Authors: Nouar AlDahoul, Myles Joshua Toledo Tan, Raghava Reddy Tera, Hezerul Abdul Karim, Chee How Lim, Manish Kumar Mishra, Yasir Zaki
Abstract: License plate recognition (LPR) involves automated systems that utilize cameras and computer vision to read vehicle license plates. Such plates collected through LPR can then be compared against databases to identify stolen vehicles, uninsured drivers, crime suspects, and more. The LPR system plays a significant role in saving time for institutions such as the police force. In the past, LPR relied heavily on Optical Character Recognition (OCR), which has been widely explored to recognize characters in images. Usually, collected plate images suffer from various limitations, including noise, blurring, weather conditions, and close characters, making the recognition complex. Existing LPR methods still require significant improvement, especially for distorted images. To fill this gap, we propose utilizing visual language models (VLMs) such as OpenAI GPT4o, Google Gemini 1.5, Google PaliGemma (Pathways Language and Image model + Gemma model), Meta Llama 3.2, Anthropic Claude 3.5 Sonnet, LLaVA, NVIDIA VILA, and moondream2 to recognize such unclear plates with close characters. This paper evaluates the VLM's capability to address the aforementioned problems. Additionally, we introduce ``VehiclePaliGemma'', a fine-tuned Open-sourced PaliGemma VLM designed to recognize plates under challenging conditions. We compared our proposed VehiclePaliGemma with state-of-the-art methods and other VLMs using a dataset of Malaysian license plates collected under complex conditions. The results indicate that VehiclePaliGemma achieved superior performance with an accuracy of 87.6\%. Moreover, it is able to predict the car's plate at a speed of 7 frames per second using A100-80GB GPU. Finally, we explored the multitasking capability of VehiclePaliGemma model to accurately identify plates containing multiple cars of various models and colors, with plates positioned and oriented in different directions.
Authors: Aroj Subedi
Abstract: Camera traps have become integral tools in wildlife conservation, providing non-intrusive means to monitor and study wildlife in their natural habitats. The utilization of object detection algorithms to automate species identification from Camera Trap images is of huge importance for research and conservation purposes. However, the generalization issue, where the trained model is unable to apply its learnings to a never-before-seen dataset, is prevalent. This thesis explores the enhancements made to the YOLOv8 object detection algorithm to address the problem of generalization. The study delves into the limitations of the baseline YOLOv8 model, emphasizing its struggles with generalization in real-world environments. To overcome these limitations, enhancements are proposed, including the incorporation of a Global Attention Mechanism (GAM) module, modified multi-scale feature fusion, and Wise Intersection over Union (WIoUv3) as a bounding box regression loss function. A thorough evaluation and ablation experiments reveal the improved model's ability to suppress the background noise, focus on object properties, and exhibit robust generalization in novel environments. The proposed enhancements not only address the challenges inherent in camera trap datasets but also pave the way for broader applicability in real-world conservation scenarios, ultimately aiding in the effective management of wildlife populations and habitats.
Authors: Le-Anh Tran, Dong-Chul Park
Abstract: This paper proposes a lightweight neural network designed for realistic image dehazing, utilizing a Distilled Pooling Transformer Encoder, named DPTE-Net. Recently, while vision transformers (ViTs) have achieved great success in various vision tasks, their self-attention (SA) module's complexity scales quadratically with image resolution, hindering their applicability on resource-constrained devices. To overcome this, the proposed DPTE-Net substitutes traditional SA modules with efficient pooling mechanisms, significantly reducing computational demands while preserving ViTs' learning capabilities. To further enhance semantic feature learning, a distillation-based training process is implemented which transfers rich knowledge from a larger teacher network to DPTE-Net. Additionally, DPTE-Net is trained within a generative adversarial network (GAN) framework, leveraging the strong generalization of GAN in image restoration, and employs a transmission-aware loss function to dynamically adapt to varying haze densities. Experimental results on various benchmark datasets have shown that the proposed DPTE-Net can achieve competitive dehazing performance when compared to state-of-the-art methods while maintaining low computational complexity, making it a promising solution for resource-limited applications. The code of this work is available at https://github.com/tranleanh/dpte-net.
Authors: Eduard Hogea, Darian M. Onchis, Ana Coporan, Adina Magda Florea, Codruta Istin
Abstract: Recent advancements in Vision Transformers (ViT) have demonstrated exceptional results in various visual recognition tasks, owing to their ability to capture long-range dependencies in images through self-attention mechanisms. However, the complex nature of ViT models requires robust explainability methods to unveil their decision-making processes. Explainable Artificial Intelligence (XAI) plays a crucial role in improving model transparency and trustworthiness by providing insights into model predictions. Current approaches to ViT explainability, based on visualization techniques such as Layer-wise Relevance Propagation (LRP) and gradient-based methods, have shown promising but sometimes limited results. In this study, we explore a hybrid approach that mixes multiple explainability techniques to overcome these limitations and enhance the interpretability of ViT models. Our experiments reveal that this hybrid approach significantly improves the interpretability of ViT models compared to individual methods. We also introduce modifications to existing techniques, such as using geometric mean for mixing, which demonstrates notable results in object segmentation tasks. To quantify the explainability gain, we introduced a novel post-hoc explainability measure by applying the Pigeonhole principle. These findings underscore the importance of refining and optimizing explainability methods for ViT models, paving the way to reliable XAI-based segmentations.
Authors: Yanpeng Sun, Jing Hao, Ke Zhu, Jiang-Jiang Liu, Yuxiang Zhao, Xiaofan Li, Gang Zhang, Zechao Li, Jingdong Wang
Abstract: Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods either distill the caption from the LMM models or construct the captions from the internet images or by human. We propose to leverage off-the-shelf visual specialists, which were trained from annotated images initially not for image captioning, for enhancing the image caption. Our approach, named DCE, explores object low-level and fine-grained attributes (e.g., depth, emotion and fine-grained categories) and object relations (e.g., relative location and human-object-interaction (HOI)), and combine the attributes into the descriptive caption. Experiments demonstrate that such visual specialists are able to improve the performance for visual understanding tasks as well as reasoning that benefits from more accurate visual understanding. We will release the source code and the pipeline so that other visual specialists are easily combined into the pipeline. The complete source code of DCE pipeline and datasets will be available at \url{https://github.com/syp2ysy/DCE}.
Authors: Nikos G. Evgenidis, Nikos A. Mitsiou, Sotiris A. Tegos, Panagiotis D. Diamantoulakis, George K. Karagiannidis
Abstract: In this paper, we propose a novel approach to minimize the inference delay in semantic segmentation using split learning (SL), tailored to the needs of real-time computer vision (CV) applications for resource-constrained devices. Semantic segmentation is essential for applications such as autonomous vehicles and smart city infrastructure, but faces significant latency challenges due to high computational and communication loads. Traditional centralized processing methods are inefficient for such scenarios, often resulting in unacceptable inference delays. SL offers a promising alternative by partitioning deep neural networks (DNNs) between edge devices and a central server, enabling localized data processing and reducing the amount of data required for transmission. Our contribution includes the joint optimization of bandwidth allocation, cut layer selection of the edge devices' DNN, and the central server's processing resource allocation. We investigate both parallel and serial data processing scenarios and propose low-complexity heuristic solutions that maintain near-optimal performance while reducing computational requirements. Numerical results show that our approach effectively reduces inference delay, demonstrating the potential of SL for improving real-time CV applications in dynamic, resource-constrained environments.
Authors: Liyao Jiang, Negar Hassanpour, Mohammad Salameh, Mohammadreza Samadi, Jiao He, Fengyu Sun, Di Niu
Abstract: Recent research explores the potential of Diffusion Models (DMs) for consistent object editing, which aims to modify object position, size, and composition, etc., while preserving the consistency of objects and background without changing their texture and attributes. Current inference-time methods often rely on DDIM inversion, which inherently compromises efficiency and the achievable consistency of edited images. Recent methods also utilize energy guidance which iteratively updates the predicted noise and can drive the latents away from the original image, resulting in distortions. In this paper, we propose PixelMan, an inversion-free and training-free method for achieving consistent object editing via Pixel Manipulation and generation, where we directly create a duplicate copy of the source object at target location in the pixel space, and introduce an efficient sampling approach to iteratively harmonize the manipulated object into the target location and inpaint its original location, while ensuring image consistency by anchoring the edited image to be generated to the pixel-manipulated image as well as by introducing various consistency-preserving optimization techniques during inference. Experimental evaluations based on benchmark datasets as well as extensive visual comparisons show that in as few as 16 inference steps, PixelMan outperforms a range of state-of-the-art training-based and training-free methods (usually requiring 50 steps) on multiple consistent object editing tasks.
Authors: Viorica P\u{a}tr\u{a}ucean, Xu Owen He, Joseph Heyward, Chuhan Zhang, Mehdi S. M. Sajjadi, George-Cristian Muraru, Artem Zholus, Mahdi Karami, Ross Goroshin, Yutian Chen, Simon Osindero, Jo\~ao Carreira, Razvan Pascanu
Abstract: We propose a novel block for video modelling. It relies on a time-space-channel factorisation with dedicated blocks for each dimension: gated linear recurrent units (LRUs) perform information mixing over time, self-attention layers perform mixing over space, and MLPs over channels. The resulting architecture TRecViT performs well on sparse and dense tasks, trained in supervised or self-supervised regimes. Notably, our model is causal and outperforms or is on par with a pure attention model ViViT-L on large scale video datasets (SSv2, Kinetics400), while having $3\times$ less parameters, $12\times$ smaller memory footprint, and $5\times$ lower FLOPs count. Code and checkpoints will be made available online at https://github.com/google-deepmind/trecvit.
Authors: Anna Manasyan, Maximilian Seitzer, Filip Radovic, Georg Martius, Andrii Zadaianchuk
Abstract: Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be both compositional and temporally consistent. Existing approaches based on recurrent processing often lack long-term stability across frames because their training objective does not enforce temporal consistency. In this work, we introduce a novel object-level temporal contrastive loss for video object-centric models that explicitly promotes temporal consistency. Our method significantly improves the temporal consistency of the learned object-centric representations, yielding more reliable video decompositions that facilitate challenging downstream tasks such as unsupervised object dynamics prediction. Furthermore, the inductive bias added by our loss strongly improves object discovery, leading to state-of-the-art results on both synthetic and real-world datasets, outperforming even weakly-supervised methods that leverage motion masks as additional cues.
Authors: Jing Wang, Wonho Bae, Jiahong Chen, Kuangen Zhang, Leonid Sigal, Clarence W. de Silva
Abstract: Source-free domain adaptation (SFDA) involves adapting a model originally trained using a labeled dataset ({\em source domain}) to perform effectively on an unlabeled dataset ({\em target domain}) without relying on any source data during adaptation. This adaptation is especially crucial when significant disparities in data distributions exist between the two domains and when there are privacy concerns regarding the source model's training data. The absence of access to source data during adaptation makes it challenging to analytically estimate the domain gap. To tackle this issue, various techniques have been proposed, such as unsupervised clustering, contrastive learning, and continual learning. In this paper, we first conduct an extensive theoretical analysis of SFDA based on contrastive learning, primarily because it has demonstrated superior performance compared to other techniques. Motivated by the obtained insights, we then introduce a straightforward yet highly effective latent augmentation method tailored for contrastive SFDA. This augmentation method leverages the dispersion of latent features within the neighborhood of the query sample, guided by the source pre-trained model, to enhance the informativeness of positive keys. Our approach, based on a single InfoNCE-based contrastive loss, outperforms state-of-the-art SFDA methods on widely recognized benchmark datasets.
Authors: Xijun Wang, Prateek Chennuri, Yu Yuan, Bole Ma, Xingguang Zhang, Stanley Chan
Abstract: While smartphone cameras today can produce astonishingly good photos, their performance in low light is still not completely satisfactory because of the fundamental limits in photon shot noise and sensor read noise. Generative image restoration methods have demonstrated promising results compared to traditional methods, but they suffer from hallucinatory content generation when the signal-to-noise ratio (SNR) is low. Recognizing the availability of personalized photo galleries on users' smartphones, we propose Personalized Generative Denoising (PGD) by building a diffusion model customized for different users. Our core innovation is an identity-consistent physical buffer that extracts the physical attributes of the person from the gallery. This ID-consistent physical buffer provides a strong prior that can be integrated with the diffusion model to restore the degraded images, without the need of fine-tuning. Over a wide range of low-light testing scenarios, we show that PGD achieves superior image denoising and enhancement performance compared to existing diffusion-based denoising approaches.
Authors: Steven Hogue, Chenxu Zhang, Yapeng Tian, Xiaohu Guo
Abstract: Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common latent space. Our experiments demonstrate that the proposed framework not only maintains state-of-the-art co-speech gesture and talking head generation performance but also significantly reduces the number of parameters required.
Authors: Sanghyoup Gu, Ratnesh Kumar
Abstract: Traditional Visual Simultaneous Localization and Mapping (VSLAM) systems assume a static environment, which makes them ineffective in highly dynamic settings. To overcome this, many approaches integrate semantic information from deep learning models to identify dynamic regions within images. However, these methods face a significant limitation as a supervised model cannot recognize objects not included in the training datasets. This paper introduces a novel feature-based Semantic VSLAM capable of detecting dynamic features in the presence of both known and unknown objects. By employing an unsupervised segmentation network, we achieve unlabeled segmentation, and next utilize an objector detector to identify any of the known classes among those. We then pair this with the computed high-gradient optical-flow information to next identify the static versus dynamic segmentations for both known and unknown object classes. A consistency check module is also introduced for further refinement and final classification into static versus dynamic features. Evaluations using public datasets demonstrate that our method offers superior performance than traditional VSLAM when unknown objects are present in the images while still matching the performance of the leading semantic VSLAM techniques when the images contain only the known objects
Authors: Elif Ayten, Shuai Wang, Hjalmar Snoep
Abstract: Recent advances in generative AI make it convenient to create different types of content, including text, images, and code. In this paper, we explore the generation of images in the style of paintings in the surrealism movement using vision-language generative models, including DALL-E, Deep Dream Generator, and DreamStudio. Our investigation starts with the generation of images under various image generation settings and different models. The primary objective is to identify the most suitable model and settings for producing such images. Additionally, we aim to understand the impact of using edited base images on the generated resulting images. Through these experiments, we evaluate the performance of selected models and gain valuable insights into their capabilities in generating such images. Our analysis shows that Dall-E 2 performs the best when using the generated prompt by ChatGPT.
Authors: Arthur Josi, Luiz Gustavo Hafemann, Abdallah Dib, Emeline Got, Rafael M. O. Cruz, Marc-Andre Carbonneau
Abstract: Monocular facial performance capture in-the-wild is challenging due to varied capture conditions, face shapes, and expressions. Most current methods rely on linear 3D Morphable Models, which represent facial expressions independently of identity at the vertex displacement level. We propose SEREP (Semantic Expression Representation), a model that disentangles expression from identity at the semantic level. It first learns an expression representation from unpaired 3D facial expressions using a cycle consistency loss. Then we train a model to predict expression from monocular images using a novel semi-supervised scheme that relies on domain adaptation. In addition, we introduce MultiREX, a benchmark addressing the lack of evaluation resources for the expression capture task. Our experiments show that SEREP outperforms state-of-the-art methods, capturing challenging expressions and transferring them to novel identities.
Authors: Phuc D. A. Nguyen
Abstract: Oriented object detection in aerial images poses a significant challenge due to their varying sizes and orientations. Current state-of-the-art detectors typically rely on either two-stage or one-stage approaches, often employing Anchor-based strategies, which can result in computationally expensive operations due to the redundant number of generated anchors during training. In contrast, Anchor-free mechanisms offer faster processing but suffer from a reduction in the number of training samples, potentially impacting detection accuracy. To address these limitations, we propose the Hybrid-Anchor Rotation Detector (HA-RDet), which combines the advantages of both anchor-based and anchor-free schemes for oriented object detection. By utilizing only one preset anchor for each location on the feature maps and refining these anchors with our Orientation-Aware Convolution technique, HA-RDet achieves competitive accuracies, including 75.41 mAP on DOTA-v1, 65.3 mAP on DIOR-R, and 90.2 mAP on HRSC2016, against current anchor-based state-of-the-art methods, while significantly reducing computational resources.
Authors: Temirlan Meiramkhanov, Arailym Tleubayeva
Abstract: Fingerprint recognition systems stand as pillars in the realm of biometric authentication, providing indispensable security measures across various domains. This study investigates integrating Convolutional Neural Networks (CNNs) with Gabor filters to improve fingerprint recognition accuracy and robustness. Leveraging a diverse dataset sourced from the Sokoto Coventry Fingerprint Dataset, our experiments meticulously evaluate the efficacy of different classification algorithms. Our findings underscore the supremacy of CNN-based approaches, boasting an impressive overall accuracy of 94\%. Furthermore, the amalgamation of Gabor filters with CNN architectures unveils promising strides in discerning altered fingerprints, illuminating new pathways for enhancing biometric authentication systems. While the CNN-Gabor fusion showcases commendable performance, our exploration of hybrid approaches combining multiple classifiers reveals nuanced outcomes. Despite these mixed results, our study illuminates the transformative potential of deep learning methodologies in reshaping the landscape of fingerprint recognition. Through rigorous experimentation and insightful analysis, this research not only contributes to advancing biometric authentication technologies but also sheds light on the intricate interplay between traditional feature extraction methods and cutting-edge deep learning architectures. These findings offer actionable insights for optimizing fingerprint recognition systems for real-world deployment, paving the way for enhanced security and reliability in diverse applications.
Authors: Xijun Liu, Yifan Zhou, Yuxiang Guo, Rama Chellappa, Cheng Peng
Abstract: Significant progress has been made in photo-realistic scene reconstruction over recent years. Various disparate efforts have enabled capabilities such as multi-appearance or large-scale modeling; however, there lacks a welldesigned dataset that can evaluate the holistic progress of scene reconstruction. We introduce a collection of imagery of the Johns Hopkins Homewood Campus, acquired at different seasons, times of day, in multiple elevations, and across a large scale. We perform a multi-stage calibration process, which efficiently recover camera parameters from phone and drone cameras. This dataset can enable researchers to rigorously explore challenges in unconstrained settings, including effects of inconsistent illumination, reconstruction from large scale and from significantly different perspectives, etc.
Authors: Jaineet Shah, Michael Gromis, Rickston Pinto
Abstract: This report presents the comprehensive implementation, evaluation, and optimization of Denoising Diffusion Probabilistic Models (DDPMs) and Denoising Diffusion Implicit Models (DDIMs), which are state-of-the-art generative models. During inference, these models take random noise as input and iteratively generate high-quality images as output. The study focuses on enhancing their generative capabilities by incorporating advanced techniques such as Classifier-Free Guidance (CFG), Latent Diffusion Models with Variational Autoencoders (VAE), and alternative noise scheduling strategies. The motivation behind this work is the growing demand for efficient and scalable generative AI models that can produce realistic images across diverse datasets, addressing challenges in applications such as art creation, image synthesis, and data augmentation. Evaluations were conducted on datasets including CIFAR-10 and ImageNet-100, with a focus on improving inference speed, computational efficiency, and image quality metrics like Frechet Inception Distance (FID). Results demonstrate that DDIM + CFG achieves faster inference and superior image quality. Challenges with VAE and noise scheduling are also highlighted, suggesting opportunities for future optimization. This work lays the groundwork for developing scalable, efficient, and high-quality generative AI systems to benefit industries ranging from entertainment to robotics.
Authors: Pramit Saha, Divyanshu Mishra, Felix Wagner, Konstantinos Kamnitsas, J. Alison Noble
Abstract: Large Vision-Language Models typically require large text and image datasets for effective fine-tuning. However, collecting data from various sites, especially in healthcare, is challenging due to strict privacy regulations. An alternative is to fine-tune these models on end-user devices, such as in medical clinics, without sending data to a server. These local clients typically have limited computing power and small datasets, which are not enough for fully fine-tuning large VLMs on their own. A naive solution to these scenarios is to leverage parameter-efficient fine-tuning (PEFT) strategies and apply federated learning (FL) algorithms to combine the learned adapter weights, thereby respecting the resource limitations and data privacy. However, this approach does not fully leverage the knowledge from multiple adapters trained on diverse data distributions and for diverse tasks. The adapters are adversely impacted by data heterogeneity and task heterogeneity across clients resulting in suboptimal convergence. To this end, we propose a novel framework called FedPIA that improves upon the naive combinations of FL and PEFT by introducing Permutation and Integration of the local Adapters in the server and global Adapters in the clients exploiting Wasserstein barycenters for improved blending of client-specific and client-agnostic knowledge. This layerwise permutation helps to bridge the gap in the parameter space of local and global adapters before integration. We conduct over 2000 client-level experiments utilizing 48 medical image datasets across five different medical vision-language FL task settings encompassing visual question answering as well as image and report-based multi-label disease detection. Our experiments involving diverse client settings, ten different modalities, and two VLM backbones demonstrate that FedPIA consistently outperforms the state-of-the-art PEFT-FL baselines.
Authors: Rangel Daroya, Elijah Cole, Oisin Mac Aodha, Grant Van Horn, Subhransu Maji
Abstract: What does the presence of a species reveal about a geographic location? We posit that habitat, climate, and environmental preferences reflected in species distributions provide a rich source of supervision for learning satellite image representations. We introduce WildSAT, which pairs satellite images with millions of geo-tagged wildlife observations readily-available on citizen science platforms. WildSAT uses a contrastive learning framework to combine information from species distribution maps with text descriptions that capture habitat and range details, alongside satellite images, to train or fine-tune models. On a range of downstream satellite image recognition tasks, this significantly improves the performance of both randomly initialized models and pre-trained models from sources like ImageNet or specialized satellite image datasets. Additionally, the alignment with text enables zero-shot retrieval, allowing for search based on general descriptions of locations. We demonstrate that WildSAT achieves better representations than recent methods that utilize other forms of cross-modal supervision, such as aligning satellite images with ground images or wildlife photos. Finally, we analyze the impact of various design choices on downstream performance, highlighting the general applicability of our approach.
Authors: Anand Kumar, Jiteng Mu, Nuno Vasconcelos
Abstract: Text-to-image (T2I) models have gained widespread adoption among content creators and the general public. However, this has sparked significant concerns regarding data privacy and copyright infringement among artists. Consequently, there is an increasing demand for T2I models to incorporate mechanisms that prevent the generation of specific artistic styles, thereby safeguarding intellectual property rights. Existing methods for style extraction typically necessitate the collection of custom datasets and the training of specialized models. This, however, is resource-intensive, time-consuming, and often impractical for real-time applications. Moreover, it may not adequately address the dynamic nature of artistic styles and the rapidly evolving landscape of digital art. We present a novel, training-free framework to solve the style attribution problem, using the features produced by a diffusion model alone, without any external modules or retraining. This is denoted as introspective style attribution (IntroStyle) and demonstrates superior performance to state-of-the-art models for style retrieval. We also introduce a synthetic dataset of Style Hacks (SHacks) to isolate artistic style and evaluate fine-grained style attribution performance.
Authors: Muhammad Usama Saleem, Ekkasit Pinyoanuntapong, Pu Wang, Hongfei Xue, Srijan Das, Chen Chen
Abstract: Human mesh recovery (HMR) is crucial in many computer vision applications; from health to arts and entertainment. HMR from monocular images has predominantly been addressed by deterministic methods that output a single prediction for a given 2D image. However, HMR from a single image is an ill-posed problem due to depth ambiguity and occlusions. Probabilistic methods have attempted to address this by generating and fusing multiple plausible 3D reconstructions, but their performance has often lagged behind deterministic approaches. In this paper, we introduce GenHMR, a novel generative framework that reformulates monocular HMR as an image-conditioned generative task, explicitly modeling and mitigating uncertainties in the 2D-to-3D mapping process. GenHMR comprises two key components: (1) a pose tokenizer to convert 3D human poses into a sequence of discrete tokens in a latent space, and (2) an image-conditional masked transformer to learn the probabilistic distributions of the pose tokens, conditioned on the input image prompt along with randomly masked token sequence. During inference, the model samples from the learned conditional distribution to iteratively decode high-confidence pose tokens, thereby reducing 3D reconstruction uncertainties. To further refine the reconstruction, a 2D pose-guided refinement technique is proposed to directly fine-tune the decoded pose tokens in the latent space, which forces the projected 3D body mesh to align with the 2D pose clues. Experiments on benchmark datasets demonstrate that GenHMR significantly outperforms state-of-the-art methods. Project website can be found at https://m-usamasaleem.github.io/publication/GenHMR/GenHMR.html
URLs: https://m-usamasaleem.github.io/publication/GenHMR/GenHMR.html
Authors: Yi Xu, Yuxin Hu, Zaiwei Zhang, Gregory P. Meyer, Siva Karthik Mustikovela, Siddhartha Srinivasa, Eric M. Wolff, Xin Huang
Abstract: Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing the underlying reasoning processes. This limitation constrains their ability to handle challenging driving scenarios. To close this gap, we propose VLM-AD, a method that leverages vision-language models (VLMs) as teachers to enhance training by providing additional supervision that incorporates unstructured reasoning information and structured action labels. Such supervision enhances the model's ability to learn richer feature representations that capture the rationale behind driving patterns. Importantly, our method does not require a VLM during inference, making it practical for real-time deployment. When integrated with state-of-the-art methods, VLM-AD achieves significant improvements in planning accuracy and reduced collision rates on the nuScenes dataset.
Authors: Jingwei Bao, Yu Liu, Zeliang Li, Shuyuan Zhu, Siu-Kei Au Yeung
Abstract: Video-based point cloud compression (V-PCC) converts the dynamic point cloud data into video sequences using traditional video codecs for efficient encoding. However, this lossy compression scheme introduces artifacts that degrade the color attributes of the data. This paper introduces a framework designed to enhance the color quality in the V-PCC compressed point clouds. We propose the lightweight de-compression Unet (LDC-Unet), a 2D neural network, to optimize the projection maps generated during V-PCC encoding. The optimized 2D maps will then be back-projected to the 3D space to enhance the corresponding point cloud attributes. Additionally, we introduce a transfer learning strategy and develop a customized natural image dataset for the initial training. The model was then fine-tuned using the projection maps of the compressed point clouds. The whole strategy effectively addresses the scarcity of point cloud training data. Our experiments, conducted on the public 8i voxelized full bodies long sequences (8iVSLF) dataset, demonstrate the effectiveness of our proposed method in improving the color quality.
Authors: Shengqi Liu, Yuhao Cheng, Zhuo Chen, Xingyu Ren, Wenhan Zhu, Lincheng Li, Mengxiao Bi, Xiaokang Yang, Yichao Yan
Abstract: Generating sewing patterns in garment design is receiving increasing attention due to its CG-friendly and flexible-editing nature. Previous sewing pattern generation methods have been able to produce exquisite clothing, but struggle to design complex garments with detailed control. To address these issues, we propose SewingLDM, a multi-modal generative model that generates sewing patterns controlled by text prompts, body shapes, and garment sketches. Initially, we extend the original vector of sewing patterns into a more comprehensive representation to cover more intricate details and then compress them into a compact latent space. To learn the sewing pattern distribution in the latent space, we design a two-step training strategy to inject the multi-modal conditions, \ie, body shapes, text prompts, and garment sketches, into a diffusion model, ensuring the generated garments are body-suited and detail-controlled. Comprehensive qualitative and quantitative experiments show the effectiveness of our proposed method, significantly surpassing previous approaches in terms of complex garment design and various body adaptability. Our project page: https://shengqiliu1.github.io/SewingLDM.
Authors: Chao Wang, Zhihao Xia, Thomas Leimkuehler, Karol Myszkowski, Xuaner Zhang
Abstract: While consumer displays increasingly support more than 10 stops of dynamic range, most image assets such as internet photographs and generative AI content remain limited to 8-bit low dynamic range (LDR), constraining their utility across high dynamic range (HDR) applications. Currently, no generative model can produce high-bit, high-dynamic range content in a generalizable way. Existing LDR-to-HDR conversion methods often struggle to produce photorealistic details and physically-plausible dynamic range in the clipped areas. We introduce LEDiff, a method that enables a generative model with HDR content generation through latent space fusion inspired by image-space exposure fusion techniques. It also functions as an LDR-to-HDR converter, expanding the dynamic range of existing low-dynamic range images. Our approach uses a small HDR dataset to enable a pretrained diffusion model to recover detail and dynamic range in clipped highlights and shadows. LEDiff brings HDR capabilities to existing generative models and converts any LDR image to HDR, creating photorealistic HDR outputs for image generation, image-based lighting (HDR environment map generation), and photographic effects such as depth of field simulation, where linear HDR data is essential for realistic quality.
Authors: Jixuan He, Wanhua Li, Ye Liu, Junsik Kim, Donglai Wei, Hanspeter Pfister
Abstract: As a common image editing operation, image composition involves integrating foreground objects into background scenes. In this paper, we expand the application of the concept of Affordance from human-centered image composition tasks to a more general object-scene composition framework, addressing the complex interplay between foreground objects and background scenes. Following the principle of Affordance, we define the affordance-aware object insertion task, which aims to seamlessly insert any object into any scene with various position prompts. To address the limited data issue and incorporate this task, we constructed the SAM-FB dataset, which contains over 3 million examples across more than 3,000 object categories. Furthermore, we propose the Mask-Aware Dual Diffusion (MADD) model, which utilizes a dual-stream architecture to simultaneously denoise the RGB image and the insertion mask. By explicitly modeling the insertion mask in the diffusion process, MADD effectively facilitates the notion of affordance. Extensive experimental results show that our method outperforms the state-of-the-art methods and exhibits strong generalization performance on in-the-wild images. Please refer to our code on https://github.com/KaKituken/affordance-aware-any.
Authors: Tung Do, Thuan Hoang Nguyen, Anh Tuan Tran, Rang Nguyen, Binh-Son Hua
Abstract: We propose a new view synthesis method via synthesizing a 3D neural field from both single or few-view input images. To address the ill-posed nature of the image-to-3D generation problem, we devise a two-stage method that involves a reconstruction model and a diffusion model for view synthesis. Our reconstruction model first lifts one or more input images to the 3D space from a volume as the coarse-scale 3D representation followed by a tri-plane as the fine-scale 3D representation. To mitigate the ambiguity in occluded regions, our diffusion model then hallucinates missing details in the rendered images from tri-planes. We then introduce a new progressive refinement technique that iteratively applies the reconstruction and diffusion model to gradually synthesize novel views, boosting the overall quality of the 3D representations and their rendering. Empirical evaluation demonstrates the superiority of our method over state-of-the-art methods on the synthetic SRN-Car dataset, the in-the-wild CO3D dataset, and large-scale Objaverse dataset while achieving both sampling efficacy and multi-view consistency.
Authors: Wengyi Zhan, Mingbao Lin, Shuicheng Yan, Rongrong Ji
Abstract: We introduce DiffusionTrend for virtual fashion try-on, which forgoes the need for retraining diffusion models. Using advanced diffusion models, DiffusionTrend harnesses latent information rich in prior information to capture the nuances of garment details. Throughout the diffusion denoising process, these details are seamlessly integrated into the model image generation, expertly directed by a precise garment mask crafted by a lightweight and compact CNN. Although our DiffusionTrend model initially demonstrates suboptimal metric performance, our exploratory approach offers some important advantages: (1) It circumvents resource-intensive retraining of diffusion models on large datasets. (2) It eliminates the necessity for various complex and user-unfriendly model inputs. (3) It delivers a visually compelling try-on experience, underscoring the potential of training-free diffusion model. This initial foray into the application of untrained diffusion models in virtual try-on technology potentially paves the way for further exploration and refinement in this industrially and academically valuable field.
Authors: Kunming Tang, Zhiguo Jiang, Jun Shi, Wei Wang, Haibo Wu, Yushan Zheng
Abstract: Gigapixel image analysis, particularly for whole slide images (WSIs), often relies on multiple instance learning (MIL). Under the paradigm of MIL, patch image representations are extracted and then fixed during the training of the MIL classifiers for efficiency consideration. However, the invariance of representations makes it difficult to perform data augmentation for WSI-level model training, which significantly limits the performance of the downstream WSI analysis. The current data augmentation methods for gigapixel images either introduce additional computational costs or result in a loss of semantic information, which is hard to meet the requirements for efficiency and stability needed for WSI model training. In this paper, we propose a Promptable Representation Distribution Learning framework (PRDL) for both patch-level representation learning and WSI-level data augmentation. Meanwhile, we explore the use of prompts to guide data augmentation in feature space, which achieves promptable data augmentation for training robust WSI-level models. The experimental results have demonstrated that the proposed method stably outperforms state-of-the-art methods.
Authors: Junjie Zhou, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian, Yongping Xiong
Abstract: Despite the rapidly growing demand for multimodal retrieval, progress in this field remains severely constrained by a lack of training data. In this paper, we introduce MegaPairs, a novel data synthesis method that leverages vision language models (VLMs) and open-domain images, together with a massive synthetic dataset generated from this method. Our empirical analysis shows that MegaPairs generates high-quality data, enabling the multimodal retriever to significantly outperform the baseline model trained on 70$\times$ more data from existing datasets. Moreover, since MegaPairs solely relies on general image corpora and open-source VLMs, it can be easily scaled up, enabling continuous improvements in retrieval performance. In this stage, we produced more than 26 million training instances and trained several models of varying sizes using this data. These new models achieve state-of-the-art zero-shot performance across 4 popular composed image retrieval (CIR) benchmarks and the highest overall performance on the 36 datasets provided by MMEB. They also demonstrate notable performance improvements with additional downstream fine-tuning. Our produced dataset, well-trained models, and data synthesis pipeline will be made publicly available to facilitate the future development of this field.
Authors: Kunpeng Song, Tingbo Hou, Zecheng He, Haoyu Ma, Jialiang Wang, Animesh Sinha, Sam Tsai, Yaqiao Luo, Xiaoliang Dai, Li Chen, Xide Xia, Peizhao Zhang, Peter Vajda, Ahmed Elgammal, Felix Juefei-Xu
Abstract: In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-video models rapidly evolve, the demand for high-quality human motion and interaction grows. To address this need and enhance the authenticity of human motions, we extend the LLM from a text generator to a video director and human motion simulator. Utilizing open-source resources from Llama 3, we train the DirectorLLM to generate detailed instructional signals, such as human poses, to guide video generation. This approach offloads the simulation of human motion from the video generator to the LLM, effectively creating informative outlines for human-centric scenes. These signals are used as conditions by the video renderer, facilitating more realistic and prompt-following video generation. As an independent LLM module, it can be applied to different video renderers, including UNet and DiT, with minimal effort. Experiments on automatic evaluation benchmarks and human evaluations show that our model outperforms existing ones in generating videos with higher human motion fidelity, improved prompt faithfulness, and enhanced rendered subject naturalness.
Authors: Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Yancheng He, Shilong Li, Bo Zheng
Abstract: Direct Preference Optimization (DPO) has been demonstrated to be highly effective in mitigating hallucinations in Large Vision Language Models (LVLMs) by aligning their outputs more closely with human preferences. Despite the recent progress, existing methods suffer from two drawbacks: 1) Lack of scalable token-level rewards; and 2) Neglect of visual-anchored tokens. To this end, we propose a novel Token Preference Optimization model with self-calibrated rewards (dubbed as TPO), which adaptively attends to visual-correlated tokens without fine-grained annotations. Specifically, we introduce a token-level \emph{visual-anchored} \emph{reward} as the difference of the logistic distributions of generated tokens conditioned on the raw image and the corrupted one. In addition, to highlight the informative visual-anchored tokens, a visual-aware training objective is proposed to enhance more accurate token-level optimization. Extensive experimental results have manifested the state-of-the-art performance of the proposed TPO. For example, by building on top of LLAVA-1.5-7B, our TPO boosts the performance absolute improvement for hallucination benchmarks.
Authors: Shu Shen, Tong Zhang, C. L. Philip Chen
Abstract: Integrating complementary information from different data modalities can yield representation with stronger expressive ability. However, data quality varies across multimodal samples, highlighting the need for learning reliable multimodal representations, especially in safety-critical applications. This paper focuses on an aspect that existing methods in this domain commonly overlook: the importance of network dynamics and adaptability in providing reliable results from diverse samples. Specifically, it highlights the model's ability to dynamically adjust its capacity and behaviour according to different samples, using the adjusted network for predicting each sample. To this end, we propose a novel framework for multimodal reliable classification termed Quality-adaptive Dynamic Multimodal Network (QADM-Net). QADM-Net first introduces a confidence-guided dynamic depths mechanism to achieve the appropriate network capacity. This mechanism adjusts the network depth according to the difficulty of each sample, which is determined by the quality of its modalities. Subsequently, we develop an informativeness-based dynamic parameters mechanism that enables QADM-Net to perform unique inference behaviour on each of the diverse samples with feature-level quality variation presented in their feature vectors. In this way, QADM-Net adequately adapts its capacity and behaviour on each sample by investigating the quality variation of samples at both modality and feature levels, thus enhancing the reliability of classification results. Experiments conducted on four datasets demonstrate that QADM-Net significantly outperforms state-of-the-art methods in classification performance and exhibits strong adaptability to data with diverse quality.
Authors: Chuang Lin, Bingbing Zhuang, Shanlin Sun, Ziyu Jiang, Jianfei Cai, Manmohan Chandraker
Abstract: The recent advent of large-scale 3D data, e.g. Objaverse, has led to impressive progress in training pose-conditioned diffusion models for novel view synthesis. However, due to the synthetic nature of such 3D data, their performance drops significantly when applied to real-world images. This paper consolidates a set of good practices to finetune large pretrained models for a real-world task -- harvesting vehicle assets for autonomous driving applications. To this end, we delve into the discrepancies between the synthetic data and real driving data, then develop several strategies to account for them properly. Specifically, we start with a virtual camera rotation of real images to ensure geometric alignment with synthetic data and consistency with the pose manifold defined by pretrained models. We also identify important design choices in object-centric data curation to account for varying object distances in real driving scenes -- learn across varying object scales with fixed camera focal length. Further, we perform occlusion-aware training in latent spaces to account for ubiquitous occlusions in real data, and handle large viewpoint changes by leveraging a symmetric prior. Our insights lead to effective finetuning that results in a $68.8\%$ reduction in FID for novel view synthesis over prior arts.
Authors: Ma Zhuoqi, Zhang Yixuan, You Zejun, Tian Long, Liu Xiyang
Abstract: Controllable artistic image stylization and generation aims to render the content provided by text or image with the learned artistic style, where content and style decoupling is the key to achieve satisfactory results. However, current methods for content and style disentanglement primarily rely on image information for supervision, which leads to two problems: 1) models can only support one modality for style or content input;2) incomplete disentanglement resulting in semantic interference from the reference image. To address the above issues, this paper proposes a content-style representation disentangling method for controllable artistic image stylization and generation. We construct a WikiStyle+ dataset consists of artworks with corresponding textual descriptions for style and content. Based on the multimodal dataset, we propose a disentangled content and style representations guided diffusion model. The disentangled representations are first learned by Q-Formers and then injected into a pre-trained diffusion model using learnable multi-step cross-attention layers for better controllable stylization. This approach allows model to accommodate inputs from different modalities. Experimental results show that our method achieves a thorough disentanglement of content and style in reference images under multimodal supervision, thereby enabling a harmonious integration of content and style in the generated outputs, successfully producing style-consistent and expressive stylized images.
Authors: Shizhan Gong, Jingwei Zhang, Qi Dou, Farzan Farnia
Abstract: Saliency maps are widely used in the computer vision community for interpreting neural network classifiers. However, due to the randomness of training samples and optimization algorithms, the resulting saliency maps suffer from a significant level of stochasticity, making it difficult for domain experts to capture the intrinsic factors that influence the neural network's decision. In this work, we propose a novel pixel partitioning strategy to boost the stability and generalizability of gradient-based saliency maps. Through both theoretical analysis and numerical experiments, we demonstrate that the grouping of pixels reduces the variance of the saliency map and improves the generalization behavior of the interpretation method. Furthermore, we propose a sensible grouping strategy based on super-pixels which cluster pixels into groups that align well with the semantic meaning of the images. We perform several numerical experiments on CIFAR-10 and ImageNet. Our empirical results suggest that the super-pixel-based interpretation maps consistently improve the stability and quality over the pixel-based saliency maps.
Authors: Jinpeng Wang, Niu Lian, Jun Li, Yuting Wang, Yan Feng, Bin Chen, Yongbing Zhang, Shu-Tao Xia
Abstract: Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory inefficiencies. Drawing inspiration from Mamba, an advanced state-space model, we explore its potential in SSVH to achieve a better balance between efficacy and efficiency. We introduce S5VH, a Mamba-based video hashing model with an improved self-supervised learning paradigm. Specifically, we design bidirectional Mamba layers for both the encoder and decoder, which are effective and efficient in capturing temporal relationships thanks to the data-dependent selective scanning mechanism with linear complexity. In our learning strategy, we transform global semantics in the feature space into semantically consistent and discriminative hash centers, followed by a center alignment loss as a global learning signal. Our self-local-global (SLG) paradigm significantly improves learning efficiency, leading to faster and better convergence. Extensive experiments demonstrate S5VH's improvements over state-of-the-art methods, superior transferability, and scalable advantages in inference efficiency. Code is available at https://github.com/gimpong/AAAI25-S5VH.
Authors: Mingdeng Cao, Chong Mou, Ziyang Yuan, Xintao Wang, Zhaoyang Zhang, Ying Shan, Yinqiang Zheng
Abstract: Consistent human-centric image and video synthesis aims to generate images or videos with new poses while preserving appearance consistency with a given reference image, which is crucial for low-cost visual content creation. Recent advances based on diffusion models typically rely on separate networks for reference appearance feature extraction and target visual generation, leading to inconsistent domain gaps between references and targets. In this paper, we frame the task as a spatially-conditioned inpainting problem, where the target image is inpainted to maintain appearance consistency with the reference. This approach enables the reference features to guide the generation of pose-compliant targets within a unified denoising network, thereby mitigating domain gaps. Additionally, to better maintain the reference appearance information, we impose a causal feature interaction framework, in which reference features can only query from themselves, while target features can query appearance information from both the reference and the target. To further enhance computational efficiency and flexibility, in practical implementation, we decompose the spatially-conditioned generation process into two stages: reference appearance extraction and conditioned target generation. Both stages share a single denoising network, with interactions restricted to self-attention layers. This proposed method ensures flexible control over the appearance of generated human images and videos. By fine-tuning existing base diffusion models on human video data, our method demonstrates strong generalization to unseen human identities and poses without requiring additional per-instance fine-tuning. Experimental results validate the effectiveness of our approach, showing competitive performance compared to existing methods for consistent human image and video synthesis.
Authors: Xiaofei Huang, Wenting Chen, Jie Liu, Qisheng Lu, Xiaoling Luo, Linlin Shen
Abstract: Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics.
Authors: Kamorudeen A. Amuda, Almustapha A. Wakili
Abstract: This study introduces a federated learning-based approach to predict HER2 status from hematoxylin and eosin (HE)-stained whole slide images (WSIs), reducing costs and speeding up treatment decisions. To address label imbalance and feature representation challenges in multisite datasets, a point transformer is proposed, incorporating dynamic label distribution, an auxiliary classifier, and farthest cosine sampling. Extensive experiments demonstrate state-of-the-art performance across four sites (2687 WSIs) and strong generalization to two unseen sites (229 WSIs).
Authors: Gui Wang, Yuexiang Li, Wenting Chen, Meidan Ding, Wooi Ping Cheah, Rong Qu, Jianfeng Ren, Linlin Shen
Abstract: Small lesions play a critical role in early disease diagnosis and intervention of severe infections. Popular models often face challenges in segmenting small lesions, as it occupies only a minor portion of an image, while down\_sampling operations may inevitably lose focus on local features of small lesions. To tackle the challenges, we propose a {\bf S}mall-{\bf S}ize-{\bf S}ensitive {\bf Mamba} ({\bf S$^3$-Mamba}), which promotes the sensitivity to small lesions across three dimensions: channel, spatial, and training strategy. Specifically, an Enhanced Visual State Space block is designed to focus on small lesions through multiple residual connections to preserve local features, and selectively amplify important details while suppressing irrelevant ones through channel-wise attention. A Tensor-based Cross-feature Multi-scale Attention is designed to integrate input image features and intermediate-layer features with edge features and exploit the attentive support of features across multiple scales, thereby retaining spatial details of small lesions at various granularities. Finally, we introduce a novel regularized curriculum learning to automatically assess lesion size and sample difficulty, and gradually focus from easy samples to hard ones like small lesions. Extensive experiments on three medical image segmentation datasets show the superiority of our S$^3$-Mamba, especially in segmenting small lesions. Our code is available at https://github.com/ErinWang2023/S3-Mamba.
Authors: Min Wang, Xin Huang, Guoqing Zhou, Qifeng Guo, Qing Wang
Abstract: Neural Radiance Fields (NeRFs) have demonstrated prominent performance in novel view synthesis. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene representation in low-light environments where images typically exhibit significant noise and severe color distortion. To address these challenges, we propose a novel approach, Bright-NeRF, which learns enhanced and high-quality radiance fields from multi-view low-light raw images in an unsupervised manner. Our method simultaneously achieves color restoration, denoising, and enhanced novel view synthesis. Specifically, we leverage a physically-inspired model of the sensor's response to illumination and introduce a chromatic adaptation loss to constrain the learning of response, enabling consistent color perception of objects regardless of lighting conditions. We further utilize the raw data's properties to expose the scene's intensity automatically. Additionally, we have collected a multi-view low-light raw image dataset to advance research in this field. Experimental results demonstrate that our proposed method significantly outperforms existing 2D and 3D approaches. Our code and dataset will be made publicly available.
Authors: Shunlin Lu, Jingbo Wang, Zeyu Lu, Ling-Hao Chen, Wenxun Dai, Junting Dong, Zhiyang Dou, Bo Dai, Ruimao Zhang
Abstract: The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation remains largely unexplored. In this paper, we introduce a scalable motion generation framework that includes the motion tokenizer Motion FSQ-VAE and a text-prefix autoregressive transformer. Through comprehensive experiments, we observe the scaling behavior of this system. For the first time, we confirm the existence of scaling laws within the context of motion generation. Specifically, our results demonstrate that the normalized test loss of our prefix autoregressive models adheres to a logarithmic law in relation to compute budgets. Furthermore, we also confirm the power law between Non-Vocabulary Parameters, Vocabulary Parameters, and Data Tokens with respect to compute budgets respectively. Leveraging the scaling law, we predict the optimal transformer size, vocabulary size, and data requirements for a compute budget of $1e18$. The test loss of the system, when trained with the optimal model size, vocabulary size, and required data, aligns precisely with the predicted test loss, thereby validating the scaling law.
Authors: Jintao Huang, Yiu-ming Cheung, Chi-man Vong, Wenbin Qian
Abstract: Partial label learning (PLL) is a complicated weakly supervised multi-classification task compounded by class imbalance. Currently, existing methods only rely on inter-class pseudo-labeling from inter-class features, often overlooking the significant impact of the intra-class imbalanced features combined with the inter-class. To address these limitations, we introduce Granular Ball Representation for Imbalanced PLL (GBRIP), a novel framework for imbalanced PLL. GBRIP utilizes coarse-grained granular ball representation and multi-center loss to construct a granular ball-based nfeature space through unsupervised learning, effectively capturing the feature distribution within each class. GBRIP mitigates the impact of confusing features by systematically refining label disambiguation and estimating imbalance distributions. The novel multi-center loss function enhances learning by emphasizing the relationships between samples and their respective centers within the granular balls. Extensive experiments on standard benchmarks demonstrate that GBRIP outperforms existing state-of-the-art methods, offering a robust solution to the challenges of imbalanced PLL.
Authors: Yongsung Kim, Minjun Park, Jooyoung Choi, Sungroh Yoon
Abstract: Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction. However, directly applying 3D Gaussian Splatting (3DGS) as a refinement step following these models presents challenges. We hypothesize that the excessive positional degrees of freedom (DoFs) in Gaussians induce geometry distortion, fitting color patterns at the cost of structural fidelity. To address this, we propose reprojection-based DoF separation, a method distinguishing positional DoFs in terms of uncertainty: image-plane-parallel DoFs and ray-aligned DoF. To independently manage each DoF, we introduce a reprojection process along with tailored constraints for each DoF. Through experiments across various datasets, we confirm that separating the positional DoFs of Gaussians and applying targeted constraints effectively suppresses geometric artifacts, producing reconstruction results that are both visually and geometrically plausible.
Authors: Ruoyu Xu, Zhiyu Xiang, Chenwei Zhang, Hanzhi Zhong, Xijun Zhao, Ruina Dang, Peng Xu, Tianyu Pu, Eryun Liu
Abstract: 3D object detection is one of the fundamental perception tasks for autonomous vehicles. Fulfilling such a task with a 4D millimeter-wave radar is very attractive since the sensor is able to acquire 3D point clouds similar to Lidar while maintaining robust measurements under adverse weather. However, due to the high sparsity and noise associated with the radar point clouds, the performance of the existing methods is still much lower than expected. In this paper, we propose a novel Semi-supervised Cross-modality Knowledge Distillation (SCKD) method for 4D radar-based 3D object detection. It characterizes the capability of learning the feature from a Lidar-radar-fused teacher network with semi-supervised distillation. We first propose an adaptive fusion module in the teacher network to boost its performance. Then, two feature distillation modules are designed to facilitate the cross-modality knowledge transfer. Finally, a semi-supervised output distillation is proposed to increase the effectiveness and flexibility of the distillation framework. With the same network structure, our radar-only student trained by SCKD boosts the mAP by 10.38% over the baseline and outperforms the state-of-the-art works on the VoD dataset. The experiment on ZJUODset also shows 5.12% mAP improvements on the moderate difficulty level over the baseline when extra unlabeled data are available. Code is available at https://github.com/Ruoyu-Xu/SCKD.
Authors: Kunpeng Wang, Keke Chen, Chenglong Li, Zhengzheng Tu, Bin Luo
Abstract: Alignment-free RGB-Thermal (RGB-T) salient object detection (SOD) aims to achieve robust performance in complex scenes by directly leveraging the complementary information from unaligned visible-thermal image pairs, without requiring manual alignment. However, the labor-intensive process of collecting and annotating image pairs limits the scale of existing benchmarks, hindering the advancement of alignment-free RGB-T SOD. In this paper, we construct a large-scale and high-diversity unaligned RGB-T SOD dataset named UVT20K, comprising 20,000 image pairs, 407 scenes, and 1256 object categories. All samples are collected from real-world scenarios with various challenges, such as low illumination, image clutter, complex salient objects, and so on. To support the exploration for further research, each sample in UVT20K is annotated with a comprehensive set of ground truths, including saliency masks, scribbles, boundaries, and challenge attributes. In addition, we propose a Progressive Correlation Network (PCNet), which models inter- and intra-modal correlations on the basis of explicit alignment to achieve accurate predictions in unaligned image pairs. Extensive experiments conducted on unaligned and aligned datasets demonstrate the effectiveness of our method.Code and dataset are available at https://github.com/Angknpng/PCNet.
Authors: Qianpu Sun, Changyong Shu, Sifan Zhou, Zichen Yu, Yan Chen, Dawei Yang, Yuan Chun
Abstract: 3D occupancy perception is gaining increasing attention due to its capability to offer detailed and precise environment representations. Previous weakly-supervised NeRF methods balance efficiency and accuracy, with mIoU varying by 5-10 points due to sampling count along camera rays. Recently, real-time Gaussian splatting has gained widespread popularity in 3D reconstruction, and the occupancy prediction task can also be viewed as a reconstruction task. Consequently, we propose GSRender, which naturally employs 3D Gaussian Splatting for occupancy prediction, simplifying the sampling process. In addition, the limitations of 2D supervision result in duplicate predictions along the same camera ray. We implemented the Ray Compensation (RC) module, which mitigates this issue by compensating for features from adjacent frames. Finally, we redesigned the loss to eliminate the impact of dynamic objects from adjacent frames. Extensive experiments demonstrate that our approach achieves SOTA (state-of-the-art) results in RayIoU (+6.0), while narrowing the gap with 3D supervision methods. Our code will be released soon.
Authors: Yiren Song, Xiaokang Liu, Mike Zheng Shou
Abstract: Diffusion models have fundamentally transformed the field of generative models, making the assessment of similarity between customized model outputs and reference inputs critically important. However, traditional perceptual similarity metrics operate primarily at the pixel and patch levels, comparing low-level colors and textures but failing to capture mid-level similarities and differences in image layout, object pose, and semantic content. Contrastive learning-based CLIP and self-supervised learning-based DINO are often used to measure semantic similarity, but they highly compress image features, inadequately assessing appearance details. This paper is the first to discover that pretrained diffusion models can be utilized for measuring visual similarity and introduces the DiffSim method, addressing the limitations of traditional metrics in capturing perceptual consistency in custom generation tasks. By aligning features in the attention layers of the denoising U-Net, DiffSim evaluates both appearance and style similarity, showing superior alignment with human visual preferences. Additionally, we introduce the Sref and IP benchmarks to evaluate visual similarity at the level of style and instance, respectively. Comprehensive evaluations across multiple benchmarks demonstrate that DiffSim achieves state-of-the-art performance, providing a robust tool for measuring visual coherence in generative models.
Authors: Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim
Abstract: With the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise. DVC involves the automatic captioning and localization of untrimmed videos. Several studies highlight the challenges of DVC and introduce improved methods utilizing prior knowledge, such as pre-training and external memory. In this research, we propose a model that leverages the prior knowledge of human-oriented hierarchical compact memory inspired by human memory hierarchy and cognition. To mimic human-like memory recall, we construct a hierarchical memory and a hierarchical memory reading module. We build an efficient hierarchical compact memory by employing clustering of memory events and summarization using large language models. Comparative experiments demonstrate that this hierarchical memory recall process improves the performance of DVC by achieving state-of-the-art performance on YouCook2 and ViTT datasets.
Authors: Zhenxin Lei, Man Yao, Jiakui Hu, Xinhao Luo, Yanye Lu, Bo Xu, Guoqi Li
Abstract: Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex architectural designs for segmentation tasks into spiking versions leads to performance degradation and non-convergence. To address this challenge, we first identify the modules in the architecture design that lead to the severe reduction in spike firing, make targeted improvements, and propose Spike2Former architecture. Second, we propose normalized integer spiking neurons to solve the training stability problem of SNNs with complex architectures. We set a new state-of-the-art for SNNs in various semantic segmentation datasets, with a significant improvement of +12.7% mIoU and 5.0 efficiency on ADE20K, +14.3% mIoU and 5.2 efficiency on VOC2012, and +9.1% mIoU and 6.6 efficiency on CityScapes.
Authors: Wenqiao Li, Bozhong Zheng, Xiaohao Xu, Jinye Gan, Fading Lu, Xiang Li, Na Ni, Zheng Tian, Xiaonan Huang, Shenghua Gao, Yingna Wu
Abstract: Object anomaly detection is essential for industrial quality inspection, yet traditional single-sensor methods face critical limitations. They fail to capture the wide range of anomaly types, as single sensors are often constrained to either external appearance, geometric structure, or internal properties. To overcome these challenges, we introduce MulSen-AD, the first high-resolution, multi-sensor anomaly detection dataset tailored for industrial applications. MulSen-AD unifies data from RGB cameras, laser scanners, and lock-in infrared thermography, effectively capturing external appearance, geometric deformations, and internal defects. The dataset spans 15 industrial products with diverse, real-world anomalies. We also present MulSen-AD Bench, a benchmark designed to evaluate multi-sensor methods, and propose MulSen-TripleAD, a decision-level fusion algorithm that integrates these three modalities for robust, unsupervised object anomaly detection. Our experiments demonstrate that multi-sensor fusion substantially outperforms single-sensor approaches, achieving 96.1% AUROC in object-level detection accuracy. These results highlight the importance of integrating multi-sensor data for comprehensive industrial anomaly detection.
Authors: Huawen Shen, Gengluo Li, Jinwen Zhong, Yu Zhou
Abstract: Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually English). Due to the extremely unbalanced quantity and quality of pre-training corpora between English and other languages, few works can extend to non-English scenarios. In this paper, we conduct systematic experiments to show that vision and layout modality hold invariance among images with different languages. If decoupling language bias from document images, a vision-layout-based model can achieve impressive cross-lingual generalization. Accordingly, we present a simple but effective multilingual training paradigm LDP (Language Decoupled Pre-training) for better utilization of monolingual pre-training data. Our proposed model LDM (Language Decoupled Model) is first pre-trained on the language-independent data, where the language knowledge is decoupled by a diffusion model, and then the LDM is fine-tuned on the downstream languages. Extensive experiments show that the LDM outperformed all SOTA multilingual pre-trained models, and also maintains competitiveness on downstream monolingual/English benchmarks.
Authors: Lei Su, Xiaochen Ma, Xuekang Zhu, Chaoqun Niu, Zeyu Lei, Ji-Zhe Zhou
Abstract: Non-semantic features or semantic-agnostic features, which are irrelevant to image context but sensitive to image manipulations, are recognized as evidential to Image Manipulation Localization (IML). Since manual labels are impossible, existing works rely on handcrafted methods to extract non-semantic features. Handcrafted non-semantic features jeopardize IML model's generalization ability in unseen or complex scenarios. Therefore, for IML, the elephant in the room is: How to adaptively extract non-semantic features? Non-semantic features are context-irrelevant and manipulation-sensitive. That is, within an image, they are consistent across patches unless manipulation occurs. Then, spare and discrete interactions among image patches are sufficient for extracting non-semantic features. However, image semantics vary drastically on different patches, requiring dense and continuous interactions among image patches for learning semantic representations. Hence, in this paper, we propose a Sparse Vision Transformer (SparseViT), which reformulates the dense, global self-attention in ViT into a sparse, discrete manner. Such sparse self-attention breaks image semantics and forces SparseViT to adaptively extract non-semantic features for images. Besides, compared with existing IML models, the sparse self-attention mechanism largely reduced the model size (max 80% in FLOPs), achieving stunning parameter efficiency and computation reduction. Extensive experiments demonstrate that, without any handcrafted feature extractors, SparseViT is superior in both generalization and efficiency across benchmark datasets.
Authors: Zheng Ren, Jingwen Zhou, Wenguan Zhang, Jiapu Yan, Bingkun Chen, Huajun Feng, Shiqi Chen
Abstract: Recently, the joint design of optical systems and downstream algorithms is showing significant potential. However, existing rays-described methods are limited to optimizing geometric degradation, making it difficult to fully represent the optical characteristics of complex, miniaturized lenses constrained by wavefront aberration or diffraction effects. In this work, we introduce a precise optical simulation model, and every operation in pipeline is differentiable. This model employs a novel initial value strategy to enhance the reliability of intersection calculation on high aspherics. Moreover, it utilizes a differential operator to reduce memory consumption during coherent point spread function calculations. To efficiently address various degradation, we design a joint optimization procedure that leverages field information. Guided by a general restoration network, the proposed method not only enhances the image quality, but also successively improves the optical performance across multiple lenses that are already in professional level. This joint optimization pipeline offers innovative insights into the practical design of sophisticated optical systems and post-processing algorithms. The source code will be made publicly available at https://github.com/Zrr-ZJU/Successive-optimization
Authors: Alexander H. Berger, Laurin Lux, Alexander Weers, Martin Menten, Daniel Rueckert, Johannes C. Paetzold
Abstract: Topological correctness, i.e., the preservation of structural integrity and specific characteristics of shape, is a fundamental requirement for medical imaging tasks, such as neuron or vessel segmentation. Despite the recent surge in topology-aware methods addressing this challenge, their real-world applicability is hindered by flawed benchmarking practices. In this paper, we identify critical pitfalls in model evaluation that include inadequate connectivity choices, overlooked topological artifacts in ground truth annotations, and inappropriate use of evaluation metrics. Through detailed empirical analysis, we uncover these issues' profound impact on the evaluation and ranking of segmentation methods. Drawing from our findings, we propose a set of actionable recommendations to establish fair and robust evaluation standards for topology-aware medical image segmentation methods.
Authors: Younhun Kim, Myung-Joon Kwon, Wonjun Lee, Changick Kim
Abstract: Previous Deepfake detection methods perform well within their training domains, but their effectiveness diminishes significantly with new synthesis techniques. Recent studies have revealed that detection models often create decision boundaries based on facial identity rather than synthetic artifacts, resulting in poor performance on cross-domain datasets. To address this limitation, we propose Facial Recognition Identity Attenuation (FRIDAY), a novel training method that mitigates facial identity influence using a face recognizer. Specifically, we first train a face recognizer using the same backbone as the Deepfake detector. The recognizer is then frozen and employed during the detector's training to reduce facial identity information. This is achieved by feeding input images into both the recognizer and the detector, and minimizing the similarity of their feature embeddings through our Facial Identity Attenuating loss. This process encourages the detector to generate embeddings distinct from the recognizer, effectively reducing the impact of facial identity. Extensive experiments demonstrate that our approach significantly enhances detection performance on both in-domain and cross-domain datasets.
Authors: Keith G. Mills, Mohammad Salameh, Ruichen Chen, Negar Hassanpour, Wei Lu, Di Niu
Abstract: Diffusion Models (DM) have democratized AI image generation through an iterative denoising process. Quantization is a major technique to alleviate the inference cost and reduce the size of DM denoiser networks. However, as denoisers evolve from variants of convolutional U-Nets toward newer Transformer architectures, it is of growing importance to understand the quantization sensitivity of different weight layers, operations and architecture types to performance. In this work, we address this challenge with Qua$^2$SeDiMo, a mixed-precision Post-Training Quantization framework that generates explainable insights on the cost-effectiveness of various model weight quantization methods for different denoiser operation types and block structures. We leverage these insights to make high-quality mixed-precision quantization decisions for a myriad of diffusion models ranging from foundational U-Nets to state-of-the-art Transformers. As a result, Qua$^2$SeDiMo can construct 3.4-bit, 3.9-bit, 3.65-bit and 3.7-bit weight quantization on PixArt-${\alpha}$, PixArt-${\Sigma}$, Hunyuan-DiT and SDXL, respectively. We further pair our weight-quantization configurations with 6-bit activation quantization and outperform existing approaches in terms of quantitative metrics and generative image quality.
Authors: Minglong Xue, Jinhong He, Shivakumara Palaiahnakote, Mingliang Zhou
Abstract: Image restoration and enhancement are pivotal for numerous computer vision applications, yet unifying these tasks efficiently remains a significant challenge. Inspired by the iterative refinement capabilities of diffusion models, we propose CycleRDM, a novel framework designed to unify restoration and enhancement tasks while achieving high-quality mapping. Specifically, CycleRDM first learns the mapping relationships among the degraded domain, the rough normal domain, and the normal domain through a two-stage diffusion inference process. Subsequently, we transfer the final calibration process to the wavelet low-frequency domain using discrete wavelet transform, performing fine-grained calibration from a frequency domain perspective by leveraging task-specific frequency spaces. To improve restoration quality, we design a feature gain module for the decomposed wavelet high-frequency domain to eliminate redundant features. Additionally, we employ multimodal textual prompts and Fourier transform to drive stable denoising and reduce randomness during the inference process. After extensive validation, CycleRDM can be effectively generalized to a wide range of image restoration and enhancement tasks while requiring only a small number of training samples to be significantly superior on various benchmarks of reconstruction quality and perceptual quality. The source code will be available at https://github.com/hejh8/CycleRDM.
Authors: Il-Seok Oh
Abstract: Fruit tree image segmentation is an essential problem in automating a variety of agricultural tasks such as phenotyping, harvesting, spraying, and pruning. Many research papers have proposed a diverse spectrum of solutions suitable to specific tasks and environments. The review scope of this paper is confined to the front views of fruit trees and based on 158 relevant papers collected using a newly designed crawling review method. These papers are systematically reviewed based on a taxonomy that sequentially considers the method, image, task, and fruit. This taxonomy will assist readers to intuitively grasp the big picture of these research activities. Our review reveals that the most noticeable deficiency of the previous studies was the lack of a versatile dataset and segmentation model that could be applied to a variety of tasks and environments. Six important future research tasks are suggested, with the expectation that these will pave the way to building a versatile tree segmentation module.
Authors: Rui Ding, Liang Yong, Sihuan Zhao, Jing Nie, Lihui Chen, Haijun Liu, Xichuan Zhou
Abstract: Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, there is often a significant performance drop compared to their full-precision counterparts. To address this issue, reconstruction methods have been incorporated into the PTQ framework to improve performance in low-bit quantization settings. Nevertheless, existing related methods predefine the reconstruction granularity and seldom explore the progressive relationships between different reconstruction granularities, which leads to sub-optimal quantization results in ViTs. To this end, in this paper, we propose a Progressive Fine-to-Coarse Reconstruction (PFCR) method for accurate PTQ, which significantly improves the performance of low-bit quantized vision transformers. Specifically, we define multi-head self-attention and multi-layer perceptron modules along with their shortcuts as the finest reconstruction units. After reconstructing these two fine-grained units, we combine them to form coarser blocks and reconstruct them at a coarser granularity level. We iteratively perform this combination and reconstruction process, achieving progressive fine-to-coarse reconstruction. Additionally, we introduce a Progressive Optimization Strategy (POS) for PFCR to alleviate the difficulty of training, thereby further enhancing model performance. Experimental results on the ImageNet dataset demonstrate that our proposed method achieves the best Top-1 accuracy among state-of-the-art methods, particularly attaining 75.61% for 3-bit quantized ViT-B in PTQ. Besides, quantization results on the COCO dataset reveal the effectiveness and generalization of our proposed method on other computer vision tasks like object detection and instance segmentation.
Authors: Eric Brouwer, Jan Erik van Woerden, Gertjan Burghouts, Matias Valedenegro-Toro, Marco Zullich
Abstract: Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive Language-Image Pre-Training (CLIP) model through adaptive prompt tuning, guided by real-time visual inputs. Unlike existing techniques such as Context Optimization (CoOp) and Visual Prompt Tuning (VPT), which are constrained by static prompts or visual token reliance, the proposed approach leverages a cross-attention mechanism to dynamically refine text prompts for the image at hand. This enables an image-specific alignment of textual features with image patches extracted from the Vision Transformer, making the model more effective for datasets with high intra-class variance and low inter-class differences. The method is evaluated on several datasets, including CUBirds, Oxford Flowers, and FGVC Aircraft, showing significant performance gains over static prompt tuning approaches. To ensure these performance gains translate into trustworthy predictions, we integrate Monte-Carlo Dropout in our approach to improve the reliability of the model predictions and uncertainty estimates. This integration provides valuable insights into the model's predictive confidence, helping to identify when predictions can be trusted and when additional verification is necessary. This dynamic approach offers a robust solution, advancing the state-of-the-art for few-shot fine-grained classification.
Authors: Jie Huang, Ruibing Hou, Jiahe Zhao, Hong Chang, Shiguang Shan
Abstract: Human-centric perceptions play a crucial role in real-world applications. While recent human-centric works have achieved impressive progress, these efforts are often constrained to the visual domain and lack interaction with human instructions, limiting their applicability in broader scenarios such as chatbots and sports analysis. This paper introduces Referring Human Perceptions, where a referring prompt specifies the person of interest in an image. To tackle the new task, we propose RefHCM (Referring Human-Centric Model), a unified framework to integrate a wide range of human-centric referring tasks. Specifically, RefHCM employs sequence mergers to convert raw multimodal data -- including images, text, coordinates, and parsing maps -- into semantic tokens. This standardized representation enables RefHCM to reformulate diverse human-centric referring tasks into a sequence-to-sequence paradigm, solved using a plain encoder-decoder transformer architecture. Benefiting from a unified learning strategy, RefHCM effectively facilitates knowledge transfer across tasks and exhibits unforeseen capabilities in handling complex reasoning. This work represents the first attempt to address referring human perceptions with a general-purpose framework, while simultaneously establishing a corresponding benchmark that sets new standards for the field. Extensive experiments showcase RefHCM's competitive and even superior performance across multiple human-centric referring tasks. The code and data are publicly at https://github.com/JJJYmmm/RefHCM.
Authors: Zijun Chen, Wenbo Hu, Guande He, Zhijie Deng, Zheng Zhang, Richang Hong
Abstract: Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare and autonomous driving. This paper investigates representative MLLMs, focusing on their calibration across various scenarios, including before and after visual fine-tuning, as well as before and after multimodal training of the base LLMs. We observed miscalibration in their performance, and at the same time, no significant differences in calibration across these scenarios. We also highlight how uncertainty differs between text and images and how their integration affects overall uncertainty. To better understand MLLMs' miscalibration and their ability to self-assess uncertainty, we construct the IDK (I don't know) dataset, which is key to evaluating how they handle unknowns. Our findings reveal that MLLMs tend to give answers rather than admit uncertainty, but this self-assessment improves with proper prompt adjustments. Finally, to calibrate MLLMs and enhance model reliability, we propose techniques such as temperature scaling and iterative prompt optimization. Our results provide insights into improving MLLMs for effective and responsible deployment in multimodal applications. Code and IDK dataset: \href{https://github.com/hfutml/Calibration-MLLM}{https://github.com/hfutml/Calibration-MLLM}.
URLs: https://github.com/hfutml/Calibration-MLLM, https://github.com/hfutml/Calibration-MLLM
Authors: Edvard O. S. Gr{\o}dem, Donatas Sederevi\v{c}ius, Esten H. Leonardsen, Bradley J. MacIntosh, Atle Bj{\o}rnerud, Till Schellhorn, {\O}ystein S{\o}rensen, Inge Amlien, Pablo F. Garrido, Anders M. Fjell
Abstract: Longitudinal imaging allows for the study of structural changes over time. One approach to detecting such changes is by non-linear image registration. This study introduces Multi-Session Temporal Registration (MUSTER), a novel method that facilitates longitudinal analysis of changes in extended series of medical images. MUSTER improves upon conventional pairwise registration by incorporating more than two imaging sessions to recover longitudinal deformations. Longitudinal analysis at a voxel-level is challenging due to effects of a changing image contrast as well as instrumental and environmental sources of bias between sessions. We show that local normalized cross-correlation as an image similarity metric leads to biased results and propose a robust alternative. We test the performance of MUSTER on a synthetic multi-site, multi-session neuroimaging dataset and show that, in various scenarios, using MUSTER significantly enhances the estimated deformations relative to pairwise registration. Additionally, we apply MUSTER on a sample of older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. The results show that MUSTER can effectively identify patterns of neuro-degeneration from T1-weighted images and that these changes correlate with changes in cognition, matching the performance of state of the art segmentation methods. By leveraging GPU acceleration, MUSTER efficiently handles large datasets, making it feasible also in situations with limited computational resources.
Authors: Estelle Aflalo, Gabriela Ben Melech Stan, Tiep Le, Man Luo, Shachar Rosenman, Sayak Paul, Shao-Yen Tseng, Vasudev Lal
Abstract: Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensuring these models utilize visual information as effectively as linguistic content when both modalities are necessary to formulate an accurate answer. We hypothesize that hallucinations arise due to the lack of effective visual grounding in current LVLMs. This issue extends to vision-language benchmarks, where it is difficult to make the image indispensable for accurate answer generation, particularly in vision question-answering tasks. In this work, we introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding and to evaluate their effectiveness in achieving it. These datasets can be utilized for both training and assessing an LVLM's ability to use image content as substantive evidence rather than relying solely on linguistic priors, providing insights into the model's reliance on visual information. To demonstrate the utility of our dataset, we introduce an innovative training task that outperforms baselines alongside a validation method and application for explainability. The code is available at https://github.com/IntelLabs/fivl.
Authors: Youngmin Oh, Hyunju Lee, Bumsub Ham
Abstract: Neural architecture search (NAS) enables finding the best-performing architecture from a search space automatically. Most NAS methods exploit an over-parameterized network (i.e., a supernet) containing all possible architectures (i.e., subnets) in the search space. However, the subnets that share the same set of parameters are likely to have different characteristics, interfering with each other during training. To address this, few-shot NAS methods have been proposed that divide the space into a few subspaces and employ a separate supernet for each subspace to limit the extent of weight sharing. They achieve state-of-the-art performance, but the computational cost increases accordingly. We introduce in this paper a novel few-shot NAS method that exploits the number of nonlinear functions to split the search space. To be specific, our method divides the space such that each subspace consists of subnets with the same number of nonlinear functions. Our splitting criterion is efficient, since it does not require comparing gradients of a supernet to split the space. In addition, we have found that dividing the space allows us to reduce the channel dimensions required for each supernet, which enables training multiple supernets in an efficient manner. We also introduce a supernet-balanced sampling (SBS) technique, sampling several subnets at each training step, to train different supernets evenly within a limited number of training steps. Extensive experiments on standard NAS benchmarks demonstrate the effectiveness of our approach. Our code is available at https://cvlab.yonsei.ac.kr/projects/EFS-NAS.
Authors: Yonghao He, Hu Su, Haiyong Yu, Cong Yang, Wei Sui, Cong Wang, Song Liu
Abstract: Open-set object detection (OSOD) is highly desirable for robotic manipulation in unstructured environments. However, existing OSOD methods often fail to meet the requirements of robotic applications due to their high computational burden and complex deployment. To address this issue, this paper proposes a light-weight framework called Decoupled OSOD (DOSOD), which is a practical and highly efficient solution to support real-time OSOD tasks in robotic systems. Specifically, DOSOD builds upon the YOLO-World pipeline by integrating a vision-language model (VLM) with a detector. A Multilayer Perceptron (MLP) adaptor is developed to transform text embeddings extracted by the VLM into a joint space, within which the detector learns the region representations of class-agnostic proposals. Cross-modality features are directly aligned in the joint space, avoiding the complex feature interactions and thereby improving computational efficiency. DOSOD operates like a traditional closed-set detector during the testing phase, effectively bridging the gap between closed-set and open-set detection. Compared to the baseline YOLO-World, the proposed DOSOD significantly enhances real-time performance while maintaining comparable accuracy. The slight DOSOD-S model achieves a Fixed AP of $26.7\%$, compared to $26.2\%$ for YOLO-World-v1-S and $22.7\%$ for YOLO-World-v2-S, using similar backbones on the LVIS minival dataset. Meanwhile, the FPS of DOSOD-S is $57.1\%$ higher than YOLO-World-v1-S and $29.6\%$ higher than YOLO-World-v2-S. Meanwhile, we demonstrate that the DOSOD model facilitates the deployment of edge devices. The codes and models are publicly available at https://github.com/D-Robotics-AI-Lab/DOSOD.
Authors: Yuchen Su, Zhineng Chen, Yongkun Du, Zhilong Ji, Kai Hu, Jinfeng Bai, Xieping Gao
Abstract: Connected component (CC) is a proper text shape representation that aligns with human reading intuition. However, CC-based text detection methods have recently faced a developmental bottleneck that their time-consuming post-processing is difficult to eliminate. To address this issue, we introduce an explicit relational reasoning network (ERRNet) to elegantly model the component relationships without post-processing. Concretely, we first represent each text instance as multiple ordered text components, and then treat these components as objects in sequential movement. In this way, scene text detection can be innovatively viewed as a tracking problem. From this perspective, we design an end-to-end tracking decoder to achieve a CC-based method dispensing with post-processing entirely. Additionally, we observe that there is an inconsistency between classification confidence and localization quality, so we propose a Polygon Monte-Carlo method to quickly and accurately evaluate the localization quality. Based on this, we introduce a position-supervised classification loss to guide the task-aligned learning of ERRNet. Experiments on challenging benchmarks demonstrate the effectiveness of our ERRNet. It consistently achieves state-of-the-art accuracy while holding highly competitive inference speed.
Authors: Shi Guo, Zixuan Chen, Ziran Zhang, Yutian Chen, Gangwei Xu, Tianfan Xue
Abstract: High dynamic range (HDR) imaging is a crucial task in computational photography, which captures details across diverse lighting conditions. Traditional HDR fusion methods face limitations in dynamic scenes with extreme exposure differences, as aligning low dynamic range (LDR) frames becomes challenging due to motion and brightness variation. In this work, we propose a novel 12-stop HDR imaging approach for dynamic scenes, leveraging a dual-camera system with an event camera and an RGB camera. The event camera provides temporally dense, high dynamic range signals that improve alignment between LDR frames with large exposure differences, reducing ghosting artifacts caused by motion. Also, a real-world finetuning strategy is proposed to increase the generalization of alignment module on real-world events. Additionally, we introduce a diffusion-based fusion module that incorporates image priors from pre-trained diffusion models to address artifacts in high-contrast regions and minimize errors from the alignment process. To support this work, we developed the ESHDR dataset, the first dataset for 12-stop HDR imaging with synchronized event signals, and validated our approach on both simulated and real-world data. Extensive experiments demonstrate that our method achieves state-of-the-art performance, successfully extending HDR imaging to 12 stops in dynamic scenes.
Authors: Jianrong Zhang, Hehe Fan, Yi Yang
Abstract: Diffusion models, particularly latent diffusion models, have demonstrated remarkable success in text-driven human motion generation. However, it remains challenging for latent diffusion models to effectively compose multiple semantic concepts into a single, coherent motion sequence. To address this issue, we propose EnergyMoGen, which includes two spectrums of Energy-Based Models: (1) We interpret the diffusion model as a latent-aware energy-based model that generates motions by composing a set of diffusion models in latent space; (2) We introduce a semantic-aware energy model based on cross-attention, which enables semantic composition and adaptive gradient descent for text embeddings. To overcome the challenges of semantic inconsistency and motion distortion across these two spectrums, we introduce Synergistic Energy Fusion. This design allows the motion latent diffusion model to synthesize high-quality, complex motions by combining multiple energy terms corresponding to textual descriptions. Experiments show that our approach outperforms existing state-of-the-art models on various motion generation tasks, including text-to-motion generation, compositional motion generation, and multi-concept motion generation. Additionally, we demonstrate that our method can be used to extend motion datasets and improve the text-to-motion task.
Authors: Kun Li, Dan Guo, Guoliang Chen, Chunxiao Fan, Jingyuan Xu, Zhiliang Wu, Hehe Fan, Meng Wang
Abstract: Micro-Action Recognition (MAR) has gained increasing attention due to its crucial role as a form of non-verbal communication in social interactions, with promising potential for applications in human communication and emotion analysis. However, current approaches often overlook the inherent ambiguity in micro-actions, which arises from the wide category range and subtle visual differences between categories. This oversight hampers the accuracy of micro-action recognition. In this paper, we propose a novel Prototypical Calibrating Ambiguous Network (\textbf{PCAN}) to unleash and mitigate the ambiguity of MAR. \textbf{Firstly}, we employ a hierarchical action-tree to identify the ambiguous sample, categorizing them into distinct sets of ambiguous samples of false negatives and false positives, considering both body- and action-level categories. \textbf{Secondly}, we implement an ambiguous contrastive refinement module to calibrate these ambiguous samples by regulating the distance between ambiguous samples and their corresponding prototypes. This calibration process aims to pull false negative ($\mathbb{FN}$) samples closer to their respective prototypes and push false positive ($\mathbb{FP}$) samples apart from their affiliated prototypes. In addition, we propose a new prototypical diversity amplification loss to strengthen the model's capacity by amplifying the differences between different prototypes. \textbf{Finally}, we propose a prototype-guided rectification to rectify prediction by incorporating the representability of prototypes. Extensive experiments conducted on the benchmark dataset demonstrate the superior performance of our method compared to existing approaches. The code is available at https://github.com/kunli-cs/PCAN.
Authors: Byeonghun Kim, Byeongjoon Noh
Abstract: In smart cities, detecting pedestrian falls is a major challenge to ensure the safety and quality of life of citizens. In this study, we propose a novel fall detection system using FLAMe (Federated Learning with Attention Mechanism), a federated learning (FL) based algorithm. FLAMe trains around important keypoint information and only transmits the trained important weights to the server, reducing communication costs and preserving data privacy. Furthermore, the lightweight keypoint transformer model is integrated into the FL framework to effectively learn spatio-temporal features. We validated the experiment using 22,672 video samples from the "Fall Accident Risk Behavior Video-Sensor Pair data" dataset from AI-Hub. As a result of the experiment, the FLAMe-based system achieved an accuracy of 94.02% with about 190,000 transmission parameters, maintaining performance similar to that of existing centralized learning while maximizing efficiency by reducing communication costs by about 40% compared to the existing FL algorithm, FedAvg. Therefore, the FLAMe algorithm has demonstrated that it provides robust performance in the distributed environment of smart cities and is a practical and effective solution for public safety.
Authors: Areeg Fagad Rasheed, M. Zarkoosh
Abstract: The objective of this research is to optimize the eleventh iteration of You Only Look Once (YOLOv11) by developing size-specific modified versions of the architecture. These modifications involve pruning unnecessary layers and reconfiguring the main architecture of YOLOv11. Each proposed version is tailored to detect objects of specific size ranges, from small to large. To ensure proper model selection based on dataset characteristics, we introduced an object classifier program. This program identifies the most suitable modified version for a given dataset. The proposed models were evaluated on various datasets and compared with the original YOLOv11 and YOLOv8 models. The experimental results highlight significant improvements in computational resource efficiency, with the proposed models maintaining the accuracy of the original YOLOv11. In some cases, the modified versions outperformed the original model regarding detection performance. Furthermore, the proposed models demonstrated reduced model sizes and faster inference times. Models weights and the object size classifier can be found in this repository
Authors: Yucheng Hu, Yanjiang Guo, Pengchao Wang, Xiaoyu Chen, Yen-Jen Wang, Jianke Zhang, Koushil Sreenath, Chaochao Lu, Jianyu Chen
Abstract: Recent advancements in robotics have focused on developing generalist policies capable of performing multiple tasks. Typically, these policies utilize pre-trained vision encoders to capture crucial information from current observations. However, previous vision encoders, which trained on two-image contrastive learning or single-image reconstruction, can not perfectly capture the sequential information essential for embodied tasks. Recently, video diffusion models (VDMs) have demonstrated the capability to accurately predict future image sequences, exhibiting a good understanding of physical dynamics. Motivated by the strong visual prediction capabilities of VDMs, we hypothesize that they inherently possess visual representations that reflect the evolution of the physical world, which we term predictive visual representations. Building on this hypothesis, we propose the Video Prediction Policy (VPP), a generalist robotic policy conditioned on the predictive visual representations from VDMs. To further enhance these representations, we incorporate diverse human or robotic manipulation datasets, employing unified video-generation training objectives. VPP consistently outperforms existing methods across two simulated and two real-world benchmarks. Notably, it achieves a 28.1\% relative improvement in the Calvin ABC-D benchmark compared to the previous state-of-the-art and delivers a 28.8\% increase in success rates for complex real-world dexterous manipulation tasks.
Authors: Chenfan Qu, Jian Liu, Haoxing Chen, Baihan Yu, Jingjing Liu, Weiqiang Wang, Lianwen Jin
Abstract: Recently, tampered text detection has attracted increasing attention due to its essential role in information security. Although existing methods can detect the tampered text region, the interpretation of such detection remains unclear, making the prediction unreliable. To address this black-box problem, we propose to explain the basis of tampered text detection with natural language via large multimodal models. To fill the data gap for this task, we propose a large-scale, comprehensive dataset, ETTD, which contains both pixel-level annotations indicating the tampered text region and natural language annotations describing the anomaly of the tampered text. Multiple methods are employed to improve the quality of the proposed data. For example, a fused mask prompt is proposed to reduce confusion when querying GPT4o to generate anomaly descriptions. By weighting the input image with the mask annotation, the tampered region can be clearly indicated and the content in and around the tampered region can also be preserved. We also propose prompting GPT4o to recognize tampered texts and filtering out the responses with low OCR accuracy, which can effectively improve annotation quality in an automatic manner. To further improve explainable tampered text detection, we propose a simple yet effective model called TTD, which benefits from improved fine-grained perception by paying attention to the suspected region with auxiliary reference grounding query. Extensive experiments on both the ETTD dataset and the public dataset have verified the effectiveness of the proposed methods. In-depth analysis is also provided to inspire further research. The dataset and code will be made publicly available.
Authors: Zhongwei Chen, Zhao-Xu Yang, Hai-Jun Rong
Abstract: Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images. However, the imaging gaps between platforms are often significant and the variations in viewpoints are substantial, which limits the ability of existing methods to effectively associate cross-view features and extract consistent and invariant characteristics. Moreover, existing methods often overlook the problem of increased computational and storage requirements when improving model performance. To handle these limitations, we propose a lightweight enhanced alignment network, called the Multi-Level Embedding and Alignment Network (MEAN). The MEAN network uses a progressive multi-level enhancement strategy, global-to-local associations, and cross-domain alignment, enabling feature communication across levels. This allows MEAN to effectively connect features at different levels and learn robust cross-view consistent mappings and modality-invariant features. Moreover, MEAN adopts a shallow backbone network combined with a lightweight branch design, effectively reducing parameter count and computational complexity. Experimental results on the University-1652 and SUES-200 datasets demonstrate that MEAN reduces parameter count by 62.17% and computational complexity by 70.99% compared to state-of-the-art models, while maintaining competitive or even superior performance. The codes will be released soon.
Authors: Shoumeng Qiu, Xinrun Li, XiangYang Xue, Jian Pu
Abstract: Although multiview fusion has demonstrated potential in LiDAR segmentation, its dependence on computationally intensive point-based interactions, arising from the lack of fixed correspondences between views such as range view and Bird's-Eye View (BEV), hinders its practical deployment. This paper challenges the prevailing notion that multiview fusion is essential for achieving high performance. We demonstrate that significant gains can be realized by directly fusing Polar and Cartesian partitioning strategies within the BEV space. Our proposed BEV-only segmentation model leverages the inherent fixed grid correspondences between these partitioning schemes, enabling a fusion process that is orders of magnitude faster (170$\times$ speedup) than conventional point-based methods. Furthermore, our approach facilitates dense feature fusion, preserving richer contextual information compared to sparse point-based alternatives. To enhance scene understanding while maintaining inference efficiency, we also introduce a hybrid Transformer-CNN architecture. Extensive evaluation on the SemanticKITTI and nuScenes datasets provides compelling evidence that our method outperforms previous multiview fusion approaches in terms of both performance and inference speed, highlighting the potential of BEV-based fusion for LiDAR segmentation. Code is available at \url{https://github.com/skyshoumeng/PC-BEV.}
Authors: Hao Huang, Yujie Lin, Siyu Chen, Haiyang Liu
Abstract: Skeleton-based action recognition using GCNs has achieved remarkable performance, but recognizing ambiguous actions, such as "waving" and "saluting", remains a significant challenge. Existing methods typically rely on a serial combination of GCNs and TCNs, where spatial and temporal features are extracted independently, leading to an unbalanced spatial-temporal information, which hinders accurate action recognition. Moreover, existing methods for ambiguous actions often overemphasize local details, resulting in the loss of crucial global context, which further complicates the task of differentiating ambiguous actions. To address these challenges, we propose a lightweight plug-and-play module called Synchronized and Fine-grained Head (SF-Head), inserted between GCN and TCN layers. SF-Head first conducts Synchronized Spatial-Temporal Extraction (SSTE) with a Feature Redundancy Loss (F-RL), ensuring a balanced interaction between the two types of features. It then performs Adaptive Cross-dimensional Feature Aggregation (AC-FA), with a Feature Consistency Loss (F-CL), which aligns the aggregated feature with their original spatial-temporal feature. This aggregation step effectively combines both global context and local details. Experimental results on NTU RGB+D 60, NTU RGB+D 120, and NW-UCLA datasets demonstrate significant improvements in distinguishing ambiguous actions. Our code will be made available at https://github.com/HaoHuang2003/SFHead.
Authors: Qihang Cao, Huangxun Chen
Abstract: 3D scene understanding is an important task, and there has been a recent surge of research interest in aligning 3D representations of point clouds with text to empower embodied AI. However, due to the lack of comprehensive 3D benchmarks, the capabilities of 3D models in real-world scenes, particularly those that are challenging with subtly distinguished objects, remain insufficiently investigated. To facilitate a more thorough evaluation of 3D models' capabilities, we propose a scheme, ObjVariantEnsemble, to systematically introduce more scenes with specified object classes, colors, shapes, quantities, and spatial relationships to meet model evaluation needs. More importantly, we intentionally construct scenes with similar objects to a certain degree and design an LLM-VLM-cooperated annotator to capture key distinctions as annotations. The resultant benchmark can better challenge 3D models, reveal their shortcomings in understanding, and potentially aid in the further development of 3D models.
Authors: Mehdi Hosseini Chagahi, Md. Jalil Piran, Niloufar Delfan, Behzad Moshiri, Jaber Hatam Parikhan
Abstract: Intracranial hemorrhage (ICH) refers to the leakage or accumulation of blood within the skull, which occurs due to the rupture of blood vessels in or around the brain. If this condition is not diagnosed in a timely manner and appropriately treated, it can lead to serious complications such as decreased consciousness, permanent neurological disabilities, or even death.The primary aim of this study is to detect the occurrence or non-occurrence of ICH, followed by determining the type of subdural hemorrhage (SDH). These tasks are framed as two separate binary classification problems. By adding two layers to the co-scale convolutional attention (CCA) classifier architecture, we introduce a novel approach for ICH detection. In the first layer, after extracting features from different slices of computed tomography (CT) scan images, we combine these features and select the 50 components that capture the highest variance in the data, considering them as informative features. We then assess the discriminative power of these features using the bootstrap forest algorithm, discarding those that lack sufficient discriminative ability between different classes. This algorithm explicitly determines the contribution of each feature to the final prediction, assisting us in developing an explainable AI model. The features feed into a boosting neural network as a latent feature space. In the second layer, we introduce a novel uncertainty-based fuzzy integral operator to fuse information from different CT scan slices. This operator, by accounting for the dependencies between consecutive slices, significantly improves detection accuracy.
Authors: Isabelle Tingzon, Utku Can Ozturk, Ivan Dotu
Abstract: Improving global school connectivity is critical for ensuring inclusive and equitable quality education. To reliably estimate the cost of connecting schools, governments and connectivity providers require complete and accurate school location data - a resource that is often scarce in many low- and middle-income countries. To address this challenge, we propose a cost-effective, scalable approach to locating schools in high-resolution satellite images using weakly supervised deep learning techniques. Our best models, which combine vision transformers and convolutional neural networks, achieve AUPRC values above 0.96 across 10 pilot African countries. Leveraging explainable AI techniques, our approach can approximate the precise geographical coordinates of the school locations using only low-cost, classification-level annotations. To demonstrate the scalability of our method, we generate nationwide maps of school location predictions in African countries and present a detailed analysis of our results, using Senegal as our case study. Finally, we demonstrate the immediate usability of our work by introducing an interactive web mapping tool to streamline human-in-the-loop model validation efforts by government partners. This work successfully showcases the real-world utility of deep learning and satellite images for planning regional infrastructure and accelerating universal school connectivity.
Authors: Shuang Li, Qian Chen, Chulhong Kim, Seongwook Choi, Yibing Wang, Yu Zhang, Changhui Li
Abstract: Photoacoustic imaging (PAI) uniquely combines optical contrast with the penetration depth of ultrasound, making it critical for clinical applications. However, the quality of 3D PAI is often degraded due to reconstruction artifacts caused by the sparse and angle-limited configuration of detector arrays. Existing iterative or deep learning-based methods are either time-consuming or require large training datasets, significantly limiting their practical application. Here, we propose Zero-Shot Artifact2Artifact (ZS-A2A), a zero-shot self-supervised artifact removal method based on a super-lightweight network, which leverages the fact that reconstruction artifacts are sensitive to irregularities caused by data loss. By introducing random perturbations to the acquired PA data, it spontaneously generates subset data, which in turn stimulates the network to learn the artifact patterns in the reconstruction results, thus enabling zero-shot artifact removal. This approach requires neither training data nor prior knowledge of the artifacts, and is capable of artifact removal for 3D PAI. For maximum amplitude projection (MAP) images or slice images in 3D PAI acquired with arbitrarily sparse or angle-limited detector arrays, ZS-A2A employs a self-incentive strategy to complete artifact removal and improves the Contrast-to-Noise Ratio (CNR). We validated ZS-A2A in both simulation study and $ in\ vivo $ animal experiments. Results demonstrate that ZS-A2A achieves state-of-the-art (SOTA) performance compared to existing zero-shot methods, and for the $ in\ vivo $ rat liver, ZS-A2A improves CNR from 17.48 to 43.46 in just 8 seconds. The project for ZS-A2A will be available in the following GitHub repository: https://github.com/JaegerCQ/ZS-A2A.
Authors: Peize Li, Qingyi Si, Peng Fu, Zheng Lin, Yan Wang
Abstract: Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "retrieve-then-answer" pipelines often suffer from cascading errors because the training objective of QA fails to optimize the retrieval stage. To address this issue, we propose a novel method to effectively introduce and reference retrieved information into the QA. Given the image set to be retrieved, we employ a multimodal large language model (visual perspective) and a large language model (textual perspective) to obtain multimodal hypothetical summary in question-form and description-form. By combining visual and textual perspectives, MHyS captures image content more specifically and replaces real images in retrieval, which eliminates the modality gap by transforming into text-to-text retrieval and helps improve retrieval. To more advantageously introduce retrieval with QA, we employ contrastive learning to align queries (questions) with MHyS. Moreover, we propose a coarse-to-fine strategy for calculating both sentence-level and word-level similarity scores, to further enhance retrieval and filter out irrelevant details. Our approach achieves a 3.7% absolute improvement over state-of-the-art methods on RETVQA and a 14.5% improvement over CLIP. Comprehensive experiments and detailed ablation studies demonstrate the superiority of our method.
Authors: Jing Zhao, Heliang Zheng, Chaoyue Wang, Long Lan, Wanrong Hunag, Yuhua Tang
Abstract: Large-scale text-to-image diffusion models, (e.g., DALL-E, SDXL) are capable of generating famous persons by simply referring to their names. Is it possible to make such models generate generic identities as simple as the famous ones, e.g., just use a name? In this paper, we explore the existence of a "Name Space", where any point in the space corresponds to a specific identity. Fortunately, we find some clues in the feature space spanned by text embedding of celebrities' names. Specifically, we first extract the embeddings of celebrities' names in the Laion5B dataset with the text encoder of diffusion models. Such embeddings are used as supervision to learn an encoder that can predict the name (actually an embedding) of a given face image. We experimentally find that such name embeddings work well in promising the generated image with good identity consistency. Note that like the names of celebrities, our predicted name embeddings are disentangled from the semantics of text inputs, making the original generation capability of text-to-image models well-preserved. Moreover, by simply plugging such name embeddings, all variants (e.g., from Civitai) derived from the same base model (i.e., SDXL) readily become identity-aware text-to-image models. Project homepage: \url{https://magicfusion.github.io/MagicNaming/}.
Authors: Zhuoran Du, Shaodi You, Cheng Cheng, Shikui Wei
Abstract: Hyperspectral image (HSI) densely samples the world in both the space and frequency domain and therefore is more distinctive than RGB images. Usually, HSI needs to be calibrated to minimize the impact of various illumination conditions. The traditional way to calibrate HSI utilizes a physical reference, which involves manual operations, occlusions, and/or limits camera mobility. These limitations inspire this paper to automatically calibrate HSIs using a learning-based method. Towards this goal, a large-scale HSI calibration dataset is created, which has 765 high-quality HSI pairs covering diversified natural scenes and illuminations. The dataset is further expanded to 7650 pairs by combining with 10 different physically measured illuminations. A spectral illumination transformer (SIT) together with an illumination attention module is proposed. Extensive benchmarks demonstrate the SoTA performance of the proposed SIT. The benchmarks also indicate that low-light conditions are more challenging than normal conditions. The dataset and codes are available online:https://github.com/duranze/Automatic-spectral-calibration-of-HSI
URLs: https://github.com/duranze/Automatic-spectral-calibration-of-HSI
Authors: Zesong Yang, Ru Zhang, Jiale Shi, Zixiang Ai, Boming Zhao, Hujun Bao, Luwei Yang, Zhaopeng Cui
Abstract: Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconstructions in the absence of ground truth mesh remains a significant challenge, due to its rendering-based optimization process and entangled learning of appearance and geometry with photometric losses. In this paper, we present a novel framework, i.e, GURecon, which establishes a geometric uncertainty field for the neural surface based on geometric consistency. Different from existing methods that rely on rendering-based measurement, GURecon models a continuous 3D uncertainty field for the reconstructed surface, and is learned by an online distillation approach without introducing real geometric information for supervision. Moreover, in order to mitigate the interference of illumination on geometric consistency, a decoupled field is learned and exploited to finetune the uncertainty field. Experiments on various datasets demonstrate the superiority of GURecon in modeling 3D geometric uncertainty, as well as its plug-and-play extension to various neural surface representations and improvement on downstream tasks such as incremental reconstruction. The code and supplementary material are available on the project website: https://zju3dv.github.io/GURecon/.
Authors: Nathan Sprague, John Evans, Michael Mardikes
Abstract: Monitoring growth behavior of maize plants such as the development of ears can give key insights into the plant's health and development. Traditionally, the measurement of the angle of ears is performed manually, which can be time-consuming and prone to human error. To address these challenges, this paper presents a computer vision-based system for detecting and tracking ears of corn in an image sequence. The proposed system could accurately detect, track, and predict the ear's orientation, which can be useful in monitoring their growth behavior. This can significantly save time compared to manual measurement and enables additional areas of ear orientation research and potential increase in efficiencies for maize production. Using an object detector with keypoint detection, the algorithm proposed could detect 90 percent of all ears. The cardinal estimation had a mean absolute error (MAE) of 18 degrees, compared to a mean 15 degree difference between two people measuring by hand. These results demonstrate the feasibility of using computer vision techniques for monitoring maize growth and can lead to further research in this area.
Authors: Xianghui Fan, Chao Ye, Anping Deng, Xiaotian Wu, Mengyang Pan, Hang Yang
Abstract: The sensing and manipulation of transparent objects present a critical challenge in industrial and laboratory robotics. Conventional sensors face challenges in obtaining the full depth of transparent objects due to the refraction and reflection of light on their surfaces and their lack of visible texture. Previous research has attempted to obtain complete depth maps of transparent objects from RGB and damaged depth maps (collected by depth sensor) using deep learning models. However, existing methods fail to fully utilize the original depth map, resulting in limited accuracy for deep completion. To solve this problem, we propose TDCNet, a novel dual-branch CNN-Transformer parallel network for transparent object depth completion. The proposed framework consists of two different branches: one extracts features from partial depth maps, while the other processes RGB-D images. Experimental results demonstrate that our model achieves state-of-the-art performance across multiple public datasets. Our code and the pre-trained model are publicly available at https://github.com/XianghuiFan/TDCNet.
Authors: Yiyu Zhuang, Jiaxi Lv, Hao Wen, Qing Shuai, Ailing Zeng, Hao Zhu, Shifeng Chen, Yujiu Yang, Xun Cao, Wei Liu
Abstract: Creating a high-fidelity, animatable 3D full-body avatar from a single image is a challenging task due to the diverse appearance and poses of humans and the limited availability of high-quality training data. To achieve fast and high-quality human reconstruction, this work rethinks the task from the perspectives of dataset, model, and representation. First, we introduce a large-scale HUman-centric GEnerated dataset, HuGe100K, consisting of 100K diverse, photorealistic sets of human images. Each set contains 24-view frames in specific human poses, generated using a pose-controllable image-to-multi-view model. Next, leveraging the diversity in views, poses, and appearances within HuGe100K, we develop a scalable feed-forward transformer model to predict a 3D human Gaussian representation in a uniform space from a given human image. This model is trained to disentangle human pose, body shape, clothing geometry, and texture. The estimated Gaussians can be animated without post-processing. We conduct comprehensive experiments to validate the effectiveness of the proposed dataset and method. Our model demonstrates the ability to efficiently reconstruct photorealistic humans at 1K resolution from a single input image using a single GPU instantly. Additionally, it seamlessly supports various applications, as well as shape and texture editing tasks.
Authors: Kangning Li, Zheyang Jia, Anyu Ying
Abstract: Multimodal video-to-text models have made considerable progress, primarily in generating brief descriptions of video content. However, there is still a deficiency in generating rich long-form text descriptions that integrate both video and audio. In this paper, we introduce a framework called M2S, designed to generate novel-length text by combining audio, video, and character recognition. M2S includes modules for video long-form text description and comprehension, audio-based analysis of emotion, speech rate, and character alignment, and visual-based character recognition alignment. By integrating multimodal information using the large language model GPT4o, M2S stands out in the field of multimodal text generation. We demonstrate the effectiveness and accuracy of M2S through comparative experiments and human evaluation. Additionally, the model framework has good scalability and significant potential for future research.
Authors: Juli\'an O'Flaherty, Rodrigo Paganini, Juan Pablo Sotelo, Julieta Umpi\'errez, Marina Gardella, Mat\'ias Tailanian, Pablo Mus\'e
Abstract: In this paper, we introduce PhotoHolmes, an open-source Python library designed to easily run and benchmark forgery detection methods on digital images. The library includes implementations of popular and state-of-the-art methods, dataset integration tools, and evaluation metrics. Utilizing the Benchmark tool in PhotoHolmes, users can effortlessly compare various methods. This facilitates an accurate and reproducible comparison between their own methods and those in the existing literature. Furthermore, PhotoHolmes includes a command-line interface (CLI) to easily run the methods implemented in the library on any suspicious image. As such, image forgery methods become more accessible to the community. The library has been built with extensibility and modularity in mind, which makes adding new methods, datasets and metrics to the library a straightforward process. The source code is available at https://github.com/photoholmes/photoholmes.
Authors: Jianhua Sun, Yuxuan Li, Jiude Wei, Longfei Xu, Nange Wang, Yining Zhang, Cewu Lu
Abstract: The acquisition of substantial volumes of 3D articulated object data is expensive and time-consuming, and consequently the scarcity of 3D articulated object data becomes an obstacle for deep learning methods to achieve remarkable performance in various articulated object understanding tasks. Meanwhile, pairing these object data with detailed annotations to enable training for various tasks is also difficult and labor-intensive to achieve. In order to expeditiously gather a significant number of 3D articulated objects with comprehensive and detailed annotations for training, we propose Articulated Object Procedural Generation toolbox, a.k.a. Arti-PG toolbox. Arti-PG toolbox consists of i) descriptions of articulated objects by means of a generalized structure program along with their analytic correspondence to the objects' point cloud, ii) procedural rules about manipulations on the structure program to synthesize large-scale and diverse new articulated objects, and iii) mathematical descriptions of knowledge (e.g. affordance, semantics, etc.) to provide annotations to the synthesized object. Arti-PG has two appealing properties for providing training data for articulated object understanding tasks: i) objects are created with unlimited variations in shape through program-oriented structure manipulation, ii) Arti-PG is widely applicable to diverse tasks by easily providing comprehensive and detailed annotations. Arti-PG now supports the procedural generation of 26 categories of articulate objects and provides annotations across a wide range of both vision and manipulation tasks, and we provide exhaustive experiments which fully demonstrate its advantages. We will make Arti-PG toolbox publicly available for the community to use.
Authors: Haitao Tian, Pierre Payeur
Abstract: Existing skeleton-based human action classification models rely on well-trimmed action-specific skeleton videos for both training and testing, precluding their scalability to real-world applications where untrimmed videos exhibiting concatenated actions are predominant. To overcome this limitation, recently introduced skeleton action segmentation models involve un-trimmed skeleton videos into end-to-end training. The model is optimized to provide frame-wise predictions for any length of testing videos, simultaneously realizing action localization and classification. Yet, achieving such an improvement im-poses frame-wise annotated skeleton videos, which remains time-consuming in practice. This paper features a novel framework for skeleton-based action segmentation trained on short trimmed skeleton videos, but that can run on longer un-trimmed videos. The approach is implemented in three steps: Stitch, Contrast, and Segment. First, Stitch proposes a tem-poral skeleton stitching scheme that treats trimmed skeleton videos as elementary human motions that compose a semantic space and can be sampled to generate multi-action stitched se-quences. Contrast learns contrastive representations from stitched sequences with a novel discrimination pretext task that enables a skeleton encoder to learn meaningful action-temporal contexts to improve action segmentation. Finally, Segment relates the proposed method to action segmentation by learning a segmentation layer while handling particular da-ta availability. Experiments involve a trimmed source dataset and an untrimmed target dataset in an adaptation formulation for real-world skeleton-based human action segmentation to evaluate the effectiveness of the proposed method.
Authors: Mang Ning, Mingxiao Li, Jianlin Su, Haozhe Jia, Lanmiao Liu, Martin Bene\v{s}, Albert Ali Salah, Itir Onal Ertugrul
Abstract: This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosine transform (DCT) space. We investigate the design space of DCTdiff and reveal the key design factors. Experiments on different frameworks (UViT, DiT), generation tasks, and various diffusion samplers demonstrate that DCTdiff outperforms pixel-based diffusion models regarding generative quality and training efficiency. Remarkably, DCTdiff can seamlessly scale up to high-resolution generation without using the latent diffusion paradigm. Finally, we illustrate several intriguing properties of DCT image modeling. For example, we provide a theoretical proof of why `image diffusion can be seen as spectral autoregression', bridging the gap between diffusion and autoregressive models. The effectiveness of DCTdiff and the introduced properties suggest a promising direction for image modeling in the frequency space. The code is at \url{https://github.com/forever208/DCTdiff}.
Authors: Zhifei Chen, Tianshuo Xu, Wenhang Ge, Leyi Wu, Dongyu Yan, Jing He, Luozhou Wang, Lu Zeng, Shunsi Zhang, Yingcong Chen
Abstract: Rendering and inverse rendering are pivotal tasks in both computer vision and graphics. The rendering equation is the core of the two tasks, as an ideal conditional distribution transfer function from intrinsic properties to RGB images. Despite achieving promising results of existing rendering methods, they merely approximate the ideal estimation for a specific scene and come with a high computational cost. Additionally, the inverse conditional distribution transfer is intractable due to the inherent ambiguity. To address these challenges, we propose a data-driven method that jointly models rendering and inverse rendering as two conditional generation tasks within a single diffusion framework. Inspired by UniDiffuser, we utilize two distinct time schedules to model both tasks, and with a tailored dual streaming module, we achieve cross-conditioning of two pre-trained diffusion models. This unified approach, named Uni-Renderer, allows the two processes to facilitate each other through a cycle-consistent constrain, mitigating ambiguity by enforcing consistency between intrinsic properties and rendered images. Combined with a meticulously prepared dataset, our method effectively decomposition of intrinsic properties and demonstrates a strong capability to recognize changes during rendering. We will open-source our training and inference code to the public, fostering further research and development in this area.
Authors: G. Andrade-Miranda, K. Chatzipapas, J. D. Arias-Londo\~no, J. I. Godino-Llorente
Abstract: The advances in the development of Facilitative Playbacks extracted from High-Speed videoendoscopic sequences of the vocal folds are hindered by a notable lack of publicly available datasets annotated with the semantic segmentations corresponding to the area of the glottal gap. This fact also limits the reproducibility and further exploration of existing research in this field. To address this gap, GIRAFE is a data repository designed to facilitate the development of advanced techniques for the semantic segmentation, analysis, and fast evaluation of High-Speed videoendoscopic sequences of the vocal folds. The repository includes 65 high-speed videoendoscopic recordings from a cohort of 50 patients (30 female, 20 male). The dataset comprises 15 recordings from healthy controls, 26 from patients with diagnosed voice disorders, and 24 with an unknown health condition. All of them were manually annotated by an expert, including the masks corresponding to the semantic segmentation of the glottal gap. The repository is also complemented with the automatic segmentation of the glottal area using different state-of-the-art approaches. This data set has already supported several studies, which demonstrates its usefulness for the development of new glottal gap segmentation algorithms from High-Speed-Videoendoscopic sequences to improve or create new Facilitative Playbacks. Despite these advances and others in the field, the broader challenge of performing an accurate and completely automatic semantic segmentation method of the glottal area remains open.
Authors: Hallee E. Wong, Jose Javier Gonzalez Ortiz, John Guttag, Adrian V. Dalca
Abstract: Medical researchers and clinicians often need to perform novel segmentation tasks on a set of related images. Existing methods for segmenting a new dataset are either interactive, requiring substantial human effort for each image, or require an existing set of manually labeled images. We introduce a system, MultiverSeg, that enables practitioners to rapidly segment an entire new dataset without requiring access to any existing labeled data from that task or domain. Along with the image to segment, the model takes user interactions such as clicks, bounding boxes or scribbles as input, and predicts a segmentation. As the user segments more images, those images and segmentations become additional inputs to the model, providing context. As the context set of labeled images grows, the number of interactions required to segment each new image decreases. We demonstrate that MultiverSeg enables users to interactively segment new datasets efficiently, by amortizing the number of interactions per image to achieve an accurate segmentation. Compared to using a state-of-the-art interactive segmentation method, using MultiverSeg reduced the total number of scribble steps by 53% and clicks by 36% to achieve 90% Dice on sets of images from unseen tasks. We release code and model weights at https://multiverseg.csail.mit.edu
Authors: Stefanos Gkikas, Manolis Tsiknakis
Abstract: The automatic estimation of pain is essential in designing an optimal pain management system offering reliable assessment and reducing the suffering of patients. In this study, we present a novel full transformer-based framework consisting of a Transformer in Transformer (TNT) model and a Transformer leveraging cross-attention and self-attention blocks. Elaborating on videos from the BioVid database, we demonstrate state-of-the-art performances, showing the efficacy, efficiency, and generalization capability across all the primary pain estimation tasks.
Authors: Lei Tan, Weihao Li, Pingyang Dai, Jie Chen, Liujuan Cao, Rongrong Ji
Abstract: In the realm of Text-Based Person Search (TBPS), mainstream methods aim to explore more efficient interaction frameworks between text descriptions and visual data. However, recent approaches encounter two principal challenges. Firstly, the widely used random-based Masked Language Modeling (MLM) considers all the words in the text equally during training. However, massive semantically vacuous words ('with', 'the', etc.) be masked fail to contribute efficient interaction in the cross-modal MLM and hampers the representation alignment. Secondly, manual descriptions in TBPS datasets are tedious and inevitably contain several inaccuracies. To address these issues, we introduce an Attention-Guided Alignment (AGA) framework featuring two innovative components: Attention-Guided Mask (AGM) Modeling and Text Enrichment Module (TEM). AGM dynamically masks semantically meaningful words by aggregating the attention weight derived from the text encoding process, thereby cross-modal MLM can capture information related to the masked word from text context and images and align their representations. Meanwhile, TEM alleviates low-quality representations caused by repetitive and erroneous text descriptions by replacing those semantically meaningful words with MLM's prediction. It not only enriches text descriptions but also prevents overfitting. Extensive experiments across three challenging benchmarks demonstrate the effectiveness of our AGA, achieving new state-of-the-art results with Rank-1 accuracy reaching 78.36%, 67.31%, and 67.4% on CUHK-PEDES, ICFG-PEDES, and RSTPReid, respectively.
Authors: Yuqing Wang, Shuhuai Ren, Zhijie Lin, Yujin Han, Haoyuan Guo, Zhenheng Yang, Difan Zou, Jiashi Feng, Xihui Liu
Abstract: Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for parallelized autoregressive visual generation that improves generation efficiency while preserving the advantages of autoregressive modeling. Our key insight is that parallel generation depends on visual token dependencies-tokens with weak dependencies can be generated in parallel, while strongly dependent adjacent tokens are difficult to generate together, as their independent sampling may lead to inconsistencies. Based on this observation, we develop a parallel generation strategy that generates distant tokens with weak dependencies in parallel while maintaining sequential generation for strongly dependent local tokens. Our approach can be seamlessly integrated into standard autoregressive models without modifying the architecture or tokenizer. Experiments on ImageNet and UCF-101 demonstrate that our method achieves a 3.6x speedup with comparable quality and up to 9.5x speedup with minimal quality degradation across both image and video generation tasks. We hope this work will inspire future research in efficient visual generation and unified autoregressive modeling. Project page: https://epiphqny.github.io/PAR-project.
Authors: Alexander Kolesnikov, Andr\'e Susano Pinto, Michael Tschannen
Abstract: In the past, normalizing generative flows have emerged as a promising class of generative models for natural images. This type of model has many modeling advantages: the ability to efficiently compute log-likelihood of the input data, fast generation and simple overall structure. Normalizing flows remained a topic of active research but later fell out of favor, as visual quality of the samples was not competitive with other model classes, such as GANs, VQ-VAE-based approaches or diffusion models. In this paper we revisit the design of the coupling-based normalizing flow models by carefully ablating prior design choices and using computational blocks based on the Vision Transformer architecture, not convolutional neural networks. As a result, we achieve state-of-the-art quantitative and qualitative performance with a much simpler architecture. While the overall visual quality is still behind the current state-of-the-art models, we argue that strong normalizing flow models can help advancing research frontier by serving as building components of more powerful generative models.
Authors: Bastian J\"ackl, Yannick Metz, Udo Schlegel, Daniel A. Keim, Maximilian T. Fischer
Abstract: Object-centric architectures can learn to extract distinct object representations from visual scenes, enabling downstream applications on the object level. Similarly to autoencoder-based image models, object-centric approaches have been trained on the unsupervised reconstruction loss of images encoded by RGB color spaces. In our work, we challenge the common assumption that RGB images are the optimal color space for unsupervised learning in computer vision. We discuss conceptually and empirically that other color spaces, such as HSV, bear essential characteristics for object-centric representation learning, like robustness to lighting conditions. We further show that models improve when requiring them to predict additional color channels. Specifically, we propose to transform the predicted targets to the RGB-S space, which extends RGB with HSV's saturation component and leads to markedly better reconstruction and disentanglement for five common evaluation datasets. The use of composite color spaces can be implemented with basically no computational overhead, is agnostic of the models' architecture, and is universally applicable across a wide range of visual computing tasks and training types. The findings of our approach encourage additional investigations in computer vision tasks beyond object-centric learning.
Authors: Yatai Ji, Jiacheng Zhang, Jie Wu, Shilong Zhang, Shoufa Chen, Chongjian GE, Peize Sun, Weifeng Chen, Wenqi Shao, Xuefeng Xiao, Weilin Huang, Ping Luo
Abstract: Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the desired output often entails multiple revisions and iterative inference to refine user-provided prompts. Current automatic methods for refining prompts encounter challenges such as Modality-Inconsistency, Cost-Discrepancy, and Model-Unaware when applied to text-to-video diffusion models. To address these problem, we introduce an LLM-based prompt adaptation framework, termed as Prompt-A-Video, which excels in crafting Video-Centric, Labor-Free and Preference-Aligned prompts tailored to specific video diffusion model. Our approach involves a meticulously crafted two-stage optimization and alignment system. Initially, we conduct a reward-guided prompt evolution pipeline to automatically create optimal prompts pool and leverage them for supervised fine-tuning (SFT) of the LLM. Then multi-dimensional rewards are employed to generate pairwise data for the SFT model, followed by the direct preference optimization (DPO) algorithm to further facilitate preference alignment. Through extensive experimentation and comparative analyses, we validate the effectiveness of Prompt-A-Video across diverse generation models, highlighting its potential to push the boundaries of video generation.
Authors: Jiacheng Zhang, Jie Wu, Weifeng Chen, Yatai Ji, Xuefeng Xiao, Weilin Huang, Kai Han
Abstract: In recent years, the field of text-to-video (T2V) generation has made significant strides. Despite this progress, there is still a gap between theoretical advancements and practical application, amplified by issues like degraded image quality and flickering artifacts. Recent advancements in enhancing the video diffusion model (VDM) through feedback learning have shown promising results. However, these methods still exhibit notable limitations, such as misaligned feedback and inferior scalability. To tackle these issues, we introduce OnlineVPO, a more efficient preference learning approach tailored specifically for video diffusion models. Our method features two novel designs, firstly, instead of directly using image-based reward feedback, we leverage the video quality assessment (VQA) model trained on synthetic data as the reward model to provide distribution and modality-aligned feedback on the video diffusion model. Additionally, we introduce an online DPO algorithm to address the off-policy optimization and scalability issue in existing video preference learning frameworks. By employing the video reward model to offer concise video feedback on the fly, OnlineVPO offers effective and efficient preference guidance. Extensive experiments on the open-source video-diffusion model demonstrate OnlineVPO as a simple yet effective and more importantly scalable preference learning algorithm for video diffusion models, offering valuable insights for future advancements in this domain.
Authors: Shunsuke Saito, Stanislav Pidhorskyi, Igor Santesteban, Forrest Iandola, Divam Gupta, Anuj Pahuja, Nemanja Bartolovic, Frank Yu, Emanuel Garbin, Tomas Simon
Abstract: Gaussian Splatting has enabled real-time 3D human avatars with unprecedented levels of visual quality. While previous methods require a desktop GPU for real-time inference of a single avatar, we aim to squeeze multiple Gaussian avatars onto a portable virtual reality headset with real-time drivable inference. We begin by training a previous work, Animatable Gaussians, on a high quality dataset captured with 512 cameras. The Gaussians are animated by controlling base set of Gaussians with linear blend skinning (LBS) motion and then further adjusting the Gaussians with a neural network decoder to correct their appearance. When deploying the model on a Meta Quest 3 VR headset, we find two major computational bottlenecks: the decoder and the rendering. To accelerate the decoder, we train the Gaussians in UV-space instead of pixel-space, and we distill the decoder to a single neural network layer. Further, we discover that neighborhoods of Gaussians can share a single corrective from the decoder, which provides an additional speedup. To accelerate the rendering, we develop a custom pipeline in Vulkan that runs on the mobile GPU. Putting it all together, we run 3 Gaussian avatars concurrently at 72 FPS on a VR headset. Demo videos are at https://forresti.github.io/squeezeme.
Authors: Or Madar, Ohad Fried
Abstract: Image tiling -- the seamless connection of disparate images to create a coherent visual field -- is crucial for applications such as texture creation, video game asset development, and digital art. Traditionally, tiles have been constructed manually, a method that poses significant limitations in scalability and flexibility. Recent research has attempted to automate this process using generative models. However, current approaches primarily focus on tiling textures and manipulating models for single-image generation, without inherently supporting the creation of multiple interconnected tiles across diverse domains. This paper presents Tiled Diffusion, a novel approach that extends the capabilities of diffusion models to accommodate the generation of cohesive tiling patterns across various domains of image synthesis that require tiling. Our method supports a wide range of tiling scenarios, from self-tiling to complex many-to-many connections, enabling seamless integration of multiple images. Tiled Diffusion automates the tiling process, eliminating the need for manual intervention and enhancing creative possibilities in various applications, such as seamlessly tiling of existing images, tiled texture creation, and 360{\deg} synthesis.
Authors: Sagar Soni, Akshay Dudhane, Hiyam Debary, Mustansar Fiaz, Muhammad Akhtar Munir, Muhammad Sohail Danish, Paolo Fraccaro, Campbell D Watson, Levente J Klein, Fahad Shahbaz Khan, Salman Khan
Abstract: Automated analysis of vast Earth observation data via interactive Vision-Language Models (VLMs) can unlock new opportunities for environmental monitoring, disaster response, and resource management. Existing generic VLMs do not perform well on Remote Sensing data, while the recent Geo-spatial VLMs remain restricted to a fixed resolution and few sensor modalities. In this paper, we introduce EarthDial, a conversational assistant specifically designed for Earth Observation (EO) data, transforming complex, multi-sensory Earth observations into interactive, natural language dialogues. EarthDial supports multi-spectral, multi-temporal, and multi-resolution imagery, enabling a wide range of remote sensing tasks, including classification, detection, captioning, question answering, visual reasoning, and visual grounding. To achieve this, we introduce an extensive instruction tuning dataset comprising over 11.11M instruction pairs covering RGB, Synthetic Aperture Radar (SAR), and multispectral modalities such as Near-Infrared (NIR) and infrared. Furthermore, EarthDial handles bi-temporal and multi-temporal sequence analysis for applications like change detection. Our extensive experimental results on 37 downstream applications demonstrate that EarthDial outperforms existing generic and domain-specific models, achieving better generalization across various EO tasks.
Authors: Moayed Haji-Ali, Willi Menapace, Aliaksandr Siarohin, Ivan Skorokhodov, Alper Canberk, Kwot Sin Lee, Vicente Ordonez, Sergey Tulyakov
Abstract: We propose AV-Link, a unified framework for Video-to-Audio and Audio-to-Video generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that enables bidirectional information exchange between our backbone video and audio diffusion models through a temporally-aligned self attention operation. Unlike prior work that uses feature extractors pretrained for other tasks for the conditioning signal, AV-Link can directly leverage features obtained by the complementary modality in a single framework i.e. video features to generate audio, or audio features to generate video. We extensively evaluate our design choices and demonstrate the ability of our method to achieve synchronized and high-quality audiovisual content, showcasing its potential for applications in immersive media generation. Project Page: snap-research.github.io/AVLink/
Authors: Borui Zhang, Wenzhao Zheng, Jie Zhou, Jiwen Lu
Abstract: Vector-quantized networks (VQNs) have exhibited remarkable performance across various tasks, yet they are prone to training instability, which complicates the training process due to the necessity for techniques such as subtle initialization and model distillation. In this study, we identify the local minima issue as the primary cause of this instability. To address this, we integrate an optimal transport method in place of the nearest neighbor search to achieve a more globally informed assignment. We introduce OptVQ, a novel vector quantization method that employs the Sinkhorn algorithm to optimize the optimal transport problem, thereby enhancing the stability and efficiency of the training process. To mitigate the influence of diverse data distributions on the Sinkhorn algorithm, we implement a straightforward yet effective normalization strategy. Our comprehensive experiments on image reconstruction tasks demonstrate that OptVQ achieves 100% codebook utilization and surpasses current state-of-the-art VQNs in reconstruction quality.
Authors: Chenxu Zhou, Lvchang Fu, Sida Peng, Yunzhi Yan, Zhanhua Zhang, Yong Chen, Jiazhi Xia, Xiaowei Zhou
Abstract: This paper targets the challenge of real-time LiDAR re-simulation in dynamic driving scenarios. Recent approaches utilize neural radiance fields combined with the physical modeling of LiDAR sensors to achieve high-fidelity re-simulation results. Unfortunately, these methods face limitations due to high computational demands in large-scale scenes and cannot perform real-time LiDAR rendering. To overcome these constraints, we propose LiDAR-RT, a novel framework that supports real-time, physically accurate LiDAR re-simulation for driving scenes. Our primary contribution is the development of an efficient and effective rendering pipeline, which integrates Gaussian primitives and hardware-accelerated ray tracing technology. Specifically, we model the physical properties of LiDAR sensors using Gaussian primitives with learnable parameters and incorporate scene graphs to handle scene dynamics. Building upon this scene representation, our framework first constructs a bounding volume hierarchy (BVH), then casts rays for each pixel and generates novel LiDAR views through a differentiable rendering algorithm. Importantly, our framework supports realistic rendering with flexible scene editing operations and various sensor configurations. Extensive experiments across multiple public benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of rendering quality and efficiency. Our project page is at https://zju3dv.github.io/lidar-rt.
Authors: Wang Zhao, Yan-Pei Cao, Jiale Xu, Yuejiang Dong, Ying Shan
Abstract: Procedural Content Generation (PCG) is powerful in creating high-quality 3D contents, yet controlling it to produce desired shapes is difficult and often requires extensive parameter tuning. Inverse Procedural Content Generation aims to automatically find the best parameters under the input condition. However, existing sampling-based and neural network-based methods still suffer from numerous sample iterations or limited controllability. In this work, we present DI-PCG, a novel and efficient method for Inverse PCG from general image conditions. At its core is a lightweight diffusion transformer model, where PCG parameters are directly treated as the denoising target and the observed images as conditions to control parameter generation. DI-PCG is efficient and effective. With only 7.6M network parameters and 30 GPU hours to train, it demonstrates superior performance in recovering parameters accurately, and generalizing well to in-the-wild images. Quantitative and qualitative experiment results validate the effectiveness of DI-PCG in inverse PCG and image-to-3D generation tasks. DI-PCG offers a promising approach for efficient inverse PCG and represents a valuable exploration step towards a 3D generation path that models how to construct a 3D asset using parametric models.
Authors: Sucheng Ren, Qihang Yu, Ju He, Xiaohui Shen, Alan Yuille, Liang-Chieh Chen
Abstract: Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR proposes scale-wise autoregressive modeling, which extends the next token prediction to the next scale prediction, preserving the 2D structure of images. However, VAR encounters two primary challenges: (1) its complex and rigid scale design limits generalization in next scale prediction, and (2) the generator's dependence on a discrete tokenizer with the same complex scale structure restricts modularity and flexibility in updating the tokenizer. To address these limitations, we introduce FlowAR, a general next scale prediction method featuring a streamlined scale design, where each subsequent scale is simply double the previous one. This eliminates the need for VAR's intricate multi-scale residual tokenizer and enables the use of any off-the-shelf Variational AutoEncoder (VAE). Our simplified design enhances generalization in next scale prediction and facilitates the integration of Flow Matching for high-quality image synthesis. We validate the effectiveness of FlowAR on the challenging ImageNet-256 benchmark, demonstrating superior generation performance compared to previous methods. Codes will be available at \url{https://github.com/OliverRensu/FlowAR}.
Authors: Shuo Xing, Hongyuan Hua, Xiangbo Gao, Shenzhe Zhu, Renjie Li, Kexin Tian, Xiaopeng Li, Heng Huang, Tianbao Yang, Zhangyang Wang, Yang Zhou, Huaxiu Yao, Zhengzhong Tu
Abstract: Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeniable candidates for end-to-end driving systems. However, limited work exists on studying the trustworthiness of DriveVLMs -- a critical factor that directly impacts public transportation safety. In this paper, we introduce AutoTrust, a comprehensive trustworthiness benchmark for large vision-language models in autonomous driving (DriveVLMs), considering diverse perspectives -- including trustfulness, safety, robustness, privacy, and fairness. We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios, comprising over 10k unique scenes and 18k queries. We evaluated six publicly available VLMs, spanning from generalist to specialist, from open-source to commercial models. Our exhaustive evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats. Specifically, we found that the general VLMs like LLaVA-v1.6 and GPT-4o-mini surprisingly outperform specialized models fine-tuned for driving in terms of overall trustworthiness. DriveVLMs like DriveLM-Agent are particularly vulnerable to disclosing sensitive information. Additionally, both generalist and specialist VLMs remain susceptible to adversarial attacks and struggle to ensure unbiased decision-making across diverse environments and populations. Our findings call for immediate and decisive action to address the trustworthiness of DriveVLMs -- an issue of critical importance to public safety and the welfare of all citizens relying on autonomous transportation systems. Our benchmark is publicly available at \url{https://github.com/taco-group/AutoTrust}, and the leaderboard is released at \url{https://taco-group.github.io/AutoTrust/}.
URLs: https://github.com/taco-group/AutoTrust, https://taco-group.github.io/AutoTrust/
Authors: Shuo Xing, Chengyuan Qian, Yuping Wang, Hongyuan Hua, Kexin Tian, Yang Zhou, Zhengzhong Tu
Abstract: Since the advent of Multimodal Large Language Models (MLLMs), they have made a significant impact across a wide range of real-world applications, particularly in Autonomous Driving (AD). Their ability to process complex visual data and reason about intricate driving scenarios has paved the way for a new paradigm in end-to-end AD systems. However, the progress of developing end-to-end models for AD has been slow, as existing fine-tuning methods demand substantial resources, including extensive computational power, large-scale datasets, and significant funding. Drawing inspiration from recent advancements in inference computing, we propose OpenEMMA, an open-source end-to-end framework based on MLLMs. By incorporating the Chain-of-Thought reasoning process, OpenEMMA achieves significant improvements compared to the baseline when leveraging a diverse range of MLLMs. Furthermore, OpenEMMA demonstrates effectiveness, generalizability, and robustness across a variety of challenging driving scenarios, offering a more efficient and effective approach to autonomous driving. We release all the codes in https://github.com/taco-group/OpenEMMA.
Authors: Muntasir Wahed, Kiet A. Nguyen, Adheesh Sunil Juvekar, Xinzhuo Li, Xiaona Zhou, Vedant Shah, Tianjiao Yu, Pinar Yanardag, Ismini Lourentzou
Abstract: Despite significant advancements in Large Vision-Language Models (LVLMs), existing pixel-grounding models operate on single-image settings, limiting their ability to perform detailed, fine-grained comparisons across multiple images. Conversely, current multi-image understanding models lack pixel-level grounding. Our work addresses this gap by introducing the task of multi-image pixel-grounded reasoning segmentation, and PRIMA, a novel LVLM that integrates pixel-level grounding with robust multi-image reasoning capabilities to produce contextually rich, pixel-grounded explanations. Central to PRIMA is an efficient vision module that queries fine-grained visual representations across multiple images, reducing TFLOPs by $25.3\%$. To support training and evaluation, we curate $M^4Seg$, a new reasoning segmentation benchmark consisting of $\sim$224K question-answer pairs that require fine-grained visual understanding across multiple images. Experimental results demonstrate PRIMA outperforms state-of-the-art baselines.
Authors: Hadi Alzayer, Philipp Henzler, Jonathan T. Barron, Jia-Bin Huang, Pratul P. Srinivasan, Dor Verbin
Abstract: Reconstructing the geometry and appearance of objects from photographs taken in different environments is difficult as the illumination and therefore the object appearance vary across captured images. This is particularly challenging for more specular objects whose appearance strongly depends on the viewing direction. Some prior approaches model appearance variation across images using a per-image embedding vector, while others use physically-based rendering to recover the materials and per-image illumination. Such approaches fail at faithfully recovering view-dependent appearance given significant variation in input illumination and tend to produce mostly diffuse results. We present an approach that reconstructs objects from images taken under different illuminations by first relighting the images under a single reference illumination with a multiview relighting diffusion model and then reconstructing the object's geometry and appearance with a radiance field architecture that is robust to the small remaining inconsistencies among the relit images. We validate our proposed approach on both synthetic and real datasets and demonstrate that it greatly outperforms existing techniques at reconstructing high-fidelity appearance from images taken under extreme illumination variation. Moreover, our approach is particularly effective at recovering view-dependent "shiny" appearance which cannot be reconstructed by prior methods.
Authors: Jo\~ao Carreira, Dilara Gokay, Michael King, Chuhan Zhang, Ignacio Rocco, Aravindh Mahendran, Thomas Albert Keck, Joseph Heyward, Skanda Koppula, Etienne Pot, Goker Erdogan, Yana Hasson, Yi Yang, Klaus Greff, Guillaume Le Moing, Sjoerd van Steenkiste, Daniel Zoran, Drew A. Hudson, Pedro V\'elez, Luisa Polan\'ia, Luke Friedman, Chris Duvarney, Ross Goroshin, Kelsey Allen, Jacob Walker, Rishabh Kabra, Eric Aboussouan, Jennifer Sun, Thomas Kipf, Carl Doersch, Viorica P\u{a}tr\u{a}ucean, Dima Damen, Pauline Luc, Mehdi S. M. Sajjadi, Andrew Zisserman
Abstract: Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x2013}$ action classification, ImageNet classification, etc. In this paper we focus on evaluating self-supervised learning on non-semantic vision tasks that are more spatial (3D) and temporal (+1D = 4D), such as camera pose estimation, point and object tracking, and depth estimation. We show that by learning from very large video datasets, masked auto-encoding (MAE) with transformer video models actually scales, consistently improving performance on these 4D tasks, as model size increases from 20M all the way to the largest by far reported self-supervised video model $\unicode{x2013}$ 22B parameters. Rigorous apples-to-apples comparison with many recent image and video models demonstrates the benefits of scaling 4D representations.
Authors: Qihao Liu, Xi Yin, Alan Yuille, Andrew Brown, Mannat Singh
Abstract: Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to the target media distribution. For cross-modal tasks such as text-to-image generation, this same mapping from noise to image is learnt whilst including a conditioning mechanism in the model. One key and thus far relatively unexplored feature of flow matching is that, unlike Diffusion models, they are not constrained for the source distribution to be noise. Hence, in this paper, we propose a paradigm shift, and ask the question of whether we can instead train flow matching models to learn a direct mapping from the distribution of one modality to the distribution of another, thus obviating the need for both the noise distribution and conditioning mechanism. We present a general and simple framework, CrossFlow, for cross-modal flow matching. We show the importance of applying Variational Encoders to the input data, and introduce a method to enable Classifier-free guidance. Surprisingly, for text-to-image, CrossFlow with a vanilla transformer without cross attention slightly outperforms standard flow matching, and we show that it scales better with training steps and model size, while also allowing for interesting latent arithmetic which results in semantically meaningful edits in the output space. To demonstrate the generalizability of our approach, we also show that CrossFlow is on par with or outperforms the state-of-the-art for various cross-modal / intra-modal mapping tasks, viz. image captioning, depth estimation, and image super-resolution. We hope this paper contributes to accelerating progress in cross-modal media generation.
Authors: Hanlin Wang, Hao Ouyang, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Qifeng Chen, Yujun Shen, Limin Wang
Abstract: The intuitive nature of drag-based interaction has led to its growing adoption for controlling object trajectories in image-to-video synthesis. Still, existing methods that perform dragging in the 2D space usually face ambiguity when handling out-of-plane movements. In this work, we augment the interaction with a new dimension, i.e., the depth dimension, such that users are allowed to assign a relative depth for each point on the trajectory. That way, our new interaction paradigm not only inherits the convenience from 2D dragging, but facilitates trajectory control in the 3D space, broadening the scope of creativity. We propose a pioneering method for 3D trajectory control in image-to-video synthesis by abstracting object masks into a few cluster points. These points, accompanied by the depth information and the instance information, are finally fed into a video diffusion model as the control signal. Extensive experiments validate the effectiveness of our approach, dubbed LeviTor, in precisely manipulating the object movements when producing photo-realistic videos from static images. Project page: https://ppetrichor.github.io/levitor.github.io/
Authors: Tao Xie, Xi Chen, Zhen Xu, Yiman Xie, Yudong Jin, Yujun Shen, Sida Peng, Hujun Bao, Xiaowei Zhou
Abstract: Reconstructing complex reflections in real-world scenes from 2D images is essential for achieving photorealistic novel view synthesis. Existing methods that utilize environment maps to model reflections from distant lighting often struggle with high-frequency reflection details and fail to account for near-field reflections. In this work, we introduce EnvGS, a novel approach that employs a set of Gaussian primitives as an explicit 3D representation for capturing reflections of environments. These environment Gaussian primitives are incorporated with base Gaussian primitives to model the appearance of the whole scene. To efficiently render these environment Gaussian primitives, we developed a ray-tracing-based renderer that leverages the GPU's RT core for fast rendering. This allows us to jointly optimize our model for high-quality reconstruction while maintaining real-time rendering speeds. Results from multiple real-world and synthetic datasets demonstrate that our method produces significantly more detailed reflections, achieving the best rendering quality in real-time novel view synthesis.
Authors: Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari
Abstract: We propose an unsupervised model for instruction-based image editing that eliminates the need for ground-truth edited images during training. Existing supervised methods depend on datasets containing triplets of input image, edited image, and edit instruction. These are generated by either existing editing methods or human-annotations, which introduce biases and limit their generalization ability. Our method addresses these challenges by introducing a novel editing mechanism called Cycle Edit Consistency (CEC), which applies forward and backward edits in one training step and enforces consistency in image and attention spaces. This allows us to bypass the need for ground-truth edited images and unlock training for the first time on datasets comprising either real image-caption pairs or image-caption-edit triplets. We empirically show that our unsupervised technique performs better across a broader range of edits with high fidelity and precision. By eliminating the need for pre-existing datasets of triplets, reducing biases associated with supervised methods, and proposing CEC, our work represents a significant advancement in unblocking scaling of instruction-based image editing.
Authors: Roberto Daza, Alvaro Becerra, Ruth Cobos, Julian Fierrez, Aythami Morales
Abstract: This work presents the IMPROVE dataset, designed to evaluate the effects of mobile phone usage on learners during online education. The dataset not only assesses academic performance and subjective learner feedback but also captures biometric, behavioral, and physiological signals, providing a comprehensive analysis of the impact of mobile phone use on learning. Multimodal data were collected from 120 learners in three groups with different phone interaction levels. A setup involving 16 sensors was implemented to collect data that have proven to be effective indicators for understanding learner behavior and cognition, including electroencephalography waves, videos, eye tracker, etc. The dataset includes metadata from the processed videos like face bounding boxes, facial landmarks, and Euler angles for head pose estimation. In addition, learner performance data and self-reported forms are included. Phone usage events were labeled, covering both supervisor-triggered and uncontrolled events. A semi-manual re-labeling system, using head pose and eye tracker data, is proposed to improve labeling accuracy. Technical validation confirmed signal quality, with statistical analyses revealing biometric changes during phone use.
Authors: Pei Chen, Fudong Wang, Yixuan Tong, Jingdong Chen, Ming Yang, Minghui Yang
Abstract: Recently, the surge of efficient and automated 3D AI-generated content (AIGC) methods has increasingly illuminated the path of transforming human imagination into complex 3D structures. However, the automated generation of 3D content is still significantly lags in industrial application. This gap exists because 3D modeling demands high-quality assets with sharp geometry, exquisite topology, and physically based rendering (PBR), among other criteria. To narrow the disparity between generated results and artists' expectations, we introduce GraphicsDreamer, a method for creating highly usable 3D meshes from single images. To better capture the geometry and material details, we integrate the PBR lighting equation into our cross-domain diffusion model, concurrently predicting multi-view color, normal, depth images, and PBR materials. In the geometry fusion stage, we continue to enforce the PBR constraints, ensuring that the generated 3D objects possess reliable texture details, supporting realistic relighting. Furthermore, our method incorporates topology optimization and fast UV unwrapping capabilities, allowing the 3D products to be seamlessly imported into graphics engines. Extensive experiments demonstrate that our model can produce high quality 3D assets in a reasonable time cost compared to previous methods.
Authors: Diogo Lameira, Filipa Ferraz
Abstract: Advances in imaging technologies have revolutionised the medical imaging and healthcare sectors, leading to the widespread adoption of PACS for the storage, retrieval, and communication of medical images. Although these systems have improved operational efficiency, significant challenges remain in effectively retrieving DICOM images, which are essential for diagnosis and overall patient care. Moreover, issues such as fragmented systems, interoperability barriers, and complex user interfaces can often prevent healthcare professionals from efficiently accessing medical images. Addressing these challenges, the Transversal PACS Browser API is a robust and user-friendly solution designed to enhance the process of querying and retrieving DICOM images. It offers advanced filtering capabilities through a variety of filter options as well as a custom field search, that allows users to easily navigate through large medical image collections with ease. Additionally, the application provides a unified interface for querying and retrieving from multiple PACS stations, addressing the challenges of fragmentation and complexity associated with accessing medical images. Other key features include the ability to pre-view images directly within the application. All of this contributes to the transversal nature of the API, serving not only healthcare providers, but anyone who relies on efficient access to these resources. To validate the performance and usability of the application, comprehensive testing was carried out with stakeholders of the field, the results of which showed general satisfaction, highlighting the API's clean design, ease of use, and effective search capabilities of the API, as well as the usefulness of previewing images within the application.
Authors: Dipam Goswami, Simone Magistri, Kai Wang, Bart{\l}omiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
Abstract: Using pre-trained models has been found to reduce the effect of data heterogeneity and speed up federated learning algorithms. Recent works have investigated the use of first-order statistics and second-order statistics to aggregate local client data distributions at the server and achieve very high performance without any training. In this work we propose a training-free method based on an unbiased estimator of class covariance matrices. Our method, which only uses first-order statistics in the form of class means communicated by clients to the server, incurs only a fraction of the communication costs required by methods based on communicating second-order statistics. We show how these estimated class covariances can be used to initialize a linear classifier, thus exploiting the covariances without actually sharing them. When compared to state-of-the-art methods which also share only class means, our approach improves performance in the range of 4-26\% with exactly the same communication cost. Moreover, our method achieves performance competitive or superior to sharing second-order statistics with dramatically less communication overhead. Finally, using our method to initialize classifiers and then performing federated fine-tuning yields better and faster convergence. Code is available at https://github.com/dipamgoswami/FedCOF.
Authors: Alexis Fox, Samarth Swarup, Abhijin Adiga
Abstract: Considering the difficulty of interpreting generative model output, there is significant current research focused on determining meaningful evaluation metrics. Several recent approaches utilize "precision" and "recall," borrowed from the classification domain, to individually quantify the output fidelity (realism) and output diversity (representation of the real data variation), respectively. With the increase in metric proposals, there is a need for a unifying perspective, allowing for easier comparison and clearer explanation of their benefits and drawbacks. To this end, we unify a class of kth-nearest-neighbors (kNN)-based metrics under an information-theoretic lens using approaches from kNN density estimation. Additionally, we propose a tri-dimensional metric composed of Precision Cross-Entropy (PCE), Recall Cross-Entropy (RCE), and Recall Entropy (RE), which separately measure fidelity and two distinct aspects of diversity, inter- and intra-class. Our domain-agnostic metric, derived from the information-theoretic concepts of entropy and cross-entropy, can be dissected for both sample- and mode-level analysis. Our detailed experimental results demonstrate the sensitivity of our metric components to their respective qualities and reveal undesirable behaviors of other metrics.
Authors: Na Min An, Eunki Kim, James Thorne, Hyunjung Shim
Abstract: Contrastive Language-Image Pretraining (CLIP) enables zero-shot inference in downstream tasks such as image-text retrieval and classification. However, recent works extending CLIP suffer from the issue of modality gap, which arises when the image and text embeddings are projected to disparate manifolds, deviating from the intended objective of image-text contrastive learning. We discover that this phenomenon is linked to the modality-specific characteristic that each image/text encoder independently possesses and propose two methods to address the modality gap: (1) a post-hoc embedding standardization method, $\text{I0T}_{\text{post}}$ that reduces the modality gap approximately to zero and (2) a trainable method, $\text{I0T}_{\text{async}}$, to alleviate the modality gap problem by adding two normalization layers for each encoder. Our I0T framework can significantly reduce the modality gap while preserving the original embedding representations of trained models with their locked parameters. In practice, $\text{I0T}_{\text{post}}$ can serve as an alternative explainable automatic evaluation metric of widely used CLIPScore (CLIP-S).
Authors: Ainaz Eftekhar, Luca Weihs, Rose Hendrix, Ege Caglar, Jordi Salvador, Alvaro Herrasti, Winson Han, Eli VanderBil, Aniruddha Kembhavi, Ali Farhadi, Ranjay Krishna, Kiana Ehsani, Kuo-Hao Zeng
Abstract: Modern robots vary significantly in shape, size, and sensor configurations used to perceive and interact with their environments. However, most navigation policies are embodiment-specific; a policy learned using one robot's configuration does not typically gracefully generalize to another. Even small changes in the body size or camera viewpoint may cause failures. With the recent surge in custom hardware developments, it is necessary to learn a single policy that can be transferred to other embodiments, eliminating the need to (re)train for each specific robot. In this paper, we introduce RING (Robotic Indoor Navigation Generalist), an embodiment-agnostic policy, trained solely in simulation with diverse randomly initialized embodiments at scale. Specifically, we augment the AI2-THOR simulator with the ability to instantiate robot embodiments with controllable configurations, varying across body size, rotation pivot point, and camera configurations. In the visual object-goal navigation task, RING achieves robust performance on real unseen robot platforms (Stretch RE-1, LoCoBot, Unitree's Go1), achieving an average of 72.1% and 78.9% success rate across 5 embodiments in simulation and 4 robot platforms in the real world. (project website: https://one-ring-policy.allen.ai/)
Authors: Xin Huang, Eric M. Wolff, Paul Vernaza, Tung Phan-Minh, Hongge Chen, David S. Hayden, Mark Edmonds, Brian Pierce, Xinxin Chen, Pratik Elias Jacob, Xiaobai Chen, Chingiz Tairbekov, Pratik Agarwal, Tianshi Gao, Yuning Chai, Siddhartha Srinivasa
Abstract: We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms a state-of-the-art baseline and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.
Authors: Saumya Saxena, Blake Buchanan, Chris Paxton, Bingqing Chen, Narunas Vaskevicius, Luigi Palmieri, Jonathan Francis, Oliver Kroemer
Abstract: In Embodied Question Answering (EQA), agents must explore and develop a semantic understanding of an unseen environment in order to answer a situated question with confidence. This remains a challenging problem in robotics, due to the difficulties in obtaining useful semantic representations, updating these representations online, and leveraging prior world knowledge for efficient exploration and planning. Aiming to address these limitations, we propose GraphEQA, a novel approach that utilizes real-time 3D metric-semantic scene graphs (3DSGs) and task relevant images as multi-modal memory for grounding Vision-Language Models (VLMs) to perform EQA tasks in unseen environments. We employ a hierarchical planning approach that exploits the hierarchical nature of 3DSGs for structured planning and semantic-guided exploration. Through experiments in simulation on the HM-EQA dataset and in the real world in home and office environments, we demonstrate that our method outperforms key baselines by completing EQA tasks with higher success rates and fewer planning steps.
Authors: Ran Lyu (Virginia Tech), Linhan Wang (Virginia Tech), Yanshen Sun (Virginia Tech), Hedanqiu Bai (Texas A&M University), Chang-Tien Lu (Virginia Tech)
Abstract: Climate change is intensifying rainfall extremes, making high-resolution precipitation projections crucial for society to better prepare for impacts such as flooding. However, current Global Climate Models (GCMs) operate at spatial resolutions too coarse for localized analyses. To address this limitation, deep learning-based statistical downscaling methods offer promising solutions, providing high-resolution precipitation projections with a moderate computational cost. In this work, we introduce a bias-informed conditional diffusion model for statistical downscaling of precipitation. Specifically, our model leverages a conditional diffusion approach to learn distribution priors from large-scale, high-resolution precipitation datasets. The long-tail distribution of precipitation poses a unique challenge for training diffusion models; to address this, we apply gamma correction during preprocessing. Additionally, to correct biases in the downscaled results, we employ a guided-sampling strategy to enhance bias correction. Our experiments demonstrate that the proposed model achieves highly accurate results in an 8 times downscaling setting, outperforming previous deterministic methods. The code and dataset are available at https://github.com/RoseLV/research_super-resolution
Authors: Masanari Ohi, Masahiro Kaneko, Naoaki Okazaki, Nakamasa Inoue
Abstract: Vision-language models (VLMs) have shown impressive abilities in text and image understanding. However, existing metrics for evaluating the text generated by VLMs focus exclusively on overall quality, leading to two limitations: 1) it is challenging to identify which aspects of the text need improvement from the overall score; 2) metrics may overlook specific evaluation criteria when predicting an overall score. To address these limitations, we propose HarmonicEval, a reference-free evaluation metric that aggregates criterion-wise scores to produce the overall score in a bottom-up manner. Furthermore, we construct the Multi-task Multi-criteria Human Evaluation (MMHE) dataset, which comprises 18,000 expert human judgments across four vision-language tasks. Our experiments demonstrate that HarmonicEval achieves higher correlations with human judgments than conventional metrics while providing numerical scores for each criterion.
Authors: Kexin Li, You-wei Wen, Xu Xiao, Mingchao Zhao
Abstract: Robust Principal Component Analysis (RPCA) is a fundamental technique for decomposing data into low-rank and sparse components, which plays a critical role for applications such as image processing and anomaly detection. Traditional RPCA methods commonly use $\ell_1$ norm regularization to enforce sparsity, but this approach can introduce bias and result in suboptimal estimates, particularly in the presence of significant noise or outliers. Non-convex regularization methods have been proposed to mitigate these challenges, but they tend to be complex to optimize and sensitive to initial conditions, leading to potential instability in solutions. To overcome these challenges, in this paper, we propose a novel RPCA model that integrates adaptive weighted least squares (AWLS) and low-rank matrix factorization (LRMF). The model employs a {self-attention-inspired} mechanism in its weight update process, allowing the weight matrix to dynamically adjust and emphasize significant components during each iteration. By employing a weighted F-norm for the sparse component, our method effectively reduces bias while simplifying the computational process compared to traditional $\ell_1$-norm-based methods. We use an alternating minimization algorithm, where each subproblem has an explicit solution, thereby improving computational efficiency. Despite its simplicity, numerical experiments demonstrate that our method outperforms existing non-convex regularization approaches, offering superior performance and stability, as well as enhanced accuracy and robustness in practical applications.
Authors: Guanting Dong, Chenghao Zhang, Mengjie Deng, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen
Abstract: Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs through Active Retrieval (AR) and Monte Carlo Tree Search (MCTS). Our approach begins with the development of a unified retrieval module that retrieves key supporting insights for solving complex reasoning problems from a hybrid-modal retrieval corpus. To bridge the gap in automated multimodal reasoning verification, we employ the MCTS algorithm combined with an active retrieval mechanism, which enables the automatic generation of step-wise annotations. This strategy dynamically retrieves key insights for each reasoning step, moving beyond traditional beam search sampling to improve the diversity and reliability of the reasoning space. Additionally, we introduce a process reward model that aligns progressively to support the automatic verification of multimodal reasoning tasks. Experimental results across three complex multimodal reasoning benchmarks confirm the effectiveness of the AR-MCTS framework in enhancing the performance of various multimodal models. Further analysis demonstrates that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
Authors: Litingyu Wang, Wenjun Liao, Shichuan Zhang, Guotai Wang
Abstract: Head and neck tumors and metastatic lymph nodes are crucial for treatment planning and prognostic analysis. Accurate segmentation and quantitative analysis of these structures require pixel-level annotation, making automated segmentation techniques essential for the diagnosis and treatment of head and neck cancer. In this study, we investigated the effects of multiple strategies on the segmentation of pre-radiotherapy (pre-RT) and mid-radiotherapy (mid-RT) images. For the segmentation of pre-RT images, we utilized: 1) a fully supervised learning approach, and 2) the same approach enhanced with pre-trained weights and the MixUp data augmentation technique. For mid-RT images, we introduced a novel computational-friendly network architecture that features separate encoders for mid-RT images and registered pre-RT images with their labels. The mid-RT encoder branch integrates information from pre-RT images and labels progressively during the forward propagation. We selected the highest-performing model from each fold and used their predictions to create an ensemble average for inference. In the final test, our models achieved a segmentation performance of 82.38% for pre-RT and 72.53% for mid-RT on aggregated Dice Similarity Coefficient (DSC) as HiLab. Our code is available at https://github.com/WltyBY/HNTS-MRG2024_train_code.
Authors: Leonardo Barcellona, Andrii Zadaianchuk, Davide Allegro, Samuele Papa, Stefano Ghidoni, Efstratios Gavves
Abstract: A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot directly and explicitly imitate the actual environment in front of a robot, often resulting in unrealistic behaviors and hallucinations that make them unsuitable for real-world applications. In this paper, we introduce a new paradigm for constructing world models that are explicit representations of the real world and its dynamics. By integrating cutting-edge advances in real-time photorealism with Gaussian Splatting and physics simulators, we propose the first compositional manipulation world model, which we call DreMa. DreMa replicates the observed world and its dynamics, allowing it to imagine novel configurations of objects and predict the future consequences of robot actions. We leverage this capability to generate new data for imitation learning by applying equivariant transformations to a small set of demonstrations. Our evaluations across various settings demonstrate significant improvements in both accuracy and robustness by incrementing actions and object distributions, reducing the data needed to learn a policy and improving the generalization of the agents. As a highlight, we show that a real Franka Emika Panda robot, powered by DreMa's imagination, can successfully learn novel physical tasks from just a single example per task variation (one-shot policy learning). Our project page and source code can be found in https://leobarcellona.github.io/DreamToManipulate/
Authors: Ozgu Goksu, Nicolas Pugeault
Abstract: The development of highly sophisticated neural networks has allowed for fast progress in every field of computer vision, however, applications where annotated data is prohibited due to privacy or security concerns remain challenging. Federated Learning (FL) offers a promising framework for individuals aiming to collaboratively develop a shared model while preserving data privacy. Nevertheless, our findings reveal that variations in data distribution among clients can profoundly affect FL methodologies, primarily due to instabilities in the aggregation process. We also propose a novel FL framework to mitigate the adverse effects of covariate shifts among federated clients by combining individual parameter pruning and regularization techniques to improve the robustness of individual clients' models to aggregate. Each client's model is optimized through magnitude-based pruning and the addition of dropout and noise injection layers to build more resilient decision pathways in the networks and improve the robustness of the model's parameter aggregation step. The proposed framework is capable of extracting robust representations even in the presence of very large covariate shifts among client data distributions and in the federation of a small number of clients. Empirical findings substantiate the effectiveness of our proposed methodology across common benchmark datasets, including CIFAR10, MNIST, SVHN, and Fashion MNIST. Furthermore, we introduce the CelebA-Gender dataset, specifically designed to evaluate performance on a more realistic domain. The proposed method is capable of extracting robust representations even in the presence of both high and low covariate shifts among client data distributions.
Authors: Riccardo Fosco Gramaccioni, Christian Marinoni, Emilian Postolache, Marco Comunit\`a, Luca Cosmo, Joshua D. Reiss, Danilo Comminiello
Abstract: Sound designers and Foley artists usually sonorize a scene, such as from a movie or video game, by manually annotating and sonorizing each action of interest in the video. In our case, the intent is to leave full creative control to sound designers with a tool that allows them to bypass the more repetitive parts of their work, thus being able to focus on the creative aspects of sound production. We achieve this presenting Stable-V2A, a two-stage model consisting of: an RMS-Mapper that estimates an envelope representative of the audio characteristics associated with the input video; and Stable-Foley, a diffusion model based on Stable Audio Open that generates audio semantically and temporally aligned with the target video. Temporal alignment is guaranteed by the use of the envelope as a ControlNet input, while semantic alignment is achieved through the use of sound representations chosen by the designer as cross-attention conditioning of the diffusion process. We train and test our model on Greatest Hits, a dataset commonly used to evaluate V2A models. In addition, to test our model on a case study of interest, we introduce Walking The Maps, a dataset of videos extracted from video games depicting animated characters walking in different locations. Samples and code available on our demo page at https://ispamm.github.io/Stable-V2A.
Authors: Zhu Liao, Nour Hezbri, Victor Qu\'etu, Van-Tam Nguyen, Enzo Tartaglione
Abstract: Today, deep neural networks are widely used since they can handle a variety of complex tasks. Their generality makes them very powerful tools in modern technology. However, deep neural networks are often overparameterized. The usage of these large models consumes a lot of computation resources. In this paper, we introduce a method called \textbf{T}ill the \textbf{L}ayers \textbf{C}ollapse (TLC), which compresses deep neural networks through the lenses of batch normalization layers. By reducing the depth of these networks, our method decreases deep neural networks' computational requirements and overall latency. We validate our method on popular models such as Swin-T, MobileNet-V2, and RoBERTa, across both image classification and natural language processing (NLP) tasks.
Authors: Weijia Shi, Xiaochuang Han, Chunting Zhou, Weixin Liang, Xi Victoria Lin, Luke Zettlemoyer, Lili Yu
Abstract: We present LlamaFusion, a framework for empowering pretrained text-only large language models (LLMs) with multimodal generative capabilities, enabling them to understand and generate both text and images in arbitrary sequences. LlamaFusion leverages existing Llama-3's weights for processing texts autoregressively while introducing additional and parallel transformer modules for processing images with diffusion. During training, the data from each modality is routed to its dedicated modules: modality-specific feedforward layers, query-key-value projections, and normalization layers process each modality independently, while the shared self-attention layers allow interactions across text and image features. By freezing the text-specific modules and only training the image-specific modules, LlamaFusion preserves the language capabilities of text-only LLMs while developing strong visual understanding and generation abilities. Compared to methods that pretrain multimodal generative models from scratch, our experiments demonstrate that, LlamaFusion improves image understanding by 20% and image generation by 3.6% using only 50% of the FLOPs while maintaining Llama-3's language capabilities. We also demonstrate that this framework can adapt existing vision-language models with multimodal generation ability. Overall, this framework not only leverages existing computational investments in text-only LLMs but also enables the parallel development of language and vision capabilities, presenting a promising direction for efficient multimodal model development.
Authors: Seonguk Seo, Mustafa Gokhan Uzunbas, Bohyung Han, Sara Cao, Ser-Nam Lim
Abstract: Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computational cost and even entails the downtime of the service. Although backward-compatible learning sidesteps this challenge by tackling query-side representations, this leads to suboptimal solutions in principle because gallery embeddings cannot benefit from model upgrades. We address this dilemma by introducing an online backfilling algorithm, which enables us to achieve a progressive performance improvement during the backfilling process while not sacrificing the final performance of new model after the completion of backfilling. To this end, we first propose a simple distance rank merge technique for online backfilling. Then, we incorporate a reverse transformation module for more effective and efficient merging, which is further enhanced by adopting a metric-compatible contrastive learning approach. These two components help to make the distances of old and new models compatible, resulting in desirable merge results during backfilling with no extra computational overhead. Extensive experiments show the effectiveness of our framework on four standard benchmarks in various settings.
Authors: Riccardo Munaf\`o, Simone Saitta, Giacomo Ingallina, Paolo Denti, Francesco Maisano, Eustachio Agricola, Alberto Redaelli, Emiliano Votta
Abstract: 3D transesophageal echocardiography (3DTEE), is the recommended method for diagnosing mitral regurgitation (MR). 3DTEE provides a high-quality 3D image of the mitral valve (MV), allowing for precise segmentation and measurement of the regurgitant valve anatomy. However, manual TEE segmentations are time-consuming and prone to intra-operator variability, affecting the reliability of the measurements. To address this, we developed a fully automated pipeline using a 3D convolutional neural network (CNN) to segment MV substructures (annulus, anterior leaflet, and posterior leaflet) and quantify MV anatomy. The 3D CNN, based on a multi-decoder residual U-Net architecture, was trained and tested on a dataset comprising 100 3DTEE images with corresponding segmentations. Within the pipeline, a custom algorithm refines the CNN-based segmentations and extracts MV models, from which anatomical landmarks and features are quantified. The accuracy of the proposed method was assessed using Dice score and mean surface distance (MSD) against ground truth segmentations, and the extracted anatomical parameters were compared against a semiautomated commercial software TomTec Image Arena. The trained 3D CNN achieved an average Dice score of 0.79 and MSD of 0.47 mm for the combined segmentation of the annulus, anterior and posterior leaflet. The proposed CNN architecture outperformed a baseline residual U-Net architecture in MV substructure segmentation, and the refinement of the predicted annulus segmentation improved MSD by 8.36%. The annular and leaflet linear measurements differed by less than 7.94 mm and 3.67 mm, respectively, compared to the 3D measurements obtained with TomTec Image Arena. The proposed pipeline was faster than the commercial software, with a modeling time of 12.54 s and a quantification time of 54.42 s.
Authors: Tuomas Jalonen, Mohammad Al-Sa'd, Roope Mellanen, Serkan Kiranyaz, Moncef Gabbouj
Abstract: The health and safety hazards posed by worn crane lifting ropes mandate periodic inspection for damage. This task is time-consuming, prone to human error, halts operation, and may result in the premature disposal of ropes. Therefore, we propose using efficient deep learning and computer vision methods to automate the process of detecting damaged ropes. Specifically, we present a vision-based system for detecting damage in synthetic fiber rope images using lightweight convolutional neural networks. We develop a camera-based apparatus to photograph the lifting rope's surface, while in operation, and capture the progressive wear-and-tear as well as the more significant degradation in the rope's health state. Experts from Konecranes annotate the collected images in accordance with the rope's condition; normal or damaged. Then, we pre-process the images, systematically design a deep learning model, evaluate its detection and prediction performance, analyze its computational complexity, and compare it with various other models. Experimental results show the proposed model outperforms other similar techniques with 96.5% accuracy, 94.8% precision, 98.3% recall, 96.5% F1-score, and 99.3% AUC. Besides, they demonstrate the model's real-time operation, low memory footprint, robustness to various environmental and operational conditions, and adequacy for deployment in industrial applications such as lifting, mooring, towing, climbing, and sailing.
Authors: Fan Yang
Abstract: The use of deep learning methods for automatic detection of students' classroom behavior is a promising approach to analyze their class performance and enhance teaching effectiveness. However, the lack of publicly available datasets on student behavior poses a challenge for researchers in this field. To address this issue, we propose a Student Classroom Behavior dataset (SCB-dataset) that reflects real-life scenarios. Our dataset includes 11,248 labels and 4,003 images, with a focus on hand-raising behavior. We evaluated the dataset using the YOLOv7 algorithm, achieving a mean average precision (map) of up to 85.3%. We believe that our dataset can serve as a robust foundation for future research in the field of student behavior detection and promote further advancements in this area.Our SCB-dataset can be downloaded from: https://github.com/Whiffe/SCB-dataset
Authors: Shaocong Xu, Pengfei Li, Qianpu Sun, Xinyu Liu, Yang Li, Shihui Guo, Zhen Wang, Bo Jiang, Rui Wang, Kehua Sheng, Bo Zhang, Li Jiang, Hao Zhao, Yilun Chen
Abstract: LiDAR-based semantic scene understanding is an important module in the modern autonomous driving perception stack. However, identifying outlier points in a LiDAR point cloud is challenging as LiDAR point clouds lack semantically-rich information. While former SOTA methods adopt heuristic architectures, we revisit this problem from the perspective of Selective Classification, which introduces a selective function into the standard closed-set classification setup. Our solution is built upon the basic idea of abstaining from choosing any inlier categories but learns a point-wise abstaining penalty with a margin-based loss. Apart from learning paradigms, synthesizing outliers to approximate unlimited real outliers is also critical, so we propose a strong synthesis pipeline that generates outliers originated from various factors: object categories, sampling patterns and sizes. We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance. We benchmark our method on SemanticKITTI and nuScenes and achieve SOTA results. Codes are available at https://github.com/Daniellli/LiON/.
Authors: Aritra Bhowmik, Pascal Mettes, Martin R. Oswald, Cees G. M. Snoek
Abstract: This paper revisits the problem of predicting box locations in object detection architectures. Typically, each box proposal or box query aims to directly maximize the intersection-over-union score with the ground truth, followed by a winner-takes-all non-maximum suppression where only the highest scoring box in each region is retained. We observe that both steps are sub-optimal: the first involves regressing proposals to the entire ground truth, which is a difficult task even with large receptive fields, and the second neglects valuable information from boxes other than the top candidate. Instead of regressing proposals to the whole ground truth, we propose a simpler approach: regress only to the area of intersection between the proposal and the ground truth. This avoids the need for proposals to extrapolate beyond their visual scope, improving localization accuracy. Rather than adopting a winner-takes-all strategy, we take the union over the regressed intersections of all boxes in a region to generate the final box outputs. Our plug-and-play method integrates seamlessly into proposal-based, grid-based, and query-based detection architectures with minimal modifications, consistently improving object localization and instance segmentation. We demonstrate its broad applicability and versatility across various detection and segmentation tasks.
Authors: Zhiyi Pan, Nan Zhang, Wei Gao, Shan Liu, Ge Li
Abstract: Utilizing uniformly distributed sparse annotations, weakly supervised learning alleviates the heavy reliance on fine-grained annotations in point cloud semantic segmentation tasks. However, few works discuss the inhomogeneity of sparse annotations, albeit it is common in real-world scenarios. Therefore, this work introduces the probability density function into the gradient sampling approximation method to qualitatively analyze the impact of annotation sparsity and inhomogeneity under weakly supervised learning. Based on our analysis, we propose an Adaptive Annotation Distribution Network (AADNet) capable of robust learning on arbitrarily distributed sparse annotations. Specifically, we propose a label-aware point cloud downsampling strategy to increase the proportion of annotations involved in the training stage. Furthermore, we design the multiplicative dynamic entropy as the gradient calibration function to mitigate the gradient bias caused by non-uniformly distributed sparse annotations and explicitly reduce the epistemic uncertainty. Without any prior restrictions and additional information, our proposed method achieves comprehensive performance improvements at multiple label rates and different annotation distributions.
Authors: Yawen Xiang, Heng Zhou, Chengyang Li, Fangwei Sun, Zhongbo Li, Yongqiang Xie
Abstract: Motion deblurring is one of the fundamental problems of computer vision and has received continuous attention. The variability in blur, both within and across images, imposes limitations on non-blind deblurring techniques that rely on estimating the blur kernel. As a response, blind motion deblurring has emerged, aiming to restore clear and detailed images without prior knowledge of the blur type, fueled by the advancements in deep learning methodologies. Despite strides in this field, a comprehensive synthesis of recent progress in deep learning-based blind motion deblurring is notably absent. This paper fills that gap by providing an exhaustive overview of the role of deep learning in blind motion deblurring, encompassing datasets, evaluation metrics, and methods developed over the last six years. Specifically, we first introduce the types of motion blur and the fundamental principles of deblurring. Next, we outline the shortcomings of traditional non-blind deblurring algorithms, emphasizing the advantages of employing deep learning techniques for deblurring tasks. Following this, we categorize and summarize existing blind motion deblurring methods based on different backbone networks, including convolutional neural networks, generative adversarial networks, recurrent neural networks, and Transformer networks. Subsequently, we elaborate not only on the fundamental principles of these different categories but also provide a comprehensive summary and comparison of their advantages and limitations. Qualitative and quantitative experimental results conducted on four widely used datasets further compare the performance of SOTA methods. Finally, an analysis of present challenges and future pathways. All collected models, benchmark datasets, source code links, and codes for evaluation have been made publicly available at https://github.com/VisionVerse/Blind-Motion-Deblurring-Survey
URLs: https://github.com/VisionVerse/Blind-Motion-Deblurring-Survey
Authors: Zhihong Chen, Maya Varma, Justin Xu, Magdalini Paschali, Dave Van Veen, Andrew Johnston, Alaa Youssef, Louis Blankemeier, Christian Bluethgen, Stephan Altmayer, Jeya Maria Jose Valanarasu, Mohamed Siddig Eltayeb Muneer, Eduardo Pontes Reis, Joseph Paul Cohen, Cameron Olsen, Tanishq Mathew Abraham, Emily B. Tsai, Christopher F. Beaulieu, Jenia Jitsev, Sergios Gatidis, Jean-Benoit Delbrouck, Akshay S. Chaudhari, Curtis P. Langlotz
Abstract: Over 1.4 billion chest X-rays (CXRs) are performed annually due to their cost-effectiveness as an initial diagnostic test. This scale of radiological studies provides a significant opportunity to streamline CXR interpretation and documentation. While foundation models are a promising solution, the lack of publicly available large-scale datasets and benchmarks inhibits their iterative development and real-world evaluation. To overcome these challenges, we constructed a large-scale dataset (CheXinstruct), which we utilized to train a vision-language foundation model (CheXagent). We systematically demonstrated competitive performance across eight distinct task types on our novel evaluation benchmark (CheXbench). Beyond technical validation, we assessed the real-world utility of CheXagent in directly drafting radiology reports. Our clinical assessment with eight radiologists revealed a 36% time saving for residents using CheXagent-drafted reports, while attending radiologists showed no significant time difference editing resident-drafted or CheXagent-drafted reports. The CheXagent-drafted reports improved the writing efficiency of both radiology residents and attending radiologists in 81% and 61% of cases, respectively, without loss of quality. Overall, we demonstrate that CheXagent can effectively perform a variety of CXR interpretation tasks and holds potential to assist radiologists in routine clinical workflows.
Authors: Qirui Jiao, Daoyuan Chen, Yilun Huang, Yaliang Li, Ying Shen
Abstract: Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing fine-grained image details, prompting researchers to use them to enhance MLLMs. One effective strategy is to infuse detection information in text format, which has proven simple and effective. However, most studies utilize this method without training, leaving the potential of adaptive training largely unexplored. Adaptive training could significantly enhance MLLMs' comprehension of unique inputs while filtering out irrelevant information. This paper addresses the crucial question: How does training impact MLLMs' understanding of infused textual detection information? We systematically experiment with various representative models to evaluate the effects of training-free, retraining, and fine-tuning strategies. We also examine the influence of training on MLLMs' original abilities and the interchangeability of detection models. Our findings indicate that fine-tuning a pre-trained MLLM to incorporate textual detection information delivers superior results compared to training-free and retraining methods, improving performance by 6.71% across 10 widely recognized benchmarks. Furthermore, fine-tuning enables MLLMs to retain performance enhancements even when detection models are swapped, indicating improved understanding of formatted textual data. We release our codes to support further exploration of fusion strategies for vision detection models and the enhancement of MLLMs' fine-grained multimodal capabilities.
Authors: Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo
Abstract: Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains. A highly effective CTTA method involves applying layer-wise adaptive learning rates for selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. This work aims to overcome these limitations by identifying layers for adaptation via quantifying model prediction uncertainty without relying on pseudo-labels. We utilize the magnitude of gradients as a metric, calculated by backpropagating the KL divergence between the softmax output and a uniform distribution, to select layers for further adaptation. Subsequently, for the parameters exclusively belonging to these selected layers, with the remaining ones frozen, we evaluate their sensitivity to approximate the domain shift and adjust their learning rates accordingly. We conduct extensive image classification experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C, demonstrating the superior efficacy of our method compared to prior approaches.
Authors: Jingkun An, Yinghao Zhu, Zongjian Li, Enshen Zhou, Haoran Feng, Xijie Huang, Bohua Chen, Yemin Shi, Chengwei Pan
Abstract: Text-to-Image (T2I) diffusion models have achieved remarkable success in image generation. Despite their progress, challenges remain in both prompt-following ability, image quality and lack of high-quality datasets, which are essential for refining these models. As acquiring labeled data is costly, we introduce AGFSync, a framework that enhances T2I diffusion models through Direct Preference Optimization (DPO) in a fully AI-driven approach. AGFSync utilizes Vision-Language Models (VLM) to assess image quality across style, coherence, and aesthetics, generating feedback data within an AI-driven loop. By applying AGFSync to leading T2I models such as SD v1.4, v1.5, and SDXL-base, our extensive experiments on the TIFA dataset demonstrate notable improvements in VQA scores, aesthetic evaluations, and performance on the HPSv2 benchmark, consistently outperforming the base models. AGFSync's method of refining T2I diffusion models paves the way for scalable alignment techniques. Our code and dataset are publicly available at https://anjingkun.github.io/AGFSync.
Authors: Ming Gui, Johannes Schusterbauer, Ulrich Prestel, Pingchuan Ma, Dmytro Kotovenko, Olga Grebenkova, Stefan Andreas Baumann, Vincent Tao Hu, Bj\"orn Ommer
Abstract: Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency by integrating external knowledge from a pre-trained image diffusion model, enabling effective transfer even across differing objectives. To further boost our model performance, we employ synthetic data and utilize image-depth pairs generated by a discriminative model on an in-the-wild image dataset. As a generative model, our model can reliably estimate depth confidence, which provides an additional advantage. Our approach achieves competitive zero-shot performance on standard benchmarks of complex natural scenes while improving sampling efficiency and only requiring minimal synthetic data for training.
Authors: Geon Yeong Park, Hyeonho Jeong, Sang Wan Lee, Jong Chul Ye
Abstract: The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion, etc. Despite these advances, challenges persist in accurately distilling motion information from video frames. While existing works leverage the consecutive frame residual as the target motion vector, they inherently lack global motion context and are vulnerable to frame-wise distortions. To address this, we present Spectral Motion Alignment (SMA), a novel framework that refines and aligns motion vectors using Fourier and wavelet transforms. SMA learns motion patterns by incorporating frequency-domain regularization, facilitating the learning of whole-frame global motion dynamics, and mitigating spatial artifacts. Extensive experiments demonstrate SMA's efficacy in improving motion transfer while maintaining computational efficiency and compatibility across various video customization frameworks.
Authors: Chao Pang, Xingxing Weng, Jiang Wu, Jiayu Li, Yi Liu, Jiaxing Sun, Weijia Li, Shuai Wang, Litong Feng, Gui-Song Xia, Conghui He
Abstract: This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly understand remote sensing images and perform diverse remote sensing tasks. Moreover, different from existing remote sensing instruction datasets that only include factual questions, HnstD contains additional deceptive questions stemming from the non-existence of objects. This feature prevents VHM from producing affirmative answers to nonsense queries, thereby ensuring its honesty. In our experiments, VHM significantly outperforms various vision language models on common tasks of scene classification, visual question answering, and visual grounding. Additionally, VHM achieves competent performance on several unexplored tasks, such as building vectorizing, multi-label classification and honest question answering. We will release the code, data and model weights at https://github.com/opendatalab/VHM .
Authors: Ziyang Chen, Wei Long, He Yao, Yongjun Zhang, Bingshu Wang, Yongbin Qin, Jia Wu
Abstract: Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at https://github.com/ZYangChen/MoCha-Stereo.
Authors: Zhiwei Wang, Ying Zhou, Shiquan He, Ting Li, Fan Huang, Qiang Ding, Xinxia Feng, Mei Liu, Qiang Li
Abstract: Photometric constraint is indispensable for self-supervised monocular depth estimation. It involves warping a source image onto a target view using estimated depth&pose, and then minimizing the difference between the warped and target images. However, the endoscopic built-in light causes significant brightness fluctuations, and thus makes the photometric constraint unreliable. Previous efforts only mitigate this relying on extra models to calibrate image brightness. In this paper, we propose MonoPCC to address the brightness inconsistency radically by reshaping the photometric constraint into a cycle form. Instead of only warping the source image, MonoPCC constructs a closed loop consisting of two opposite forward-backward warping paths: from target to source and then back to target. Thus, the target image finally receives an image cycle-warped from itself, which naturally makes the constraint invariant to brightness changes. Moreover, MonoPCC transplants the source image's phase-frequency into the intermediate warped image to avoid structure lost, and also stabilizes the training via an exponential moving average (EMA) strategy to avoid frequent changes in the forward warping. The comprehensive and extensive experimental results on four endoscopic datasets demonstrate that our proposed MonoPCC shows a great robustness to the brightness inconsistency, and exceeds other state-of-the-arts by reducing the absolute relative error by at least 7.27%, 9.38%, 9.90% and 3.17%, respectively.
Authors: Donggyun Kim, Seongwoong Cho, Semin Kim, Chong Luo, Seunghoon Hong
Abstract: Large language models have evolved data-efficient generalists, benefiting from the universal language interface and large-scale pre-training. However, constructing a data-efficient generalist for dense visual prediction presents a distinct challenge due to the variation in label structures across different tasks. Consequently, generalization to unseen dense prediction tasks in the low-data regime is not straightforward and has received less attention from previous vision generalists. In this study, we explore a universal model that can flexibly adapt to unseen dense label structures with a few examples, enabling it to serve as a data-efficient vision generalist in diverse real-world scenarios. To this end, we base our method on a powerful meta-learning framework and explore several axes to improve its performance and versatility for real-world problems, such as flexible adaptation mechanisms and scalability. We evaluate our model across a spectrum of unseen real-world scenarios where low-shot learning is desirable, including video, 3D, medical, biological, and user-interactive tasks. Equipped with a generic architecture and an effective adaptation mechanism, our model flexibly adapts to all of these tasks with at most 50 labeled images, showcasing a significant advancement over existing data-efficient generalist approaches. Codes are available at https://github.com/GitGyun/chameleon.
Authors: Jing Xu, Anqi Zhu, Jingyu Lin, Qiuhong Ke, Cunjian Chen
Abstract: Human action recognition is crucial in computer vision systems. However, in real-world scenarios, human actions often fall outside the distribution of training data, requiring a model to both recognize in-distribution (ID) actions and reject out-of-distribution (OOD) ones. Despite its importance, there has been limited research on OOD detection in human actions. Existing works on OOD detection mainly focus on image data with RGB structure, and many methods are post-hoc in nature. While these methods are convenient and computationally efficient, they often lack sufficient accuracy, fail to consider the exposure of OOD samples, and ignore the application in skeleton structure data. To address these challenges, we propose a novel end-to-end skeleton-based model called Skeleton-OOD, which is committed to improving the effectiveness of OOD tasks while ensuring the accuracy of ID recognition. Through extensive experiments conducted on NTU-RGB+D 60, NTU-RGB+D 120, and Kinetics-400 datasets, Skeleton-OOD demonstrates the superior performance of our proposed approach compared to state-of-the-art methods. Our findings underscore the effectiveness of classic OOD detection techniques in the context of skeleton-based action recognition tasks, offering promising avenues for future research in this field. Code is available at https://github.com/YilliaJing/Skeleton-OOD.git.
Authors: Xiaolong Sun, Liushuai Shi, Le Wang, Sanping Zhou, Kun Xia, Yabing Wang, Gang Hua
Abstract: Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer from overlapped and redundant proposals, leading to inaccurate predictions. We attribute this limitation to the lack of task-related guidance for the learnable queries to serve a specific mode. Furthermore, the complex solution space generated by variable and open-vocabulary language descriptions complicates optimization, making it harder for learnable queries to distinguish each other adaptively. To tackle this limitation, we present a Region-Guided TRansformer (RGTR) for temporal sentence grounding, which diversifies moment queries to eliminate overlapped and redundant predictions. Instead of using learnable queries, RGTR adopts a set of anchor pairs as moment queries to introduce explicit regional guidance. Each anchor pair takes charge of moment prediction for a specific temporal region, which reduces the optimization difficulty and ensures the diversity of the final predictions. In addition, we design an IoU-aware scoring head to improve proposal quality. Extensive experiments demonstrate the effectiveness of RGTR, outperforming state-of-the-art methods on QVHighlights, Charades-STA and TACoS datasets. Codes are available at https://github.com/TensorsSun/RGTR
Authors: Tero Karras, Miika Aittala, Tuomas Kynk\"a\"anniemi, Jaakko Lehtinen, Timo Aila, Samuli Laine
Abstract: The primary axes of interest in image-generating diffusion models are image quality, the amount of variation in the results, and how well the results align with a given condition, e.g., a class label or a text prompt. The popular classifier-free guidance approach uses an unconditional model to guide a conditional model, leading to simultaneously better prompt alignment and higher-quality images at the cost of reduced variation. These effects seem inherently entangled, and thus hard to control. We make the surprising observation that it is possible to obtain disentangled control over image quality without compromising the amount of variation by guiding generation using a smaller, less-trained version of the model itself rather than an unconditional model. This leads to significant improvements in ImageNet generation, setting record FIDs of 1.01 for 64x64 and 1.25 for 512x512, using publicly available networks. Furthermore, the method is also applicable to unconditional diffusion models, drastically improving their quality.
Authors: Liting Huang, Zhihao Zhang, Yiran Zhang, Xiyue Zhou, Shoujin Wang
Abstract: The recent generative AI models' capability of creating realistic and human-like content is significantly transforming the ways in which people communicate, create and work. The appropriate use of generative AI models can benefit society, while their misuse poses threats to the society. However, the lack of aligned multimodal datasets has inhibited the development of effective and robust methods for detecting machine-generated content, particularly in triple-modality settings (e.g., text, image, and voice). In this paper, we introduce RU-AI, a new large-scale multimodal dataset for robust and efficient detection of machine-generated content in text, image and voice. Our dataset is constructed on the basis of three large publicly available datasets: Flickr8K, COCO and Places205, by adding their corresponding AI duplicates, resulting total of 1,475,370 data instances. In addition, we create a noise variant of each modality of the datasets aiming to analyse the models' robustness. Given our dataset, we conduct extensive experiments with the current SOTA detection methods. The results reveal that existing models still struggle to achieve accurate and robust classification after training on our dataset. The RU-AI dataset is designed to support the development of detection methods across modalities and can be effectively utilised for identifying machine-generated content. The source code and dataset are available at https://github.com/ZhihaoZhang97/RU-AI.
Authors: Haowen Hou, Peigen Zeng, Fei Ma, Fei Richard Yu
Abstract: Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV.
Authors: Jinkun Hao, Junshu Tang, Jiangning Zhang, Ran Yi, Yijia Hong, Moran Li, Weijian Cao, Yating Wang, Chengjie Wang, Lizhuang Ma
Abstract: While recent works have achieved great success on image-to-3D object generation, high quality and fidelity 3D head generation from a single image remains a great challenge. Previous text-based methods for generating 3D heads were limited by text descriptions and image-based methods struggled to produce high-quality head geometry. To handle this challenging problem, we propose a novel framework, ID-Sculpt, to generate high-quality 3D heads while preserving their identities. Our work incorporates the identity information of the portrait image into three parts: 1) geometry initialization, 2) geometry sculpting, and 3) texture generation stages. Given a reference portrait image, we first align the identity features with text features to realize ID-aware guidance enhancement, which contains the control signals representing the face information. We then use the canny map, ID features of the portrait image, and a pre-trained text-to-normal/depth diffusion model to generate ID-aware geometry supervision, and 3D-GAN inversion is employed to generate ID-aware geometry initialization. Furthermore, with the ability to inject identity information into 3D head generation, we use ID-aware guidance to calculate ID-aware Score Distillation (ISD) for geometry sculpting. For texture generation, we adopt the ID Consistent Texture Inpainting and Refinement which progressively expands the view for texture inpainting to obtain an initialization UV texture map. We then use the ID-aware guidance to provide image-level supervision for noisy multi-view images to obtain a refined texture map. Extensive experiments demonstrate that we can generate high-quality 3D heads with accurate geometry and texture from a single in-the-wild portrait image.
Authors: Jaihyun Lew, Jooyoung Choi, Chaehun Shin, Dahuin Jung, Sungroh Yoon
Abstract: Video Frame Interpolation (VFI) aims to synthesize intermediate frames between existing frames to enhance visual smoothness and quality. Beyond the conventional methods based on the reconstruction loss, recent works have employed generative models for improved perceptual quality. However, they require complex training and large computational costs for pixel space modeling. In this paper, we introduce disentangled Motion Modeling (MoMo), a diffusion-based approach for VFI that enhances visual quality by focusing on intermediate motion modeling. We propose a disentangled two-stage training process. In the initial stage, frame synthesis and flow models are trained to generate accurate frames and flows optimal for synthesis. In the subsequent stage, we introduce a motion diffusion model, which incorporates our novel U-Net architecture specifically designed for optical flow, to generate bi-directional flows between frames. By learning the simpler low-frequency representation of motions, MoMo achieves superior perceptual quality with reduced computational demands compared to the generative modeling methods on the pixel space. MoMo surpasses state-of-the-art methods in perceptual metrics across various benchmarks, demonstrating its efficacy and efficiency in VFI.
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: Zihan Gao, Lingling Li, Licheng Jiao, Fang Liu, Xu Liu, Wenping Ma, Yuwei Guo, Shuyuan Yang
Abstract: Understanding 3D scenes is a crucial challenge in computer vision research with applications spanning multiple domains. Recent advancements in distilling 2D vision-language foundation models into neural fields, like NeRF and 3DGS, enable open-vocabulary segmentation of 3D scenes from 2D multi-view images without the need for precise 3D annotations. However, while effective, these methods typically rely on the per-pixel distillation of high-dimensional CLIP features, introducing ambiguity and necessitating complex regularization strategies, which adds inefficiency during training. This paper presents MaskField, which enables efficient 3D open-vocabulary segmentation with neural fields from a novel perspective. Unlike previous methods, MaskField decomposes the distillation of mask and semantic features from foundation models by formulating a mask feature field and queries. MaskField overcomes ambiguous object boundaries by naturally introducing SAM segmented object shapes without extra regularization during training. By circumventing the direct handling of dense high-dimensional CLIP features during training, MaskField is particularly compatible with explicit scene representations like 3DGS. Our extensive experiments show that MaskField not only surpasses prior state-of-the-art methods but also achieves remarkably fast convergence. We hope that MaskField will inspire further exploration into how neural fields can be trained to comprehend 3D scenes from 2D models.
Authors: Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Gustavo Adolfo Vargas Hakim, David Osowiechi, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers
Abstract: Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited control over the diversity of generated images and lack assurance that these images span distinct distributions. To address these challenges, we propose FDS, Feedback-guided Domain Synthesis, a novel strategy that employs diffusion models to synthesize novel, pseudo-domains by training a single model on all source domains and performing domain mixing based on learned features. By incorporating images that pose classification challenges to models trained on original samples, alongside the original dataset, we ensure the generation of a training set that spans a broad distribution spectrum. Our comprehensive evaluations demonstrate that this methodology sets new benchmarks in domain generalization performance across a range of challenging datasets, effectively managing diverse types of domain shifts. The code can be found at: \url{https://github.com/Mehrdad-Noori/FDS.git}.
Authors: Haozhe Zhao, Xiaojian Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, Baobao Chang
Abstract: This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix and MagicBrush, and provide a systematic approach to producing massive and high-quality image editing samples. UltraEdit offers several distinct advantages: 1) It features a broader range of editing instructions by leveraging the creativity of large language models (LLMs) alongside in-context editing examples from human raters; 2) Its data sources are based on real images, including photographs and artworks, which provide greater diversity and reduced bias compared to datasets solely generated by text-to-image models; 3) It also supports region-based editing, enhanced by high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on UltraEdit set new records on MagicBrush and Emu-Edit benchmarks. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models can be found in https://ultra-editing.github.io.
Authors: Jeongseok Hyun, Su Ho Han, Hyolim Kang, Joon-Young Lee, Seon Joo Kim
Abstract: The vocabulary size in temporal action localization (TAL) is limited by the scarcity of large-scale annotated datasets. To overcome this, recent works integrate vision-language models (VLMs), such as CLIP, for open-vocabulary TAL (OV-TAL). However, despite the success of VLMs trained on extensive datasets, existing OV-TAL methods still rely on human-labeled TAL datasets of limited size to train action localizers, limiting their generalizability. In this paper, we explore the scalability of self-training with unlabeled YouTube videos for OV-TAL. Our approach consists of two stages: (1) a class-agnostic action localizer is trained on a human-labeled TAL dataset to generate pseudo-labels for unlabeled videos, and (2) the large-scale pseudo-labeled dataset is then used to train the localizer. Extensive experiments demonstrate that leveraging web-scale videos in self-training significantly enhances the generalizability of an action localizer. Additionally, we identify limitations in existing OV-TAL evaluation schemes and propose a new benchmark for thorough assessment. Finally, we showcase the TAL performance of the large multimodal model Gemini-1.5 on our new benchmark. Code is released at https://github.com/HYUNJS/STOV-TAL.
Authors: Jinting Luo, Ru Li, Chengzhi Jiang, Xiaoming Zhang, Mingyan Han, Ting Jiang, Haoqiang Fan, Shuaicheng Liu
Abstract: We propose Diff-Shadow, a global-guided diffusion model for shadow removal. Previous transformer-based approaches can utilize global information to relate shadow and non-shadow regions but are limited in their synthesis ability and recover images with obvious boundaries. In contrast, diffusion-based methods can generate better content but they are not exempt from issues related to inconsistent illumination. In this work, we combine the advantages of diffusion models and global guidance to achieve shadow-free restoration. Specifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images. A Reweight Cross Attention (RCA) module is designed to integrate global contextual information of non-shadow regions into the local branch. We further design a Global-guided Sampling Strategy (GSS) that mitigates patch boundary issues and ensures consistent illumination across shaded and unshaded regions in the recovered image. Comprehensive experiments on datasets ISTD, ISTD+, and SRD have demonstrated the effectiveness of Diff-Shadow. Compared to state-of-the-art methods, our method achieves a significant improvement in terms of PSNR, increasing from 32.33dB to 33.69dB on the ISTD dataset.
Authors: Aditya Kapoor, Harshad Khadilkar, Jayvardhana Gubbi
Abstract: Distortion identification and rectification in images and videos is vital for achieving good performance in downstream vision applications. Instead of relying on fixed trial-and-error based image processing pipelines, we propose a two-level sequential planning approach for automated image distortion classification and rectification. At the higher level it detects the class of corruptions present in the input image, if any. The lower level selects a specific algorithm to be applied, from a set of externally provided candidate algorithms. The entire two-level setup runs in the form of a single forward pass during inference and it is to be queried iteratively until the retrieval of the original image. We demonstrate improvements compared to three baselines on the object detection task on COCO image dataset with rich set of distortions. The advantage of our approach is its dynamic reconfiguration, conditioned on the input image and generalisability to unseen candidate algorithms at inference time, since it relies only on the comparison of their output of the image embeddings.
Authors: Junyan Ye, Jun He, Weijia Li, Zhutao Lv, Yi Lin, Jinhua Yu, Haote Yang, Conghui He
Abstract: Ground-to-aerial image synthesis focuses on generating realistic aerial images from corresponding ground street view images while maintaining consistent content layout, simulating a top-down view. The significant viewpoint difference leads to domain gaps between views, and dense urban scenes limit the visible range of street views, making this cross-view generation task particularly challenging. In this paper, we introduce SkyDiffusion, a novel cross-view generation method for synthesizing aerial images from street view images, utilizing a diffusion model and the Bird's-Eye View (BEV) paradigm. The Curved-BEV method in SkyDiffusion converts street-view images into a BEV perspective, effectively bridging the domain gap, and employs a "multi-to-one" mapping strategy to address occlusion issues in dense urban scenes. Next, SkyDiffusion designed a BEV-guided diffusion model to generate content-consistent and realistic aerial images. Additionally, we introduce a novel dataset, Ground2Aerial-3, designed for diverse ground-to-aerial image synthesis applications, including disaster scene aerial synthesis, historical high-resolution satellite image synthesis, and low-altitude UAV image synthesis tasks. Experimental results demonstrate that SkyDiffusion outperforms state-of-the-art methods on cross-view datasets across natural (CVUSA), suburban (CVACT), urban (VIGOR-Chicago), and various application scenarios (G2A-3), achieving realistic and content-consistent aerial image generation. More result and dataset information can be found at https://opendatalab.github.io/skydiffusion/ .
Authors: Qirui Jiao, Daoyuan Chen, Yilun Huang, Bolin Ding, Yaliang Li, Ying Shen
Abstract: High-performance Multimodal Large Language Models (MLLMs) are heavily dependent on data quality. To advance fine-grained image recognition within MLLMs, we introduce a novel data synthesis method inspired by contrastive learning and image difference captioning. Our key idea involves challenging the model to discern both matching and distinct elements by scrutinizing object differences in detailed regions across similar images. We begin by generating pairs of similar images that emphasize object variations. Following this, we employ a Difference Area Generator to pinpoint object differences, and subsequently, a Difference Captions Generator to articulate these differences. This process results in a high-quality dataset of "object replacement" samples, termed Img-Diff, which can be scaled as needed due to its automated nature. We leverage this generated dataset to fine-tune state-of-the-art (SOTA) MLLMs, such as InternVL2, achieving substantial improvements across various image difference and Visual Question Answering tasks. Notably, the trained models significantly outperform existing SOTA models like GPT-4V and Gemini on the MMVP benchmark. Additionally, we conduct comprehensive evaluations to validate the dataset's diversity, quality, and robustness, offering several insights into the synthesis of such contrastive datasets. We release our codes and dataset to encourage further research on multimodal data synthesis and MLLMs' fundamental capabilities for image understanding.
Authors: Jihwan Kim, Miso Lee, Cheol-Ho Cho, Jihyun Lee, Jae-Pil Heo
Abstract: Temporal Action Detection (TAD) is fundamental yet challenging for real-world video applications. Leveraging the unique benefits of transformers, various DETR-based approaches have been adopted in TAD. However, it has recently been identified that the attention collapse in self-attention causes the performance degradation of DETR for TAD. Building upon previous research, this paper newly addresses the attention collapse problem in cross-attention within DETR-based TAD methods. Moreover, our findings reveal that cross-attention exhibits patterns distinct from predictions, indicating a short-cut phenomenon. To resolve this, we propose a new framework, Prediction-Feedback DETR (Pred-DETR), which utilizes predictions to restore the collapse and align the cross- and self-attention with predictions. Specifically, we devise novel prediction-feedback objectives using guidance from the relations of the predictions. As a result, Pred-DETR significantly alleviates the collapse and achieves state-of-the-art performance among DETR-based methods on various challenging benchmarks including THUMOS14, ActivityNet-v1.3, HACS, and FineAction.
Authors: Yi Chen, Jian Xu, Xu-Yao Zhang, Wen-Zhuo Liu, Yang-Yang Liu, Cheng-Lin Liu
Abstract: With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current large-scale multimodal models achieve this by mapping visual features obtained from the visual encoder into a large language model and using them as inputs alongside text for downstream tasks. Therefore, the number of visual tokens directly affects the training and inference speed of the model. There has been significant work on token pruning for visual transformers, but for large multimodal models, only relying on visual information for token pruning or compression may lead to significant loss of important information. On the other hand, the textual input in the form of a question may contain valuable information that can aid in answering the question, providing additional knowledge to the model. To address the potential oversimplification and excessive pruning that can occur with most purely visual token pruning methods, we propose a text information-guided dynamic visual token recovery mechanism that does not require training. This mechanism leverages the similarity between the question text and visual tokens to recover visually meaningful tokens with important text information while merging other less important tokens. Experimental results demonstrate that our proposed method achieves comparable performance to the original approach while compressing the visual tokens to an average of 10% of the original quantity. Our source code will be made publicly available following acceptance.
Authors: Changsong Liu, Wei Zhang, Yanyan Liu, Mingyang Li, Wenlin Li, Yimeng Fan, Xiangnan Bai, Liang Zhang
Abstract: Edge detection, as a fundamental task in computer vision, has garnered increasing attention. The advent of deep learning has significantly advanced this field. However, recent deep learning-based methods generally face two significant issues: 1) reliance on large-scale pre-trained weights, and 2) generation of thick edges. We construct a U-shape encoder-decoder model named CPD-Net that successfully addresses these two issues simultaneously. In response to issue 1), we propose a novel cycle pixel difference convolution (CPDC), which effectively integrates edge prior knowledge with modern convolution operations, consequently successfully eliminating the dependence on large-scale pre-trained weights. As for issue 2), we construct a multi-scale information enhancement module (MSEM) and a dual residual connection-based (DRC) decoder to enhance the edge location ability of the model, thereby generating crisp and clean contour maps. Comprehensive experiments conducted on four standard benchmarks demonstrate that our method achieves competitive performance on the BSDS500 dataset (ODS=0.813 and AC=0.352), NYUD-V2 (ODS=0.760 and AC=0.223), BIPED dataset (ODS=0.898 and AC=0.426), and CID (ODS=0.59). Our approach provides a novel perspective for addressing these challenges in edge detection.
Authors: Shuo Wang, Chunlong Xia, Feng Lv, Yifeng Shi
Abstract: RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian matching provides much sparser supervision, leading to insufficient model training and difficult to achieve optimal results. To address these issues, we proposed a hierarchical dense positive supervision method based on RT-DETR, named RT-DETRv3. Firstly, we introduce a CNN-based auxiliary branch that provides dense supervision that collaborates with the original decoder to enhance the encoder feature representation. Secondly, to address insufficient decoder training, we propose a novel learning strategy involving self-attention perturbation. This strategy diversifies label assignment for positive samples across multiple query groups, thereby enriching positive supervisions. Additionally, we introduce a shared-weight decoder branch for dense positive supervision to ensure more high-quality queries matching each ground truth. Notably, all aforementioned modules are training-only. We conduct extensive experiments to demonstrate the effectiveness of our approach on COCO val2017. RT-DETRv3 significantly outperforms existing real-time detectors, including the RT-DETR series and the YOLO series. For example, RT-DETRv3-R18 achieves 48.1% AP (+1.6%/+1.4%) compared to RT-DETR-R18/RT-DETRv2-R18, while maintaining the same latency. Furthermore, RT-DETRv3-R101 can attain an impressive 54.6% AP outperforming YOLOv10-X. The code will be released at https://github.com/clxia12/RT-DETRv3.
Authors: J\'er\'emy Lebreton, Ingo Ahrns, Roland Brochard, Christoph Haskamp, Hans Kr\"uger, Matthieu Le Goff, Nicolas Menga, Nicolas Ollagnier, Ralf Regele, Francesco Capolupo, Massimo Casasco
Abstract: Vision Based Navigation consists in utilizing cameras as precision sensors for GNC after extracting information from images. To enable the adoption of machine learning for space applications, one of obstacles is the demonstration that available training datasets are adequate to validate the algorithms. The objective of the study is to generate datasets of images and metadata suitable for training machine learning algorithms. Two use cases were selected and a robust methodology was developed to validate the datasets including the ground truth. The first use case is in-orbit rendezvous with a man-made object: a mockup of satellite ENVISAT. The second use case is a Lunar landing scenario. Datasets were produced from archival datasets (Chang'e 3), from the laboratory at DLR TRON facility and at Airbus Robotic laboratory, from SurRender software high fidelity image simulator using Model Capture and from Generative Adversarial Networks. The use case definition included the selection of algorithms as benchmark: an AI-based pose estimation algorithm and a dense optical flow algorithm were selected. Eventually it is demonstrated that datasets produced with SurRender and selected laboratory facilities are adequate to train machine learning algorithms.
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 specific data, we identify an unintended utility drop-correlation collapse-in which the essential correlations between image features and true labels weaken 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: Katja Ludwig, Julian Lorenz, Daniel Kienzle, Tuan Bui, Rainer Lienhart
Abstract: The basic body shape (i.e., the body shape in T-pose) of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different, thus inconsistent basic body shape for each video frame. Furthermore, we find that SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated 3D keypoint positions. We solve the problem of inconsistent body shapes by leveraging anthropometric measurements like taken by tailors from humans. We create a model called A2B that converts given anthropometric measurements to basic body shape parameters of human mesh models. We obtain superior and consistent human meshes by combining the A2B model results with the keypoints of 3D HPE models using inverse kinematics. We evaluate our approach on challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing estimates of the body shape parameters from existing HME models with A2B results not only increases the performance of these HME models, but also guarantees consistent body shapes.
Authors: Ameer Hamza, Abdullah, Yong Hyun Ahn, Sungyoung Lee, Seong Tae Kim
Abstract: Generating Natural Language Explanations (NLEs) for model predictions on medical images, particularly those depicting thoracic pathologies, remains a critical and challenging task. Existing methodologies often struggle due to general models' insufficient domain-specific medical knowledge and privacy concerns associated with retrieval-based augmentation techniques. To address these issues, we propose a novel Vision-Language framework augmented with a Knowledge Graph (KG)-based datastore, which enhances the model's understanding by incorporating additional domain-specific medical knowledge essential for generating accurate and informative NLEs. Our framework employs a KG-based retrieval mechanism that not only improves the precision of the generated explanations but also preserves data privacy by avoiding direct data retrieval. The KG datastore is designed as a plug-and-play module, allowing for seamless integration with various model architectures. We introduce and evaluate three distinct frameworks within this paradigm: KG-LLaVA, which integrates the pre-trained LLaVA model with KG-RAG; Med-XPT, a custom framework combining MedCLIP, a transformer-based projector, and GPT-2; and Bio-LLaVA, which adapts LLaVA by incorporating the Bio-ViT-L vision model. These frameworks are validated on the MIMIC-NLE dataset, where they achieve state-of-the-art results, underscoring the effectiveness of KG augmentation in generating high-quality NLEs for thoracic pathologies.
Authors: Chong-Yang Xiang, Jun-Yan He, Zhi-Qi Cheng, Xiao Wu, Xian-Sheng Hua
Abstract: Achieving a balance between accuracy and efficiency is a critical challenge in facial landmark detection (FLD). This paper introduces Parallel Optimal Position Search (POPoS), a high-precision encoding-decoding framework designed to address the limitations of traditional FLD methods. POPoS employs three key contributions: (1) Pseudo-range multilateration is utilized to correct heatmap errors, improving landmark localization accuracy. By integrating multiple anchor points, it reduces the impact of individual heatmap inaccuracies, leading to robust overall positioning. (2) To enhance the pseudo-range accuracy of selected anchor points, a new loss function, named multilateration anchor loss, is proposed. This loss function enhances the accuracy of the distance map, mitigates the risk of local optima, and ensures optimal solutions. (3) A single-step parallel computation algorithm is introduced, boosting computational efficiency and reducing processing time. Extensive evaluations across five benchmark datasets demonstrate that POPoS consistently outperforms existing methods, particularly excelling in low-resolution heatmaps scenarios with minimal computational overhead. These advantages make POPoS a highly efficient and accurate tool for FLD, with broad applicability in real-world scenarios.
Authors: David Schneider, Sina Sajadmanesh, Vikash Sehwag, Saquib Sarfraz, Rainer Stiefelhagen, Lingjuan Lyu, Vivek Sharma
Abstract: Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence. Prevalent methods tackling this problem use differential privacy (DP) or obfuscation techniques to protect the privacy of individuals. In both cases, the utility of the trained model is sacrificed heavily in this process. In this work, we present an anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context, employing a combined rendering and stable diffusion-based strategy. Additionally we propose masked differential privacy ({MaskDP}) to protect non-anonymized but privacy sensitive background information. MaskDP allows for controlling sensitive regions where differential privacy is applied, in contrast to applying DP on the entire input. This combined methodology provides strong privacy protection while minimizing the usual performance penalty of privacy preserving methods. Experiments on multiple challenging action recognition datasets demonstrate that our proposed techniques result in better utility-privacy trade-offs compared to standard differentially private training in the especially demanding $\epsilon<1$ regime.
Authors: Jiawei Xu, Zexin Fan, Jian Yang, Jin Xie
Abstract: Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene rendering models. However, plane-based methods rely on the inappropriate low-rank assumption and excessively decompose the space-time 4D encoding, resulting in overmuch feature overlap and unsatisfactory rendering quality. To tackle these problems, we propose Grid4D, a dynamic scene rendering model based on Gaussian splatting and employing a novel explicit encoding method for the 4D input through the hash encoding. Different from plane-based explicit representations, we decompose the 4D encoding into one spatial and three temporal 3D hash encodings without the low-rank assumption. Additionally, we design a novel attention module that generates the attention scores in a directional range to aggregate the spatial and temporal features. The directional attention enables Grid4D to more accurately fit the diverse deformations across distinct scene components based on the spatial encoded features. Moreover, to mitigate the inherent lack of smoothness in explicit representation methods, we introduce a smooth regularization term that keeps our model from the chaos of deformation prediction. Our experiments demonstrate that Grid4D significantly outperforms the state-of-the-art models in visual quality and rendering speed.
Authors: Mingkun Zhang, Keping Bi, Wei Chen, Quanrun Chen, Jiafeng Guo, Xueqi Cheng
Abstract: Despite ongoing efforts to defend neural classifiers from adversarial attacks, they remain vulnerable, especially to unseen attacks. In contrast, humans are difficult to be cheated by subtle manipulations, since we make judgments only based on essential factors. Inspired by this observation, we attempt to model label generation with essential label-causative factors and incorporate label-non-causative factors to assist data generation. For an adversarial example, we aim to discriminate the perturbations as non-causative factors and make predictions only based on the label-causative factors. Concretely, we propose a casual diffusion model (CausalDiff) that adapts diffusion models for conditional data generation and disentangles the two types of casual factors by learning towards a novel casual information bottleneck objective. Empirically, CausalDiff has significantly outperformed state-of-the-art defense methods on various unseen attacks, achieving an average robustness of 86.39% (+4.01%) on CIFAR-10, 56.25% (+3.13%) on CIFAR-100, and 82.62% (+4.93%) on GTSRB (German Traffic Sign Recognition Benchmark). The code is available at https://github.com/CAS-AISafetyBasicResearchGroup/CausalDiff
URLs: https://github.com/CAS-AISafetyBasicResearchGroup/CausalDiff
Authors: Qinqian Lei, Bo Wang, Robby T. Tan
Abstract: Detecting Human-Object Interactions (HOI) in zero-shot settings, where models must handle unseen classes, poses significant challenges. Existing methods that rely on aligning visual encoders with large Vision-Language Models (VLMs) to tap into the extensive knowledge of VLMs, require large, computationally expensive models and encounter training difficulties. Adapting VLMs with prompt learning offers an alternative to direct alignment. However, fine-tuning on task-specific datasets often leads to overfitting to seen classes and suboptimal performance on unseen classes, due to the absence of unseen class labels. To address these challenges, we introduce a novel prompt learning-based framework for Efficient Zero-Shot HOI detection (EZ-HOI). First, we introduce Large Language Model (LLM) and VLM guidance for learnable prompts, integrating detailed HOI descriptions and visual semantics to adapt VLMs to HOI tasks. However, because training datasets contain seen-class labels alone, fine-tuning VLMs on such datasets tends to optimize learnable prompts for seen classes instead of unseen ones. Therefore, we design prompt learning for unseen classes using information from related seen classes, with LLMs utilized to highlight the differences between unseen and related seen classes. Quantitative evaluations on benchmark datasets demonstrate that our EZ-HOI achieves state-of-the-art performance across various zero-shot settings with only 10.35% to 33.95% of the trainable parameters compared to existing methods. Code is available at https://github.com/ChelsieLei/EZ-HOI.
Authors: Olaf Wysocki, Yue Tan, Thomas Froech, Yan Xia, Magdalena Wysocki, Ludwig Hoegner, Daniel Cremers, Christoph Holst
Abstract: Facade semantic segmentation is a long-standing challenge in photogrammetry and computer vision. Although the last decades have witnessed the influx of facade segmentation methods, there is a lack of comprehensive facade classes and data covering the architectural variability. In ZAHA, we introduce Level of Facade Generalization (LoFG), novel hierarchical facade classes designed based on international urban modeling standards, ensuring compatibility with real-world challenging classes and uniform methods' comparison. Realizing the LoFG, we present to date the largest semantic 3D facade segmentation dataset, providing 601 million annotated points at five and 15 classes of LoFG2 and LoFG3, respectively. Moreover, we analyze the performance of baseline semantic segmentation methods on our introduced LoFG classes and data, complementing it with a discussion on the unresolved challenges for facade segmentation. We firmly believe that ZAHA shall facilitate further development of 3D facade semantic segmentation methods, enabling robust segmentation indispensable in creating urban digital twins.
Authors: Andreas Floros, Seyed-Mohsen Moosavi-Dezfooli, Pier Luigi Dragotti
Abstract: Diffusion models have revolutionized image synthesis, garnering significant research interest in recent years. Diffusion is an iterative algorithm in which samples are generated step-by-step, starting from pure noise. This process introduces the notion of diffusion trajectories, i.e., paths from the standard Gaussian distribution to the target image distribution. In this context, we study discriminative algorithms operating on these trajectories. Specifically, given a pre-trained diffusion model, we consider the problem of classifying images as part of the training dataset, generated by the model or originating from an external source. Our approach demonstrates the presence of patterns across steps that can be leveraged for classification. We also conduct ablation studies, which reveal that using higher-order gradient features to characterize the trajectories leads to significant performance gains and more robust algorithms.
Authors: Yongdong Luo, Xiawu Zheng, Xiao Yang, Guilin Li, Haojia Lin, Jinfa Huang, Jiayi Ji, Fei Chao, Jiebo Luo, Rongrong Ji
Abstract: Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions. However, fine-tuning LVLMs would require extensive high-quality data and substantial GPU resources, while GPT-based agents would rely on proprietary models (e.g., GPT-4o). In this paper, we propose Video Retrieval-Augmented Generation (Video-RAG), a training-free and cost-effective pipeline that employs visually-aligned auxiliary texts to help facilitate cross-modality alignment while providing additional information beyond the visual content. Specifically, we leverage open-source external tools to extract visually-aligned information from pure video data (e.g., audio, optical character, and object detection), and incorporate the extracted information into an existing LVLM as auxiliary texts, alongside video frames and queries, in a plug-and-play manner. Our Video-RAG offers several key advantages: (i) lightweight with low computing overhead due to single-turn retrieval; (ii) easy implementation and compatibility with any LVLM; and (iii) significant, consistent performance gains across long video understanding benchmarks, including Video-MME, MLVU, and LongVideoBench. Notably, our model demonstrates superior performance over proprietary models like Gemini-1.5-Pro and GPT-4o when utilized with a 72B model.
Authors: Rundi Wu, Ruiqi Gao, Ben Poole, Alex Trevithick, Changxi Zheng, Jonathan T. Barron, Aleksander Holynski
Abstract: We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets to enable novel view synthesis at any specified camera poses and timestamps. Combined with a novel sampling approach, this model can transform a single monocular video into a multi-view video, enabling robust 4D reconstruction via optimization of a deformable 3D Gaussian representation. We demonstrate competitive performance on novel view synthesis and dynamic scene reconstruction benchmarks, and highlight the creative capabilities for 4D scene generation from real or generated videos. See our project page for results and interactive demos: https://cat-4d.github.io/.
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: Hee-Seon Kim, Minbeom Kim, Changick Kim
Abstract: Large Vision-Language Models (VLMs) have demonstrated remarkable performance across multimodal tasks by integrating vision encoders with large language models (LLMs). However, these models remain vulnerable to adversarial attacks. Among such attacks, Universal Adversarial Perturbations (UAPs) are especially powerful, as a single optimized perturbation can mislead the model across various input images. In this work, we introduce a novel UAP specifically designed for VLMs: the Doubly-Universal Adversarial Perturbation (Doubly-UAP), capable of universally deceiving VLMs across both image and text inputs. To successfully disrupt the vision encoder's fundamental process, we analyze the core components of the attention mechanism. After identifying value vectors in the middle-to-late layers as the most vulnerable, we optimize Doubly-UAP in a label-free manner with a frozen model. Despite being developed as a black-box to the LLM, Doubly-UAP achieves high attack success rates on VLMs, consistently outperforming baseline methods across vision-language tasks. Extensive ablation studies and analyses further demonstrate the robustness of Doubly-UAP and provide insights into how it influences internal attention mechanisms.
Authors: Quang-Hung Le, Long Hoang Dang, Ngan Le, Truyen Tran, Thao Minh Le
Abstract: Existing Large Vision-Language Models (LVLMs) excel at matching concepts across multi-modal inputs but struggle with compositional concepts and high-level relationships between entities. This paper introduces Progressive multi-granular Vision-Language alignments (PromViL), a novel framework to enhance LVLMs' ability in performing grounded compositional visual reasoning tasks. Our approach constructs a hierarchical structure of multi-modal alignments, ranging from simple to complex concepts. By progressively aligning textual descriptions with corresponding visual regions, our model learns to leverage contextual information from lower levels to inform higher-level reasoning. To facilitate this learning process, we introduce a data generation process that creates a novel dataset derived from Visual Genome, providing a wide range of nested compositional vision-language pairs. Experimental results demonstrate that our PromViL framework significantly outperforms baselines on various visual grounding and compositional question answering tasks. The code is available at: https://github.com/lqh52/PromViL.
Authors: Sora Kim, Sungho Suh, Minsik Lee
Abstract: Diffusion models have achieved remarkable success in image generation, with applications broadening across various domains. Inpainting is one such application that can benefit significantly from diffusion models. Existing methods either hijack the reverse process of a pretrained diffusion model or cast the problem into a larger framework, \ie, conditioned generation. However, these approaches often require nested loops in the generation process or additional components for conditioning. In this paper, we present region-aware diffusion models (RAD) for inpainting with a simple yet effective reformulation of the vanilla diffusion models. RAD utilizes a different noise schedule for each pixel, which allows local regions to be generated asynchronously while considering the global image context. A plain reverse process requires no additional components, enabling RAD to achieve inference time up to 100 times faster than the state-of-the-art approaches. Moreover, we employ low-rank adaptation (LoRA) to fine-tune RAD based on other pretrained diffusion models, reducing computational burdens in training as well. Experiments demonstrated that RAD provides state-of-the-art results both qualitatively and quantitatively, on the FFHQ, LSUN Bedroom, and ImageNet datasets.
Authors: Yuzheng Liu, Siyan Dong, Shuzhe Wang, Yanchao Yang, Qingnan Fan, Baoquan Chen
Abstract: In this paper, we introduce SLAM3R, a novel and effective monocular RGB SLAM system for real-time and high-quality dense 3D reconstruction. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a globally consistent scene reconstruction - all without explicitly solving any camera parameters. Experiments across datasets consistently show that SLAM3R achieves state-of-the-art reconstruction accuracy and completeness while maintaining real-time performance at 20+ FPS. Code and weights at: https://github.com/PKU-VCL-3DV/SLAM3R.
Authors: Qiaoyu Zheng, Chaoyi Wu, Pengcheng Qiu, Lisong Dai, Ya Zhang, Yanfeng Wang, Weidi Xie
Abstract: Advancements in large language models (LLMs) have paved the way for LLM-based agent systems that offer enhanced accuracy and interpretability across various domains. Radiology, with its complex analytical requirements, is an ideal field for the application of these agents. This paper aims to investigate the pre-requisite question for building concrete radiology agents which is, `Can modern LLMs act as agent cores in radiology environments?' To investigate it, we introduce RadABench with three-fold contributions: First, we present RadABench-Data, a comprehensive synthetic evaluation dataset for LLM-based agents, generated from an extensive taxonomy encompassing 6 anatomies, 5 imaging modalities, 10 tool categories, and 11 radiology tasks. Second, we propose RadABench-EvalPlat, a novel evaluation platform for agents featuring a prompt-driven workflow and the capability to simulate a wide range of radiology toolsets. Third, we assess the performance of 7 leading LLMs on our benchmark from 5 perspectives with multiple metrics. Our findings indicate that while current LLMs demonstrate strong capabilities in many areas, they are still not sufficiently advanced to serve as the central agent core in a fully operational radiology agent system. Additionally, we identify key factors influencing the performance of LLM-based agent cores, offering insights for clinicians on how to apply agent systems in real-world radiology practices effectively. All of our code and data are open-sourced in https://github.com/MAGIC-AI4Med/RadABench.
Authors: Xueting Li, Ye Yuan, Shalini De Mello, Gilles Daviet, Jonathan Leaf, Miles Macklin, Jan Kautz, Umar Iqbal
Abstract: We introduce SimAvatar, a framework designed to generate simulation-ready clothed 3D human avatars from a text prompt. Current text-driven human avatar generation methods either model hair, clothing, and the human body using a unified geometry or produce hair and garments that are not easily adaptable for simulation within existing simulation pipelines. The primary challenge lies in representing the hair and garment geometry in a way that allows leveraging established prior knowledge from foundational image diffusion models (e.g., Stable Diffusion) while being simulation-ready using either physics or neural simulators. To address this task, we propose a two-stage framework that combines the flexibility of 3D Gaussians with simulation-ready hair strands and garment meshes. Specifically, we first employ three text-conditioned 3D generative models to generate garment mesh, body shape and hair strands from the given text prompt. To leverage prior knowledge from foundational diffusion models, we attach 3D Gaussians to the body mesh, garment mesh, as well as hair strands and learn the avatar appearance through optimization. To drive the avatar given a pose sequence, we first apply physics simulators onto the garment meshes and hair strands. We then transfer the motion onto 3D Gaussians through carefully designed mechanisms for each body part. As a result, our synthesized avatars have vivid texture and realistic dynamic motion. To the best of our knowledge, our method is the first to produce highly realistic, fully simulation-ready 3D avatars, surpassing the capabilities of current approaches.
Authors: Taiming Lu, Tianmin Shu, Junfei Xiao, Luoxin Ye, Jiahao Wang, Cheng Peng, Chen Wei, Daniel Khashabi, Rama Chellappa, Alan Yuille, Jieneng Chen
Abstract: Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms priors (expectations) about the surrounding environments. GenEx generates an entire 3D-consistent imaginative environment from as little as a single RGB image, bringing it to life through panoramic video streams. Leveraging scalable 3D world data curated from Unreal Engine, our generative model is rounded in the physical world. It captures a continuous 360-degree environment with little effort, offering a boundless landscape for AI agents to explore and interact with. GenEx achieves high-quality world generation, robust loop consistency over long trajectories, and demonstrates strong 3D capabilities such as consistency and active 3D mapping. Powered by generative imagination of the world, GPT-assisted agents are equipped to perform complex embodied tasks, including both goal-agnostic exploration and goal-driven navigation. These agents utilize predictive expectation regarding unseen parts of the physical world to refine their beliefs, simulate different outcomes based on potential decisions, and make more informed choices. In summary, we demonstrate that GenEx provides a transformative platform for advancing embodied AI in imaginative spaces and brings potential for extending these capabilities to real-world exploration.
Authors: Deng Siqin, Zhou Xiaoyi
Abstract: Vision Transformers (ViTs) have achieved record-breaking performance in various visual tasks. However, concerns about their robustness against backdoor attacks have grown. Backdoor attacks involve associating a specific trigger with a target label, causing the model to predict the attacker-specified label when the trigger is present, while correctly identifying clean images.We found that ViTs exhibit higher attack success rates for quasi-triggers(patterns different from but similar to the original training triggers)compared to CNNs. Moreover, some backdoor features in clean samples can suppress the original trigger, making quasi-triggers more effective.To better understand and exploit these vulnerabilities, we developed a tool called the Perturbation Sensitivity Distribution Map (PSDM). PSDM computes and sums gradients over many inputs to show how sensitive the model is to small changes in the input. In ViTs, PSDM reveals a patch-like pattern where central pixels are more sensitive than edges. We use PSDM to guide the creation of quasi-triggers.Based on these findings, we designed "WorstVIT," a simple yet effective data poisoning backdoor for ViT models. This attack requires an extremely low poisoning rate, trains for just one epoch, and modifies a single pixel to successfully attack all validation images.
Authors: Jin-Yu Liu, Xian-Ling Mao, Tian-Yi Che, Rong-Cheng Tu
Abstract: Multi-modal hashing methods have gained popularity due to their fast speed and low storage requirements. Among them, the supervised methods demonstrate better performance by utilizing labels as supervisory signals compared with unsupervised methods. Currently, for almost all supervised multi-modal hashing methods, there is a hidden assumption that training sets have no noisy labels. However, labels are often annotated incorrectly due to manual labeling in real-world scenarios, which will greatly harm the retrieval performance. To address this issue, we first discover a significant distribution consistency pattern through experiments, i.e., the 1-0 distribution of the presence or absence of each category in the label is consistent with the high-low distribution of similarity scores of the hash codes relative to category centers. Then, inspired by this pattern, we propose a novel Distribution-Consistency-Guided Multi-modal Hashing (DCGMH), which aims to filter and reconstruct noisy labels to enhance retrieval performance. Specifically, the proposed method first randomly initializes several category centers, which are used to compute the high-low distribution of similarity scores; Noisy and clean labels are then separately filtered out via the discovered distribution consistency pattern to mitigate the impact of noisy labels; Subsequently, a correction strategy, which is indirectly designed via the distribution consistency pattern, is applied to the filtered noisy labels, correcting high-confidence ones while treating low-confidence ones as unlabeled for unsupervised learning, thereby further enhancing the model's performance. Extensive experiments on three widely used datasets demonstrate the superiority of the proposed method compared to state-of-the-art baselines in multi-modal retrieval tasks. The code is available at https://github.com/LiuJinyu1229/DCGMH.
Authors: Junda Cheng, Zhipeng Cai, Zhaoxing Zhang, Wei Yin, Matthias Muller, Michael Paulitsch, Xin Yang
Abstract: Visual odometry (VO) aims to estimate camera poses from visual inputs -- a fundamental building block for many applications such as VR/AR and robotics. This work focuses on monocular RGB VO where the input is a monocular RGB video without IMU or 3D sensors. Existing approaches lack robustness under this challenging scenario and fail to generalize to unseen data (especially outdoors); they also cannot recover metric-scale poses. We propose Robust Metric Visual Odometry (RoMeO), a novel method that resolves these issues leveraging priors from pre-trained depth models. RoMeO incorporates both monocular metric depth and multi-view stereo (MVS) models to recover metric-scale, simplify correspondence search, provide better initialization and regularize optimization. Effective strategies are proposed to inject noise during training and adaptively filter noisy depth priors, which ensure the robustness of RoMeO on in-the-wild data. As shown in Fig.1, RoMeO advances the state-of-the-art (SOTA) by a large margin across 6 diverse datasets covering both indoor and outdoor scenes. Compared to the current SOTA DPVO, RoMeO reduces the relative (align the trajectory scale with GT) and absolute trajectory errors both by >50%. The performance gain also transfers to the full SLAM pipeline (with global BA & loop closure). Code will be released upon acceptance.
Authors: Xiaokun Sun, Zeyu Cai, Ying Tai, Jian Yang, Zhenyu Zhang
Abstract: While haircut indicates distinct personality, existing avatar generation methods fail to model practical hair due to the general or entangled representation. We propose StrandHead, a novel text to 3D head avatar generation method capable of generating disentangled 3D hair with strand representation. Without using 3D data for supervision, we demonstrate that realistic hair strands can be generated from prompts by distilling 2D generative diffusion models. To this end, we propose a series of reliable priors on shape initialization, geometric primitives, and statistical haircut features, leading to a stable optimization and text-aligned performance. Extensive experiments show that StrandHead achieves the state-of-the-art reality and diversity of generated 3D head and hair. The generated 3D hair can also be easily implemented in the Unreal Engine for physical simulation and other applications. The code will be available at https://xiaokunsun.github.io/StrandHead.github.io.
Authors: Pingchuan Ma, Lennart Rietdorf, Dmytro Kotovenko, Vincent Tao Hu, Bj\"orn Ommer
Abstract: Accurately describing images with text is a foundation of explainable AI. Vision-Language Models (VLMs) like CLIP have recently addressed this by aligning images and texts in a shared embedding space, expressing semantic similarities between vision and language embeddings. VLM classification can be improved with descriptions generated by Large Language Models (LLMs). However, it is difficult to determine the contribution of actual description semantics, as the performance gain may also stem from a semantic-agnostic ensembling effect, where multiple modified text prompts act as a noisy test-time augmentation for the original one. We propose an alternative evaluation scenario to decide if a performance boost of LLM-generated descriptions is caused by such a noise augmentation effect or rather by genuine description semantics. The proposed scenario avoids noisy test-time augmentation and ensures that genuine, distinctive descriptions cause the performance boost. Furthermore, we propose a training-free method for selecting discriminative descriptions that work independently of classname-ensembling effects. Our approach identifies descriptions that effectively differentiate classes within a local CLIP label neighborhood, improving classification accuracy across seven datasets. Additionally, we provide insights into the explainability of description-based image classification with VLMs.
Authors: Mohaddeseh Chegini, Ali Mahloojifar
Abstract: Breast cancer is a heterogeneous disease with different molecular subtypes, clinical behavior, treatment responses as well as survival outcomes. The development of a reliable, accurate, available and inexpensive method to predict the molecular subtypes using medical images plays an important role in the diagnosis and prognosis of breast cancer. Recently, deep learning methods have shown good performance in the breast cancer classification tasks using various medical images. Despite all that success, classical deep learning cannot deliver the predictive uncertainty. The uncertainty represents the validity of the predictions. Therefore, the high predicted uncertainty might cause a negative effect in the accurate diagnosis of breast cancer molecular subtypes. To overcome this, uncertainty quantification methods are used to determine the predictive uncertainty. Accordingly, in this study, we proposed an uncertainty-aware Bayesian deep learning model using the full mammogram images. In addition, to increase the performance of the multi-class molecular subtype classification task, we proposed a novel hierarchical classification strategy, named the two-stage classification strategy. The separate AUC of the proposed model for each subtype was 0.71, 0.75 and 0.86 for HER2-enriched, luminal and triple-negative classes, respectively. The proposed model not only has a comparable performance to other studies in the field of breast cancer molecular subtypes prediction, even using full mammography images, but it is also more reliable, due to quantify the predictive uncertainty.
Authors: Guangwenjie Zou, Liang Yao, Fan Liu, Chuanyi Zhang, Xin Li, Ning Chen, Shengxiang Xu, Jun Zhou
Abstract: Since high resolution remote sensing image classification often requires a relatively high computation complexity, lightweight models tend to be practical and efficient. Model pruning is an effective method for model compression. However, existing methods rarely take into account the specificity of remote sensing images, resulting in significant accuracy loss after pruning. To this end, we propose an effective structural pruning approach for remote sensing image classification. Specifically, a pruning strategy that amplifies the differences in channel importance of the model is introduced. Then an adaptive mining loss function is designed for the fine-tuning process of the pruned model. Finally, we conducted experiments on two remote sensing classification datasets. The experimental results demonstrate that our method achieves minimal accuracy loss after compressing remote sensing classification models, achieving state-of-the-art (SoTA) performance.
Authors: Zhengdi Yu, Stefanos Zafeiriou, Tolga Birdal
Abstract: We propose Dyn-HaMR, to the best of our knowledge, the first approach to reconstruct 4D global hand motion from monocular videos recorded by dynamic cameras in the wild. Reconstructing accurate 3D hand meshes from monocular videos is a crucial task for understanding human behaviour, with significant applications in augmented and virtual reality (AR/VR). However, existing methods for monocular hand reconstruction typically rely on a weak perspective camera model, which simulates hand motion within a limited camera frustum. As a result, these approaches struggle to recover the full 3D global trajectory and often produce noisy or incorrect depth estimations, particularly when the video is captured by dynamic or moving cameras, which is common in egocentric scenarios. Our Dyn-HaMR consists of a multi-stage, multi-objective optimization pipeline, that factors in (i) simultaneous localization and mapping (SLAM) to robustly estimate relative camera motion, (ii) an interacting-hand prior for generative infilling and to refine the interaction dynamics, ensuring plausible recovery under (self-)occlusions, and (iii) hierarchical initialization through a combination of state-of-the-art hand tracking methods. Through extensive evaluations on both in-the-wild and indoor datasets, we show that our approach significantly outperforms state-of-the-art methods in terms of 4D global mesh recovery. This establishes a new benchmark for hand motion reconstruction from monocular video with moving cameras. Our project page is at https://dyn-hamr.github.io/.
Authors: Wenhao Sun, Benlei Cui, Xue-Mei Dong, Jingqun Tang
Abstract: Recently, diffusion models have emerged as promising newcomers in the field of generative models, shining brightly in image generation. However, when employed for object removal tasks, they still encounter issues such as generating random artifacts and the incapacity to repaint foreground object areas with appropriate content after removal. To tackle these problems, we propose Attentive Eraser, a tuning-free method to empower pre-trained diffusion models for stable and effective object removal. Firstly, in light of the observation that the self-attention maps influence the structure and shape details of the generated images, we propose Attention Activation and Suppression (ASS), which re-engineers the self-attention mechanism within the pre-trained diffusion models based on the given mask, thereby prioritizing the background over the foreground object during the reverse generation process. Moreover, we introduce Self-Attention Redirection Guidance (SARG), which utilizes the self-attention redirected by ASS to guide the generation process, effectively removing foreground objects within the mask while simultaneously generating content that is both plausible and coherent. Experiments demonstrate the stability and effectiveness of Attentive Eraser in object removal across a variety of pre-trained diffusion models, outperforming even training-based methods. Furthermore, Attentive Eraser can be implemented in various diffusion model architectures and checkpoints, enabling excellent scalability. Code is available at https://github.com/Anonym0u3/AttentiveEraser.
Authors: Shengeng Tang, Jiayi He, Dan Guo, Yanyan Wei, Feng Li, Richang Hong
Abstract: Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as discrete three-dimensional coordinates and directly fit them, which overlooks the relative positional relationships among joints. To this end, we provide a new perspective, constraining joint associations and gesture details by modeling the limb bones to improve the accuracy and naturalness of the generated poses. In this work, we propose a pioneering iconicity disentangled diffusion framework, termed Sign-IDD, specifically designed for SLP. Sign-IDD incorporates a novel Iconicity Disentanglement (ID) module to bridge the gap between relative positions among joints. The ID module disentangles the conventional 3D joint representation into a 4D bone representation, comprising the 3D spatial direction vector and 1D spatial distance vector between adjacent joints. Additionally, an Attribute Controllable Diffusion (ACD) module is introduced to further constrain joint associations, in which the attribute separation layer aims to separate the bone direction and length attributes, and the attribute control layer is designed to guide the pose generation by leveraging the above attributes. The ACD module utilizes the gloss embeddings as semantic conditions and finally generates sign poses from noise embeddings. Extensive experiments on PHOENIX14T and USTC-CSL datasets validate the effectiveness of our method. The code is available at: https://github.com/NaVi-start/Sign-IDD.
Authors: Tony Cheng Tong, Sirui He, Zhiwen Shao, Dit-Yan Yeung
Abstract: Evaluation metric of visual captioning is important yet not thoroughly explored. Traditional metrics like BLEU, METEOR, CIDEr, and ROUGE often miss semantic depth, while trained metrics such as CLIP-Score, PAC-S, and Polos are limited in zero-shot scenarios. Advanced Language Model-based metrics also struggle with aligning to nuanced human preferences. To address these issues, we introduce G-VEval, a novel metric inspired by G-Eval and powered by the new GPT-4o. G-VEval uses chain-of-thought reasoning in large multimodal models and supports three modes: reference-free, reference-only, and combined, accommodating both video and image inputs. We also propose MSVD-Eval, a new dataset for video captioning evaluation, to establish a more transparent and consistent framework for both human experts and evaluation metrics. It is designed to address the lack of clear criteria in existing datasets by introducing distinct dimensions of Accuracy, Completeness, Conciseness, and Relevance (ACCR). Extensive results show that G-VEval outperforms existing methods in correlation with human annotations, as measured by Kendall tau-b and Kendall tau-c. This provides a flexible solution for diverse captioning tasks and suggests a straightforward yet effective approach for large language models to understand video content, paving the way for advancements in automated captioning. Codes are available at https://github.com/ztangaj/gveval
Authors: Jiaqi Yang, Chu'ai Zhang, Zhengbao Wang, Xinyue Cao, Xuan Ouyang, Xiyu Zhang, Zhenxuan Zeng, Zhao Zeng, Borui Lu, Zhiyi Xia, Qian Zhang, Yulan Guo, Yanning Zhang
Abstract: 3D point cloud registration is a fundamental problem in computer vision, computer graphics, robotics, remote sensing, and etc. Over the last thirty years, we have witnessed the amazing advancement in this area with numerous kinds of solutions. Although a handful of relevant surveys have been conducted, their coverage is still limited. In this work, we present a comprehensive survey on 3D point cloud registration, covering a set of sub-areas such as pairwise coarse registration, pairwise fine registration, multi-view registration, cross-scale registration, and multi-instance registration. The datasets, evaluation metrics, method taxonomy, discussions of the merits and demerits, insightful thoughts of future directions are comprehensively presented in this survey. The regularly updated project page of the survey is available at https://github.com/Amyyyy11/3D-Registration-in-30-Years-A-Survey.
URLs: https://github.com/Amyyyy11/3D-Registration-in-30-Years-A-Survey.
Authors: Zixuan Chen, Jiaxin Li, Liming Tan, Yejie Guo, Junxuan Liang, Cewu Lu, Yong-Lu Li
Abstract: Intelligent robots need to interact with diverse objects across various environments. The appearance and state of objects frequently undergo complex transformations depending on the object properties, e.g., phase transitions. However, in the vision community, segmenting dynamic objects with phase transitions is overlooked. In light of this, we introduce the concept of phase in segmentation, which categorizes real-world objects based on their visual characteristics and potential morphological and appearance changes. Then, we present a new benchmark, Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (M$^3$-VOS), to verify the ability of models to understand object phases, which consists of 479 high-resolution videos spanning over 10 distinct everyday scenarios. It provides dense instance mask annotations that capture both object phases and their transitions. We evaluate state-of-the-art methods on M$^3$-VOS, yielding several key insights. Notably, current appearancebased approaches show significant room for improvement when handling objects with phase transitions. The inherent changes in disorder suggest that the predictive performance of the forward entropy-increasing process can be improved through a reverse entropy-reducing process. These findings lead us to propose ReVOS, a new plug-andplay model that improves its performance by reversal refinement. Our data and code will be publicly available at https://zixuan-chen.github.io/M-cubeVOS.github.io/.
Authors: Fu Wang, Yanghao Zhang, Xiangyu Yin, Guangliang Cheng, Zeyu Fu, Xiaowei Huang, Wenjie Ruan
Abstract: Camera-based Bird's Eye View (BEV) perception models receive increasing attention for their crucial role in autonomous driving, a domain where concerns about the robustness and reliability of deep learning have been raised. While only a few works have investigated the effects of randomly generated semantic perturbations, aka natural corruptions, on the multi-view BEV detection task, we develop a black-box robustness evaluation framework that adversarially optimises three common semantic perturbations: geometric transformation, colour shifting, and motion blur, to deceive BEV models, serving as the first approach in this emerging field. To address the challenge posed by optimising the semantic perturbation, we design a smoothed, distance-based surrogate function to replace the mAP metric and introduce SimpleDIRECT, a deterministic optimisation algorithm that utilises observed slopes to guide the optimisation process. By comparing with randomised perturbation and two optimisation baselines, we demonstrate the effectiveness of the proposed framework. Additionally, we provide a benchmark on the semantic robustness of ten recent BEV models. The results reveal that PolarFormer, which emphasises geometric information from multi-view images, exhibits the highest robustness, whereas BEVDet is fully compromised, with its precision reduced to zero.
Authors: Ziyang Xu, Huangxuan Zhao, Wenyu Liu, Xinggang Wang
Abstract: The rapid and accurate direct multi-frame interpolation method for Digital Subtraction Angiography (DSA) images is crucial for reducing radiation and providing real-time assistance to physicians for precise diagnostics and treatment. DSA images contain complex vascular structures and various motions. Applying natural scene Video Frame Interpolation (VFI) methods results in motion artifacts, structural dissipation, and blurriness. Recently, MoSt-DSA has specifically addressed these issues for the first time and achieved SOTA results. However, MoSt-DSA's focus on real-time performance leads to insufficient suppression of high-frequency noise and incomplete filtering of low-frequency noise in the generated images. To address these issues within the same computational time scale, we propose GaraMoSt. Specifically, we optimize the network pipeline with a parallel design and propose a module named MG-MSFE. MG-MSFE extracts frame-relative motion and structural features at various granularities in a fully convolutional parallel manner and supports independent, flexible adjustment of context-aware granularity at different scales, thus enhancing computational efficiency and accuracy. Extensive experiments demonstrate that GaraMoSt achieves the SOTA performance in accuracy, robustness, visual effects, and noise suppression, comprehensively surpassing MoSt-DSA and other natural scene VFI methods. The code and models are available at https://github.com/ZyoungXu/GaraMoSt.
Authors: Sihui Ji, Yiyang Wang, Xi Chen, Xiaogang Xu, Hao Luo, Hengshuang Zhao
Abstract: We present FashionComposer for compositional fashion image generation. Unlike previous methods, FashionComposer is highly flexible. It takes multi-modal input (i.e., text prompt, parametric human model, garment image, and face image) and supports personalizing the appearance, pose, and figure of the human and assigning multiple garments in one pass. To achieve this, we first develop a universal framework capable of handling diverse input modalities. We construct scaled training data to enhance the model's robust compositional capabilities. To accommodate multiple reference images (garments and faces) seamlessly, we organize these references in a single image as an "asset library" and employ a reference UNet to extract appearance features. To inject the appearance features into the correct pixels in the generated result, we propose subject-binding attention. It binds the appearance features from different "assets" with the corresponding text features. In this way, the model could understand each asset according to their semantics, supporting arbitrary numbers and types of reference images. As a comprehensive solution, FashionComposer also supports many other applications like human album generation, diverse virtual try-on tasks, etc.
Authors: Zhihang Yuan, Yuzhang Shang, Hanling Zhang, Tongcheng Fang, Rui Xie, Bingxin Xu, Yan Yan, Shengen Yan, Guohao Dai, Yu Wang
Abstract: Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential token generation nature and reliance on computationally intensive diffusion-based sampling. We present ECAR (Efficient Continuous Auto-Regressive Image Generation via Multistage Modeling), an approach that addresses these limitations through two intertwined innovations: (1) a stage-wise continuous token generation strategy that reduces computational complexity and provides progressively refined token maps as hierarchical conditions, and (2) a multistage flow-based distribution modeling method that transforms only partial-denoised distributions at each stage comparing to complete denoising in normal diffusion models. Holistically, ECAR operates by generating tokens at increasing resolutions while simultaneously denoising the image at each stage. This design not only reduces token-to-image transformation cost by a factor of the stage number but also enables parallel processing at the token level. Our approach not only enhances computational efficiency but also aligns naturally with image generation principles by operating in continuous token space and following a hierarchical generation process from coarse to fine details. Experimental results demonstrate that ECAR achieves comparable image quality to DiT Peebles & Xie [2023] while requiring 10$\times$ FLOPs reduction and 5$\times$ speedup to generate a 256$\times$256 image.
Authors: Chunwei Tian, Xuanyu Zhang, Qi Zhu, Bob Zhang, Jerry Chun-Wei Lin
Abstract: Single image super-resolution (SISR) has played an important role in the field of image processing. Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples. However, there are little literatures summarizing different GANs in SISR. In this paper, we conduct a comparative study of GANs from different perspectives. We first take a look at developments of GANs. Second, we present popular architectures for GANs in big and small samples for image applications. Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised manners, where these GANs are analyzed via integrating different network architectures, prior knowledge, loss functions and multiple tasks. Next, we compare performance of these popular GANs on public datasets via quantitative and qualitative analysis in SISR. Finally, we highlight challenges of GANs and potential research points for SISR.
Authors: Runmin Cong, Wenyu Yang, Wei Zhang, Chongyi Li, Chun-Le Guo, Qingming Huang, Sam Kwong
Abstract: Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement sub-network (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics.
Authors: Yue Song, Wei Wang, Nicu Sebe
Abstract: The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings. In this paper, we observe that the singular value distributions of the in-distribution (ID) and OOD features are quite different: the OOD feature matrix tends to have a larger dominant singular value than the ID feature, and the class predictions of OOD samples are largely determined by it. This observation motivates us to propose \texttt{RankFeat}, a simple yet effective \emph{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature. \texttt{RankFeat} achieves \emph{state-of-the-art} performance and reduces the average false positive rate (FPR95) by 17.90\% compared with the previous best method. The success of \texttt{RankFeat} motivates us to investigate whether a similar phenomenon would exist in the parameter matrices of neural networks. We thus propose \texttt{RankWeight} which removes the rank-1 weight from the parameter matrices of a single deep layer. Our \texttt{RankWeight}is also \emph{post hoc} and only requires computing the rank-1 matrix once. As a standalone approach, \texttt{RankWeight} has very competitive performance against other methods across various backbones. Moreover, \texttt{RankWeight} enjoys flexible compatibility with a wide range of OOD detection methods. The combination of \texttt{RankWeight} and \texttt{RankFeat} refreshes the new \emph{state-of-the-art} performance, achieving the FPR95 as low as 16.13\% on the ImageNet-1k benchmark. Extensive ablation studies and comprehensive theoretical analyses are presented to support the empirical results. Code is publicly available via \url{https://github.com/KingJamesSong/RankFeat}.
Authors: Paul San Sebastian, Mikel Ca\~nizo, Rom\'an Or\'us
Abstract: Variational quantum algorithms are gaining attention as an early application of Noisy Intermediate-Scale Quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of Barren Plateaus, present in the optimization of variational parameters. Adding geometric inductive bias to the quantum models has been proposed as a potential solution to mitigate this problem, leading to a new field called Geometric Quantum Machine Learning. In this work, an equivariant architecture for variational quantum classifiers is introduced to create a label-invariant model for image classification with $C_4$ rotational label symmetry. The equivariant circuit is benchmarked against two different architectures, and it is experimentally observed that the geometric approach boosts the model's performance. Finally, a classical equivariant convolution operation is proposed to extend the quantum model for the processing of larger images, employing the resources available in NISQ devices.
Authors: Shuofei Qiao, Runnan Fang, Ningyu Zhang, Yuqi Zhu, Xiang Chen, Shumin Deng, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen
Abstract: Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in global planning and generating hallucinatory actions in local planning due to their poor understanding of the ``real'' physical world. Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric World Knowledge Model (WKM) to facilitate agent planning. Concretely, we steer the agent model to self-synthesize knowledge from both expert and sampled trajectories. Then we develop WKM, providing prior task knowledge to guide the global planning and dynamic state knowledge to assist the local planning. Experimental results on three complex real-world simulated datasets with three state-of-the-art open-source LLMs, Mistral-7B, Gemma-7B, and Llama-3-8B, demonstrate that our method can achieve superior performance compared to various strong baselines. Besides, we analyze to illustrate that our WKM can effectively alleviate the blind trial-and-error and hallucinatory action issues, providing strong support for the agent's understanding of the world. Other interesting findings include: 1) our instance-level task knowledge can generalize better to unseen tasks, 2) weak WKM can guide strong agent model planning, and 3) unified WKM training has promising potential for further development. The code is available at https://github.com/zjunlp/WKM.
Authors: Peng Wang, Zexi Li, Ningyu Zhang, Ziwen Xu, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen
Abstract: Large language models (LLMs) need knowledge updates to meet the ever-growing world facts and correct the hallucinated responses, facilitating the methods of lifelong model editing. Where the updated knowledge resides in memories is a fundamental question for model editing. In this paper, we find that editing either long-term memory (direct model parameters) or working memory (non-parametric knowledge of neural network activations/representations by retrieval) will result in an impossible triangle -- reliability, generalization, and locality can not be realized together in the lifelong editing settings. For long-term memory, directly editing the parameters will cause conflicts with irrelevant pretrained knowledge or previous edits (poor reliability and locality). For working memory, retrieval-based activations can hardly make the model understand the edits and generalize (poor generalization). Therefore, we propose WISE to bridge the gap between memories. In WISE, we design a dual parametric memory scheme, which consists of the main memory for the pretrained knowledge and a side memory for the edited knowledge. We only edit the knowledge in the side memory and train a router to decide which memory to go through when given a query. For continual editing, we devise a knowledge-sharding mechanism where different sets of edits reside in distinct subspaces of parameters, and are subsequently merged into a shared memory without conflicts. Extensive experiments show that WISE can outperform previous model editing methods and overcome the impossible triangle under lifelong model editing of question answering, hallucination, and out-of-distribution settings across trending LLM architectures, e.g., GPT, LLaMA, and Mistral. Code is available at https://github.com/zjunlp/EasyEdit.
Authors: Yunzhi Yao, Ningyu Zhang, Zekun Xi, Mengru Wang, Ziwen Xu, Shumin Deng, Huajun Chen
Abstract: The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these models store knowledge have long been a subject of intense interest and investigation among researchers. To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head. In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. The experiments, conducted with GPT2 and TinyLLAMA, have allowed us to observe how certain information heads, relation heads, and Multilayer Perceptrons collaboratively encode knowledge within the model. Moreover, we evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies. Finally, we utilize knowledge circuits to analyze and interpret language model behaviors such as hallucinations and in-context learning. We believe the knowledge circuits hold potential for advancing our understanding of Transformers and guiding the improved design of knowledge editing. Code and data are available in https://github.com/zjunlp/KnowledgeCircuits.
Authors: Zixuan Liu, Hanwen Xu, Addie Woicik, Linda G. Shapiro, Marian Blazes, Yue Wu, Verena Steffen, Catherine Cukras, Cecilia S. Lee, Miao Zhang, Aaron Y. Lee, Sheng Wang
Abstract: We present OCTCube-M, a 3D OCT-based multi-modal foundation model for jointly analyzing OCT and en face images. OCTCube-M first developed OCTCube, a 3D foundation model pre-trained on 26,685 3D OCT volumes encompassing 1.62 million 2D OCT images. It then exploits a novel multi-modal contrastive learning framework COEP to integrate other retinal imaging modalities, such as fundus autofluorescence and infrared retinal imaging, into OCTCube, efficiently extending it into multi-modal foundation models. OCTCube achieves best performance on predicting 8 retinal diseases, demonstrating strong generalizability on cross-cohort, cross-device and cross-modality prediction. OCTCube can also predict cross-organ nodule malignancy (CT) and low cardiac ejection fraction as well as systemic diseases, such as diabetes and hypertension, revealing its wide applicability beyond retinal diseases. We further develop OCTCube-IR using COEP with 26,685 OCT and IR image pairs. OCTCube-IR can accurately retrieve between OCT and IR images, allowing joint analysis between 3D and 2D retinal imaging modalities. Finally, we trained a tri-modal foundation model OCTCube-EF from 4 million 2D OCT images and 400K en face retinal images. OCTCube-EF attains the best performance on predicting the growth rate of geographic atrophy (GA) across datasets collected from 6 multi-center global trials conducted in 23 countries. This improvement is statistically equivalent to running a clinical trial with more than double the size of the original study. Our analysis based on another retrospective case study reveals OCTCube-EF's ability to avoid false positive Phase-III results according to its accurate treatment effect estimation on the Phase-II results. In sum, OCTCube-M is a 3D multi-modal foundation model framework that integrates OCT and other retinal imaging modalities revealing substantial diagnostic and prognostic benefits.
Authors: Chang Zou, Xuyang Liu, Ting Liu, Siteng Huang, Linfeng Zhang
Abstract: Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion transformers by caching the features in previous timesteps and reusing them in the following timesteps. However, previous caching methods ignore that different tokens exhibit different sensitivities to feature caching, and feature caching on some tokens may lead to 10$\times$ more destruction to the overall generation quality compared with other tokens. In this paper, we introduce token-wise feature caching, allowing us to adaptively select the most suitable tokens for caching, and further enable us to apply different caching ratios to neural layers in different types and depths. Extensive experiments on PixArt-$\alpha$, OpenSora, and DiT demonstrate our effectiveness in both image and video generation with no requirements for training. For instance, 2.36$\times$ and 1.93$\times$ acceleration are achieved on OpenSora and PixArt-$\alpha$ with almost no drop in generation quality.
Authors: Jintao Zhang, Haofeng Huang, Pengle Zhang, Jia Wei, Jun Zhu, Jianfei Chen
Abstract: Although quantization for linear layers has been widely used, its application to accelerate the attention process remains limited. To further enhance the efficiency of attention computation compared to SageAttention while maintaining precision, we propose SageAttention2, which utilizes significantly faster 4-bit matrix multiplication (Matmul) alongside additional precision-enhancing techniques. First, we propose to quantize matrixes $(Q, K)$ to INT4 in a hardware-friendly thread-level granularity and quantize matrixes $(\widetilde P, V)$ to FP8. Second, we propose a method to smooth $Q$, enhancing the accuracy of INT4 $QK$. Third, we propose to use an FP32 Matmul buffer for $PV$ to enhance the accuracy of FP8 $\widetilde PV$. The operations per second (OPS) of SageAttention2 surpass FlashAttention2 and xformers by about 3x and 5x on RTX4090, respectively. Comprehensive experiments confirm that our approach incurs negligible end-to-end metrics loss across diverse models, including those for large language processing, image generation, and video generation. The codes are available at https://github.com/thu-ml/SageAttention.
Authors: Xichen Ye, Yifan Wu, Weizhong Zhang, Xiaoqiang Li, Yifan Chen, Cheng Jin
Abstract: Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for gradient clipping through validation data to obtain the desired robustness against noise. However, this common practice overlooks the dynamic distribution of gradients from both clean and noisy-labeled samples at different stages of training, significantly limiting the model capability to adapt to the variable nature of gradients throughout the training process. To address this issue, we propose a simple yet effective approach called Optimized Gradient Clipping (OGC), which dynamically adjusts the clipping threshold based on the ratio of noise gradients to clean gradients after clipping, estimated by modeling the distributions of clean and noisy samples. This approach allows us to modify the clipping threshold at each training step, effectively controlling the influence of noise gradients. Additionally, we provide statistical analysis to certify the noise-tolerance ability of OGC. Our extensive experiments across various types of label noise, including symmetric, asymmetric, instance-dependent, and real-world noise, demonstrate the effectiveness of our approach.
Authors: Axel Durbet, Paul-Marie Grollemund, Pascal Lafourcade, Kevin Thiry-Atighehchi
Abstract: Biometric systems are widely used for identity verification and identification, including authentication (i.e., one-to-one matching to verify a claimed identity) and identification (i.e., one-to-many matching to find a subject in a database). The matching process relies on measuring similarities or dissimilarities between a fresh biometric template and enrolled templates. The False Match Rate FMR is a key metric for assessing the accuracy and reliability of such systems. This paper analyzes biometric systems based on their FMR, with two main contributions. First, we explore untargeted attacks, where an adversary aims to impersonate any user within a database. We determine the number of trials required for an attacker to successfully impersonate a user and derive the critical population size (i.e., the maximum number of users in the database) required to maintain a given level of security. Furthermore, we compute the critical FMR value needed to ensure resistance against untargeted attacks as the database size increases. Second, we revisit the biometric birthday problem to evaluate the approximate and exact probabilities that two users in a database collide (i.e., can impersonate each other). Based on this analysis, we derive both the approximate critical population size and the critical FMR value needed to bound the likelihood of such collisions occurring with a given probability. These thresholds offer insights for designing systems that mitigate the risk of impersonation and collisions, particularly in large-scale biometric databases. Our findings indicate that current biometric systems fail to deliver sufficient accuracy to achieve an adequate security level against untargeted attacks, even in small-scale databases. Moreover, state-of-the-art systems face significant challenges in addressing the biometric birthday problem, especially as database sizes grow.