a single GPU thanks to KV caching. Our approach also enables streaming video-to-video translation, image-to-video, and dynamic prompting in a zero-shot manner. We will release the code based on an open-source model in the future.
Authors: Xi Chen, Zhifei Zhang, He Zhang, Yuqian Zhou, Soo Ye Kim, Qing Liu, Yijun Li, Jianming Zhang, Nanxuan Zhao, Yilin Wang, Hui Ding, Zhe Lin, Hengshuang Zhao
Abstract: We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image generation, editing, customization, composition, etc. Although designed for image-level tasks, we leverage videos as a scalable source for universal supervision. UniReal learns world dynamics from large-scale videos, demonstrating advanced capability in handling shadows, reflections, pose variation, and object interaction, while also exhibiting emergent capability for novel applications.
Authors: Alexander Pondaven, Aliaksandr Siarohin, Sergey Tulyakov, Philip Torr, Fabio Pizzati
Abstract: We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process the reference video with a pre-trained DiT to analyze cross-frame attention maps and extract a patch-wise motion signal called the Attention Motion Flow (AMF). We guide the latent denoising process in an optimization-based, training-free, manner by optimizing latents with our AMF loss to generate videos reproducing the motion of the reference one. We also apply our optimization strategy to transformer positional embeddings, granting us a boost in zero-shot motion transfer capabilities. We evaluate DiTFlow against recently published methods, outperforming all across multiple metrics and human evaluation.
Authors: Han Yue, Jun Cheng, Yu-Xuan Ren, Philip Heng Wai Leong, Steve Feng Shu
Abstract: Ptychographic imaging confronts limitations in applying deep learning (DL) for retrieval from diffraction patterns. Conventional neural architectures are optimized for natural images, overlooking the unique physical characteristics of diffraction data, including radial intensity decay and coherent information distributed in concentric rings. In this paper, we present Ptychoformer, a physics-guided DL framework for ptychographic imaging that aligns attention mechanisms and feature extraction with these diffraction physics properties through introducing a dual-branch architecture which accounts for both local and non-local dependencies from the patterns. It consists of a Polar Coordinate Attention (PCA) mechanism that is inspired by the Ewald construction in X-ray crystallography to enhance high-frequency component fidelity. Experimental results demonstrate Ptychoformer's superior performance across both simulated and real data in preserving fine details and suppressing artifacts. On simulated data, Ptychoformer achieves up to 5.4% higher PSNR and 4.2% higher SSIM for amplitude retrieval compared to existing methods. For real experimental data, it demonstrates up to 12.5% higher PSNR and 31.3% higher SSIM for amplitude retrieval. Notably, Ptychoformer maintains robust performance under limited training data and low overlap ratios, outperforming existing models.
Authors: Andrea Avogaro, Luigi Capogrosso, Franco Fummi, Marco Cristani
Abstract: The fast fashion industry suffers from significant environmental impacts due to overproduction and unsold inventory. Accurately predicting sales volumes for unreleased products could significantly improve efficiency and resource utilization. However, predicting performance for entirely new items is challenging due to the lack of historical data and rapidly changing trends, and existing deterministic models often struggle with domain shifts when encountering items outside the training data distribution. The recently proposed diffusion models address this issue using a continuous-time diffusion process. This allows us to simulate how new items are adopted, reducing the impact of domain shift challenges faced by deterministic models. As a result, in this paper, we propose MDiFF: a novel two-step multimodal diffusion models-based pipeline for New Fashion Product Performance Forecasting (NFPPF). First, we use a score-based diffusion model to predict multiple future sales for different clothes over time. Then, we refine these multiple predictions with a lightweight Multi-layer Perceptron (MLP) to get the final forecast. MDiFF leverages the strengths of both architectures, resulting in the most accurate and efficient forecasting system for the fast-fashion industry at the state-of-the-art. The code can be found at https://github.com/intelligolabs/MDiFF.
Authors: Mohamed R. Ibrahim, Josef Musil, Irene Gallou
Abstract: In the domain of architectural design, the foundational essence of creativity and human intelligence lies in the mastery of solving floorplans, a skill demanding distinctive expertise and years of experience. Traditionally, the architectural design process of creating floorplans often requires substantial manual labour and architectural expertise. Even when relying on parametric design approaches, the process is limited based on the designer's ability to build a complex set of parameters to iteratively explore design alternatives. As a result, these approaches hinder creativity and limit discovery of an optimal solution. Here, we present a generative latent diffusion model that learns to generate floorplans for various building types based on building footprints and design briefs. The introduced model learns from the complexity of the inter-connections between diverse building types and the mutations of architectural designs. By harnessing the power of latent diffusion models, this research surpasses conventional limitations in the design process. The model's ability to learn from diverse building types means that it cannot only replicate existing designs but also produce entirely new configurations that fuse design elements in unexpected ways. This innovation introduces a new dimension of creativity into architectural design, allowing architects, urban planners and even individuals without specialised expertise to explore uncharted territories of form and function with speed and cost-effectiveness.
Authors: Raul Sena Ferreira, Joris Gu\'erin, Kevin Delmas, J\'er\'emie Guiochet, H\'el\`ene Waeselynck
Abstract: Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML predictions are used in safety-critical applications, like autonomous cars and surgical robots. Thus, the use of fault tolerance mechanisms, such as safety monitors, is essential to ensure the safe behavior of the system despite the occurrence of faults. This paper presents an extensive literature review on safety monitoring of perception functions using ML in a safety-critical context. In this review, we structure the existing literature to highlight key factors to consider when designing such monitors: threat identification, requirements elicitation, detection of failure, reaction, and evaluation. We also highlight the ongoing challenges associated with safety monitoring and suggest directions for future research.
Authors: Ankit Kumar Patel, Dewanshi Paul, Sneha Chaudhary, Sarthak Giri
Abstract: Password-based security is prone to forgetting, guessing, and hacking. Similarly, standalone biometric-based security is susceptible to template spoofing and replay attacks. This paper proposes a biocryptosystem based on face recognition technique to bridge this gap such that it can encrypt and decrypt any kind of file using the Advanced Encryption Standard (AES). The biocryptosystem uses a combination of biometric identification and cryptographic methods to protect sensitive information in a secure and effective manner. To verify a user's identity, our proposed system first captures an image of their face and extracts facial traits. The Histogram of Oriented Gradients (HOG) detects all the unique facial traits because HOG effectively captures edge-based features even in dim lighting. Every data type, including text, audio, and video files, can be encrypted and decrypted using this system. Biometric evidence is inherently tied to an individual, so it is almost impossible for attackers to access the user's data. This method also offers a high level of security by employing biometric data as an element in the 2-factor authentication process. The precision, efficiency, and security of this biocryptosystem are experimentally proven by different metrics like entropy and avalanche effect. Applications for the proposed system include safe file sharing, online transactions, and data archiving. Hence, it offers a strong and dependable option for safeguarding sensitive data.
Authors: Amirhossein Abaskohi, Spandana Gella, Giuseppe Carenini, Issam H. Laradji
Abstract: Multimodal multihop question answering is a complex task that requires reasoning over multiple sources of information, such as images and text, to answer questions. While there has been significant progress in visual question answering, the multihop setting remains unexplored due to the lack of high-quality datasets. Current methods focus on single-hop question answering or a single modality, which makes them unsuitable for real-world scenarios such as analyzing multimodal educational materials, summarizing lengthy academic articles, or interpreting scientific studies that combine charts, images, and text. To address this gap, we propose a novel methodology, introducing the first framework for creating a high-quality dataset that enables training models for multimodal multihop question answering. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimodal documents from Wikipedia, synthetically generating high-level questions and answers, and validating them through rigorous criteria to ensure quality data. We evaluate our methodology by training models on our synthesized dataset and testing on two benchmarks, our results demonstrate that, with an equal sample size, models trained on our synthesized data outperform those trained on human-collected data by 1.9 in exact match (EM) on average. We believe our data synthesis method will serve as a strong foundation for training and evaluating multimodal multihop question answering models.
Authors: Mengying Lei, Lijun Sun
Abstract: Real-world datasets often contain missing or corrupted values. Completing multidimensional tensor-structured data with missing entries is essential for numerous applications. Smoothness-constrained low-rank factorization models have shown superior performance with reduced computational costs. While effective at capturing global and long-range correlations, these models struggle to reproduce short-scale, high-frequency variations in the data. In this paper, we introduce the \Generalized Least Squares Kernelized Tensor Factorization (GLSKF) framework for tensor completion. GLSKF integrates smoothness-constrained low-rank factorization with a locally correlated residual process; the resulting additive structure can effectively characterize both global dependencies and local variations. In particular, we define the covariance norm to enforce the smoothness of factor matrices in the global low-rank factorization, and use structured covariance/kernel functions to model the local processes. For model estimation, we develop an alternating least squares (ALS) procedure with closed-form solutions for each subproblem. To efficiently handle missing data, GLSKF utilizes projection matrices that preserve the Kronecker structure of covariances, facilitating fast computations through conjugate gradient (CG) and preconditioned conjugate gradient (PCG) algorithms. The proposed framework is evaluated on four real-world datasets across diverse tasks: traffic speed imputation, color image inpainting, video completion, and MRI image reconstruction. Experimental results confirm that GLSKF delivers superior effectiveness and scalability, establishing it as a robust solution for multidimensional tensor completion.
Authors: Qiang Qu, Xiaoming Chen, Vera Chung, Zhibo Chen
Abstract: In multimedia broadcasting, no-reference image quality assessment (NR-IQA) is used to indicate the user-perceived quality of experience (QoE) and to support intelligent data transmission while optimizing user experience. This paper proposes an improved no-reference light field image quality assessment (NR-LFIQA) metric for future immersive media broadcasting services. First, we extend the concept of depthwise separable convolution (DSC) to the spatial domain of light field image (LFI) and introduce "light field depthwise separable convolution (LF-DSC)", which can extract the LFI's spatial features efficiently. Second, we further theoretically extend the LF-DSC to the angular space of LFI and introduce the novel concept of "light field anglewise separable convolution (LF-ASC)", which is capable of extracting both the spatial and angular features for comprehensive quality assessment with low complexity. Third, we define the spatial and angular feature estimations as auxiliary tasks in aiding the primary NR-LFIQA task by providing spatial and angular quality features as hints. To the best of our knowledge, this work is the first exploration of deep auxiliary learning with spatial-angular hints on NR-LFIQA. Experiments were conducted in mainstream LFI datasets such as Win5-LID and SMART with comparisons to the mainstream full reference IQA metrics as well as the state-of-the-art NR-LFIQA methods. The experimental results show that the proposed metric yields overall 42.86% and 45.95% smaller prediction errors than the second-best benchmarking metric in Win5-LID and SMART, respectively. In some challenging cases with particular distortion types, the proposed metric can reduce the errors significantly by more than 60%.
Authors: Shaobing Gao, Yongjie Li
Abstract: Color constancy (CC) is an important ability of the human visual system to stably perceive the colors of objects despite considerable changes in the color of the light illuminating them. While increasing evidence from the field of neuroscience supports that multiple levels of the visual system contribute to the realization of CC, how the primary visual cortex (V1) plays role in CC is not fully resolved. In specific, double-opponent (DO) neurons in V1 have been thought to contribute to realizing a degree of CC, but the computational mechanism is not clear. We build an electrophysiologically based V1 neural model to learn the color of the light source from a natural image dataset with the ground truth illuminants as the labels. Based on the qualitative and quantitative analysis of the responsive properties of the learned model neurons, we found that both the spatial structures and color weights of the receptive fields of the learned model neurons are quite similar to those of the simple and DO neurons recorded in V1. Computationally, DO cells perform more robustly than the simple cells in V1 for illuminant prediction. Therefore, this work provides computational evidence supporting that V1 DO neurons serve to realize color constancy by encoding the illuminant,which is contradictory to the common hypothesis that V1 contributes to CC by discounting the illuminant using its DO cells. This evidence is expected to not only help resolve the visual mechanisms of CC, but also provide inspiration to develop more effective computer vision models.
Authors: Yansong Xu, Xiaohui Wang, Junlin Li, Xiaoqian Zhang, Feng Li, Qing Gao, Chenglong Fu, Yuquan Leng
Abstract: The anthropomorphism of grasping process significantly benefits the experience and grasping efficiency of prosthetic hand wearers. Currently, prosthetic hands controlled by signals such as brain-computer interfaces (BCI) and electromyography (EMG) face difficulties in precisely recognizing the amputees' grasping gestures and executing anthropomorphic grasp processes. Although prosthetic hands equipped with vision systems enables the objects' feature recognition, they lack perception of human grasping intention. Therefore, this paper explores the estimation of grasping gestures solely through visual data to accomplish anthropopathic grasping control and the determination of grasping intention within a multi-object environment. To address this, we propose the Spatial Geometry-based Gesture Mapping (SG-GM) method, which constructs gesture functions based on the geometric features of the human hand grasping processes. It's subsequently implemented on the prosthetic hand. Furthermore, we propose the Motion Trajectory Regression-based Grasping Intent Estimation (MTR-GIE) algorithm. This algorithm predicts pre-grasping object utilizing regression prediction and prior spatial segmentation estimation derived from the prosthetic hand's position and trajectory. The experiments were conducted to grasp 8 common daily objects including cup, fork, etc. The experimental results presented a similarity coefficient $R^{2}$ of grasping process of 0.911, a Root Mean Squared Error ($RMSE$) of 2.47\degree, a success rate of grasping of 95.43$\%$, and an average duration of grasping process of 3.07$\pm$0.41 s. Furthermore, grasping experiments in a multi-object environment were conducted. The average accuracy of intent estimation reached 94.35$\%$. Our methodologies offer a groundbreaking approach to enhance the prosthetic hand's functionality and provides valuable insights for future research.
Authors: Peijie Qiu, Satrajit Chakrabarty, Phuc Nguyen, Soumyendu Sekhar Ghosh, Aristeidis Sotiras
Abstract: Deep learning has made significant strides in automated brain tumor segmentation from magnetic resonance imaging (MRI) scans in recent years. However, the reliability of these tools is hampered by the presence of poor-quality segmentation outliers, particularly in out-of-distribution samples, making their implementation in clinical practice difficult. Therefore, there is a need for quality control (QC) to screen the quality of the segmentation results. Although numerous automatic QC methods have been developed for segmentation quality screening, most were designed for cardiac MRI segmentation, which involves a single modality and a single tissue type. Furthermore, most prior works only provided subject-level predictions of segmentation quality and did not identify erroneous parts segmentation that may require refinement. To address these limitations, we proposed a novel multi-task deep learning architecture, termed QCResUNet, which produces subject-level segmentation-quality measures as well as voxel-level segmentation error maps for each available tissue class. To validate the effectiveness of the proposed method, we conducted experiments on assessing its performance on evaluating the quality of two distinct segmentation tasks. First, we aimed to assess the quality of brain tumor segmentation results. For this task, we performed experiments on one internal and two external datasets. Second, we aimed to evaluate the segmentation quality of cardiac Magnetic Resonance Imaging (MRI) data from the Automated Cardiac Diagnosis Challenge. The proposed method achieved high performance in predicting subject-level segmentation-quality metrics and accurately identifying segmentation errors on a voxel basis. This has the potential to be used to guide human-in-the-loop feedback to improve segmentations in clinical settings.
Authors: Tal Zeevi, Ravid Shwartz-Ziv, Yann LeCun, Lawrence H. Staib, John A. Onofrey
Abstract: Accurate uncertainty estimation is crucial for deploying neural networks in risk-sensitive applications such as medical diagnosis. Monte Carlo Dropout is a widely used technique for approximating predictive uncertainty by performing stochastic forward passes with dropout during inference. However, using static dropout rates across all layers and inputs can lead to suboptimal uncertainty estimates, as it fails to adapt to the varying characteristics of individual inputs and network layers. Existing approaches optimize dropout rates during training using labeled data, resulting in fixed inference-time parameters that cannot adjust to new data distributions, compromising uncertainty estimates in Monte Carlo simulations. In this paper, we propose Rate-In, an algorithm that dynamically adjusts dropout rates during inference by quantifying the information loss induced by dropout in each layer's feature maps. By treating dropout as controlled noise injection and leveraging information-theoretic principles, Rate-In adapts dropout rates per layer and per input instance without requiring ground truth labels. By quantifying the functional information loss in feature maps, we adaptively tune dropout rates to maintain perceptual quality across diverse medical imaging tasks and architectural configurations. Our extensive empirical study on synthetic data and real-world medical imaging tasks demonstrates that Rate-In improves calibration and sharpens uncertainty estimates compared to fixed or heuristic dropout rates without compromising predictive performance. Rate-In offers a practical, unsupervised, inference-time approach to optimizing dropout for more reliable predictive uncertainty estimation in critical applications.
Authors: Syed Saim Gardezi, Soyiba Jawed, Mahnoor Khan, Muneeba Bukhari, Rizwan Ahmed Khan
Abstract: A multitude of individuals across the globe grapple with motor disabilities. Neural prosthetics utilizing Brain-Computer Interface (BCI) technology exhibit promise for improving motor rehabilitation outcomes. The intricate nature of EEG data poses a significant hurdle for current BCI systems. Recently, a qualitative repository of EEG signals tied to both upper and lower limb execution of motor and motor imagery tasks has been unveiled. Despite this, the productivity of the Machine Learning (ML) Models that were trained on this dataset was alarmingly deficient, and the evaluation framework seemed insufficient. To enhance outcomes, robust feature engineering (signal processing) methodologies are implemented. A collection of time domain, frequency domain, and wavelet-derived features was obtained from 16-channel EEG signals, and the Maximum Relevance Minimum Redundancy (MRMR) approach was employed to identify the four most significant features. For classification K Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Na\"ive Bayes (NB) models were implemented with these selected features, evaluating their effectiveness through metrics such as testing accuracy, precision, recall, and F1 Score. By leveraging SVM with a Gaussian Kernel, a remarkable maximum testing accuracy of 92.50% for motor activities and 95.48% for imagery activities is achieved. These results are notably more dependable and gratifying compared to the previous study, where the peak accuracy was recorded at 74.36%. This research work provides an in-depth analysis of the MI Limb EEG dataset and it will help in designing and developing simple, cost-effective and reliable BCI systems for neuro-rehabilitation.
Authors: Wan Jiang, He Wang, Xin Zhang, Dan Guo, Zhaoxin Fan, Yunfeng Diao, Richang Hong
Abstract: Score-based Generative Models (SGMs) have demonstrated remarkable generalization abilities, e.g. generating unseen, but natural data. However, the greater the generalization power, the more likely the unintended generalization, and the more dangerous the abuse. Research on moderated generalization in SGMs remains limited. To fill this gap, we first examine the current 'gold standard' in Machine Unlearning (MU), i.e., re-training the model after removing the undesirable training data, and find it does not work in SGMs. Further analysis of score functions reveals that the MU 'gold standard' does not alter the original score function, which explains its ineffectiveness. Based on this insight, we propose the first Moderated Score-based Generative Model (MSGM), which introduces a novel score adjustment strategy that redirects the score function away from undesirable data during the continuous-time stochastic differential equation process. Extensive experimental results demonstrate that MSGM significantly reduces the likelihood of generating undesirable content while preserving high visual quality for normal image generation. Albeit designed for SGMs, MSGM is a general and flexible MU framework that is compatible with diverse diffusion architectures (SGM and DDPM) and training strategies (re-training and fine-tuning), and enables zero-shot transfer of the pre-trained models to downstream tasks, e.g. image inpainting and reconstruction. The code will be shared upon acceptance.
Authors: Yuzhi Zhao, Lai-Man Po, Xin Ye, Yongzhe Xu, Qiong Yan
Abstract: Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion blur. While short exposures can capture clear motion, they suffer from noise amplification. Long exposures reduce noise but introduce blur. Learning-based single-image enhancers tend to be over-smooth due to the limited information. Multi-image solutions using burst mode avoid this tradeoff by capturing more spatial-temporal information but often struggle with misalignment from camera/scene motion. To address these limitations, we propose a physical-model-based image restoration approach leveraging a novel dual-exposure Quad-Bayer pattern sensor. By capturing pairs of short and long exposures at the same starting point but with varying durations, this method integrates complementary noise-blur information within a single image. We further introduce a Quad-Bayer synthesis method (B2QB) to simulate sensor data from Bayer patterns to facilitate training. Based on this dual-exposure sensor model, we design a hierarchical convolutional neural network called QRNet to recover high-quality RGB images. The network incorporates input enhancement blocks and multi-level feature extraction to improve restoration quality. Experiments demonstrate superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets. The code, model, and datasets are publicly available at https://github.com/zhaoyuzhi/QRNet.
Authors: Salvatore Calcagno, Isaak Kavasidis, Simone Palazzo, Marco Brondi, Luca Sit\`a, Giacomo Turri, Daniela Giordano, Vladimir R. Kostic, Tommaso Fellin, Massimiliano Pontil, Concetto Spampinato
Abstract: Understanding complex animal behaviors hinges on deciphering the neural activity patterns within brain circuits, making the ability to forecast neural activity crucial for developing predictive models of brain dynamics. This capability holds immense value for neuroscience, particularly in applications such as real-time optogenetic interventions. While traditional encoding and decoding methods have been used to map external variables to neural activity and vice versa, they focus on interpreting past data. In contrast, neural forecasting aims to predict future neural activity, presenting a unique and challenging task due to the spatiotemporal sparsity and complex dependencies of neural signals. Existing transformer-based forecasting methods, while effective in many domains, struggle to capture the distinctiveness of neural signals characterized by spatiotemporal sparsity and intricate dependencies. To address this challenge, we here introduce QuantFormer, a transformer-based model specifically designed for forecasting neural activity from two-photon calcium imaging data. Unlike conventional regression-based approaches, QuantFormerreframes the forecasting task as a classification problem via dynamic signal quantization, enabling more effective learning of sparse neural activation patterns. Additionally, QuantFormer tackles the challenge of analyzing multivariate signals from an arbitrary number of neurons by incorporating neuron-specific tokens, allowing scalability across diverse neuronal populations. Trained with unsupervised quantization on the Allen dataset, QuantFormer sets a new benchmark in forecasting mouse visual cortex activity. It demonstrates robust performance and generalization across various stimuli and individuals, paving the way for a foundational model in neural signal prediction.
Authors: Florin Condrea, Saikiran Rapaka, Marius Leordeanu
Abstract: Pulmonary Embolisms (PE) are a leading cause of cardiovascular death. Computed tomographic pulmonary angiography (CTPA) stands as the gold standard for diagnosing pulmonary embolisms (PE) and there has been a lot of interest in developing AI-based models for assisting in PE diagnosis. Performance of these algorithms has been hindered by the scarcity of annotated data, especially those with fine-grained delineation of the thromboembolic burden. In this paper we attempt to address this issue by introducing a weakly supervised learning pipeline, that leverages model explainability to generate fine-grained (pixel level) masks for embolisms starting from more coarse-grained (binary, image level) PE annotations. Furthermore, we show that training models using the automatically generated pixel annotations yields good PE localization performance. We demonstrate the effectiveness of our pipeline on the large-scale, multi-center RSPECT augmented dataset for PE detection and localization.
Authors: Churan Wang, Fei Gao, Lijun Yan, Siwen Wang, Yizhou Yu, Yizhou Wang
Abstract: Magnetic resonance imaging (MRI) is indispensable for diagnosing and planning treatment in various medical conditions due to its ability to produce multi-series images that reveal different tissue characteristics. However, integrating these diverse series to form a coherent analysis presents significant challenges, such as differing spatial resolutions and contrast patterns meanwhile requiring extensive annotated data, which is scarce in clinical practice. Due to these issues, we introduce a novel Cross-Series Masking (CSM) Strategy for effectively learning MRI representation in a self-supervised manner. Specifically, CSM commences by randomly sampling a subset of regions and series, which are then strategically masked. In the training process, the cross-series representation is learned by utilizing the unmasked data to reconstruct the masked portions. This process not only integrates information across different series but also facilitates the ability to model both intra-series and inter-series correlations and complementarities. With the learned representation, the downstream tasks like segmentation and classification are also enhanced. Taking brain tissue segmentation, breast tumor benign/malignant classification, and prostate cancer diagnosis as examples, our method achieves state-of-the-art performance on both public and in-house datasets.
Authors: Yik Lung Pang, Alessio Xompero, Changjae Oh, Andrea Cavallaro
Abstract: Jointly estimating hand and object shape ensures the success of the robot grasp in human-to-robot handovers. However, relying on hand-crafted prior knowledge about the geometric structure of the object fails when generalising to unseen objects, and depth sensors fail to detect transparent objects such as drinking glasses. In this work, we propose a stereo-based method for hand-object reconstruction that combines single-view reconstructions probabilistically to form a coherent stereo reconstruction. We learn 3D shape priors from a large synthetic hand-object dataset to ensure that our method is generalisable, and use RGB inputs instead of depth as RGB can better capture transparent objects. We show that our method achieves a lower object Chamfer distance compared to existing RGB based hand-object reconstruction methods on single view and stereo settings. We process the reconstructed hand-object shape with a projection-based outlier removal step and use the output to guide a human-to-robot handover pipeline with wide-baseline stereo RGB cameras. Our hand-object reconstruction enables a robot to successfully receive a diverse range of household objects from the human.
Authors: Nicharee Srikijkasemwat, Soumya Snigdha Kundu, Fuping Wu, Bartlomiej W. Papiez
Abstract: Knee osteoarthritis (OA) is the most common joint disorder and a leading cause of disability. Diagnosing OA severity typically requires expert assessment of X-ray images and is commonly based on the Kellgren-Lawrence grading system, a time-intensive process. This study aimed to develop an automated deep learning model to classify knee OA severity, reducing the need for expert evaluation. First, we evaluated ten state-of-the-art deep learning models, achieving a top accuracy of 0.69 with individual models. To address class imbalance, we employed weighted sampling, improving accuracy to 0.70. We further applied Smooth-GradCAM++ to visualize decision-influencing regions, enhancing the explainability of the best-performing model. Finally, we developed ensemble models using majority voting and a shallow neural network. Our ensemble model, KneeXNet, achieved the highest accuracy of 0.72, demonstrating its potential as an automated tool for knee OA assessment.
Authors: Jiahua Xu, Dawei Zhou, Lei Hu, Jianfeng Guo, Feng Yang, Zaiyi Liu, Nannan Wang, Xinbo Gao
Abstract: Motion artifacts present in magnetic resonance imaging (MRI) can seriously interfere with clinical diagnosis. Removing motion artifacts is a straightforward solution and has been extensively studied. However, paired data are still heavily relied on in recent works and the perturbations in \textit{k}-space (frequency domain) are not well considered, which limits their applications in the clinical field. To address these issues, we propose a novel unsupervised purification method which leverages pixel-frequency information of noisy MRI images to guide a pre-trained diffusion model to recover clean MRI images. Specifically, considering that motion artifacts are mainly concentrated in high-frequency components in \textit{k}-space, we utilize the low-frequency components as the guide to ensure correct tissue textures. Additionally, given that high-frequency and pixel information are helpful for recovering shape and detail textures, we design alternate complementary masks to simultaneously destroy the artifact structure and exploit useful information. Quantitative experiments are performed on datasets from different tissues and show that our method achieves superior performance on several metrics. Qualitative evaluations with radiologists also show that our method provides better clinical feedback. Our code is available at https://github.com/medcx/PFAD.
Authors: Ashik E Rasul, Humaira Tasnim, Hyung-Jin Yoon, Ayoosh Bansal, Duo Wang, Naira Hovakimyan, Lui Sha, Petros Voulgaris
Abstract: Learning-based solutions have enabled incredible capabilities for autonomous systems. Autonomous vehicles, both aerial and ground, rely on DNN for various integral tasks, including perception. The efficacy of supervised learning solutions hinges on the quality of the training data. Discrepancies between training data and operating conditions result in faults that can lead to catastrophic incidents. However, collecting vast amounts of context-sensitive data, with broad coverage of possible operating environments, is prohibitively difficult. Synthetic data generation techniques for DNN allow for the easy exploration of diverse scenarios. However, synthetic data generation solutions for aerial vehicles are still lacking. This work presents a data augmentation framework for aerial vehicle's perception training, leveraging photorealistic simulation integrated with high-fidelity vehicle dynamics. Safe landing is a crucial challenge in the development of autonomous air taxis, therefore, landing maneuver is chosen as the focus of this work. With repeated simulations of landing in varying scenarios we assess the landing performance of the VTOL type UAV and gather valuable data. The landing performance is used as the objective function to optimize the DNN through retraining. Given the high computational cost of DNN retraining, we incorporated Bayesian Optimization in our framework that systematically explores the data augmentation parameter space to retrain the best-performing models. The framework allowed us to identify high-performing data augmentation parameters that are consistently effective across different landing scenarios. Utilizing the capabilities of this data augmentation framework, we obtained a robust perception model. The model consistently improved the perception-based landing success rate by at least 20% under different lighting and weather conditions.
Authors: Tyler J. Kovach, Daniel Schug, M. A. Wolfe, E. R. MacQuarrie, Patrick J. Walsh, Jared Benson, Mark Friesen, M. A. Eriksson, Justyna P. Zwolak
Abstract: Semiconductor quantum dot (QD) devices have become central to advancements in spin-based quantum computing. As the complexity of QD devices grows, manual tuning becomes increasingly infeasible, necessitating robust and scalable autotuning solutions. Tuning large arrays of QD qubits depends on efficient choices of automated protocols. Here, we introduce a bootstrapping, autonomous testing, and initialization system (BATIS), an automated framework designed to streamline QD device testing and initialization. BATIS navigates high-dimensional gate voltage spaces, automating essential steps such as leakage testing and gate characterization. The current channel formation protocol follows a novel and scalable approach that requires a single measurement regardless of the number of channels. Demonstrated at 1.3 K on a quad-QD Si/Si$_x$Ge$_{1-x}$ device, BATIS eliminates the need for deep cryogenic environments during initial device diagnostics, significantly enhancing scalability and reducing setup times. By requiring minimal prior knowledge of the device architecture, BATIS represents a platform-agnostic solution, adaptable to various QD systems, which bridges a critical gap in QD autotuning.
Authors: Khush Mendiratta (Indian Institute of Technology Roorkee), Shweta Singh (Indian Institute of Technology BHU), Pratik Chattopadhyay (Indian Institute of Technology BHU)
Abstract: Early detection of brain tumors through magnetic resonance imaging (MRI) is essential for timely treatment, yet access to diagnostic facilities remains limited in remote areas. Gliomas, the most common primary brain tumors, arise from the carcinogenesis of glial cells in the brain and spinal cord, with glioblastoma patients having a median survival time of less than 14 months. MRI serves as a non-invasive and effective method for tumor detection, but manual segmentation of brain MRI scans has traditionally been a labor-intensive task for neuroradiologists. Recent advancements in computer-aided design (CAD), machine learning (ML), and deep learning (DL) offer promising solutions for automating this process. This study proposes an automated deep learning model for brain tumor detection and classification using MRI data. The model, incorporating spatial attention, achieved 96.90% accuracy, enhancing the aggregation of contextual information for better pattern recognition. Experimental results demonstrate that the proposed approach outperforms baseline models, highlighting its robustness and potential for advancing automated MRI-based brain tumor analysis.
Authors: Zhen Liu, Tim Z. Xiao, Weiyang Liu, Yoshua Bengio, Dinghuai Zhang
Abstract: While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models on some reward functions that are either designed by experts or learned from small-scale datasets. Existing methods for finetuning diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. Inspired by recent successes in generative flow networks (GFlowNets), a class of probabilistic models that sample with the unnormalized density of a reward function, we propose a novel GFlowNet method dubbed Nabla-GFlowNet (abbreviated as $\nabla$-GFlowNet), the first GFlowNet method that leverages the rich signal in reward gradients, together with an objective called $\nabla$-DB plus its variant residual $\nabla$-DB designed for prior-preserving diffusion alignment. We show that our proposed method achieves fast yet diversity- and prior-preserving alignment of Stable Diffusion, a large-scale text-conditioned image diffusion model, on different realistic reward functions.
Authors: Hao Li
Abstract: This note complements the author's recent paper "Robust representation learning with feedback for single image deraining" by providing heuristically theoretical explanations on the mechanism of representation learning with feedback, namely an essential merit of the works presented in this recent article. This note facilitates understanding of key points in the mechanism of representation learning with feedback.
Authors: Daoan Zhang, Chenming Li, Haoquan Li, Wenjian Huang, Lingyun Huang, Jianguo Zhang
Abstract: Unsupervised image semantic segmentation(UISS) aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS and image-wise representation learning. Based on the analysis, we argue that the existing MI-based methods in UISS suffer from representation collapse. By this, we proposed a robust network called Semantic Attention Network(SAN), in which a new module Semantic Attention(SEAT) is proposed to generate pixel-wise and semantic features dynamically. Experimental results on multiple semantic segmentation benchmarks show that our unsupervised segmentation framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods.
Authors: Zixuan Chen, Xiaohua Xie, Lingxiao Yang, Jianhuang Lai
Abstract: Anomaly detectors are widely used in industrial manufacturing to detect and localize unknown defects in query images. These detectors are trained on anomaly-free samples and have successfully distinguished anomalies from most normal samples. However, hard-normal examples are scattered and far apart from most normal samples, and thus they are often mistaken for anomalies by existing methods. To address this issue, we propose Hard-normal Example-aware Template Mutual Matching (HETMM), an efficient framework to build a robust prototype-based decision boundary. Specifically, HETMM employs the proposed Affine-invariant Template Mutual Matching (ATMM) to mitigate the affection brought by the affine transformations and easy-normal examples. By mutually matching the pixel-level prototypes within the patch-level search spaces between query and template set, ATMM can accurately distinguish between hard-normal examples and anomalies, achieving low false-positive and missed-detection rates. In addition, we also propose PTS to compress the original template set for speed-up. PTS selects cluster centres and hard-normal examples to preserve the original decision boundary, allowing this tiny set to achieve comparable performance to the original one. Extensive experiments demonstrate that HETMM outperforms state-of-the-art methods, while using a 60-sheet tiny set can achieve competitive performance and real-time inference speed (around 26.1 FPS) on a Quadro 8000 RTX GPU. HETMM is training-free and can be hot-updated by directly inserting novel samples into the template set, which can promptly address some incremental learning issues in industrial manufacturing.
Authors: Daiki Miyake, Akihiro Iohara, Yu Saito, Toshiyuki Tanaka
Abstract: In image editing employing diffusion models, it is crucial to preserve the reconstruction fidelity to the original image while changing its style. Although existing methods ensure reconstruction fidelity through optimization, a drawback of these is the significant amount of time required for optimization. In this paper, we propose negative-prompt inversion, a method capable of achieving equivalent reconstruction solely through forward propagation without optimization, thereby enabling ultrafast editing processes. We experimentally demonstrate that the reconstruction fidelity of our method is comparable to that of existing methods, allowing for inversion at a resolution of 512 pixels and with 50 sampling steps within approximately 5 seconds, which is more than 30 times faster than null-text inversion. Reduction of the computation time by the proposed method further allows us to use a larger number of sampling steps in diffusion models to improve the reconstruction fidelity with a moderate increase in computation time.
Authors: Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard, Paul Novello, Julien Colin, Drew Linsley, Tom Rousseau, R\'emi Cad\`ene, Lore Goetschalckx, Laurent Gardes, Thomas Serre
Abstract: Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability. However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks. Here, we describe MACO, a simple approach to address these shortcomings. The main idea is to generate images by optimizing the phase spectrum while keeping the magnitude constant to ensure that generated explanations lie in the space of natural images. Our approach yields significantly better results (both qualitatively and quantitatively) and unlocks efficient and interpretable feature visualizations for large state-of-the-art neural networks. We also show that our approach exhibits an attribution mechanism allowing us to augment feature visualizations with spatial importance. We validate our method on a novel benchmark for comparing feature visualization methods, and release its visualizations for all classes of the ImageNet dataset on https://serre-lab.github.io/Lens/. Overall, our approach unlocks, for the first time, feature visualizations for large, state-of-the-art deep neural networks without resorting to any parametric prior image model.
Authors: Jiafu Wu, Jian Li, Jiangning Zhang, Boshen Zhang, Mingmin Chi, Yabiao Wang, Chengjie Wang
Abstract: Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects. Though Vision GNN (ViG) adopts graph-level features for complex images, it has some issues, such as inaccurate neighbor node selection, expensive node information aggregation calculation, and over-smoothing in the deep layers. To address the above problems, we propose a Progressive Vision Graph (PVG) architecture for vision recognition task. Compared with previous works, PVG contains three main components: 1) Progressively Separated Graph Construction (PSGC) to introduce second-order similarity by gradually increasing the channel of the global graph branch and decreasing the channel of local branch as the layer deepens; 2) Neighbor nodes information aggregation and update module by using Max pooling and mathematical Expectation (MaxE) to aggregate rich neighbor information; 3) Graph error Linear Unit (GraphLU) to enhance low-value information in a relaxed form to reduce the compression of image detail information for alleviating the over-smoothing. Extensive experiments on mainstream benchmarks demonstrate the superiority of PVG over state-of-the-art methods, e.g., our PVG-S obtains 83.0% Top-1 accuracy on ImageNet-1K that surpasses GNN-based ViG-S by +0.9 with the parameters reduced by 18.5%, while the largest PVG-B obtains 84.2% that has +0.5 improvement than ViG-B. Furthermore, our PVG-S obtains +1.3 box AP and +0.4 mask AP gains than ViG-S on COCO dataset.
Authors: Daigo Shoji
Abstract: In Asian countries, there is a tradition that a rabbit, known as the Moon rabbit, lives on the Moon. Typically, two reasons are mentioned for the origin of this tradition. The first reason is that the color pattern of the lunar surface resembles the shape of a rabbit. The second reason is that both the Moon and rabbits are symbols of fertility, as the Moon appears and disappears (i.e., waxing and waning) cyclically and rabbits are known for their high fertility. Considering the latter reason, is the color pattern of the lunar surface not similar to a rabbit? Here, the similarity between rabbit and the lunar surface pattern was evaluated using seven AI architectures. In the test conducted with Contrastive Language-Image Pre-Training (CLIP), which can classify images based on given words, it was assumed that people frequently observe the Moon in the early evening. Under this condition, the lunar surface pattern was found to be more similar to a rabbit than a face in low-latitude regions, while it could also be classified as a face as the latitude increases. This result is consistent with that the oldest literatures about the Moon rabbit were written in India and that a tradition of seeing a human face in the Moon exists in Europe. In a 1000-class test using seven AI architectures, ConvNeXt and CLIP sometimes classified the lunar surface pattern as a rabbit with relatively high probabilities. Cultures are generated by our attitude to the environment. Both dynamic and static similarities may be essential to induce our imagination.
Authors: Minghui Li, Xianlong Wang, Zhifei Yu, Shengshan Hu, Ziqi Zhou, Longling Zhang, Leo Yu Zhang
Abstract: Convolution-based unlearnable examples (UEs) employ class-wise multiplicative convolutional noise to training samples, severely compromising model performance. This fire-new type of UEs have successfully countered all defense mechanisms against UEs. The failure of such defenses can be attributed to the absence of norm constraints on convolutional noise, leading to severe blurring of image features. To address this, we first design an Edge Pixel-based Detector (EPD) to identify convolution-based UEs. Upon detection of them, we propose the first defense scheme against convolution-based UEs, COrrupting these samples via random matrix multiplication by employing bilinear INterpolation (COIN) such that disrupting the distribution of class-wise multiplicative noise. To evaluate the generalization of our proposed COIN, we newly design two convolution-based UEs called VUDA and HUDA to expand the scope of convolution-based UEs. Extensive experiments demonstrate the effectiveness of detection scheme EPD and that our defense COIN outperforms 11 state-of-the-art (SOTA) defenses, achieving a significant improvement on the CIFAR and ImageNet datasets.
Authors: Matthew Gwilliam, Michael Cogswell, Meng Ye, Karan Sikka, Abhinav Shrivastava, Ajay Divakaran
Abstract: Existing long video retrieval systems are trained and tested in the paragraph-to-video retrieval regime, where every long video is described by a single long paragraph. This neglects the richness and variety of possible valid descriptions of a video, which could range anywhere from moment-by-moment detail to a single phrase summary. To provide a more thorough evaluation of the capabilities of long video retrieval systems, we propose a pipeline that leverages state-of-the-art large language models to carefully generate a diverse set of synthetic captions for long videos. We validate this pipeline's fidelity via rigorous human inspection. We use synthetic captions from this pipeline to perform a benchmark of a representative set of video language models using long video datasets, and show that the models struggle on shorter captions. We show that finetuning on this data can both mitigate these issues (+2.8% R@1 over SOTA on ActivityNet with diverse captions), and even improve performance on standard paragraph-to-video retrieval (+1.0% R@1 on ActivityNet). We also use synthetic data from our pipeline as query expansion in the zero-shot setting (+3.4% R@1 on ActivityNet). We derive insights by analyzing failure cases for retrieval with short captions. For data access and other details, please refer to our project website at https://mgwillia.github.io/10k-words.
Authors: Joanna Materzynska, Josef Sivic, Eli Shechtman, Antonio Torralba, Richard Zhang, Bryan Russell
Abstract: We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training data. By leveraging a few video samples demonstrating specific movements as input, our method learns and generalizes the input motion patterns for diverse, text-specified scenarios. Our contributions are threefold. First, to achieve our results, we finetune an existing text-to-video model to learn a novel mapping between the depicted motion in the input examples to a new unique token. To avoid overfitting to the new custom motion, we introduce an approach for regularization over videos. Second, by leveraging the motion priors in a pretrained model, our method can produce novel videos featuring multiple people doing the custom motion, and can invoke the motion in combination with other motions. Furthermore, our approach extends to the multimodal customization of motion and appearance of individualized subjects, enabling the generation of videos featuring unique characters and distinct motions. Third, to validate our method, we introduce an approach for quantitatively evaluating the learned custom motion and perform a systematic ablation study. We show that our method significantly outperforms prior appearance-based customization approaches when extended to the motion customization task.
Authors: Fangjinhua Wang, Marie-Julie Rakotosaona, Michael Niemeyer, Richard Szeliski, Marc Pollefeys, Federico Tombari
Abstract: Neural 3D scene representations have shown great potential for 3D reconstruction from 2D images. However, reconstructing real-world captures of complex scenes still remains a challenge. Existing generic 3D reconstruction methods often struggle to represent fine geometric details and do not adequately model reflective surfaces of large-scale scenes. Techniques that explicitly focus on reflective surfaces can model complex and detailed reflections by exploiting better reflection parameterizations. However, we observe that these methods are often not robust in real scenarios where non-reflective as well as reflective components are present. In this work, we propose UniSDF, a general purpose 3D reconstruction method that can reconstruct large complex scenes with reflections. We investigate both camera view as well as reflected view-based color parameterization techniques and find that explicitly blending these representations in 3D space enables reconstruction of surfaces that are more geometrically accurate, especially for reflective surfaces. We further combine this representation with a multi-resolution grid backbone that is trained in a coarse-to-fine manner, enabling faster reconstructions than prior methods. Extensive experiments on object-level datasets DTU, Shiny Blender as well as unbounded datasets Mip-NeRF 360 and Ref-NeRF real demonstrate that our method is able to robustly reconstruct complex large-scale scenes with fine details and reflective surfaces, leading to the best overall performance. Project page: \url{https://fangjinhuawang.github.io/UniSDF}.
Authors: Nuoyan Zhou, Dawei Zhou, Decheng Liu, Nannan Wang, Xinbo Gao
Abstract: Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by adversarial perturbation and lead to an unexpectedly increasing gap between features in the last hidden layer of natural and adversarial samples. To address this issue, we propose a disentanglement-based approach to explicitly model and further remove the specific latent features. We introduce a feature disentangler to separate out the specific latent features from the features of the adversarial samples, thereby boosting robustness by eliminating the specific latent features. Besides, we align clean features in the pre-trained model with features of adversarial samples in the fine-tuned model, to benefit from the intrinsic features of natural samples. Empirical evaluations on three benchmark datasets demonstrate that our approach surpasses existing adversarial fine-tuning methods and adversarial training baselines.
Authors: Daniele Cattaneo, Abhinav Valada
Abstract: LiDARs are widely used for mapping and localization in dynamic environments. However, their high cost limits their widespread adoption. On the other hand, monocular localization in LiDAR maps using inexpensive cameras is a cost-effective alternative for large-scale deployment. Nevertheless, most existing approaches struggle to generalize to new sensor setups and environments, requiring retraining or fine-tuning. In this paper, we present CMRNext, a novel approach for camera-LIDAR matching that is independent of sensor-specific parameters, generalizable, and can be used in the wild for monocular localization in LiDAR maps and camera-LiDAR extrinsic calibration. CMRNext exploits recent advances in deep neural networks for matching cross-modal data and standard geometric techniques for robust pose estimation. We reformulate the point-pixel matching problem as an optical flow estimation problem and solve the Perspective-n-Point problem based on the resulting correspondences to find the relative pose between the camera and the LiDAR point cloud. We extensively evaluate CMRNext on six different robotic platforms, including three publicly available datasets and three in-house robots. Our experimental evaluations demonstrate that CMRNext outperforms existing approaches on both tasks and effectively generalizes to previously unseen environments and sensor setups in a zero-shot manner. We make the code and pre-trained models publicly available at http://cmrnext.cs.uni-freiburg.de .
Authors: Dragos Costea, Alina Marcu, Cristina Lazar, Marius Leordeanu
Abstract: Modeling face-to-face communication in computer vision, which focuses on recognizing and analyzing nonverbal cues and behaviors during interactions, serves as the foundation for our proposed alternative to text-based Human-AI interaction. By leveraging nonverbal visual communication, through facial expressions, head and body movements, we aim to enhance engagement and capture the user's attention through a novel improvisational element, that goes beyond mirroring gestures. Our goal is to track and analyze facial expressions, and other nonverbal cues in real-time, and use this information to build models that can predict and understand human behavior. Operating in real-time and requiring minimal computational resources, our approach signifies a major leap forward in making AI interactions more natural and accessible. We offer three different complementary approaches, based on retrieval, statistical, and deep learning techniques. A key novelty of our work is the integration of an artistic component atop an efficient human-computer interaction system, using art as a medium to transmit emotions. Our approach is not art-specific and can be adapted to various paintings, animations, and avatars. In our experiments, we compare state-of-the-art diffusion models as mediums for emotion translation in 2D, and our 3D avatar, Maia, that we introduce in this work, with not just facial movements but also body motions for a more natural and engaging experience. We demonstrate the effectiveness of our approach in translating AI-generated emotions into human-relatable expressions, through both human and automatic evaluation procedures, highlighting its potential to significantly enhance the naturalness and engagement of Human-AI interactions across various applications.
Authors: Wenxiao Cai, Wankou Yang
Abstract: The topic of stitching images with globally natural structures holds paramount significance, with two main goals: pixel-level alignment and distortion prevention. The existing approaches exhibit the ability to align well, yet fall short in maintaining object structures. In this paper, we endeavour to safeguard the overall OBJect-level structures within images based on Global Similarity Prior (OBJ-GSP), on the basis of good alignment performance. Our approach leverages semantic segmentation models like the family of Segment Anything Model to extract the contours of any objects in a scene. Triangular meshes are employed in image transformation to protect the overall shapes of objects within images. The balance between alignment and distortion prevention is achieved by allowing the object meshes to strike a balance between similarity and projective transformation. We also demonstrate that object-level semantic information is necessary in low-altitude aerial image stitching. Additionally, we propose StitchBench, the largest image stitching benchmark with most diverse scenarios. Extensive experimental results demonstrate that OBJ-GSP outperforms existing methods in both pixel alignment and shape preservation. Code and dataset is publicly available at \url{https://github.com/RussRobin/OBJ-GSP}.
Authors: Kangfu Mei, Zhengzhong Tu, Mauricio Delbracio, Hossein Talebi, Vishal M. Patel, Peyman Milanfar
Abstract: We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion models, the role of model size -- a critical determinant of sampling efficiency -- has not been thoroughly examined. Through empirical analysis of established text-to-image diffusion models, we conduct an in-depth investigation into how model size influences sampling efficiency across varying sampling steps. Our findings unveil a surprising trend: when operating under a given inference budget, smaller models frequently outperform their larger equivalents in generating high-quality results. Moreover, we extend our study to demonstrate the generalizability of the these findings by applying various diffusion samplers, exploring diverse downstream tasks, evaluating post-distilled models, as well as comparing performance relative to training compute. These findings open up new pathways for the development of LDM scaling strategies which can be employed to enhance generative capabilities within limited inference budgets.
Authors: Ethan Weber, Riley Peterlinz, Rohan Mathur, Frederik Warburg, Alexei A. Efros, Angjoo Kanazawa
Abstract: We recover the underlying 3D structure from images of cartoons and anime depicting the same scene. This is an interesting problem domain because images in creative media are often depicted without explicit geometric consistency for storytelling and creative expression-they are only 3D in a qualitative sense. While humans can easily perceive the underlying 3D scene from these images, existing Structure-from-Motion (SfM) methods that assume 3D consistency fail catastrophically. We present Toon3D for reconstructing geometrically inconsistent images. Our key insight is to deform the input images while recovering camera poses and scene geometry, effectively explaining away geometrical inconsistencies to achieve consistency. This process is guided by the structure inferred from monocular depth predictions. We curate a dataset with multi-view imagery from cartoons and anime that we annotate with reliable sparse correspondences using our user-friendly annotation tool. Our recovered point clouds can be plugged into novel-view synthesis methods to experience cartoons from viewpoints never drawn before. We evaluate against classical and recent learning-based SfM methods, where Toon3D is able to obtain more reliable camera poses and scene geometry.
Authors: Zhicheng Sun, Zhenhao Yang, Yang Jin, Haozhe Chi, Kun Xu, Kun Xu, Liwei Chen, Hao Jiang, Yang Song, Kun Gai, Yadong Mu
Abstract: Customizing diffusion models to generate identity-preserving images from user-provided reference images is an intriguing new problem. The prevalent approaches typically require training on extensive domain-specific images to achieve identity preservation, which lacks flexibility across different use cases. To address this issue, we exploit classifier guidance, a training-free technique that steers diffusion models using an existing classifier, for personalized image generation. Our study shows that based on a recent rectified flow framework, the major limitation of vanilla classifier guidance in requiring a special classifier can be resolved with a simple fixed-point solution, allowing flexible personalization with off-the-shelf image discriminators. Moreover, its solving procedure proves to be stable when anchored to a reference flow trajectory, with a convergence guarantee. The derived method is implemented on rectified flow with different off-the-shelf image discriminators, delivering advantageous personalization results for human faces, live subjects, and certain objects. Code is available at https://github.com/feifeiobama/RectifID.
Authors: Siyi Hu, Diego Martin Arroyo, Stephanie Debats, Fabian Manhardt, Luca Carlone, Federico Tombari
Abstract: Generating realistic 3D scenes is an area of growing interest in computer vision and robotics. However, creating high-quality, diverse synthetic 3D content often requires expert intervention, making it costly and complex. Recently, efforts to automate this process with learning techniques, particularly diffusion models, have shown significant improvements in tasks like furniture rearrangement. However, applying diffusion models to floor-conditioned indoor scene synthesis remains under-explored. This task is especially challenging as it requires arranging objects in continuous space while selecting from discrete object categories, posing unique difficulties for conventional diffusion methods. To bridge this gap, we present MiDiffusion, a novel mixed discrete-continuous diffusion model designed to synthesize plausible 3D indoor scenes given a floor plan and pre-arranged objects. We represent a scene layout by a 2D floor plan and a set of objects, each defined by category, location, size, and orientation. Our approach uniquely applies structured corruption across mixed discrete semantic and continuous geometric domains, resulting in a better-conditioned problem for denoising. Evaluated on the 3D-FRONT dataset, MiDiffusion outperforms state-of-the-art autoregressive and diffusion models in floor-conditioned 3D scene synthesis. Additionally, it effectively handles partial object constraints via a corruption-and-masking strategy without task-specific training, demonstrating advantages in scene completion and furniture arrangement tasks.
Authors: Man Liu, Huihui Bai, Feng Li, Chunjie Zhang, Yunchao Wei, Tat-Seng Chua, Yao Zhao
Abstract: Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, prompt learning has emerged in ZSL and demonstrated significant potential as it allows the zero-shot transfer of diverse visual concepts to downstream tasks. However, current methods explore the fixed adaption of learnable prompt on seen domains, which makes them over-emphasize the primary visual features observed during training, limiting their generalization capabilities to unseen domains. In this work, we propose AENet, which endows semantic information into the visual prompt to distill semantic-enhanced prompt for visual representation enrichment, enabling effective knowledge transfer for ZSL. AENet comprises two key steps: 1) exploring the concept-harmonized tokens for the visual and attribute modalities, grounded on the modal-sharing token that represents consistent visual-semantic concepts; and 2) yielding semantic-enhanced prompt via the visual residual refinement unit with attribute consistency supervision. These are further integrated with primary visual features to attend to semantic-related information for visual enhancement, thus strengthening transferable ability. Experimental results on three benchmarks show that our AENet outperforms existing state-of-the-art ZSL methods. The code is provided in the zip file of supplementary materials.
Authors: Nikolaos-Antonios Ypsilantis, Kaifeng Chen, Andr\'e Araujo, Ond\v{r}ej Chum
Abstract: Universal image representations are critical in enabling real-world fine-grained and instance-level recognition applications, where objects and entities from any domain must be identified at large scale. Despite recent advances, existing methods fail to capture important domain-specific knowledge, while also ignoring differences in data distribution across different domains. This leads to a large performance gap between efficient universal solutions and expensive approaches utilising a collection of specialist models, one for each domain. In this work, we make significant strides towards closing this gap, by introducing a new learning technique, dubbed UDON (Universal Dynamic Online DistillatioN). UDON employs multi-teacher distillation, where each teacher is specialized in one domain, to transfer detailed domain-specific knowledge into the student universal embedding. UDON's distillation approach is not only effective, but also very efficient, by sharing most model parameters between the student and all teachers, where all models are jointly trained in an online manner. UDON also comprises a sampling technique which adapts the training process to dynamically allocate batches to domains which are learned slower and require more frequent processing. This boosts significantly the learning of complex domains which are characterised by a large number of classes and long-tail distributions. With comprehensive experiments, we validate each component of UDON, and showcase significant improvements over the state of the art in the recent UnED benchmark. Code: https://github.com/nikosips/UDON .
Authors: Fei Zhou, Tianhao Gu, Zhicong Huang, Guoping Qiu
Abstract: The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA).While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation.
Authors: Elisabeta-Iulia Dima, Pablo G\'omez, Sandor Kruk, Peter Kretschmar, Simon Rosen, C\u{a}lin-Adrian Popa
Abstract: Reflected or scattered light produce artefacts in astronomical observations that can negatively impact the scientific study. Hence, automated detection of these artefacts is highly beneficial, especially with the increasing amounts of data gathered. Machine learning methods are well-suited to this problem, but currently there is a lack of annotated data to train such approaches to detect artefacts in astronomical observations. In this work, we present a dataset of images from the XMM-Newton space telescope Optical Monitoring camera showing different types of artefacts. We hand-annotated a sample of 1000 images with artefacts which we use to train automated ML methods. We further demonstrate techniques tailored for accurate detection and masking of artefacts using instance segmentation. We adopt a hybrid approach, combining knowledge from both convolutional neural networks (CNNs) and transformer-based models and use their advantages in segmentation. The presented method and dataset will advance artefact detection in astronomical observations by providing a reproducible baseline. All code and data are made available (https://github.com/ESA-Datalabs/XAMI-model and https://github.com/ESA-Datalabs/XAMI-dataset).
URLs: https://github.com/ESA-Datalabs/XAMI-model, https://github.com/ESA-Datalabs/XAMI-dataset).
Authors: Jiaxin Zhang, Wentao Yang, Songxuan Lai, Zecheng Xie, Lianwen Jin
Abstract: Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layouts typical of document images. These characteristics demand a high level of detail perception ability from MLLMs. While increasing input resolution improves detail perception capability, it also leads to longer sequences of visual tokens, increasing computational costs and straining the models' ability to handle long contexts. To address these challenges, we introduce DocKylin, a document-centric MLLM that performs visual content slimming at both the pixel and token levels, thereby reducing token sequence length in VDU scenarios. We introduce an Adaptive Pixel Slimming (APS) preprocessing module to perform pixel-level slimming, increasing the proportion of informative pixels. Moreover, we propose a novel Dynamic Token Slimming (DTS) module to conduct token-level slimming, filtering essential tokens and removing others to adaptively create a more compact visual sequence. Experiments demonstrate DocKylin's promising performance across various VDU benchmarks and the effectiveness of each component.
Authors: Istv\'an S\'ar\'andi, Gerard Pons-Moll
Abstract: With the explosive growth of available training data, single-image 3D human modeling is ahead of a transition to a data-centric paradigm. A key to successfully exploiting data scale is to design flexible models that can be supervised from various heterogeneous data sources produced by different researchers or vendors. To this end, we propose a simple yet powerful paradigm for seamlessly unifying different human pose and shape-related tasks and datasets. Our formulation is centered on the ability -- both at training and test time -- to query any arbitrary point of the human volume, and obtain its estimated location in 3D. We achieve this by learning a continuous neural field of body point localizer functions, each of which is a differently parameterized 3D heatmap-based convolutional point localizer (detector). For generating parametric output, we propose an efficient post-processing step for fitting SMPL-family body models to nonparametric joint and vertex predictions. With this approach, we can naturally exploit differently annotated data sources including mesh, 2D/3D skeleton and dense pose, without having to convert between them, and thereby train large-scale 3D human mesh and skeleton estimation models that considerably outperform the state-of-the-art on several public benchmarks including 3DPW, EMDB, EHF, SSP-3D and AGORA.
Authors: Yuxuan Zhang, Qing Zhang, Yiren Song, Jichao Zhang, Hao Tang, Jiaming Liu
Abstract: Current hair transfer methods struggle to handle diverse and intricate hairstyles, limiting their applicability in real-world scenarios. In this paper, we propose a novel diffusion-based hair transfer framework, named \textit{Stable-Hair}, which robustly transfers a wide range of real-world hairstyles to user-provided faces for virtual hair try-on. To achieve this goal, our Stable-Hair framework is designed as a two-stage pipeline. In the first stage, we train a Bald Converter alongside stable diffusion to remove hair from the user-provided face images, resulting in bald images. In the second stage, we specifically designed a Hair Extractor and a Latent IdentityNet to transfer the target hairstyle with highly detailed and high-fidelity to the bald image. The Hair Extractor is trained to encode reference images with the desired hairstyles, while the Latent IdentityNet ensures consistency in identity and background. To minimize color deviations between source images and transfer results, we introduce a novel Latent ControlNet architecture, which functions as both the Bald Converter and Latent IdentityNet. After training on our curated triplet dataset, our method accurately transfers highly detailed and high-fidelity hairstyles to the source images. Extensive experiments demonstrate that our approach achieves state-of-the-art performance compared to existing hair transfer methods. Project page: \textcolor{red}{\url{https://xiaojiu-z.github.io/Stable-Hair.github.io/}}
Authors: Mingyang Lei, Jingfan Fan, Long Shao, Hong Song, Deqiang Xiao, Danni Ai, Tianyu Fu, Ying Gu, Jian Yang
Abstract: The structured light (SL)-based three-dimensional (3D) measurement techniques with deep learning have been widely studied to improve measurement efficiency, among which fringe projection profilometry (FPP) and speckle projection profilometry (SPP) are two popular methods. However, they generally use a single projection pattern for reconstruction, resulting in fringe order ambiguity or poor reconstruction accuracy. To alleviate these problems, we propose a parallel dual-branch Convolutional Neural Network (CNN)-Transformer network (PDCNet), to take advantage of convolutional operations and self-attention mechanisms for processing different SL modalities. Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images. To fully integrate complementary features, we design a double-stream attention aggregation module (DAAM) that consists of a parallel attention subnetwork for aggregating multi-scale spatial structure information. This module can dynamically retain local and global representations to the maximum extent. Moreover, an adaptive mixture density head with bimodal Gaussian distribution is proposed for learning a representation that is precise near discontinuities. Compared to the standard disparity regression strategy, this adaptive mixture head can effectively improve performance at object boundaries. Extensive experiments demonstrate that our method can reduce fringe order ambiguity while producing high-accuracy results on self-made datasets.
Authors: Yu Feng, Weiming Zeng, Yifan Xie, Hongyu Chen, Lei Wang, Yingying Wang, Hongjie Yan, Kaile Zhang, Ran Tao, Wai Ting Siok, Nizhuan Wang
Abstract: Background: Although it has been noticed that depressed patients show differences in processing emotions, the precise neural modulation mechanisms of positive and negative emotions remain elusive. FMRI is a cutting-edge medical imaging technology renowned for its high spatial resolution and dynamic temporal information, making it particularly suitable for the neural dynamics of depression research. Methods: To address this gap, our study firstly leveraged fMRI to delineate activated regions associated with positive and negative emotions in healthy individuals, resulting in the creation of positive emotion atlas (PEA) and negative emotion atlas (NEA). Subsequently, we examined neuroimaging changes in depression patients using these atlases and evaluated their diagnostic performance based on machine learning. Results: Our findings demonstrate that the classification accuracy of depressed patients based on PEA and NEA exceeded 0.70, a notable improvement compared to the whole-brain atlases. Furthermore, ALFF analysis unveiled significant differences between depressed patients and healthy controls in eight functional clusters during the NEA, focusing on the left cuneus, cingulate gyrus, and superior parietal lobule. In contrast, the PEA revealed more pronounced differences across fifteen clusters, involving the right fusiform gyrus, parahippocampal gyrus, and inferior parietal lobule. Limitations: Due to the limited sample size and subtypes of depressed patients, the efficacy may need further validation in future. Conclusions: These findings emphasize the complex interplay between emotion modulation and depression, showcasing significant alterations in both PEA and NEA among depression patients. This research enhances our understanding of emotion modulation in depression, with implications for diagnosis and treatment evaluation.
Authors: Duc-Hai Pham, Duc Dung Nguyen, Hoang-Anh Pham, Ho Lai Tuan, Phong Ha Nguyen, Khoi Nguyen, Rang Nguyen
Abstract: Accurate prediction of 3D semantic occupancy from 2D visual images is vital in enabling autonomous agents to comprehend their surroundings for planning and navigation. State-of-the-art methods typically employ fully supervised approaches, necessitating a huge labeled dataset acquired through expensive LiDAR sensors and meticulous voxel-wise labeling by human annotators. The resource-intensive nature of this annotating process significantly hampers the application and scalability of these methods. We introduce a novel semi-supervised framework to alleviate the dependency on densely annotated data. Our approach leverages 2D foundation models to generate essential 3D scene geometric and semantic cues, facilitating a more efficient training process. Our framework exhibits notable properties: (1) Generalizability, applicable to various 3D semantic scene completion approaches, including 2D-3D lifting and 3D-2D transformer methods. (2) Effectiveness, as demonstrated through experiments on SemanticKITTI and NYUv2, wherein our method achieves up to 85% of the fully-supervised performance using only 10% labeled data. This approach not only reduces the cost and labor associated with data annotation but also demonstrates the potential for broader adoption in camera-based systems for 3D semantic occupancy prediction.
Authors: Haopeng Li, Jinyue Yang, Kexin Wang, Xuerui Qiu, Yuhong Chou, Xin Li, Guoqi Li
Abstract: We introduce AiM, an autoregressive (AR) image generative model based on Mamba architecture. AiM employs Mamba, a novel state-space model characterized by its exceptional performance for long-sequence modeling with linear time complexity, to supplant the commonly utilized Transformers in AR image generation models, aiming to achieve both superior generation quality and enhanced inference speed. Unlike existing methods that adapt Mamba to handle two-dimensional signals via multi-directional scan, AiM directly utilizes the next-token prediction paradigm for autoregressive image generation. This approach circumvents the need for extensive modifications to enable Mamba to learn 2D spatial representations. By implementing straightforward yet strategically targeted modifications for visual generative tasks, we preserve Mamba's core structure, fully exploiting its efficient long-sequence modeling capabilities and scalability. We provide AiM models in various scales, with parameter counts ranging from 148M to 1.3B. On the ImageNet1K 256*256 benchmark, our best AiM model achieves a FID of 2.21, surpassing all existing AR models of comparable parameter counts and demonstrating significant competitiveness against diffusion models, with 2 to 10 times faster inference speed. Code is available at https://github.com/hp-l33/AiM
Authors: Fangjinhua Wang, Qingtian Zhu, Di Chang, Quankai Gao, Junlin Han, Tong Zhang, Richard Hartley, Marc Pollefeys
Abstract: 3D reconstruction aims to recover the dense 3D structure of a scene. It plays an essential role in various applications such as Augmented/Virtual Reality (AR/VR), autonomous driving and robotics. Leveraging multiple views of a scene captured from different viewpoints, Multi-View Stereo (MVS) algorithms synthesize a comprehensive 3D representation, enabling precise reconstruction in complex environments. Due to its efficiency and effectiveness, MVS has become a pivotal method for image-based 3D reconstruction. Recently, with the success of deep learning, many learning-based MVS methods have been proposed, achieving impressive performance against traditional methods. We categorize these learning-based methods as: depth map-based, voxel-based, NeRF-based, 3D Gaussian Splatting-based, and large feed-forward methods. Among these, we focus significantly on depth map-based methods, which are the main family of MVS due to their conciseness, flexibility and scalability. In this survey, we provide a comprehensive review of the literature at the time of this writing. We investigate these learning-based methods, summarize their performances on popular benchmarks, and discuss promising future research directions in this area.
Authors: Haojian Huang, Chuanyu Qin, Zhe Liu, Kaijing Ma, Jin Chen, Han Fang, Chao Ban, Hao Sun, Zhongjiang He
Abstract: Multi-view classification (MVC) faces inherent challenges due to domain gaps and inconsistencies across different views, often resulting in uncertainties during the fusion process. While Evidential Deep Learning (EDL) has been effective in addressing view uncertainty, existing methods predominantly rely on the Dempster-Shafer combination rule, which is sensitive to conflicting evidence and often neglects the critical role of neighborhood structures within multi-view data. To address these limitations, we propose a Trusted Unified Feature-NEighborhood Dynamics (TUNED) model for robust MVC. This method effectively integrates local and global feature-neighborhood (F-N) structures for robust decision-making. Specifically, we begin by extracting local F-N structures within each view. To further mitigate potential uncertainties and conflicts in multi-view fusion, we employ a selective Markov random field that adaptively manages cross-view neighborhood dependencies. Additionally, we employ a shared parameterized evidence extractor that learns global consensus conditioned on local F-N structures, thereby enhancing the global integration of multi-view features. Experiments on benchmark datasets show that our method improves accuracy and robustness over existing approaches, particularly in scenarios with high uncertainty and conflicting views. The code will be made available at https://github.com/JethroJames/TUNED.
Authors: Fuchen Zheng, Xinyi Chen, Xuhang Chen, Haolun Li, Xiaojiao Guo, Weihuang Liu, Chi-Man Pun, Shoujun Zhou
Abstract: Medical image segmentation, a crucial task in computer vision, facilitates the automated delineation of anatomical structures and pathologies, supporting clinicians in diagnosis, treatment planning, and disease monitoring. Notably, transformers employing shifted window-based self-attention have demonstrated exceptional performance. However, their reliance on local window attention limits the fusion of local and global contextual information, crucial for segmenting microtumors and miniature organs. To address this limitation, we propose the Adaptive Semantic Segmentation Network (ASSNet), a transformer architecture that effectively integrates local and global features for precise medical image segmentation. ASSNet comprises a transformer-based U-shaped encoder-decoder network. The encoder utilizes shifted window self-attention across five resolutions to extract multi-scale features, which are then propagated to the decoder through skip connections. We introduce an augmented multi-layer perceptron within the encoder to explicitly model long-range dependencies during feature extraction. Recognizing the constraints of conventional symmetrical encoder-decoder designs, we propose an Adaptive Feature Fusion (AFF) decoder to complement our encoder. This decoder incorporates three key components: the Long Range Dependencies (LRD) block, the Multi-Scale Feature Fusion (MFF) block, and the Adaptive Semantic Center (ASC) block. These components synergistically facilitate the effective fusion of multi-scale features extracted by the decoder while capturing long-range dependencies and refining object boundaries. Comprehensive experiments on diverse medical image segmentation tasks, including multi-organ, liver tumor, and bladder tumor segmentation, demonstrate that ASSNet achieves state-of-the-art results. Code and models are available at: \url{https://github.com/lzeeorno/ASSNet}.
Authors: Stefan Smeu, Elisabeta Oneata, Dan Oneata
Abstract: Generative models can create entirely new images, but they can also partially modify real images in ways that are undetectable to the human eye. In this paper, we address the challenge of automatically detecting such local manipulations. One of the most pressing problems in deepfake detection remains the ability of models to generalize to different classes of generators. In the case of fully manipulated images, representations extracted from large self-supervised models (such as CLIP) provide a promising direction towards more robust detectors. Here, we introduce DeCLIP, a first attempt to leverage such large pretrained features for detecting local manipulations. We show that, when combined with a reasonably large convolutional decoder, pretrained self-supervised representations are able to perform localization and improve generalization capabilities over existing methods. Unlike previous work, our approach is able to perform localization on the challenging case of latent diffusion models, where the entire image is affected by the fingerprint of the generator. Moreover, we observe that this type of data, which combines local semantic information with a global fingerprint, provides more stable generalization than other categories of generative methods.
Authors: Neelabh Sinha, Vinija Jain, Aman Chadha
Abstract: Visual Question-Answering (VQA) has become key to user experience, particularly after improved generalization capabilities of Vision-Language Models (VLMs). But evaluating VLMs for an application requirement using a standardized framework in practical settings is still challenging. This paper aims to solve that using an end-to-end framework. We present VQA360 - a novel dataset derived from established VQA benchmarks, annotated with task types, application domains, and knowledge types, for a comprehensive evaluation. We also introduce GoEval, a multimodal evaluation metric developed using GPT-4o, achieving a correlation factor of 56.71% with human judgments. Our experiments with state-of-the-art VLMs reveal that no single model excels universally, thus, making a right choice a key design decision. Proprietary models such as Gemini-1.5-Pro and GPT-4o-mini generally outperform others, but open-source models like InternVL-2-8B and CogVLM-2-Llama-3-19B also demonstrate competitive strengths, while providing additional advantages. Our framework can also be extended to other tasks.
Authors: Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla
Abstract: We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion retrieval process. By effectively prompting large language models (LLMs), we address spelling errors and rephrasing issues in motion retrieval. Our approach utilizes a multi-part retrieval strategy to improve the generalizability of motion retrieval across the language space. We create diverse samples through the spatial composition of the retrieved motions. Furthermore, by utilizing low-level, part-specific motion information, we can construct motion samples for unseen text descriptions. Our experiments demonstrate that our framework can serve as a plug-and-play module, improving the performance of motion diffusion models. Code, pretrained models and sample videos are available at: https://motion-rag.github.io/
Authors: Chengkun Sun, Jinqian Pan, Zhuoli Jin, Russell Stevens Terry, Jiang Bian, Jie Xu
Abstract: Training deep Convolutional Neural Networks (CNNs) presents unique challenges, including the pervasive issue of elimination singularities, consistent deactivation of nodes leading to degenerate manifolds within the loss landscape. These singularities impede efficient learning by disrupting feature propagation. To mitigate this, we introduce Pool Skip, an architectural enhancement that strategically combines a Max Pooling, a Max Unpooling, a 3 times 3 convolution, and a skip connection. This configuration helps stabilize the training process and maintain feature integrity across layers. We also propose the Weight Inertia hypothesis, which underpins the development of Pool Skip, providing theoretical insights into mitigating degradation caused by elimination singularities through dimensional and affine compensation. We evaluate our method on a variety of benchmarks, focusing on both 2D natural and 3D medical imaging applications, including tasks such as classification and segmentation. Our findings highlight Pool Skip's effectiveness in facilitating more robust CNN training and improving model performance.
Authors: Yan Shu, Zheng Liu, Peitian Zhang, Minghao Qin, Junjie Zhou, Zhengyang Liang, Tiejun Huang, Bo Zhao
Abstract: Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos. Although several existing methods attempt to reduce visual tokens, their strategies encounter severe bottleneck, restricting MLLMs' ability to perceive fine-grained visual details. In this work, we propose Video-XL, a novel approach that leverages MLLMs' inherent key-value (KV) sparsification capacity to condense the visual input. Specifically, we introduce a new special token, the Visual Summarization Token (VST), for each interval of the video, which summarizes the visual information within the interval as its associated KV. The VST module is trained by instruction fine-tuning, where two optimizing strategies are offered. 1.Curriculum learning, where VST learns to make small (easy) and large compression (hard) progressively. 2. Composite data curation, which integrates single-image, multi-image, and synthetic data to overcome the scarcity of long-video instruction data. The compression quality is further improved by dynamic compression, which customizes compression granularity based on the information density of different video intervals. Video-XL's effectiveness is verified from three aspects. First, it achieves a superior long-video understanding capability, outperforming state-of-the-art models of comparable sizes across multiple popular benchmarks. Second, it effectively preserves video information, with minimal compression loss even at 16x compression ratio. Third, it realizes outstanding cost-effectiveness, enabling high-quality processing of thousands of frames on a single A100 GPU.
Authors: Dasol Choi, Dongbin Na
Abstract: With the explosive growth of deep learning applications and increasing privacy concerns, the right to be forgotten has become a critical requirement in various AI industries. For example, given a facial recognition system, some individuals may wish to remove their personal data that might have been used in the training phase. Unfortunately, deep neural networks sometimes unexpectedly leak personal identities, making this removal challenging. While recent machine unlearning algorithms aim to enable models to forget such data, we observe an unintended utility drop, termed correlation collapse, where these algorithms inadvertently weaken the essential correlations between image features and true labels during the forgetting process. To address this challenge, we propose Distribution-Level Feature Distancing (DLFD), a novel method that efficiently forgets instances while preserving task-relevant feature correlations. Our method synthesizes data samples by optimizing the feature distribution to be distinctly different from that of forget samples, achieving effective results within a single training epoch. Through extensive experiments on facial recognition datasets, we demonstrate that our approach significantly outperforms state-of-the-art machine unlearning methods in both forgetting performance and model utility preservation.
Authors: Hongyi Wang, Xiuju Du, Jing Liu, Shuyi Ouyang, Yen-Wei Chen, Lanfen Lin
Abstract: The advancement of Spatial Transcriptomics (ST) has facilitated the spatially-aware profiling of gene expressions based on histopathology images. Although ST data offers valuable insights into the micro-environment of tumors, its acquisition cost remains expensive. Therefore, directly predicting the ST expressions from digital pathology images is desired. Current methods usually adopt existing regression backbones along with patch-sampling for this task, which ignores the inherent multi-scale information embedded in the pyramidal data structure of digital pathology images, and wastes the inter-spot visual information crucial for accurate gene expression prediction. To address these limitations, we propose M2OST, a many-to-one regression Transformer that can accommodate the hierarchical structure of the pathology images via a decoupled multi-scale feature extractor. Unlike traditional models that are trained with one-to-one image-label pairs, M2OST uses multiple images from different levels of the digital pathology image to jointly predict the gene expressions in their common corresponding spot. Built upon our many-to-one scheme, M2OST can be easily scaled to fit different numbers of inputs, and its network structure inherently incorporates nearby inter-spot features, enhancing regression performance. We have tested M2OST on three public ST datasets and the experimental results show that M2OST can achieve state-of-the-art performance with fewer parameters and floating-point operations (FLOPs). The code is available at: https://github.com/Dootmaan/M2OST.
Authors: Mostafa Hajighasemloua, Samad Sheikhaei, Hamid Soltanian-Zadeh
Abstract: Artificial intelligence algorithms have demonstrated their image classification and segmentation ability in the past decade. However, artificial intelligence algorithms perform less for actual clinical data than those used for simulations. This research aims to present a novel hybrid learning model using self-supervised learning and knowledge distillation, which can achieve sufficient generalization and robustness. The self-attention mechanism and tokens employed in ViT, besides the local-to-global learning approach used in the hybrid model, enable the proposed algorithm to extract a high-dimensional and high-quality feature space from images. To demonstrate the proposed neural network's capability in classifying and extracting feature spaces from medical images, we use it on a dataset of Diabetic Retinopathy images, specifically the EyePACS dataset. This dataset is more complex structurally and challenging regarding damaged areas than other medical images. For the first time in this study, self-supervised learning and knowledge distillation are used to classify this dataset. In our algorithm, for the first time among all self-supervised learning and knowledge distillation models, the test dataset is 50% larger than the training dataset. Unlike many studies, we have not removed any images from the dataset. Finally, our algorithm achieved an accuracy of 79.1% in the linear classifier and 74.36% in the k-NN algorithm for multiclass classification. Compared to a similar state-of-the-art model, our results achieved higher accuracy and more effective representation spaces.
Authors: Junyu Chen, Han Cai, Junsong Chen, Enze Xie, Shang Yang, Haotian Tang, Muyang Li, Yao Lu, Song Han
Abstract: We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio (e.g., 8x), but fail to maintain satisfactory reconstruction accuracy for high spatial compression ratios (e.g., 64x). We address this challenge by introducing two key techniques: (1) Residual Autoencoding, where we design our models to learn residuals based on the space-to-channel transformed features to alleviate the optimization difficulty of high spatial-compression autoencoders; (2) Decoupled High-Resolution Adaptation, an efficient decoupled three-phases training strategy for mitigating the generalization penalty of high spatial-compression autoencoders. With these designs, we improve the autoencoder's spatial compression ratio up to 128 while maintaining the reconstruction quality. Applying our DC-AE to latent diffusion models, we achieve significant speedup without accuracy drop. For example, on ImageNet 512x512, our DC-AE provides 19.1x inference speedup and 17.9x training speedup on H100 GPU for UViT-H while achieving a better FID, compared with the widely used SD-VAE-f8 autoencoder. Our code is available at https://github.com/mit-han-lab/efficientvit.
Authors: Naga Venkata Sai Raviteja Chappa, Khoa Luu
Abstract: Group Activity Recognition (GAR) remains challenging in computer vision due to the complex nature of multi-agent interactions. This paper introduces LiGAR, a LIDAR-Guided Hierarchical Transformer for Multi-Modal Group Activity Recognition. LiGAR leverages LiDAR data as a structural backbone to guide the processing of visual and textual information, enabling robust handling of occlusions and complex spatial arrangements. Our framework incorporates a Multi-Scale LIDAR Transformer, Cross-Modal Guided Attention, and an Adaptive Fusion Module to integrate multi-modal data at different semantic levels effectively. LiGAR's hierarchical architecture captures group activities at various granularities, from individual actions to scene-level dynamics. Extensive experiments on the JRDB-PAR, Volleyball, and NBA datasets demonstrate LiGAR's superior performance, achieving state-of-the-art results with improvements of up to 10.6% in F1-score on JRDB-PAR and 5.9% in Mean Per Class Accuracy on the NBA dataset. Notably, LiGAR maintains high performance even when LiDAR data is unavailable during inference, showcasing its adaptability. Our ablation studies highlight the significant contributions of each component and the effectiveness of our multi-modal, multi-scale approach in advancing the field of group activity recognition.
Authors: Corwin Grant Jeon MacMillan, K. Andrea Scott, Matthew Garvin, Zhao Pan
Abstract: Rapid ice recession in the Arctic Ocean, with predictions of ice-free summers by 2060, opens new maritime routes but requires reliable navigation solutions. Current approaches rely heavily on subjective expert judgment, underscoring the need for automated, data-driven solutions. This study leverages machine learning to assess ice conditions using ship-borne optical data, introducing a finely annotated dataset of 946 images, and a semi-manual, region-based annotation technique. The proposed video segmentation model, UPerFlow, advances the SegFlow architecture by incorporating a six-channel ResNet encoder, two UPerNet-based segmentation decoders for each image, PWCNet as the optical flow encoder, and cross-connections that integrate bi-directional flow features without loss of latent information. The proposed architecture outperforms baseline image segmentation networks by an average 38% in occluded regions, demonstrating the robustness of video segmentation in addressing challenging Arctic conditions.
Authors: Shravan Venkatraman, Jaskaran Singh Walia, Joe Dhanith P R
Abstract: Image classification is a computer vision task where a model analyzes an image to categorize it into a specific label. Vision Transformers (ViT) improve this task by leveraging self-attention to capture complex patterns and long range relationships between image patches. However, a key challenge for ViTs is efficiently incorporating multiscale feature representations, which is inherent in CNNs through their hierarchical structure. In this paper, we introduce the Scale-Aware Graph Attention Vision Transformer (SAG-ViT), a novel framework that addresses this challenge by integrating multi-scale features. Using EfficientNet as a backbone, the model extracts multi-scale feature maps, which are divided into patches to preserve semantic information. These patches are organized into a graph based on spatial and feature similarities, with a Graph Attention Network (GAT) refining the node embeddings. Finally, a Transformer encoder captures long-range dependencies and complex interactions. The SAG-ViT is evaluated on benchmark datasets, demonstrating its effectiveness in enhancing image classification performance. Our code and weights are publicly available at https://github.com/shravan-18/SAG-ViT
Authors: Fabian Immel, Richard Fehler, Frank Bieder, Jan-Hendrik Pauls, Christoph Stiller
Abstract: Autonomous vehicles require road information for their operation, usually in form of HD maps. Since offline maps eventually become outdated or may only be partially available, online HD map construction methods have been proposed to infer map information from live sensor data. A key issue remains how to exploit such partial or outdated map information as a prior. We introduce M3TR (Multi-Masking Map Transformer), a generalist approach for HD map construction both with and without map priors. We address shortcomings in ground truth generation for Argoverse 2 and nuScenes and propose the first realistic scenarios with semantically diverse map priors. Examining various query designs, we use an improved method for integrating prior map elements into a HD map construction model, increasing performance by +4.3 mAP. Finally, we show that training across all prior scenarios yields a single Generalist model, whose performance is on par with previous Expert models that can handle only one specific type of map prior. M3TR thus is the first model capable of leveraging variable map priors, making it suitable for real-world deployment. Code is available at https://github.com/immel-f/m3tr
Authors: Bowen Yuan, Zijian Wang, Mahsa Baktashmotlagh, Yadan Luo, Zi Huang
Abstract: Dataset Distillation (DD) is designed to generate condensed representations of extensive image datasets, enhancing training efficiency. Despite recent advances, there remains considerable potential for improvement, particularly in addressing the notable redundancy within the color space of distilled images. In this paper, we propose AutoPalette, a framework that minimizes color redundancy at the individual image and overall dataset levels, respectively. At the image level, we employ a palette network, a specialized neural network, to dynamically allocate colors from a reduced color space to each pixel. The palette network identifies essential areas in synthetic images for model training and consequently assigns more unique colors to them. At the dataset level, we develop a color-guided initialization strategy to minimize redundancy among images. Representative images with the least replicated color patterns are selected based on the information gain. A comprehensive performance study involving various datasets and evaluation scenarios is conducted, demonstrating the superior performance of our proposed color-aware DD compared to existing DD methods. The code is available at \url{https://github.com/KeViNYuAn0314/AutoPalette}.
Authors: Yuncong Yang, Han Yang, Jiachen Zhou, Peihao Chen, Hongxin Zhang, Yilun Du, Chuang Gan
Abstract: Constructing compact and informative 3D scene representations is essential for effective embodied exploration and reasoning, especially in complex environments over extended periods. Existing representations, such as object-centric 3D scene graphs, oversimplify spatial relationships by modeling scenes as isolated objects with restrictive textual relationships, making it difficult to address queries requiring nuanced spatial understanding. Moreover, these representations lack natural mechanisms for active exploration and memory management, hindering their application to lifelong autonomy. In this work, we propose 3D-Mem, a novel 3D scene memory framework for embodied agents. 3D-Mem employs informative multi-view images, termed Memory Snapshots, to represent the scene and capture rich visual information of explored regions. It further integrates frontier-based exploration by introducing Frontier Snapshots-glimpses of unexplored areas-enabling agents to make informed decisions by considering both known and potential new information. To support lifelong memory in active exploration settings, we present an incremental construction pipeline for 3D-Mem, as well as a memory retrieval technique for memory management. Experimental results on three benchmarks demonstrate that 3D-Mem significantly enhances agents' exploration and reasoning capabilities in 3D environments, highlighting its potential for advancing applications in embodied AI.
Authors: Xu Chen, Keke He, Junwei Zhu, Yanhao Ge, Wei Li, Chengjie Wang
Abstract: Face swapping aims to generate results that combine the identity from the source with attributes from the target. Existing methods primarily focus on image-based face swapping. When processing videos, each frame is handled independently, making it difficult to ensure temporal stability. From a model perspective, face swapping is gradually shifting from generative adversarial networks (GANs) to diffusion models (DMs), as DMs have been shown to possess stronger generative capabilities. Current diffusion-based approaches often employ inpainting techniques, which struggle to preserve fine-grained attributes like lighting and makeup. To address these challenges, we propose a high fidelity video face swapping (HiFiVFS) framework, which leverages the strong generative capability and temporal prior of Stable Video Diffusion (SVD). We build a fine-grained attribute module to extract identity-disentangled and fine-grained attribute features through identity desensitization and adversarial learning. Additionally, We introduce detailed identity injection to further enhance identity similarity. Extensive experiments demonstrate that our method achieves state-of-the-art (SOTA) in video face swapping, both qualitatively and quantitatively.
Authors: Zhibo Yang, Jun Tang, Zhaohai Li, Pengfei Wang, Jianqiang Wan, Humen Zhong, Xuejing Liu, Mingkun Yang, Peng Wang, Shuai Bai, LianWen Jin, Junyang Lin
Abstract: Large Multimodal Models (LMMs) have demonstrated impressive performance in recognizing document images with natural language instructions. However, it remains unclear to what extent capabilities in literacy with rich structure and fine-grained visual challenges. The current landscape lacks a comprehensive benchmark to effectively measure the literate capabilities of LMMs. Existing benchmarks are often limited by narrow scenarios and specified tasks. To this end, we introduce CC-OCR, a comprehensive benchmark that possesses a diverse range of scenarios, tasks, and challenges. CC-OCR comprises four OCR-centric tracks: multi-scene text reading, multilingual text reading, document parsing, and key information extraction. It includes 39 subsets with 7,058 full annotated images, of which 41% are sourced from real applications, and released for the first time. We evaluate nine prominent LMMs and reveal both the strengths and weaknesses of these models, particularly in text grounding, multi-orientation, and hallucination of repetition. CC-OCR aims to comprehensively evaluate the capabilities of LMMs on OCR-centered tasks, facilitating continued progress in this crucial area.
Authors: Jingyu Lin, Jiaqi Gu, Lubin Fan, Bojian Wu, Yujing Lou, Renjie Chen, Ligang Liu, Jieping Ye
Abstract: Generating high-quality novel view renderings of 3D Gaussian Splatting (3DGS) in scenes featuring transient objects is challenging. We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per image and maintaining traditional 3D Gaussians for the whole static scenes. Note that, the 3DGS itself is better suited for modeling static scenes that assume multi-view consistency, but the transient objects appear occasionally and do not adhere to the assumption, thus we model them as planar objects from a single view, represented with 2D Gaussians. Our novel representation decomposes the scene from the perspective of fundamental viewpoint consistency, making it more reasonable. Additionally, we present a novel multi-view regulated supervision method for 3DGS that leverages information from co-visible regions, further enhancing the distinctions between the transients and statics. Then, we propose a straightforward yet effective multi-stage training strategy to ensure robust training and high-quality view synthesis across various settings. Experiments on benchmark datasets show our state-of-the-art performance of novel view synthesis in both indoor and outdoor scenes, even in the presence of distracting elements.
Authors: Sejong Yang, Seoung Wug Oh, Yang Zhou, Seon Joo Kim
Abstract: We introduce a novel approach for high-resolution talking head generation from a single image and audio input. Prior methods using explicit face models, like 3D morphable models (3DMM) and facial landmarks, often fall short in generating high-fidelity videos due to their lack of appearance-aware motion representation. While generative approaches such as video diffusion models achieve high video quality, their slow processing speeds limit practical application. Our proposed model, Implicit Face Motion Diffusion Model (IF-MDM), employs implicit motion to encode human faces into appearance-aware compressed facial latents, enhancing video generation. Although implicit motion lacks the spatial disentanglement of explicit models, which complicates alignment with subtle lip movements, we introduce motion statistics to help capture fine-grained motion information. Additionally, our model provides motion controllability to optimize the trade-off between motion intensity and visual quality during inference. IF-MDM supports real-time generation of 512x512 resolution videos at up to 45 frames per second (fps). Extensive evaluations demonstrate its superior performance over existing diffusion and explicit face models. The code will be released publicly, available alongside supplementary materials. The video results can be found on https://bit.ly/ifmdm_supplementary.
Authors: Thomas Walker, Salvatore Esposito, Daniel Rebain, Amir Vaxman, Arno Onken, Changjian Li, Oisin Mac Aodha
Abstract: Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography. Out-of-the-box point cloud reconstruction methods can often fail due to the data sparsity between slicing planes, while current bespoke methods struggle to reconstruct thin geometric structures and preserve topological continuity. This is important for medical applications where thin vessel structures are present in CT and MRI scans. This paper introduces CrossSDF, a novel approach for extracting a 3D signed distance field from 2D signed distances generated from planar contours. Our approach makes the training of neural SDFs contour-aware by using losses designed for the case where geometry is known within 2D slices. Our results demonstrate a significant improvement over existing methods, effectively reconstructing thin structures and producing accurate 3D models without the interpolation artifacts or over-smoothing of prior approaches.
Authors: Sunung Mun, Jinhwan Nam, Sunghyun Cho, Jungseul Ok
Abstract: Diffusion models have become a cornerstone in image editing, offering flexibility with language prompts and source images. However, a key challenge is attribute leakage, where unintended modifications occur in non-target regions or within target regions due to attribute interference. Existing methods often suffer from leakage due to naive text embeddings and inadequate handling of End-of-Sequence (EOS) token embeddings. To address this, we propose ALE-Edit (Attribute-leakage-free editing), a novel framework to minimize attribute leakage with three components: (1) Object-Restricted Embeddings (ORE) to localize object-specific attributes in text embeddings, (2) Region-Guided Blending for Cross-Attention Masking (RGB-CAM) to align attention with target regions, and (3) Background Blending (BB) to preserve non-edited regions. Additionally, we introduce ALE-Bench, a benchmark for evaluating attribute leakage with new metrics for target-external and target-internal leakage. Experiments demonstrate that our framework significantly reduces attribute leakage while maintaining high editing quality, providing an efficient and tuning-free solution for multi-object image editing.
Authors: Xiangyu Han, Zhen Jia, Boyi Li, Yan Wang, Boris Ivanovic, Yurong You, Lingjie Liu, Yue Wang, Marco Pavone, Chen Feng, Yiming Li
Abstract: Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capability that generates diverse unseen viewpoints to accommodate the broad and continuous pose distribution of AVs. Recent advances in radiance fields, such as 3D Gaussian Splatting, achieve photorealistic rendering at real-time speeds and have been widely used in modeling large-scale driving scenes. However, their performance is commonly evaluated using an interpolated setup with highly correlated training and test views. In contrast, extrapolation, where test views largely deviate from training views, remains underexplored, limiting progress in generalizable simulation technology. To address this gap, we leverage publicly available AV datasets with multiple traversals, multiple vehicles, and multiple cameras to build the first Extrapolated Urban View Synthesis (EUVS) benchmark. Meanwhile, we conduct quantitative and qualitative evaluations of state-of-the-art Gaussian Splatting methods across different difficulty levels. Our results show that Gaussian Splatting is prone to overfitting to training views. Besides, incorporating diffusion priors and improving geometry cannot fundamentally improve NVS under large view changes, highlighting the need for more robust approaches and large-scale training. We have released our data to help advance self-driving and urban robotics simulation technology.
Authors: Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese
Abstract: While open-source multi-modal language models perform well on simple question answering tasks, they often fail on complex questions that require multiple capabilities, such as fine-grained recognition, visual grounding, and reasoning, and that demand multi-step solutions. We present TACO, a family of multi-modal large action models designed to improve performance on such complex, multi-step, and multi-modal tasks. During inference, TACO produces chains-of-thought-and-action (CoTA), executes intermediate steps by invoking external tools such as OCR, depth estimation and calculator, then integrates both the thoughts and action outputs to produce coherent responses. To train TACO, we create a large dataset of over 1M synthetic CoTA traces generated with GPT-4o and Python programs. We then experiment with various data filtering and mixing techniques and obtain a final subset of 293K high-quality CoTA examples. This dataset enables TACO to learn complex reasoning and action paths, surpassing existing models trained on instruction tuning data with only direct answers. Our model TACO outperforms the instruction-tuned baseline across 8 benchmarks, achieving a 3.6% improvement on average, with gains of up to 15% in MMVet tasks involving OCR, mathematical reasoning, and spatial reasoning. Training on high-quality CoTA traces sets a new standard for complex multi-modal reasoning, highlighting the need for structured, multi-step instruction tuning in advancing open-source mutli-modal models' capabilities.
Authors: Xu Liu, Zhouhui Lian
Abstract: Remote Sensing Vision-Language Models (RS VLMs) have made much progress in the tasks of remote sensing (RS) image comprehension. While performing well in multi-modal reasoning and multi-turn conversations, the existing models lack pixel-level understanding and struggle with multi-image inputs. In this work, we propose RSUniVLM, a unified, end-to-end RS VLM designed for comprehensive vision understanding across multiple granularity, including image-level, region-level, and pixel-level tasks. RSUniVLM also performs effectively in multi-image analysis, with instances of change detection and change captioning. To enhance the model's ability to capture visual information at different levels without increasing model size, we design a novel architecture called Granularity-oriented Mixture of Experts to constraint the model to about 1 billion parameters. We also construct a large-scale RS instruction-following dataset based on a variety of existing datasets in both RS and general domain, encompassing various tasks such as object localization, visual question answering, and semantic segmentation. Substantial experiments have been conducted to validate the superiority of the proposed RSUniVLM up to state-of-the-art across various RS tasks. Code and model will be available at \href{https://github.com/xuliu-cyber/RSUniVLM}{here}.
Authors: Qinchan Li, Kenneth Chen, Changyue Su, Qi Sun
Abstract: Diffusion models have shown unprecedented success in the task of text-to-image generation. While these models are capable of generating high-quality and realistic images, the complexity of sequential denoising has raised societal concerns regarding high computational demands and energy consumption. In response, various efforts have been made to improve inference efficiency. However, most of the existing efforts have taken a fixed approach with neural network simplification or text prompt optimization. Are the quality improvements from all denoising computations equally perceivable to humans? We observed that images from different text prompts may require different computational efforts given the desired content. The observation motivates us to present BudgetFusion, a novel model that suggests the most perceptually efficient number of diffusion steps before a diffusion model starts to generate an image. This is achieved by predicting multi-level perceptual metrics relative to diffusion steps. With the popular Stable Diffusion as an example, we conduct both numerical analyses and user studies. Our experiments show that BudgetFusion saves up to five seconds per prompt without compromising perceptual similarity. We hope this work can initiate efforts toward answering a core question: how much do humans perceptually gain from images created by a generative model, per watt of energy?
Authors: Yugang Chang, Hongyu Chen, Fei Wang, Chengcheng Chen, Weiming Zeng
Abstract: This paper introduces the Maritime Ship Navigation Behavior Dataset (MID), designed to address challenges in ship detection within complex maritime environments using Oriented Bounding Boxes (OBB). MID contains 5,673 images with 135,884 finely annotated target instances, supporting both supervised and semi-supervised learning. It features diverse maritime scenarios such as ship encounters under varying weather, docking maneuvers, small target clustering, and partial occlusions, filling critical gaps in datasets like HRSID, SSDD, and NWPU-10. MID's images are sourced from high-definition video clips of real-world navigation across 43 water areas, with varied weather and lighting conditions (e.g., rain, fog). Manually curated annotations enhance the dataset's variety, ensuring its applicability to real-world demands in busy ports and dense maritime regions. This diversity equips models trained on MID to better handle complex, dynamic environments, supporting advancements in maritime situational awareness. To validate MID's utility, we evaluated 10 detection algorithms, providing an in-depth analysis of the dataset, detection results from various models, and a comparative study of baseline algorithms, with a focus on handling occlusions and dense target clusters. The results highlight MID's potential to drive innovation in intelligent maritime traffic monitoring and autonomous navigation systems. The dataset will be made publicly available at https://github.com/VirtualNew/MID_DataSet.
Authors: Hyeonho Jeong, Chun-Hao Paul Huang, Jong Chul Ye, Niloy Mitra, Duygu Ceylan
Abstract: While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a single network by making minimal changes to existing video generation architectures. Using Stable Video Diffusion as a backbone, Track4Gen demonstrates that it is possible to unify video generation and point tracking, which are typically handled as separate tasks. Our extensive evaluations show that Track4Gen effectively reduces appearance drift, resulting in temporally stable and visually coherent video generation. Project page: hyeonho99.github.io/track4gen
Authors: Shuangfei Zhai, Ruixiang Zhang, Preetum Nakkiran, David Berthelot, Jiatao Gu, Huangjie Zheng, Tianrong Chen, Miguel Angel Bautista, Navdeep Jaitly, Josh Susskind
Abstract: Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relatively little attention in recent years. In this work, we demonstrate that NFs are more powerful than previously believed. We present TarFlow: a simple and scalable architecture that enables highly performant NF models. TarFlow can be thought of as a Transformer-based variant of Masked Autoregressive Flows (MAFs): it consists of a stack of autoregressive Transformer blocks on image patches, alternating the autoregression direction between layers. TarFlow is straightforward to train end-to-end, and capable of directly modeling and generating pixels. We also propose three key techniques to improve sample quality: Gaussian noise augmentation during training, a post training denoising procedure, and an effective guidance method for both class-conditional and unconditional settings. Putting these together, TarFlow sets new state-of-the-art results on likelihood estimation for images, beating the previous best methods by a large margin, and generates samples with quality and diversity comparable to diffusion models, for the first time with a stand-alone NF model. We make our code available at https://github.com/apple/ml-tarflow.
Authors: Xuesong Zhang, Yunbo Xu, Jia Li, Zhenzhen Hu, Richnag Hong
Abstract: Navigating unseen environments based on natural language instructions remains difficult for egocentric agents in Vision-and-Language Navigation (VLN). While recent advancements have yielded promising outcomes, they primarily rely on RGB images for environmental representation, often overlooking the underlying semantic knowledge and spatial cues. Intuitively, humans inherently ground textual semantics within the spatial layout during indoor navigation. Inspired by this, we propose a versatile Semantic Understanding and Spatial Awareness (SUSA) architecture to facilitate navigation. SUSA includes a Textual Semantic Understanding (TSU) module, which narrows the modality gap between instructions and environments by generating and associating the descriptions of environmental landmarks in the agent's immediate surroundings. Additionally, a Depth-based Spatial Perception (DSP) module incrementally constructs a depth exploration map, enabling a more nuanced comprehension of environmental layouts. Experimental results demonstrate that SUSA hybrid semantic-spatial representations effectively enhance navigation performance, setting new state-of-the-art performance across three VLN benchmarks (REVERIE, R2R, and SOON). The source code will be publicly available.
Authors: Shidan He, Lei Liu, Shen Zhao
Abstract: Anomaly synthesis is a crucial approach to augment abnormal data for advancing anomaly inspection. Based on the knowledge from the large-scale pre-training, existing text-to-image anomaly synthesis methods predominantly focus on textual information or coarse-aligned visual features to guide the entire generation process. However, these methods often lack sufficient descriptors to capture the complicated characteristics of realistic anomalies (e.g., the fine-grained visual pattern of anomalies), limiting the realism and generalization of the generation process. To this end, we propose a novel anomaly synthesis framework called AnomalyControl to learn cross-modal semantic features as guidance signals, which could encode the generalized anomaly cues from text-image reference prompts and improve the realism of synthesized abnormal samples. Specifically, AnomalyControl adopts a flexible and non-matching prompt pair (i.e., a text-image reference prompt and a targeted text prompt), where a Cross-modal Semantic Modeling (CSM) module is designed to extract cross-modal semantic features from the textual and visual descriptors. Then, an Anomaly-Semantic Enhanced Attention (ASEA) mechanism is formulated to allow CSM to focus on the specific visual patterns of the anomaly, thus enhancing the realism and contextual relevance of the generated anomaly features. Treating cross-modal semantic features as the prior, a Semantic Guided Adapter (SGA) is designed to encode effective guidance signals for the adequate and controllable synthesis process. Extensive experiments indicate that AnomalyControl can achieve state-of-the-art results in anomaly synthesis compared with existing methods while exhibiting superior performance for downstream tasks.
Authors: Hongze Mi, Jinyuan Li, Xuying Zhang, Haoran Cheng, Jiahao Wang, Di Sun, Gang Pan
Abstract: Multimodal Entity Linking (MEL) is extensively utilized in the domains of information retrieval. However, existing MEL methods typically utilize mention words as mentions for retrieval. This results in a significant dependence of MEL on mention words, thereby constraining its capacity to effectively leverage information from both images and text. In situations where mention words are absent, MEL methods struggle to leverage image-text pairs for entity linking. To solve these issues, we introduce a Visual Prompts guided Multimodal Entity Linking (VP-MEL) task. VP-MEL directly marks specific regions within the image. These markers are referred to as visual prompts in VP-MEL. Without mention words, VP-MEL aims to utilize marked image-text pairs to align visual prompts with specific entities in the knowledge bases. A new dataset for the VP-MEL task, VPWiki, is proposed in this paper. Moreover, we propose a framework named FBMEL, which enhances the significance of visual prompts and fully leverages the information in image-text pairs. Experimental results on the VPWiki dataset demonstrate that FBMEL outperforms baseline methods across multiple benchmarks for the VP-MEL task.
Authors: Andrei-Robert Alexandrescu, Razvan-Gabriel Petec, Alexandru Manole, Laura-Silvia Diosan
Abstract: Deep Learning became an ubiquitous paradigm due to its extraordinary effectiveness and applicability in numerous domains. However, the approach suffers from the high demand of data required to achieve the potential of this type of model. An ever-increasing sub-field of Artificial Intelligence, Image Synthesis, aims to address this limitation through the design of intelligent models capable of creating original and realistic images, endeavour which could drastically reduce the need for real data. The Stable Diffusion generation paradigm recently propelled state-of-the-art approaches to exceed all previous benchmarks. In this work, we propose the ContRail framework based on the novel Stable Diffusion model ControlNet, which we empower through a multi-modal conditioning method. We experiment with the task of synthetic railway image generation, where we improve the performance in rail-specific tasks, such as rail semantic segmentation by enriching the dataset with realistic synthetic images.
Authors: Vincent Tao Hu, Bj\"orn Ommer
Abstract: In generative models, two paradigms have gained attraction in various applications: next-set prediction-based Masked Generative Models and next-noise prediction-based Non-Autoregressive Models, e.g., Diffusion Models. In this work, we propose using discrete-state models to connect them and explore their scalability in the vision domain. First, we conduct a step-by-step analysis in a unified design space across two types of models including timestep-independence, noise schedule, temperature, guidance strength, etc in a scalable manner. Second, we re-cast typical discriminative tasks, e.g., image segmentation, as an unmasking process from [MASK] tokens on a discrete-state model. This enables us to perform various sampling processes, including flexible conditional sampling by only training once to model the joint distribution. All aforementioned explorations lead to our framework named Discrete Interpolants, which enables us to achieve state-of-the-art or competitive performance compared to previous discrete-state based methods in various benchmarks, like ImageNet256, MS COCO, and video dataset FaceForensics. In summary, by leveraging [MASK] in discrete-state models, we can bridge Masked Generative and Non-autoregressive Diffusion models, as well as generative and discriminative tasks.
Authors: Carlo Alberto Barbano, Enzo Tartaglione, Marco Grangetto
Abstract: Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and confounding factors, inadvertently acquired during training. Existing approaches to address this problem typically involve explicit supervision of bias attributes or reliance on prior knowledge about the biases. In this study, we address the challenging scenario where no explicit annotations of bias are available, and there's no prior knowledge about its nature. We present a fully unsupervised debiasing framework with three key steps: firstly, leveraging the inherent tendency to learn malignant biases to acquire a bias-capturing model; next, employing a pseudo-labeling process to obtain bias labels; and finally, applying cutting-edge supervised debiasing techniques to achieve an unbiased model. Additionally, we introduce a theoretical framework for evaluating model biasedness and conduct a detailed analysis of how biases impact neural network training. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of our method, showcasing state-of-the-art performance in various settings, occasionally surpassing fully supervised debiasing approaches.
Authors: Charles Guille-Escuret, Pau Rodriguez, David Vazquez, Ioannis Mitliagkas, Joao Monteiro
Abstract: Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of OOD samples: unseen classes and adversarial perturbations. First, we pair self-supervised contrastive learning with the maximum mean discrepancy (MMD) two-sample test. This approach enables us to robustly test whether two independent sets of samples originate from the same distribution, and we demonstrate its effectiveness by discriminating between CIFAR-10 and CIFAR-10.1 with higher confidence than previous work. Motivated by this success, we introduce CADet (Contrastive Anomaly Detection), a novel method for OOD detection of single samples. CADet draws inspiration from MMD, but leverages the similarity between contrastive transformations of a same sample. CADet outperforms existing adversarial detection methods in identifying adversarially perturbed samples on ImageNet and achieves comparable performance to unseen label detection methods on two challenging benchmarks: ImageNet-O and iNaturalist. Significantly, CADet is fully self-supervised and requires neither labels for in-distribution samples nor access to OOD examples.
Authors: Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis, Kate Saenko, Bryan A. Plummer
Abstract: Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impractical. A common DG baseline minimizes the empirical risk on the source domains. Recent studies have shown that this approach, known as Empirical Risk Minimization (ERM), can outperform most more complex DG methods when properly tuned. However, these studies have primarily focused on a narrow set of hyperparameters, neglecting other factors that can enhance robustness and prevent overfitting and catastrophic forgetting, properties which are critical for strong DG performance. In our investigation of training data utilization (i.e., duration and setting validation splits), initialization, and additional regularizers, we find that tuning these previously overlooked factors significantly improves model generalization across diverse datasets without adding much complexity. We call this improved, yet simple baseline ERM++. Despite its ease of implementation, ERM++ improves DG performance by over 5\% compared to prior ERM baselines on a standard benchmark of 5 datasets with a ResNet-50 and over 15\% with a ViT-B/16. It also outperforms all state-of-the-art methods on DomainBed datasets with both architectures. Importantly, ERM++ is easy to integrate into existing frameworks like DomainBed, making it a practical and powerful tool for researchers and practitioners. Overall, ERM++ challenges the need for more complex DG methods by providing a stronger, more reliable baseline that maintains simplicity and ease of use. Code is available at \url{https://github.com/piotr-teterwak/erm_plusplus}
Authors: Daniel Wesego, Pedram Rooshenas
Abstract: Multimodal Variational Autoencoders (VAEs) represent a promising group of generative models that facilitate the construction of a tractable posterior within the latent space given multiple modalities. Previous studies have shown that as the number of modalities increases, the generative quality of each modality declines. In this study, we explore an alternative approach to enhance the generative performance of multimodal VAEs by jointly modeling the latent space of independently trained unimodal VAEs using score-based models (SBMs). The role of the SBM is to enforce multimodal coherence by learning the correlation among the latent variables. Consequently, our model combines a better generative quality of unimodal VAEs with coherent integration across different modalities using the latent score-based model. In addition, our approach provides the best unconditional coherence.
Authors: Charles Guille-Escuret, Pierre-Andr\'e No\"el, Ioannis Mitliagkas, David Vazquez, Joao Monteiro
Abstract: Improving the reliability of deployed machine learning systems often involves developing methods to detect out-of-distribution (OOD) inputs. However, existing research often narrowly focuses on samples from classes that are absent from the training set, neglecting other types of plausible distribution shifts. This limitation reduces the applicability of these methods in real-world scenarios, where systems encounter a wide variety of anomalous inputs. In this study, we categorize five distinct types of distribution shifts and critically evaluate the performance of recent OOD detection methods on each of them. We publicly release our benchmark under the name BROAD (Benchmarking Resilience Over Anomaly Diversity). Our findings reveal that while these methods excel in detecting unknown classes, their performance is inconsistent when encountering other types of distribution shifts. In other words, they only reliably detect unexpected inputs that they have been specifically designed to expect. As a first step toward broad OOD detection, we learn a generative model of existing detection scores with a Gaussian mixture. By doing so, we present an ensemble approach that offers a more consistent and comprehensive solution for broad OOD detection, demonstrating superior performance compared to existing methods. Our code to download BROAD and reproduce our experiments is publicly available.
Authors: Ganesh Babu, Aoife Gowen, Michael Fop, Isobel Claire Gormley
Abstract: The use of hyperspectral imaging to investigate food samples has grown due to the improved performance and lower cost of instrumentation. Food engineers use hyperspectral images to classify the type and quality of a food sample, typically using classification methods. In order to train these methods, every pixel in each training image needs to be labelled. Typically, computationally cheap threshold-based approaches are used to label the pixels, and classification methods are trained based on those labels. However, threshold-based approaches are subjective and cannot be generalized across hyperspectral images taken in different conditions and of different foods. Here a consensus-constrained parsimonious Gaussian mixture model (ccPGMM) is proposed to label pixels in hyperspectral images using a model-based clustering approach. The ccPGMM utilizes information that is available on some pixels and specifies constraints on those pixels belonging to the same or different clusters while clustering the rest of the pixels in the image. A latent variable model is used to represent the high-dimensional data in terms of a small number of underlying latent factors. To ensure computational feasibility, a consensus clustering approach is employed, where the data are divided into multiple randomly selected subsets of variables and constrained clustering is applied to each data subset; the clustering results are then consolidated across all data subsets to provide a consensus clustering solution. The ccPGMM approach is applied to simulated datasets and real hyperspectral images of three types of puffed cereal, corn, rice, and wheat. Improved clustering performance and computational efficiency are demonstrated when compared to other current state-of-the-art approaches.
Authors: Filip Granqvist, Congzheng Song, \'Aine Cahill, Rogier van Dalen, Martin Pelikan, Yi Sheng Chan, Xiaojun Feng, Natarajan Krishnaswami, Vojta Jina, Mona Chitnis
Abstract: Federated learning (FL) is an emerging machine learning (ML) training paradigm where clients own their data and collaborate to train a global model, without revealing any data to the server and other participants. Researchers commonly perform experiments in a simulation environment to quickly iterate on ideas. However, existing open-source tools do not offer the efficiency required to simulate FL on larger and more realistic FL datasets. We introduce pfl-research, a fast, modular, and easy-to-use Python framework for simulating FL. It supports TensorFlow, PyTorch, and non-neural network models, and is tightly integrated with state-of-the-art privacy algorithms. We study the speed of open-source FL frameworks and show that pfl-research is 7-72$\times$ faster than alternative open-source frameworks on common cross-device setups. Such speedup will significantly boost the productivity of the FL research community and enable testing hypotheses on realistic FL datasets that were previously too resource intensive. We release a suite of benchmarks that evaluates an algorithm's overall performance on a diverse set of realistic scenarios. The code is available on GitHub at https://github.com/apple/pfl-research.
Authors: Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kiant\'e Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun
Abstract: While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g. value networks, clipping), and is notorious for its sensitivity to the precise implementation of these components. In response, we take a step back and ask what a minimalist RL algorithm for the era of generative models would look like. We propose REBEL, an algorithm that cleanly reduces the problem of policy optimization to regressing the relative reward between two completions to a prompt in terms of the policy, enabling strikingly lightweight implementation. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL, which allows us to match the strongest known theoretical guarantees in terms of convergence and sample complexity in the RL literature. REBEL can also cleanly incorporate offline data and be extended to handle the intransitive preferences we frequently see in practice. Empirically, we find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO, all while being simpler to implement and more computationally efficient than PPO. When fine-tuning Llama-3-8B-Instruct, REBEL achieves strong performance in AlpacaEval 2.0, MT-Bench, and Open LLM Leaderboard.
Authors: Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, Vincent Sitzmann
Abstract: This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens without fully diffusing past ones. Our approach is shown to combine the strengths of next-token prediction models, such as variable-length generation, with the strengths of full-sequence diffusion models, such as the ability to guide sampling to desirable trajectories. Our method offers a range of additional capabilities, such as (1) rolling-out sequences of continuous tokens, such as video, with lengths past the training horizon, where baselines diverge and (2) new sampling and guiding schemes that uniquely profit from Diffusion Forcing's variable-horizon and causal architecture, and which lead to marked performance gains in decision-making and planning tasks. In addition to its empirical success, our method is proven to optimize a variational lower bound on the likelihoods of all subsequences of tokens drawn from the true joint distribution. Project website: https://boyuan.space/diffusion-forcing
Authors: Gurucharan Marthi Krishna Kumar, Janine Mendola, Amir Shmuel
Abstract: Deformable image registration is crucial for aligning medical images in a nonlinear fashion across different modalities, allowing for precise spatial correspondence between varying anatomical structures. This paper presents NestedMorph, a novel network utilizing a Nested Attention Fusion approach to improve intra-subject deformable registration between T1-weighted (T1w) MRI and diffusion MRI (dMRI) data. NestedMorph integrates high-resolution spatial details from an encoder with semantic information from a decoder using a multi-scale framework, enhancing both local and global feature extraction. Our model notably outperforms existing methods, including CNN-based approaches like VoxelMorph, MIDIR, and CycleMorph, as well as Transformer-based models such as TransMorph and ViT-V-Net, and traditional techniques like NiftyReg and SyN. Evaluations using the HCP dataset demonstrate that NestedMorph achieves superior performance across key metrics, including SSIM, HD95, and SDlogJ, with the highest SSIM of 0.89, the lowest HD95 of 2.5 and SDlogJ of 0.22. These results highlight NestedMorph's ability to capture both local and global image features effectively, leading to superior registration performance. The promising outcomes of this study underscore NestedMorph's potential to significantly advance deformable medical image registration, providing a robust framework for future research and clinical applications. The source code and our implementation are available at: https://github.com/AS-Lab/Marthi-et-al-2024-NestedMorph-Deformable-Medical-Image-Registration
URLs: https://github.com/AS-Lab/Marthi-et-al-2024-NestedMorph-Deformable-Medical-Image-Registration
Authors: Pengyao Qin, Arun J. Thirunavukarasu, Theodoros Arvanitis, Le Zhang
Abstract: Diabetic macular edema (DME) is a severe complication of diabetes, characterized by thickening of the central portion of the retina due to accumulation of fluid. DME is a significant and common cause of visual impairment in diabetic patients. Center-involved DME (ci-DME) is the highest risk form of disease because fluid extends close to the fovea which is responsible for sharp central vision. Earlier diagnosis or prediction of ci-DME may improve treatment outcomes. Here, we propose an ensemble method to predict ci-DME onset within a year, after using synthetic ultra-wide field color fundus photography (UWF-CFP) images provided by the DIAMOND Challenge during development. We adopted a variety of baseline state-of-the-art classification networks including ResNet, DenseNet, EfficientNet, and VGG with the aim of enhancing model robustness. The best performing models were Densenet-121, Resnet-152 and EfficientNet-b7, and these were assembled into a definitive predictive model. The final ensemble model demonstrates a strong performance with an Area Under Curve (AUC) of 0.7017, an F1 score of 0.6512, and an Expected Calibration Error (ECE) of 0.2057 when deployed on the synthetic test dataset. Results from our ensemble model were superior/comparable to previous recorded results in highly curated settings using conventional fundus photography/ultra-wide field fundus photography. Optimal sensitivity in previous studies (using humans or computers to diagnose) ranges from 67.3%-98%, specificity from 47.8%-80%. Therefore, our method can be used safely and effectively in a range of settings may facilitate earlier diagnosis, better treatment decisions, and improved prognostication in ci-DME.
Authors: Mingliang Liang, Martha Larson
Abstract: We propose Word-Frequency-based Image-Text Pair Pruning (WFPP), a novel data pruning method that improves the efficiency of VLMs. Unlike MetaCLIP, our method does not need metadata for pruning, but selects text-image pairs to prune based on the content of the text. Specifically, WFPP prunes text-image pairs containing high-frequency words across the entire training dataset. The effect of WFPP is to reduce the dominance of frequent words. The result a better balanced word-frequency distribution in the dataset, which is known to improve the training of word embedding models. After pre-training on the pruned subset, we fine-tuned the model on the entire dataset for one additional epoch to achieve better performance. Our experiments demonstrate that applying WFPP when training a CLIP model improves performance on a wide range of downstream tasks. WFPP also provides the advantage of speeding up pre-training by using fewer samples. Additionally, we analyze the training data before and after pruning to visualize how WFPP changes the balance of word frequencies. We hope our work encourages researchers to consider the distribution of words in the training data when pre-training VLMs, not limited to CLIP.
Authors: Guan Zhe Hong, Yin Cui, Ariel Fuxman, Stanley Chan, Enming Luo
Abstract: Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better generalization than pretraining with coarse-labeled data. While there is ample empirical evidence supporting this, the theoretical justification remains an open problem. This paper addresses this gap by introducing a "hierarchical multi-view" structure to confine the input data distribution. Under this framework, we prove that: 1) coarse-grained pretraining only allows a neural network to learn the common features well, while 2) fine-grained pretraining helps the network learn the rare features in addition to the common ones, leading to improved accuracy on hard downstream test samples.
Authors: Song-Jiang Lai, Tsun-Hin Cheung, Ka-Chun Fung, Kai-wen Xue, Kin-Man Lam
Abstract: In the research area of image super-resolution, Swin-transformer-based models are favored for their global spatial modeling and shifting window attention mechanism. However, existing methods often limit self-attention to non overlapping windows to cut costs and ignore the useful information that exists across channels. To address this issue, this paper introduces a novel model, the Hybrid Attention Aggregation Transformer (HAAT), designed to better leverage feature information. HAAT is constructed by integrating Swin-Dense-Residual-Connected Blocks (SDRCB) with Hybrid Grid Attention Blocks (HGAB). SDRCB expands the receptive field while maintaining a streamlined architecture, resulting in enhanced performance. HGAB incorporates channel attention, sparse attention, and window attention to improve nonlocal feature fusion and achieve more visually compelling results. Experimental evaluations demonstrate that HAAT surpasses state-of-the-art methods on benchmark datasets. Keywords: Image super-resolution, Computer vision, Attention mechanism, Transformer
Authors: Weixin Mao, Weiheng Zhong, Zhou Jiang, Dong Fang, Zhongyue Zhang, Zihan Lan, Fan Jia, Tiancai Wang, Haoqiang Fan, Osamu Yoshie
Abstract: Existing policy learning methods predominantly adopt the task-centric paradigm, necessitating the collection of task data in an end-to-end manner. Consequently, the learned policy tends to fail to tackle novel tasks. Moreover, it is hard to localize the errors for a complex task with multiple stages due to end-to-end learning. To address these challenges, we propose RoboMatrix, a skill-centric and hierarchical framework for scalable task planning and execution. We first introduce a novel skill-centric paradigm that extracts the common meta-skills from different complex tasks. This allows for the capture of embodied demonstrations through a skill-centric approach, enabling the completion of open-world tasks by combining learned meta-skills. To fully leverage meta-skills, we further develop a hierarchical framework that decouples complex robot tasks into three interconnected layers: (1) a high-level modular scheduling layer; (2) a middle-level skill layer; and (3) a low-level hardware layer. Experimental results illustrate that our skill-centric and hierarchical framework achieves remarkable generalization performance across novel objects, scenes, tasks, and embodiments. This framework offers a novel solution for robot task planning and execution in open-world scenarios. Our software and hardware are available at https://github.com/WayneMao/RoboMatrix.
Authors: Hyesu Jang, Wooseong Yang, Hanguen Kim, Dongje Lee, Yongjin Kim, Jinbum Park, Minsoo Jeon, Jaeseong Koh, Yejin Kang, Minwoo Jung, Sangwoo Jung, Ayoung Kim
Abstract: Maritime environmental sensing requires overcoming challenges from complex conditions such as harsh weather, platform perturbations, large dynamic objects, and the requirement for long detection ranges. While cameras and LiDAR are commonly used in ground vehicle navigation, their applicability in maritime settings is limited by range constraints and hardware maintenance issues. Radar sensors, however, offer robust long-range detection capabilities and resilience to physical contamination from weather and saline conditions, making it a powerful sensor for maritime navigation. Among various radar types, X-band radar (e.g., marine radar) is widely employed for maritime vessel navigation, providing effective long-range detection essential for situational awareness and collision avoidance. Nevertheless, it exhibits limitations during berthing operations where close-range object detection is critical. To address this shortcoming, we incorporate W-band radar (e.g., Navtech imaging radar), which excels in detecting nearby objects with a higher update rate. We present a comprehensive maritime sensor dataset featuring multi-range detection capabilities. This dataset integrates short-range LiDAR data, medium-range W-band radar data, and long-range X-band radar data into a unified framework. Additionally, it includes object labels for oceanic object detection usage, derived from radar and stereo camera images. The dataset comprises seven sequences collected from diverse regions with varying levels of estimation difficulty, ranging from easy to challenging, and includes common locations suitable for global localization tasks. This dataset serves as a valuable resource for advancing research in place recognition, odometry estimation, SLAM, object detection, and dynamic object elimination within maritime environments. Dataset can be found in following link: https://sites.google.com/view/rpmmoana
Authors: Zilin Wang, Shengqi Chen, Jianrong Dai, Shirui Qin, Ying Cao, Ruiao Zhao, Guohua Wu, Yuan Tang, Jiayun Chen
Abstract: Objective:To develop a no-reference image quality assessment method using automated distortion recognition to boost MRI-guided radiotherapy precision.Methods:We analyzed 106,000 MR images from 10 patients with liver metastasis,captured with the Elekta Unity MR-LINAC.Our No-Reference Quality Assessment Model includes:1)image preprocessing to enhance visibility of key diagnostic features;2)feature extraction and directional analysis using MSCN coefficients across four directions to capture textural attributes and gradients,vital for identifying image features and potential distortions;3)integrative Quality Index(QI)calculation,which integrates features via AGGD parameter estimation and K-means clustering.The QI,based on a weighted MAD computation of directional scores,provides a comprehensive image quality measure,robust against outliers.LOO-CV assessed model generalizability and performance.Tumor tracking algorithm performance was compared with and without preprocessing to verify tracking accuracy enhancements.Results:Preprocessing significantly improved image quality,with the QI showing substantial positive changes and surpassing other metrics.After normalization,the QI's average value was 79.6 times higher than CNR,indicating improved image definition and contrast.It also showed higher sensitivity in detail recognition with average values 6.5 times and 1.7 times higher than Tenengrad gradient and entropy.The tumor tracking algorithm confirmed significant tracking accuracy improvements with preprocessed images,validating preprocessing effectiveness.Conclusions:This study introduces a novel no-reference image quality evaluation method based on automated distortion recognition,offering a new quality control tool for MRIgRT tumor tracking.It enhances clinical application accuracy and facilitates medical image quality assessment standardization, with significant clinical and research value.