Authors: Yutong Xiong, Xun Zhu, Ming Wu, Weiqing Li, Fanbin Mo, Chuang Zhang, Bin Zhang
Abstract: Sparse meteorological forecasting is indispensable for fine-grained weather forecasting and deserves extensive attention. Recent studies have highlighted the potential of spatio-temporal graph convolutional networks (ST-GCNs) in predicting numerical data from ground weather stations. However, as one of the highest fidelity and lowest latency data, the application of the vision data from satellites in ST-GCNs remains unexplored. There are few studies to demonstrate the effectiveness of combining the above multi-modal data for sparse meteorological forecasting. Towards this objective, we introduce Vision-Numerical Fusion Graph Convolutional Network (VN-Net), which mainly utilizes: 1) Numerical-GCN (N-GCN) to adaptively model the static and dynamic patterns of spatio-temporal numerical data; 2) Vision-LSTM Network (V-LSTM) to capture multi-scale joint channel and spatial features from time series satellite images; 4) a GCN-based decoder to generate hourly predictions of specified meteorological factors. As far as we know, VN-Net is the first attempt to introduce GCN method to utilize multi-modal data for better handling sparse spatio-temporal meteorological forecasting. Our experiments on Weather2k dataset show VN-Net outperforms state-of-the-art by a significant margin on mean absolute error (MAE) and root mean square error (RMSE) for temperature, relative humidity, and visibility forecasting. Furthermore, we conduct interpretation analysis and design quantitative evaluation metrics to assess the impact of incorporating vision data.
Authors: Pengyuan Zhou, Lin Wang, Zhi Liu, Yanbin Hao, Pan Hui, Sasu Tarkoma, Jussi Kangasharju
Abstract: This paper offers an insightful examination of how currently top-trending AI technologies, i.e., generative artificial intelligence (Generative AI) and large language models (LLMs), are reshaping the field of video technology, including video generation, understanding, and streaming. It highlights the innovative use of these technologies in producing highly realistic videos, a significant leap in bridging the gap between real-world dynamics and digital creation. The study also delves into the advanced capabilities of LLMs in video understanding, demonstrating their effectiveness in extracting meaningful information from visual content, thereby enhancing our interaction with videos. In the realm of video streaming, the paper discusses how LLMs contribute to more efficient and user-centric streaming experiences, adapting content delivery to individual viewer preferences. This comprehensive review navigates through the current achievements, ongoing challenges, and future possibilities of applying Generative AI and LLMs to video-related tasks, underscoring the immense potential these technologies hold for advancing the field of video technology related to multimedia, networking, and AI communities.
Authors: Eric Slyman, Stefan Lee, Scott Cohen, Kushal Kafle
Abstract: Recent dataset deduplication techniques have demonstrated that content-aware dataset pruning can dramatically reduce the cost of training Vision-Language Pretrained (VLP) models without significant performance losses compared to training on the original dataset. These results have been based on pruning commonly used image-caption datasets collected from the web -- datasets that are known to harbor harmful social biases that may then be codified in trained models. In this work, we evaluate how deduplication affects the prevalence of these biases in the resulting trained models and introduce an easy-to-implement modification to the recent SemDeDup algorithm that can reduce the negative effects that we observe. When examining CLIP-style models trained on deduplicated variants of LAION-400M, we find our proposed FairDeDup algorithm consistently leads to improved fairness metrics over SemDeDup on the FairFace and FACET datasets while maintaining zero-shot performance on CLIP benchmarks.
Authors: Rashadul Hasan Badhon, Atalie Carina Thompson, Jennifer I. Lim, Theodore Leng, Minhaj Nur Alam
Abstract: Purpose: This study explores the feasibility of using generative machine learning (ML) to translate Optical Coherence Tomography (OCT) images into Optical Coherence Tomography Angiography (OCTA) images, potentially bypassing the need for specialized OCTA hardware. Methods: The method involved implementing a generative adversarial network framework that includes a 2D vascular segmentation model and a 2D OCTA image translation model. The study utilizes a public dataset of 500 patients, divided into subsets based on resolution and disease status, to validate the quality of TR-OCTA images. The validation employs several quality and quantitative metrics to compare the translated images with ground truth OCTAs (GT-OCTA). We then quantitatively characterize vascular features generated in TR-OCTAs with GT-OCTAs to assess the feasibility of using TR-OCTA for objective disease diagnosis. Result: TR-OCTAs showed high image quality in both 3 and 6 mm datasets (high-resolution, moderate structural similarity and contrast quality compared to GT-OCTAs). There were slight discrepancies in vascular metrics, especially in diseased patients. Blood vessel features like tortuosity and vessel perimeter index showed a better trend compared to density features which are affected by local vascular distortions. Conclusion: This study presents a promising solution to the limitations of OCTA adoption in clinical practice by using vascular features from TR-OCTA for disease detection. Translation relevance: This study has the potential to significantly enhance the diagnostic process for retinal diseases by making detailed vascular imaging more widely available and reducing dependency on costly OCTA equipment.
Authors: Filipa Lino, Carlos Santiago, Manuel Marques
Abstract: In the field of 3D Human Pose Estimation (HPE), accurately estimating human pose, especially in scenarios with occlusions, is a significant challenge. This work identifies and addresses a gap in the current state of the art in 3D HPE concerning the scarcity of data and strategies for handling occlusions. We introduce our novel BlendMimic3D dataset, designed to mimic real-world situations where occlusions occur for seamless integration in 3D HPE algorithms. Additionally, we propose a 3D pose refinement block, employing a Graph Convolutional Network (GCN) to enhance pose representation through a graph model. This GCN block acts as a plug-and-play solution, adaptable to various 3D HPE frameworks without requiring retraining them. By training the GCN with occluded data from BlendMimic3D, we demonstrate significant improvements in resolving occluded poses, with comparable results for non-occluded ones. Project web page is available at https://blendmimic3d.github.io/BlendMimic3D/.
Authors: Melih Yazgan, Thomas Graf, Min Liu, J. Marius Zoellner
Abstract: This survey analyzes intermediate fusion methods in collaborative perception for autonomous driving, categorized by real-world challenges. We examine various methods, detailing their features and the evaluation metrics they employ. The focus is on addressing challenges like transmission efficiency, localization errors, communication disruptions, and heterogeneity. Moreover, we explore strategies to counter adversarial attacks and defenses, as well as approaches to adapt to domain shifts. The objective is to present an overview of how intermediate fusion methods effectively meet these diverse challenges, highlighting their role in advancing the field of collaborative perception in autonomous driving.
Authors: Kuan-I Chung, Daniel Moyer
Abstract: We introduce an assessment procedure for interactive segmentation models. Based on concepts from Bayesian Experimental Design, the procedure measures a model's understanding of point prompts and their correspondence with the desired segmentation mask. We show that Oracle Dice index measurements are insensitive or even misleading in measuring this property. We demonstrate the use of the proposed procedure on three interactive segmentation models and subsets of two large image segmentation datasets.
Authors: Samyak Rawlekar, Shubhang Bhatnagar, Vishnuvardhan Pogunulu Srinivasulu, Narendra Ahuja
Abstract: Multi-label Recognition (MLR) involves the identification of multiple objects within an image. To address the additional complexity of this problem, recent works have leveraged information from vision-language models (VLMs) trained on large text-images datasets for the task. These methods learn an independent classifier for each object (class), overlooking correlations in their occurrences. Such co-occurrences can be captured from the training data as conditional probabilities between a pair of classes. We propose a framework to extend the independent classifiers by incorporating the co-occurrence information for object pairs to improve the performance of independent classifiers. We use a Graph Convolutional Network (GCN) to enforce the conditional probabilities between classes, by refining the initial estimates derived from image and text sources obtained using VLMs. We validate our method on four MLR datasets, where our approach outperforms all state-of-the-art methods.
Authors: Marcos V. Conde, Saman Zadtootaghaj, Nabajeet Barman, Radu Timofte, Chenlong He, Qi Zheng, Ruoxi Zhu, Zhengzhong Tu, Haiqiang Wang, Xiangguang Chen, Wenhui Meng, Xiang Pan, Huiying Shi, Han Zhu, Xiaozhong Xu, Lei Sun, Zhenzhong Chen, Shan Liu, Zicheng Zhang, Haoning Wu, Yingjie Zhou, Chunyi Li, Xiaohong Liu, Weisi Lin, Guangtao Zhai, Wei Sun, Yuqin Cao, Yanwei Jiang, Jun Jia, Zhichao Zhang, Zijian Chen, Weixia Zhang, Xiongkuo Min, Steve G\"oring, Zihao Qi, Chen Feng
Abstract: This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge, focused on User-Generated Content (UGC). The aim of this challenge is to gather deep learning-based methods capable of estimating the perceptual quality of UGC videos. The user-generated videos from the YouTube UGC Dataset include diverse content (sports, games, lyrics, anime, etc.), quality and resolutions. The proposed methods must process 30 FHD frames under 1 second. In the challenge, a total of 102 participants registered, and 15 submitted code and models. The performance of the top-5 submissions is reviewed and provided here as a survey of diverse deep models for efficient video quality assessment of user-generated content.
Authors: Arjun Somayazulu, Sagnik Majumder, Changan Chen, Kristen Grauman
Abstract: An environment acoustic model represents how sound is transformed by the physical characteristics of an indoor environment, for any given source/receiver location. Traditional methods for constructing acoustic models involve expensive and time-consuming collection of large quantities of acoustic data at dense spatial locations in the space, or rely on privileged knowledge of scene geometry to intelligently select acoustic data sampling locations. We propose active acoustic sampling, a new task for efficiently building an environment acoustic model of an unmapped environment in which a mobile agent equipped with visual and acoustic sensors jointly constructs the environment acoustic model and the occupancy map on-the-fly. We introduce ActiveRIR, a reinforcement learning (RL) policy that leverages information from audio-visual sensor streams to guide agent navigation and determine optimal acoustic data sampling positions, yielding a high quality acoustic model of the environment from a minimal set of acoustic samples. We train our policy with a novel RL reward based on information gain in the environment acoustic model. Evaluating on diverse unseen indoor environments from a state-of-the-art acoustic simulation platform, ActiveRIR outperforms an array of methods--both traditional navigation agents based on spatial novelty and visual exploration as well as existing state-of-the-art methods.
Authors: Ruilong Li, Sanja Fidler, Angjoo Kanazawa, Francis Williams
Abstract: We present NeRF-XL, a principled method for distributing Neural Radiance Fields (NeRFs) across multiple GPUs, thus enabling the training and rendering of NeRFs with an arbitrarily large capacity. We begin by revisiting existing multi-GPU approaches, which decompose large scenes into multiple independently trained NeRFs, and identify several fundamental issues with these methods that hinder improvements in reconstruction quality as additional computational resources (GPUs) are used in training. NeRF-XL remedies these issues and enables the training and rendering of NeRFs with an arbitrary number of parameters by simply using more hardware. At the core of our method lies a novel distributed training and rendering formulation, which is mathematically equivalent to the classic single-GPU case and minimizes communication between GPUs. By unlocking NeRFs with arbitrarily large parameter counts, our approach is the first to reveal multi-GPU scaling laws for NeRFs, showing improvements in reconstruction quality with larger parameter counts and speed improvements with more GPUs. We demonstrate the effectiveness of NeRF-XL on a wide variety of datasets, including the largest open-source dataset to date, MatrixCity, containing 258K images covering a 25km^2 city area.
Authors: Tushar Nagarajan, Lorenzo Torresani
Abstract: Comparing a user video to a reference how-to video is a key requirement for AR/VR technology delivering personalized assistance tailored to the user's progress. However, current approaches for language-based assistance can only answer questions about a single video. We propose an approach that first automatically generates large amounts of visual instruction tuning data involving pairs of videos from HowTo100M by leveraging existing step annotations and accompanying narrations, and then trains a video-conditioned language model to jointly reason across multiple raw videos. Our model achieves state-of-the-art performance at identifying differences between video pairs and ranking videos based on the severity of these differences, and shows promising ability to perform general reasoning over multiple videos.
Authors: Marcos V. Conde, Florin-Alexandru Vasluianu, Radu Timofte, Jianxing Zhang, Jia Li, Fan Wang, Xiaopeng Li, Zikun Liu, Hyunhee Park, Sejun Song, Changho Kim, Zhijuan Huang, Hongyuan Yu, Cheng Wan, Wending Xiang, Jiamin Lin, Hang Zhong, Qiaosong Zhang, Yue Sun, Xuanwu Yin, Kunlong Zuo, Senyan Xu, Siyuan Jiang, Zhijing Sun, Jiaying Zhu, Liangyan Li, Ke Chen, Yunzhe Li, Yimo Ning, Guanhua Zhao, Jun Chen, Jinyang Yu, Kele Xu, Qisheng Xu, Yong Dou
Abstract: This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. Th goal of this challenge is to upscale RAW Bayer images by 2x, considering unknown degradations such as noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. The performance of the top-5 submissions is reviewed and provided here as a gauge for the current state-of-the-art in RAW Image Super-Resolution.
Authors: Yifan Zhao, Zhenyu Liang, Zhichao Lu, Ran Cheng
Abstract: As one of the emerging challenges in Automated Machine Learning, the Hardware-aware Neural Architecture Search (HW-NAS) tasks can be treated as black-box multi-objective optimization problems (MOPs). An important application of HW-NAS is real-time semantic segmentation, which plays a pivotal role in autonomous driving scenarios. The HW-NAS for real-time semantic segmentation inherently needs to balance multiple optimization objectives, including model accuracy, inference speed, and hardware-specific considerations. Despite its importance, benchmarks have yet to be developed to frame such a challenging task as multi-objective optimization. To bridge the gap, we introduce a tailored streamline to transform the task of HW-NAS for real-time semantic segmentation into standard MOPs. Building upon the streamline, we present a benchmark test suite, CitySeg/MOP, comprising fifteen MOPs derived from the Cityscapes dataset. The CitySeg/MOP test suite is integrated into the EvoXBench platform to provide seamless interfaces with various programming languages (e.g., Python and MATLAB) for instant fitness evaluations. We comprehensively assessed the CitySeg/MOP test suite on various multi-objective evolutionary algorithms, showcasing its versatility and practicality. Source codes are available at https://github.com/EMI-Group/evoxbench.
Authors: Akshatha Mohan, Joshua Peeples
Abstract: Pooling layers (e.g., max and average) may overlook important information encoded in the spatial arrangement of pixel intensity and/or feature values. We propose a novel lacunarity pooling layer that aims to capture the spatial heterogeneity of the feature maps by evaluating the variability within local windows. The layer operates at multiple scales, allowing the network to adaptively learn hierarchical features. The lacunarity pooling layer can be seamlessly integrated into any artificial neural network architecture. Experimental results demonstrate the layer's effectiveness in capturing intricate spatial patterns, leading to improved feature extraction capabilities. The proposed approach holds promise in various domains, especially in agricultural image analysis tasks. This work contributes to the evolving landscape of artificial neural network architectures by introducing a novel pooling layer that enriches the representation of spatial features. Our code is publicly available.
Authors: Ao Xiang, Jingyu Zhang, Qin Yang, Liyang Wang, Yu Cheng
Abstract: With the development and widespread application of digital image processing technology, image splicing has become a common method of image manipulation, raising numerous security and legal issues. This paper introduces a new splicing image detection algorithm based on the statistical characteristics of natural images, aimed at improving the accuracy and efficiency of splicing image detection. By analyzing the limitations of traditional methods, we have developed a detection framework that integrates advanced statistical analysis techniques and machine learning methods. The algorithm has been validated using multiple public datasets, showing high accuracy in detecting spliced edges and locating tampered areas, as well as good robustness. Additionally, we explore the potential applications and challenges faced by the algorithm in real-world scenarios. This research not only provides an effective technological means for the field of image tampering detection but also offers new ideas and methods for future related research.
Authors: Ting Li, Jianshu Chao, Deyu An
Abstract: Unsupervised Domain Adaptation (UDA) refers to the method that utilizes annotated source domain data and unlabeled target domain data to train a model capable of generalizing to the target domain data. Domain discrepancy leads to a significant decrease in the performance of general network models trained on the source domain data when applied to the target domain. We introduce a straightforward approach to mitigate the domain discrepancy, which necessitates no additional parameter calculations and seamlessly integrates with self-training-based UDA methods. Through the transfer of the target domain style to the source domain in the latent feature space, the model is trained to prioritize the target domain style during the decision-making process. We tackle the problem at both the image-level and shallow feature map level by transferring the style information from the target domain to the source domain data. As a result, we obtain a model that exhibits superior performance on the target domain. Our method yields remarkable enhancements in the state-of-the-art performance for synthetic-to-real UDA tasks. For example, our proposed method attains a noteworthy UDA performance of 76.93 mIoU on the GTA->Cityscapes dataset, representing a notable improvement of +1.03 percentage points over the previous state-of-the-art results.
Authors: Haoyuan Li, Qi Hu, You Yao, Kailun Yang, Peng Chen
Abstract: Cross-modality images that integrate visible-infrared spectra cues can provide richer complementary information for object detection. Despite this, existing visible-infrared object detection methods severely degrade in severe weather conditions. This failure stems from the pronounced sensitivity of visible images to environmental perturbations, such as rain, haze, and snow, which frequently cause false negatives and false positives in detection. To address this issue, we introduce a novel and challenging task, termed visible-infrared object detection under adverse weather conditions. To foster this task, we have constructed a new Severe Weather Visible-Infrared Dataset (SWVID) with diverse severe weather scenes. Furthermore, we introduce the Cross-modality Fusion Mamba with Weather-removal (CFMW) to augment detection accuracy in adverse weather conditions. Thanks to the proposed Weather Removal Diffusion Model (WRDM) and Cross-modality Fusion Mamba (CFM) modules, CFMW is able to mine more essential information of pedestrian features in cross-modality fusion, thus could transfer to other rarer scenarios with high efficiency and has adequate availability on those platforms with low computing power. To the best of our knowledge, this is the first study that targeted improvement and integrated both Diffusion and Mamba modules in cross-modality object detection, successfully expanding the practical application of this type of model with its higher accuracy and more advanced architecture. Extensive experiments on both well-recognized and self-created datasets conclusively demonstrate that our CFMW achieves state-of-the-art detection performance, surpassing existing benchmarks. The dataset and source code will be made publicly available at https://github.com/lhy-zjut/CFMW.
Authors: Zhiwei Dong, Xi Zhu, Xiya Cao, Ran Ding, Wei Li, Caifa Zhou, Yongliang Wang, Qiangbo Liu
Abstract: Lane detection has made significant progress in recent years, but there is not a unified architecture for its two sub-tasks: 2D lane detection and 3D lane detection. To fill this gap, we introduce B\'{e}zierFormer, a unified 2D and 3D lane detection architecture based on B\'{e}zier curve lane representation. B\'{e}zierFormer formulate queries as B\'{e}zier control points and incorporate a novel B\'{e}zier curve attention mechanism. This attention mechanism enables comprehensive and accurate feature extraction for slender lane curves via sampling and fusing multiple reference points on each curve. In addition, we propose a novel Chamfer IoU-based loss which is more suitable for the B\'{e}zier control points regression. The state-of-the-art performance of B\'{e}zierFormer on widely-used 2D and 3D lane detection benchmarks verifies its effectiveness and suggests the worthiness of further exploration.
Authors: Haomiao Ni, Bernhard Egger, Suhas Lohit, Anoop Cherian, Ye Wang, Toshiaki Koike-Akino, Sharon X. Huang, Tim K. Marks
Abstract: Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is drinking water."). Existing TI2V frameworks often require costly training on video-text datasets and specific model designs for text and image conditioning. In this paper, we propose TI2V-Zero, a zero-shot, tuning-free method that empowers a pretrained text-to-video (T2V) diffusion model to be conditioned on a provided image, enabling TI2V generation without any optimization, fine-tuning, or introducing external modules. Our approach leverages a pretrained T2V diffusion foundation model as the generative prior. To guide video generation with the additional image input, we propose a "repeat-and-slide" strategy that modulates the reverse denoising process, allowing the frozen diffusion model to synthesize a video frame-by-frame starting from the provided image. To ensure temporal continuity, we employ a DDPM inversion strategy to initialize Gaussian noise for each newly synthesized frame and a resampling technique to help preserve visual details. We conduct comprehensive experiments on both domain-specific and open-domain datasets, where TI2V-Zero consistently outperforms a recent open-domain TI2V model. Furthermore, we show that TI2V-Zero can seamlessly extend to other tasks such as video infilling and prediction when provided with more images. Its autoregressive design also supports long video generation.
Authors: Jiamin Wu, Kenkun Liu, Han Gao, Xiaoke Jiang, Lei Zhang
Abstract: In this paper, we study the problem of 3D reconstruction from a single-view RGB image and propose a novel approach called DIG3D for 3D object reconstruction and novel view synthesis. Our method utilizes an encoder-decoder framework which generates 3D Gaussians in decoder with the guidance of depth-aware image features from encoder. In particular, we introduce the use of deformable transformer, allowing efficient and effective decoding through 3D reference point and multi-layer refinement adaptations. By harnessing the benefits of 3D Gaussians, our approach offers an efficient and accurate solution for 3D reconstruction from single-view images. We evaluate our method on the ShapeNet SRN dataset, getting PSNR of 24.21 and 24.98 in car and chair dataset, respectively. The result outperforming the recent method by around 2.25%, demonstrating the effectiveness of our method in achieving superior results.
Authors: Hedda Cohen Indelman, Elay Dahan, Angeles M. Perez-Agosto, Carmit Shiran, Doron Shaked, Nati Daniel
Abstract: Despite the remarkable success of deep learning in medical imaging analysis, medical image segmentation remains challenging due to the scarcity of high-quality labeled images for supervision. Further, the significant domain gap between natural and medical images in general and ultrasound images in particular hinders fine-tuning models trained on natural images to the task at hand. In this work, we address the performance degradation of segmentation models in low-data regimes and propose a prompt-less segmentation method harnessing the ability of segmentation foundation models to segment abstract shapes. We do that via our novel prompt point generation algorithm which uses coarse semantic segmentation masks as input and a zero-shot prompt-able foundation model as an optimization target. We demonstrate our method on a segmentation findings task (pathologic anomalies) in ultrasound images. Our method's advantages are brought to light in varying degrees of low-data regime experiments on a small-scale musculoskeletal ultrasound images dataset, yielding a larger performance gain as the training set size decreases.
Authors: Zitong Huang, Ze Chen, Bowen Dong, Chaoqi Liang, Erjin Zhou, Wangmeng Zuo
Abstract: Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models. This paper first empirically finds that 1) the vanilla MWA can benefit the class-imbalanced learning, and 2) performing model averaging in the early epochs of training yields a greater performance improvement than doing that in later epochs. Inspired by these two observations, in this paper we propose a novel MWA technique for class-imbalanced learning tasks named Iterative Model Weight Averaging (IMWA). Specifically, IMWA divides the entire training stage into multiple episodes. Within each episode, multiple models are concurrently trained from the same initialized model weight, and subsequently averaged into a singular model. Then, the weight of this average model serves as a fresh initialization for the ensuing episode, thus establishing an iterative learning paradigm. Compared to vanilla MWA, IMWA achieves higher performance improvements with the same computational cost. Moreover, IMWA can further enhance the performance of those methods employing EMA strategy, demonstrating that IMWA and EMA can complement each other. Extensive experiments on various class-imbalanced learning tasks, i.e., class-imbalanced image classification, semi-supervised class-imbalanced image classification and semi-supervised object detection tasks showcase the effectiveness of our IMWA.
Authors: Sifan Long, Linbin Wang, Zhen Zhao, Zichang Tan, Yiming Wu, Shengsheng Wang, Jingdong Wang
Abstract: Prompt learning has become the most effective paradigm for adapting large pre-trained vision-language models (VLMs) to downstream tasks. Recently, unsupervised prompt tuning methods, such as UPL and POUF, directly leverage pseudo-labels as supervisory information to fine-tune additional adaptation modules on unlabeled data. However, inaccurate pseudo labels easily misguide the tuning process and result in poor representation capabilities. In light of this, we propose Training-Free Unsupervised Prompts (TFUP), which maximally preserves the inherent representation capabilities and enhances them with a residual connection to similarity-based prediction probabilities in a training-free and labeling-free manner. Specifically, we integrate both instance confidence and prototype scores to select representative samples, which are used to customize a reliable Feature Cache Model (FCM) for training-free inference. Then, we design a Multi-level Similarity Measure (MSM) that considers both feature-level and semantic-level similarities to calculate the distance between each test image and the cached sample as the weight of the corresponding cached label to generate similarity-based prediction probabilities. In this way, TFUP achieves surprising performance, even surpassing the training-base method on multiple classification datasets. Based on our TFUP, we propose a training-based approach (TFUP-T) to further boost the adaptation performance. In addition to the standard cross-entropy loss, TFUP-T adopts an additional marginal distribution entropy loss to constrain the model from a global perspective. Our TFUP-T achieves new state-of-the-art classification performance compared to unsupervised and few-shot adaptation approaches on multiple benchmarks. In particular, TFUP-T improves the classification accuracy of POUF by 3.3% on the most challenging Domain-Net dataset.
Authors: Zhijie Rao, Jingcai Guo, Xiaocheng Lu, Jingming Liang, Jie Zhang, Haozhao Wang, Kang Wei, Xiaofeng Cao
Abstract: Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping function to align and correlate the sample regions and subattributes, ignoring two crucial issues: 1) the inherent asymmetry of attributes; and 2) the unutilized channel information. This paper addresses these issues by introducing a simple yet effective approach, dubbed Dual Expert Distillation Network (DEDN), where two experts are dedicated to coarse- and fine-grained visual-attribute modeling, respectively. Concretely, one coarse expert, namely cExp, has a complete perceptual scope to coordinate visual-attribute similarity metrics across dimensions, and moreover, another fine expert, namely fExp, consists of multiple specialized subnetworks, each corresponds to an exclusive set of attributes. Two experts cooperatively distill from each other to reach a mutual agreement during training. Meanwhile, we further equip DEDN with a newly designed backbone network, i.e., Dual Attention Network (DAN), which incorporates both region and channel attention information to fully exploit and leverage visual semantic knowledge. Experiments on various benchmark datasets indicate a new state-of-the-art.
Authors: Cong Wu, Xiao-Jun Wu, Tianyang Xu, Josef Kittler
Abstract: Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling. In this paper, we propose an Improved Graph Pooling Network, referred to as IGPN. The main innovations include: Our method incorporates a region-awareness pooling strategy based on structural partitioning. The correlation matrix of the original feature is used to adaptively adjust the weight of information in different regions of the newly generated features, resulting in more flexible and effective processing. To prevent the irreversible loss of discriminative information, we propose a cross fusion module and an information supplement module to provide block-level and input-level information respectively. As a plug-and-play structure, the proposed operation can be seamlessly combined with existing GCN-based models. We conducted extensive evaluations on several challenging benchmarks, and the experimental results indicate the effectiveness of our proposed solutions. For example, in the cross-subject evaluation of the NTU-RGB+D 60 dataset, IGPN achieves a significant improvement in accuracy compared to the baseline while reducing Flops by nearly 70%; a heavier version has also been introduced to further boost accuracy.
Authors: Xinxin Fan, Lin Liu, Haoran Zhang
Abstract: The use of multimodal data in assisted diagnosis and segmentation has emerged as a prominent area of interest in current research. However, one of the primary challenges is how to effectively fuse multimodal features. Most of the current approaches focus on the integration of multimodal features while ignoring the correlation and consistency between different modal features, leading to the inclusion of potentially irrelevant information. To address this issue, we introduce an innovative Multimodal Information Cross Transformer (MicFormer), which employs a dual-stream architecture to simultaneously extract features from each modality. Leveraging the Cross Transformer, it queries features from one modality and retrieves corresponding responses from another, facilitating effective communication between bimodal features. Additionally, we incorporate a deformable Transformer architecture to expand the search space. We conducted experiments on the MM-WHS dataset, and in the CT-MRI multimodal image segmentation task, we successfully improved the whole-heart segmentation DICE score to 85.57 and MIoU to 75.51. Compared to other multimodal segmentation techniques, our method outperforms by margins of 2.83 and 4.23, respectively. This demonstrates the efficacy of MicFormer in integrating relevant information between different modalities in multimodal tasks. These findings hold significant implications for multimodal image tasks, and we believe that MicFormer possesses extensive potential for broader applications across various domains. Access to our method is available at https://github.com/fxxJuses/MICFormer
Authors: An Yan, Zhengyuan Yang, Junda Wu, Wanrong Zhu, Jianwei Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Julian McAuley, Jianfeng Gao, Lijuan Wang
Abstract: Set-of-Mark (SoM) Prompting unleashes the visual grounding capability of GPT-4V, by enabling the model to associate visual objects with tags inserted on the image. These tags, marked with alphanumerics, can be indexed via text tokens for easy reference. Despite the extraordinary performance from GPT-4V, we observe that other Multimodal Large Language Models (MLLMs) struggle to understand these visual tags. To promote the learning of SoM prompting for open-source models, we propose a new learning paradigm: "list items one by one," which asks the model to enumerate and describe all visual tags placed on the image following the alphanumeric orders of tags. By integrating our curated dataset with other visual instruction tuning datasets, we are able to equip existing MLLMs with the SoM prompting ability. Furthermore, we evaluate our finetuned SoM models on five MLLM benchmarks. We find that this new dataset, even in a relatively small size (10k-30k images with tags), significantly enhances visual reasoning capabilities and reduces hallucinations for MLLMs. Perhaps surprisingly, these improvements persist even when the visual tags are omitted from input images during inference. This suggests the potential of "list items one by one" as a new paradigm for training MLLMs, which strengthens the object-text alignment through the use of visual tags in the training stage. Finally, we conduct analyses by probing trained models to understand the working mechanism of SoM. Our code and data are available at \url{https://github.com/zzxslp/SoM-LLaVA}.
Authors: Zuocheng Wen, Lingzhong Guo
Abstract: Deep convolutional neural networks (DCNNs) are a class of artificial neural networks, primarily for computer vision tasks such as segmentation and classification. Many nonlinear operations, such as activation functions and pooling strategies, are used in DCNNs to enhance their ability to process different signals with different tasks. Conceptional convolution, a linear filter, is the essential component of DCNNs while nonlinear convolution is generally implemented as higher-order Volterra filters, However, for Volterra filtering, significant memory and computational costs pose a primary limitation for its widespread application in DCNN applications. In this study, we propose a novel method to perform higher-order Volterra filtering with lower memory and computation cost in forward and backward pass in DCNN training. The proposed method demonstrates computational advantages compared with conventional Volterra filter implementation. Furthermore, based on the proposed method, a new attention module called Higher-order Local Attention Block (HLA) is proposed and tested on CIFAR-100 dataset, which shows competitive improvement for classification task. Source code is available at: https://github.com/WinterWen666/Efficient-High-Order-Volterra-Convolution.git
URLs: https://github.com/WinterWen666/Efficient-High-Order-Volterra-Convolution.git
Authors: Jiawei Chen, Dingkang Yang, Yue Jiang, Mingcheng Li, Jinjie Wei, Xiaolu Hou, Lihua Zhang
Abstract: In the realm of Medical Visual Language Models (Med-VLMs), the quest for universal efficient fine-tuning mechanisms remains paramount, especially given researchers in interdisciplinary fields are often extremely short of training resources, yet largely unexplored. Given the unique challenges in the medical domain, such as limited data scope and significant domain-specific requirements, evaluating and adapting Parameter-Efficient Fine-Tuning (PEFT) methods specifically for Med-VLMs is essential. Most of the current PEFT methods on Med-VLMs have yet to be comprehensively investigated but mainly focus on adding some components to the model's structure or input. However, fine-tuning intrinsic model components often yields better generality and consistency, and its impact on the ultimate performance of Med-VLMs has been widely overlooked and remains understudied. In this paper, we endeavour to explore an alternative to traditional PEFT methods, especially the impact of fine-tuning LayerNorm layers, FFNs and Attention layers on the Med-VLMs. Our comprehensive studies span both small-scale and large-scale Med-VLMs, evaluating their performance under various fine-tuning paradigms across tasks such as Medical Visual Question Answering and Medical Imaging Report Generation. The findings reveal unique insights into the effects of intrinsic parameter fine-tuning methods on fine-tuning Med-VLMs to downstream tasks and expose fine-tuning solely the LayerNorm layers not only surpasses the efficiency of traditional PEFT methods but also retains the model's accuracy and generalization capabilities across a spectrum of medical downstream tasks. The experiments show LayerNorm fine-tuning's superior adaptability and scalability, particularly in the context of large-scale Med-VLMs.
Authors: Zhimeng Zheng, Tao Huang, Gongsheng Li, Zuyi Wang
Abstract: Recently, the performance of monocular depth estimation (MDE) has been significantly boosted with the integration of transformer models. However, the transformer models are usually computationally-expensive, and their effectiveness in light-weight models are limited compared to convolutions. This limitation hinders their deployment on resource-limited devices. In this paper, we propose a cross-architecture knowledge distillation method for MDE, dubbed DisDepth, to enhance efficient CNN models with the supervision of state-of-the-art transformer models. Concretely, we first build a simple framework of convolution-based MDE, which is then enhanced with a novel local-global convolution module to capture both local and global information in the image. To effectively distill valuable information from the transformer teacher and bridge the gap between convolution and transformer features, we introduce a method to acclimate the teacher with a ghost decoder. The ghost decoder is a copy of the student's decoder, and adapting the teacher with the ghost decoder aligns the features to be student-friendly while preserving their original performance. Furthermore, we propose an attentive knowledge distillation loss that adaptively identifies features valuable for depth estimation. This loss guides the student to focus more on attentive regions, improving its performance. Extensive experiments on KITTI and NYU Depth V2 datasets demonstrate the effectiveness of DisDepth. Our method achieves significant improvements on various efficient backbones, showcasing its potential for efficient monocular depth estimation.
Authors: Ryoya Nara, Yu-Chieh Lin, Yuji Nozawa, Youyang Ng, Goh Itoh, Osamu Torii, Yusuke Matsui
Abstract: Many image retrieval studies use metric learning to train an image encoder. However, metric learning cannot handle differences in users' preferences, and requires data to train an image encoder. To overcome these limitations, we revisit relevance feedback, a classic technique for interactive retrieval systems, and propose an interactive CLIP-based image retrieval system with relevance feedback. Our retrieval system first executes the retrieval, collects each user's unique preferences through binary feedback, and returns images the user prefers. Even when users have various preferences, our retrieval system learns each user's preference through the feedback and adapts to the preference. Moreover, our retrieval system leverages CLIP's zero-shot transferability and achieves high accuracy without training. We empirically show that our retrieval system competes well with state-of-the-art metric learning in category-based image retrieval, despite not training image encoders specifically for each dataset. Furthermore, we set up two additional experimental settings where users have various preferences: one-label-based image retrieval and conditioned image retrieval. In both cases, our retrieval system effectively adapts to each user's preferences, resulting in improved accuracy compared to image retrieval without feedback. Overall, our work highlights the potential benefits of integrating CLIP with classic relevance feedback techniques to enhance image retrieval.
Authors: Aimi Okabayashi (IRISA, OBELIX), Nicolas Audebert (CEDRIC - VERTIGO, CNAM, LaSTIG, IGN), Simon Donike (IPL), Charlotte Pelletier (OBELIX, IRISA)
Abstract: Satellite imaging generally presents a trade-off between the frequency of acquisitions and the spatial resolution of the images. Super-resolution is often advanced as a way to get the best of both worlds. In this work, we investigate multi-image super-resolution of satellite image time series, i.e. how multiple images of the same area acquired at different dates can help reconstruct a higher resolution observation. In particular, we extend state-of-the-art deep single and multi-image super-resolution algorithms, such as SRDiff and HighRes-net, to deal with irregularly sampled Sentinel-2 time series. We introduce BreizhSR, a new dataset for 4x super-resolution of Sentinel-2 time series using very high-resolution SPOT-6 imagery of Brittany, a French region. We show that using multiple images significantly improves super-resolution performance, and that a well-designed temporal positional encoding allows us to perform super-resolution for different times of the series. In addition, we observe a trade-off between spectral fidelity and perceptual quality of the reconstructed HR images, questioning future directions for super-resolution of Earth Observation data.
Authors: Yu Wang, Sanping Zhou, Kun Xia, Le Wang
Abstract: Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to making ambiguous predictions under scarce labeled data, embodied as the limitation of distinguishing different actions with similar spatio-temporal information. In this paper, we approach this problem by empowering the model two aspects of capability, namely discriminative spatial modeling and temporal structure modeling for learning discriminative spatio-temporal representations. Specifically, we propose an Adaptive Contrastive Learning~(ACL) strategy. It assesses the confidence of all unlabeled samples by the class prototypes of the labeled data, and adaptively selects positive-negative samples from a pseudo-labeled sample bank to construct contrastive learning. Additionally, we introduce a Multi-scale Temporal Learning~(MTL) strategy. It could highlight informative semantics from long-term clips and integrate them into the short-term clip while suppressing noisy information. Afterwards, both of these two new techniques are integrated in a unified framework to encourage the model to make accurate predictions. Extensive experiments on UCF101, HMDB51 and Kinetics400 show the superiority of our method over prior state-of-the-art approaches.
Authors: Moritz Sturm, Lorenzo Cerrone, Fred A. Hamprecht
Abstract: Cell tracking remains a pivotal yet challenging task in biomedical research. The full potential of deep learning for this purpose is often untapped due to the limited availability of comprehensive and varied training data sets. In this paper, we present SynCellFactory, a generative cell video augmentation. At the heart of SynCellFactory lies the ControlNet architecture, which has been fine-tuned to synthesize cell imagery with photorealistic accuracy in style and motion patterns. This technique enables the creation of synthetic yet realistic cell videos that mirror the complexity of authentic microscopy time-lapses. Our experiments demonstrate that SynCellFactory boosts the performance of well-established deep learning models for cell tracking, particularly when original training data is sparse.
Authors: Zhibo Zhang, Ximing Yang, Weizhong Zhang, Cheng Jin
Abstract: This paper presents a robust fine-tuning method designed for pre-trained 3D point cloud models, to enhance feature robustness in downstream fine-tuned models. We highlight the limitations of current fine-tuning methods and the challenges of learning robust models. The proposed method, named Weight-Space Ensembles for Fine-Tuning then Linear Probing (WiSE-FT-LP), integrates the original pre-training and fine-tuning models through weight space integration followed by Linear Probing. This approach significantly enhances the performance of downstream fine-tuned models under distribution shifts, improving feature robustness while maintaining high performance on the target distribution. We apply this robust fine-tuning method to mainstream 3D point cloud pre-trained models and evaluate the quality of model parameters and the degradation of downstream task performance. Experimental results demonstrate the effectiveness of WiSE-FT-LP in enhancing model robustness, effectively balancing downstream task performance and model feature robustness without altering the model structures.
Authors: Hongyu Yan, Yadong Mu
Abstract: Image-guided object assembly represents a burgeoning research topic in computer vision. This paper introduces a novel task: translating multi-view images of a structural 3D model (for example, one constructed with building blocks drawn from a 3D-object library) into a detailed sequence of assembly instructions executable by a robotic arm. Fed with multi-view images of the target 3D model for replication, the model designed for this task must address several sub-tasks, including recognizing individual components used in constructing the 3D model, estimating the geometric pose of each component, and deducing a feasible assembly order adhering to physical rules. Establishing accurate 2D-3D correspondence between multi-view images and 3D objects is technically challenging. To tackle this, we propose an end-to-end model known as the Neural Assembler. This model learns an object graph where each vertex represents recognized components from the images, and the edges specify the topology of the 3D model, enabling the derivation of an assembly plan. We establish benchmarks for this task and conduct comprehensive empirical evaluations of Neural Assembler and alternative solutions. Our experiments clearly demonstrate the superiority of Neural Assembler.
Authors: Vincent Hackstein, Paul Fauth-Mayer, Matthias Rothermel, Norbert Haala
Abstract: While originally developed for novel view synthesis, Neural Radiance Fields (NeRFs) have recently emerged as an alternative to multi-view stereo (MVS). Triggered by a manifold of research activities, promising results have been gained especially for texture-less, transparent, and reflecting surfaces, while such scenarios remain challenging for traditional MVS-based approaches. However, most of these investigations focus on close-range scenarios, with studies for airborne scenarios still missing. For this task, NeRFs face potential difficulties at areas of low image redundancy and weak data evidence, as often found in street canyons, facades or building shadows. Furthermore, training such networks is computationally expensive. Thus, the aim of our work is twofold: First, we investigate the applicability of NeRFs for aerial image blocks representing different characteristics like nadir-only, oblique and high-resolution imagery. Second, during these investigations we demonstrate the benefit of integrating depth priors from tie-point measures, which are provided during presupposed Bundle Block Adjustment. Our work is based on the state-of-the-art framework VolSDF, which models 3D scenes by signed distance functions (SDFs), since this is more applicable for surface reconstruction compared to the standard volumetric representation in vanilla NeRFs. For evaluation, the NeRF-based reconstructions are compared to results of a publicly available benchmark dataset for airborne images.
Authors: Ayumu Saito, Jiju Poovvancheri
Abstract: Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in the input space, or the necessity of additional modalities. In order to address these issues, we introduce Point-JEPA, a joint embedding predictive architecture designed specifically for point cloud data. To this end, we introduce a sequencer that orders point cloud tokens to efficiently compute and utilize tokens proximity based on their indices during target and context selection. The sequencer also allows shared computations of the tokens proximity between context and target selection, further improving the efficiency. Experimentally, our method achieves competitive results with state-of-the-art methods while avoiding the reconstruction in the input space or additional modality.
Authors: Zongyao He, Zhi Jin
Abstract: The recent work Local Implicit Image Function (LIIF) and subsequent Implicit Neural Representation (INR) based works have achieved remarkable success in Arbitrary-Scale Super-Resolution (ASSR) by using MLP to decode Low-Resolution (LR) features. However, these continuous image representations typically implement decoding in High-Resolution (HR) High-Dimensional (HD) space, leading to a quadratic increase in computational cost and seriously hindering the practical applications of ASSR. To tackle this problem, we propose a novel Latent Modulated Function (LMF), which decouples the HR-HD decoding process into shared latent decoding in LR-HD space and independent rendering in HR Low-Dimensional (LD) space, thereby realizing the first computational optimal paradigm of continuous image representation. Specifically, LMF utilizes an HD MLP in latent space to generate latent modulations of each LR feature vector. This enables a modulated LD MLP in render space to quickly adapt to any input feature vector and perform rendering at arbitrary resolution. Furthermore, we leverage the positive correlation between modulation intensity and input image complexity to design a Controllable Multi-Scale Rendering (CMSR) algorithm, offering the flexibility to adjust the decoding efficiency based on the rendering precision. Extensive experiments demonstrate that converting existing INR-based ASSR methods to LMF can reduce the computational cost by up to 99.9%, accelerate inference by up to 57 times, and save up to 76% of parameters, while maintaining competitive performance. The code is available at https://github.com/HeZongyao/LMF.
Authors: Lihua Jing, Rui Wang, Wenqi Ren, Xin Dong, Cong Zou
Abstract: Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility. Existing defense methods, which rely on attack data or prior knowledge, struggle to effectively address a wide range of adversarial patches. In this paper, we show two inherent characteristics of adversarial patches, semantic independence and spatial heterogeneity, independent of their appearance, shape, size, quantity, and location. Semantic independence indicates that adversarial patches operate autonomously within their semantic context, while spatial heterogeneity manifests as distinct image quality of the patch area that differs from original clean image due to the independent generation process. Based on these observations, we propose PAD, a novel adversarial patch localization and removal method that does not require prior knowledge or additional training. PAD offers patch-agnostic defense against various adversarial patches, compatible with any pre-trained object detectors. Our comprehensive digital and physical experiments involving diverse patch types, such as localized noise, printable, and naturalistic patches, exhibit notable improvements over state-of-the-art works. Our code is available at https://github.com/Lihua-Jing/PAD.
Authors: Mingcheng Li, Dingkang Yang, Xiao Zhao, Shuaibing Wang, Yan Wang, Kun Yang, Mingyang Sun, Dongliang Kou, Ziyun Qian, Lihua Zhang
Abstract: Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However, in real-world applications, some practical factors cause uncertain modality missingness, which drastically degrades the model's performance. To this end, we propose a Correlation-decoupled Knowledge Distillation (CorrKD) framework for the MSA task under uncertain missing modalities. Specifically, we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics. Moreover, a category-guided prototype distillation mechanism is introduced to capture cross-category correlations using category prototypes to align feature distributions and generate favorable joint representations. Eventually, we design a response-disentangled consistency distillation strategy to optimize the sentiment decision boundaries of the student network through response disentanglement and mutual information maximization. Comprehensive experiments on three datasets indicate that our framework can achieve favorable improvements compared with several baselines.
Authors: Panagiotis Sapoutzoglou, Georgios Giapitzakis Tzintanos, George Terzakis, Maria Pateraki
Abstract: We present a generic algorithm for scoring pose estimation methods that rely on single image semantic analysis. The algorithm employs a lightweight putative shape representation using a combination of multiple Gaussian Processes. Each Gaussian Process (GP) yields distance normal distributions from multiple reference points in the object's coordinate system to its surface, thus providing a geometric evaluation framework for scoring predicted poses. Our confidence measure comprises the average mixture probability of pixel back-projections onto the shape template. In the reported experiments, we compare the accuracy of our GP based representation of objects versus the actual geometric models and demonstrate the ability of our method to capture the influence of outliers as opposed to the corresponding intrinsic measures that ship with the segmentation and pose estimation methods.
Authors: Zhihao Shuai, Yinan Chen, Shunqiang Mao, Yihan Zho, Xiaohong Zhang
Abstract: Weakly supervised medical image segmentation (MIS) using generative models is crucial for clinical diagnosis. However, the accuracy of the segmentation results is often limited by insufficient supervision and the complex nature of medical imaging. Existing models also only provide a single outcome, which does not allow for the measurement of uncertainty. In this paper, we introduce DiffSeg, a segmentation model for skin lesions based on diffusion difference which exploits diffusion model principles to ex-tract noise-based features from images with diverse semantic information. By discerning difference between these noise features, the model identifies diseased areas. Moreover, its multi-output capability mimics doctors' annotation behavior, facilitating the visualization of segmentation result consistency and ambiguity. Additionally, it quantifies output uncertainty using Generalized Energy Distance (GED), aiding interpretability and decision-making for physicians. Finally, the model integrates outputs through the Dense Conditional Random Field (DenseCRF) algorithm to refine the segmentation boundaries by considering inter-pixel correlations, which improves the accuracy and optimizes the segmentation results. We demonstrate the effectiveness of DiffSeg on the ISIC 2018 Challenge dataset, outperforming state-of-the-art U-Net-based methods.
Authors: Marcos V. Conde, Zhijun Lei, Wen Li, Cosmin Stejerean, Ioannis Katsavounidis, Radu Timofte, Kihwan Yoon, Ganzorig Gankhuyag, Jiangtao Lv, Long Sun, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Zhiyuan Li, Hao Wei, Chenyang Ge, Dongyang Zhang, Tianle Liu, Huaian Chen, Yi Jin, Menghan Zhou, Yiqiang Yan, Si Gao, Biao Wu, Shaoli Liu, Chengjian Zheng, Diankai Zhang, Ning Wang, Xintao Qiu, Yuanbo Zhou, Kongxian Wu, Xinwei Dai, Hui Tang, Wei Deng, Qingquan Gao, Tong Tong, Jae-Hyeon Lee, Ui-Jin Choi, Min Yan, Xin Liu, Qian Wang, Xiaoqian Ye, Zhan Du, Tiansen Zhang, Long Peng, Jiaming Guo, Xin Di, Bohao Liao, Zhibo Du, Peize Xia, Renjing Pei, Yang Wang, Yang Cao, Zhengjun Zha, Bingnan Han, Hongyuan Yu, Zhuoyuan Wu, Cheng Wan, Yuqing Liu, Haodong Yu, Jizhe Li, Zhijuan Huang, Yuan Huang, Yajun Zou, Xianyu Guan, Qi Jia, Heng Zhang, Xuanwu Yin, Kunlong Zuo, Hyeon-Cheol Moon, Tae-hyun Jeong, Yoonmo Yang, Jae-Gon Kim, Jinwoo Jeong, Sunjei Kim
Abstract: This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing a variety of 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 10ms. Out of the 160 participants, 25 teams submitted their code and models. The solutions present novel designs tailored for memory-efficiency and runtime on edge devices. This survey describes the best solutions for real-time SR of compressed high-resolution images.
Authors: Hai Wu, Shijia Zhao, Xun Huang, Chenglu Wen, Xin Li, Cheng Wang
Abstract: The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes. However, the challenge arises due to the sparsity of LiDAR scans, which leads to pseudo-labels with erroneous size and position, resulting in subpar detection performance. To tackle this problem, this paper introduces a Commonsense Prototype-based Detector, termed CPD, for unsupervised 3D object detection. CPD first constructs Commonsense Prototype (CProto) characterized by high-quality bounding box and dense points, based on commonsense intuition. Subsequently, CPD refines the low-quality pseudo-labels by leveraging the size prior from CProto. Furthermore, CPD enhances the detection accuracy of sparsely scanned objects by the geometric knowledge from CProto. CPD outperforms state-of-the-art unsupervised 3D detectors on Waymo Open Dataset (WOD), PandaSet, and KITTI datasets by a large margin. Besides, by training CPD on WOD and testing on KITTI, CPD attains 90.85% and 81.01% 3D Average Precision on easy and moderate car classes, respectively. These achievements position CPD in close proximity to fully supervised detectors, highlighting the significance of our method. The code will be available at https://github.com/hailanyi/CPD.
Authors: Xu Zheng, Pengyuan Zhou, Athanasios V. Vasilakos, Lin Wang
Abstract: In this paper, we address the challenging source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation, given only a pinhole image pre-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is non-trivial due to three critical challenges: 1) semantic mismatches from the distinct Field-of-View (FoV) between domains, 2) style discrepancies inherent in the UDA problem, and 3) inevitable distortion of the panoramic images. To tackle these problems, we propose 360SFUDA++ that effectively extracts knowledge from the source pinhole model with only unlabeled panoramic images and transfers the reliable knowledge to the target panoramic domain. Specifically, we first utilize Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection (ERP) to patches with fixed FoV projection (FFP) to mimic the pinhole images. Both projections are shown effective in extracting knowledge from the source model. However, as the distinct projections make it less possible to directly transfer knowledge between domains, we then propose Reliable Panoramic Prototype Adaptation Module (RP2AM) to transfer knowledge at both prediction and prototype levels. RP$^2$AM selects the confident knowledge and integrates panoramic prototypes for reliable knowledge adaptation. Moreover, we introduce Cross-projection Dual Attention Module (CDAM), which better aligns the spatial and channel characteristics across projections at the feature level between domains. Both knowledge extraction and transfer processes are synchronously updated to reach the best performance. Extensive experiments on the synthetic and real-world benchmarks, including outdoor and indoor scenarios, demonstrate that our 360SFUDA++ achieves significantly better performance than prior SFUDA methods.
Authors: Xiaotong Yu, Chang-Wen Chen
Abstract: Efficient visual perception using mobile systems is crucial, particularly in unknown environments such as search and rescue operations, where swift and comprehensive perception of objects of interest is essential. In such real-world applications, objects of interest are often situated in complex environments, making the selection of the 'Next Best' view based solely on maximizing visibility gain suboptimal. Semantics, providing a higher-level interpretation of perception, should significantly contribute to the selection of the next viewpoint for various perception tasks. In this study, we formulate a novel information gain that integrates both visibility gain and semantic gain in a unified form to select the semantic-aware Next-Best-View. Additionally, we design an adaptive strategy with termination criterion to support a two-stage search-and-acquisition manoeuvre on multiple objects of interest aided by a multi-degree-of-freedoms (Multi-DoFs) mobile system. Several semantically relevant reconstruction metrics, including perspective directivity and region of interest (ROI)-to-full reconstruction volume ratio, are introduced to evaluate the performance of the proposed approach. Simulation experiments demonstrate the advantages of the proposed approach over existing methods, achieving improvements of up to 27.13% for the ROI-to-full reconstruction volume ratio and a 0.88234 average perspective directivity. Furthermore, the planned motion trajectory exhibits better perceiving coverage toward the target.
Authors: Guohao Li, Hongyu Yang, Di Huang, Yunhong Wang
Abstract: Generative 3D face models featuring disentangled controlling factors hold immense potential for diverse applications in computer vision and computer graphics. However, previous 3D face modeling methods face a challenge as they demand specific labels to effectively disentangle these factors. This becomes particularly problematic when integrating multiple 3D face datasets to improve the generalization of the model. Addressing this issue, this paper introduces a Weakly-Supervised Disentanglement Framework, denoted as WSDF, to facilitate the training of controllable 3D face models without an overly stringent labeling requirement. Adhering to the paradigm of Variational Autoencoders (VAEs), the proposed model achieves disentanglement of identity and expression controlling factors through a two-branch encoder equipped with dedicated identity-consistency prior. It then faithfully re-entangles these factors via a tensor-based combination mechanism. Notably, the introduction of the Neutral Bank allows precise acquisition of subject-specific information using only identity labels, thereby averting degeneration due to insufficient supervision. Additionally, the framework incorporates a label-free second-order loss function for the expression factor to regulate deformation space and eliminate extraneous information, resulting in enhanced disentanglement. Extensive experiments have been conducted to substantiate the superior performance of WSDF. Our code is available at https://github.com/liguohao96/WSDF.
Authors: Ye Mao, Junpeng Jing, Krystian Mikolajczyk
Abstract: Recent advances in Vision and Language Models (VLMs) have improved open-world 3D representation, facilitating 3D zero-shot capability in unseen categories. Existing open-world methods pre-train an extra 3D encoder to align features from 3D data (e.g., depth maps or point clouds) with CAD-rendered images and corresponding texts. However, the limited color and texture variations in CAD images can compromise the alignment robustness. Furthermore, the volume discrepancy between pre-training datasets of the 3D encoder and VLM leads to sub-optimal 2D to 3D knowledge transfer. To overcome these issues, we propose OpenDlign, a novel framework for learning open-world 3D representations, that leverages depth-aligned images generated from point cloud-projected depth maps. Unlike CAD-rendered images, our generated images provide rich, realistic color and texture diversity while preserving geometric and semantic consistency with the depth maps. OpenDlign also optimizes depth map projection and integrates depth-specific text prompts, improving 2D VLM knowledge adaptation for 3D learning efficient fine-tuning. Experimental results show that OpenDlign significantly outperforms existing benchmarks in zero-shot and few-shot 3D tasks, exceeding prior scores by 8.0% on ModelNet40 and 16.4% on OmniObject3D with just 6 million tuned parameters. Moreover, integrating generated depth-aligned images into existing 3D learning pipelines consistently improves their performance.
Authors: Daniel Dworak, Mateusz Komorkiewicz, Pawe{\l} Skruch, Jerzy Baranowski
Abstract: In this paper, we propose a novel approach to address the problem of camera and radar sensor fusion for 3D object detection in autonomous vehicle perception systems. Our approach builds on recent advances in deep learning and leverages the strengths of both sensors to improve object detection performance. Precisely, we extract 2D features from camera images using a state-of-the-art deep learning architecture and then apply a novel Cross-Domain Spatial Matching (CDSM) transformation method to convert these features into 3D space. We then fuse them with extracted radar data using a complementary fusion strategy to produce a final 3D object representation. To demonstrate the effectiveness of our approach, we evaluate it on the NuScenes dataset. We compare our approach to both single-sensor performance and current state-of-the-art fusion methods. Our results show that the proposed approach achieves superior performance over single-sensor solutions and could directly compete with other top-level fusion methods.
Authors: Petr Hruby, Timothy Duff, Marc Pollefeys
Abstract: We revisit certain problems of pose estimation based on 3D--2D correspondences between features which may be points or lines. Specifically, we address the two previously-studied minimal problems of estimating camera extrinsics from $p \in \{ 1, 2 \}$ point--point correspondences and $l=3-p$ line--line correspondences. To the best of our knowledge, all of the previously-known practical solutions to these problems required computing the roots of degree $\ge 4$ (univariate) polynomials when $p=2$, or degree $\ge 8$ polynomials when $p=1.$ We describe and implement two elementary solutions which reduce the degrees of the needed polynomials from $4$ to $2$ and from $8$ to $4$, respectively. We show experimentally that the resulting solvers are numerically stable and fast: when compared to the previous state-of-the art, we may obtain nearly an order of magnitude speedup. The code is available at \url{https://github.com/petrhruby97/efficient\_absolute}
Authors: Parul Gupta, Munawar Hayat, Abhinav Dhall, Thanh-Toan Do
Abstract: Few-shot image synthesis entails generating diverse and realistic images of novel categories using only a few example images. While multiple recent efforts in this direction have achieved impressive results, the existing approaches are dependent only upon the few novel samples available at test time in order to generate new images, which restricts the diversity of the generated images. To overcome this limitation, we propose Conditional Distribution Modelling (CDM) -- a framework which effectively utilizes Diffusion models for few-shot image generation. By modelling the distribution of the latent space used to condition a Diffusion process, CDM leverages the learnt statistics of the training data to get a better approximation of the unseen class distribution, thereby removing the bias arising due to limited number of few shot samples. Simultaneously, we devise a novel inversion based optimization strategy that further improves the approximated unseen class distribution, and ensures the fidelity of the generated samples to the unseen class. The experimental results on four benchmark datasets demonstrate the effectiveness of our proposed CDM for few-shot generation.
Authors: Kuofeng Gao, Jindong Gu, Yang Bai, Shu-Tao Xia, Philip Torr, Wei Liu, Zhifeng Li
Abstract: Despite the exceptional performance of multi-modal large language models (MLLMs), their deployment requires substantial computational resources. Once malicious users induce high energy consumption and latency time (energy-latency cost), it will exhaust computational resources and harm availability of service. In this paper, we investigate this vulnerability for MLLMs, particularly image-based and video-based ones, and aim to induce high energy-latency cost during inference by crafting an imperceptible perturbation. We find that high energy-latency cost can be manipulated by maximizing the length of generated sequences, which motivates us to propose verbose samples, including verbose images and videos. Concretely, two modality non-specific losses are proposed, including a loss to delay end-of-sequence (EOS) token and an uncertainty loss to increase the uncertainty over each generated token. In addition, improving diversity is important to encourage longer responses by increasing the complexity, which inspires the following modality specific loss. For verbose images, a token diversity loss is proposed to promote diverse hidden states. For verbose videos, a frame feature diversity loss is proposed to increase the feature diversity among frames. To balance these losses, we propose a temporal weight adjustment algorithm. Experiments demonstrate that our verbose samples can largely extend the length of generated sequences.
Authors: Leandro Di Bella, Yangxintong Lyu, Adrian Munteanu
Abstract: This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep-learning-based Kalman Filter. By integrating a Bi-directional Kalman filter strategy utilizing forward and backward time-series processing, combined with a learnable motion model to represent complex motion patterns, our method significantly improves pose accuracy and robustness across various conditions, particularly for occluded or distant vehicles. Experimental validation on the KITTI dataset confirms that DeepKalPose outperforms existing methods in both pose accuracy and temporal consistency.
Authors: Ruiyang Wang, Haonan Wang, Junfeng Sun, Mingjia Zhao, Meng Liu
Abstract: In recent years, with the rapid development of computer information technology, the development of artificial intelligence has been accelerating. The traditional geometry recognition technology is relatively backward and the recognition rate is low. In the face of massive information database, the traditional algorithm model inevitably has the problems of low recognition accuracy and poor performance. Deep learning theory has gradually become a very important part of machine learning. The implementation of convolutional neural network (CNN) reduces the difficulty of graphics generation algorithm. In this paper, using the advantages of lenet-5 architecture sharing weights and feature extraction and classification, the proposed geometric pattern recognition algorithm model is faster in the training data set. By constructing the shared feature parameters of the algorithm model, the cross-entropy loss function is used in the recognition process to improve the generalization of the model and improve the average recognition accuracy of the test data set.
Authors: Zhiwei Wang, Ying Zhou, Shiquan He, Ting Li, Yitong Zhang, 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 three 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%.
Authors: Haotian Yan, Ming Wu, Chuang Zhang
Abstract: Multi-scale learning is central to semantic segmentation. We visualize the effective receptive field (ERF) of canonical multi-scale representations and point out two risks in learning them: scale inadequacy and field inactivation. A novel multi-scale learner, varying window attention (VWA), is presented to address these issues. VWA leverages the local window attention (LWA) and disentangles LWA into the query window and context window, allowing the context's scale to vary for the query to learn representations at multiple scales. However, varying the context to large-scale windows (enlarging ratio R) can significantly increase the memory footprint and computation cost (R^2 times larger than LWA). We propose a simple but professional re-scaling strategy to zero the extra induced cost without compromising performance. Consequently, VWA uses the same cost as LWA to overcome the receptive limitation of the local window. Furthermore, depending on VWA and employing various MLPs, we introduce a multi-scale decoder (MSD), VWFormer, to improve multi-scale representations for semantic segmentation. VWFormer achieves efficiency competitive with the most compute-friendly MSDs, like FPN and MLP decoder, but performs much better than any MSDs. For instance, using nearly half of UPerNet's computation, VWFormer outperforms it by 1.0%-2.5% mIoU on ADE20K. With little extra overhead, ~10G FLOPs, Mask2Former armed with VWFormer improves by 1.0%-1.3%.
Authors: Risto Ojala, Eerik Alamikkotervo
Abstract: In below freezing winter conditions, road surface friction can greatly vary based on the mixture of snow, ice, and water on the road. Friction between the road and vehicle tyres is a critical parameter defining vehicle dynamics, and therefore road surface friction information is essential to acquire for several intelligent transportation applications, such as safe control of automated vehicles or alerting drivers of slippery road conditions. This paper explores computer vision-based evaluation of road surface friction from roadside cameras. Previous studies have extensively investigated the application of convolutional neural networks for the task of evaluating the road surface condition from images. Here, we propose a hybrid deep learning architecture, WCamNet, consisting of a pretrained visual transformer model and convolutional blocks. The motivation of the architecture is to combine general visual features provided by the transformer model, as well as finetuned feature extraction properties of the convolutional blocks. To benchmark the approach, an extensive dataset was gathered from national Finnish road infrastructure network of roadside cameras and optical road surface friction sensors. Acquired results highlight that the proposed WCamNet outperforms previous approaches in the task of predicting the road surface friction from the roadside camera images.
Authors: Kaixin Shen, Ruijie Quan, Linchao Zhu, Jun Xiao, Yi Yang
Abstract: Audio-driven visual scene editing endeavors to manipulate the visual background while leaving the foreground content unchanged, according to the given audio signals. Unlike current efforts focusing primarily on image editing, audio-driven video scene editing has not been extensively addressed. In this paper, we introduce AudioScenic, an audio-driven framework designed for video scene editing. AudioScenic integrates audio semantics into the visual scene through a temporal-aware audio semantic injection process. As our focus is on background editing, we further introduce a SceneMasker module, which maintains the integrity of the foreground content during the editing process. AudioScenic exploits the inherent properties of audio, namely, audio magnitude and frequency, to guide the editing process, aiming to control the temporal dynamics and enhance the temporal consistency. First, we present an audio Magnitude Modulator module that adjusts the temporal dynamics of the scene in response to changes in audio magnitude, enhancing the visual dynamics. Second, the audio Frequency Fuser module is designed to ensure temporal consistency by aligning the frequency of the audio with the dynamics of the video scenes, thus improving the overall temporal coherence of the edited videos. These integrated features enable AudioScenic to not only enhance visual diversity but also maintain temporal consistency throughout the video. We present a new metric named temporal score for more comprehensive validation of temporal consistency. We demonstrate substantial advancements of AudioScenic over competing methods on DAVIS and Audioset datasets.
Authors: Jiaying Lin, Jiajun Wen, Mengyuan Liu, Jinfu Liu, Baiqiao Yin, Yue Li
Abstract: The task of spatiotemporal action localization in chaotic scenes is a challenging task toward advanced video understanding. Paving the way with high-quality video feature extraction and enhancing the precision of detector-predicted anchors can effectively improve model performance. To this end, we propose a high-performance dual-stream spatiotemporal feature extraction network SFMViT with an anchor pruning strategy. The backbone of our SFMViT is composed of ViT and SlowFast with prior knowledge of spatiotemporal action localization, which fully utilizes ViT's excellent global feature extraction capabilities and SlowFast's spatiotemporal sequence modeling capabilities. Secondly, we introduce the confidence maximum heap to prune the anchors detected in each frame of the picture to filter out the effective anchors. These designs enable our SFMViT to achieve a mAP of 26.62% in the Chaotic World dataset, far exceeding existing models. Code is available at https://github.com/jfightyr/SlowFast-Meet-ViT.
Authors: Chenxi Liu, Gan Sun, Wenqi Liang, Jiahua Dong, Can Qin, Yang Cong
Abstract: Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting issue make it hard to continually synthesize new user-provided styles while retaining the satisfying results amongst learned styles. In this paper, we propose MuseumMaker, a method that enables the synthesis of images by following a set of customized styles in a never-end manner, and gradually accumulate these creative artistic works as a Museum. When facing with a new customization style, we develop a style distillation loss module to transfer the style of the whole dataset into generation of images. It can minimize the learning biases caused by content of images, and address the catastrophic overfitting issue induced by few-shot images. To deal with catastrophic forgetting amongst past learned styles, we devise a dual regularization for shared-LoRA module to optimize the direction of model update, which could regularize the diffusion model from both weight and feature aspects, respectively. Meanwhile, a unique token embedding corresponding to this new style is learned by a task-wise token learning module, which could preserve historical knowledge from past styles with the limitation of LoRA parameter quantity. As any new user-provided style come, our MuseumMaker can capture the nuances of the new styles while maintaining the details of learned styles. Experimental results on diverse style datasets validate the effectiveness of our proposed MuseumMaker method, showcasing its robustness and versatility across various scenarios.
Authors: Jean-Eric Campagne
Abstract: This paper aims to explore the evolution of image denoising in a pedagological way. We briefly review classical methods such as Fourier analysis and wavelet bases, highlighting the challenges they faced until the emergence of neural networks, notably the U-Net, in the 2010s. The remarkable performance of these networks has been demonstrated in studies such as Kadkhodaie et al. (2024). They exhibit adaptability to various image types, including those with fixed regularity, facial images, and bedroom scenes, achieving optimal results and biased towards geometry-adaptive harmonic basis. The introduction of score diffusion has played a crucial role in image generation. In this context, denoising becomes essential as it facilitates the estimation of probability density scores. We discuss the prerequisites for genuine learning of probability densities, offering insights that extend from mathematical research to the implications of universal structures.
Authors: Jer Pelhan, Alan Luke\v{z}i\v{c}, Vitjan Zavrtanik, Matej Kristan
Abstract: Low-shot counters estimate the number of objects corresponding to a selected category, based on only few or no exemplars annotated in the image. The current state-of-the-art estimates the total counts as the sum over the object location density map, but does not provide individual object locations and sizes, which are crucial for many applications. This is addressed by detection-based counters, which, however fall behind in the total count accuracy. Furthermore, both approaches tend to overestimate the counts in the presence of other object classes due to many false positives. We propose DAVE, a low-shot counter based on a detect-and-verify paradigm, that avoids the aforementioned issues by first generating a high-recall detection set and then verifying the detections to identify and remove the outliers. This jointly increases the recall and precision, leading to accurate counts. DAVE outperforms the top density-based counters by ~20% in the total count MAE, it outperforms the most recent detection-based counter by ~20% in detection quality and sets a new state-of-the-art in zero-shot as well as text-prompt-based counting.
Authors: Leonardo Rossi, Akbar Karimi, Andrea Prati
Abstract: Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances. In this paper, we address the Intersection over the Union (IoU) distribution imbalance of positive input Regions of Interest (RoIs) during the training of the second stage. Our Self-Balanced R-CNN (SBR-CNN), an evolved version of the Hybrid Task Cascade (HTC) model, brings brand new loop mechanisms of bounding box and mask refinements. With an improved Generic RoI Extraction (GRoIE), we also address the feature-level imbalance at the Feature Pyramid Network (FPN) level, originated by a non-uniform integration between low- and high-level features from the backbone layers. In addition, the redesign of the architecture heads toward a fully convolutional approach with FCC further reduces the number of parameters and obtains more clues to the connection between the task to solve and the layers used. Moreover, our SBR-CNN model shows the same or even better improvements if adopted in conjunction with other state-of-the-art models. In fact, with a lightweight ResNet-50 as backbone, evaluated on COCO minival 2017 dataset, our model reaches 45.3% and 41.5% AP for object detection and instance segmentation, with 12 epochs and without extra tricks. The code is available at https://github.com/IMPLabUniPr/mmdetection/tree/sbr_cnn
URLs: https://github.com/IMPLabUniPr/mmdetection/tree/sbr_cnn
Authors: Liang Zhang, Anwen Hu, Haiyang Xu, Ming Yan, Yichen Xu, Qin Jin, Ji Zhang, Fei Huang
Abstract: Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various chart understanding tasks. However, the sheer size of these models in terms of parameters and computational requirements limits their use in resource-constrained environments. In this paper, we present TinyChart, an efficient MLLM for chart understanding with only 3B parameters. TinyChart overcomes two key challenges in efficient chart understanding: (1) reduce the burden of learning numerical computations through a Program-of-Thoughts (PoT) learning strategy, which trains the model to generate Python programs for numerical calculations, and (2) reduce lengthy vision feature sequences produced by the vision transformer for high-resolution images through a Vision Token Merging module, which gradually merges most similar vision tokens. Extensive experiments demonstrate that our 3B TinyChart achieves SOTA performance on a variety of chart understanding benchmarks including ChartQA, Chart-to-Text, Chart-to-Table, OpenCQA, and ChartX. It outperforms several chart understanding MLLM with up to 13B parameters such as ChartLlama and ChartAst, and close-sourced general-purpose MLLM GPT-4V on ChartQA. It also demonstrates its superior efficiency with higher throughput during inference due to a smaller model scale and more efficient vision encoding. Our code and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/TinyChart.
URLs: https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/TinyChart.
Authors: Niclas Popp, Jan Hendrik Metzen, Matthias Hein
Abstract: Multi-modal foundation models such as CLIP have showcased impressive zero-shot capabilities. However, their applicability in resource-constrained environments is limited due to their large number of parameters and high inference time. While existing approaches have scaled down the entire CLIP architecture, we focus on training smaller variants of the image encoder, which suffices for efficient zero-shot classification. The use of synthetic data has shown promise in distilling representations from larger teachers, resulting in strong few-shot and linear probe performance. However, we find that this approach surprisingly fails in true zero-shot settings when using contrastive losses. We identify the exploitation of spurious features as being responsible for poor generalization between synthetic and real data. However, by using the image feature-based L2 distillation loss, we mitigate these problems and train students that achieve zero-shot performance which on four domain-specific datasets is on-par with a ViT-B/32 teacher model trained on DataCompXL, while featuring up to 92% fewer parameters.
Authors: Junfeng Ni, Yixin Chen, Bohan Jing, Nan Jiang, Bin Wang, Bo Dai, Yixin Zhu, Song-Chun Zhu, Siyuan Huang
Abstract: While neural implicit representations have gained popularity in multi-view 3D reconstruction, previous work struggles to yield physically plausible results, thereby limiting their applications in physics-demanding domains like embodied AI and robotics. The lack of plausibility originates from both the absence of physics modeling in the existing pipeline and their inability to recover intricate geometrical structures. In this paper, we introduce PhyRecon, which stands as the first approach to harness both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Our framework proposes a novel differentiable particle-based physical simulator seamlessly integrated with the neural implicit representation. At its core is an efficient transformation between SDF-based implicit representation and explicit surface points by our proposed algorithm, Surface Points Marching Cubes (SP-MC), enabling differentiable learning with both rendering and physical losses. Moreover, we model both rendering and physical uncertainty to identify and compensate for the inconsistent and inaccurate monocular geometric priors. The physical uncertainty additionally enables a physics-guided pixel sampling to enhance the learning of slender structures. By amalgamating these techniques, our model facilitates efficient joint modeling with appearance, geometry, and physics. Extensive experiments demonstrate that PhyRecon significantly outperforms all state-of-the-art methods in terms of reconstruction quality. Our reconstruction results also yield superior physical stability, verified by Isaac Gym, with at least a 40% improvement across all datasets, opening broader avenues for future physics-based applications.
Authors: Hongxia Xie, Chu-Jun Peng, Yu-Wen Tseng, Hung-Jen Chen, Chan-Feng Hsu, Hong-Han Shuai, Wen-Huang Cheng
Abstract: Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but is still unexplored in vision emotion understanding. In this work, we focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. Initially, we identify key visual clues critical to visual emotion recognition. Subsequently, we introduce a novel GPT-assisted pipeline for generating emotion visual instruction data, effectively addressing the scarcity of annotated instruction data in this domain. Expanding on the groundwork established by InstructBLIP, our proposed EmoVIT architecture incorporates emotion-specific instruction data, leveraging the powerful capabilities of Large Language Models to enhance performance. Through extensive experiments, our model showcases its proficiency in emotion classification, adeptness in affective reasoning, and competence in comprehending humor. The comparative analysis provides a robust benchmark for Emotion Visual Instruction Tuning in the era of LLMs, providing valuable insights and opening avenues for future exploration in this domain. Our code is available at \url{https://github.com/aimmemotion/EmoVIT}.
Authors: Han Wang, Xinning Chai, Yiwen Wang, Yuhong Zhang, Rong Xie, Li Song
Abstract: Colorizing grayscale images offers an engaging visual experience. Existing automatic colorization methods often fail to generate satisfactory results due to incorrect semantic colors and unsaturated colors. In this work, we propose an automatic colorization pipeline to overcome these challenges. We leverage the extraordinary generative ability of the diffusion prior to synthesize color with plausible semantics. To overcome the artifacts introduced by the diffusion prior, we apply the luminance conditional guidance. Moreover, we adopt multimodal high-level semantic priors to help the model understand the image content and deliver saturated colors. Besides, a luminance-aware decoder is designed to restore details and enhance overall visual quality. The proposed pipeline synthesizes saturated colors while maintaining plausible semantics. Experiments indicate that our proposed method considers both diversity and fidelity, surpassing previous methods in terms of perceptual realism and gain most human preference.
Authors: Huiyu Zhai, Mo Chen, Xingxing Yang, Gusheng Kang
Abstract: The NIR-to-RGB spectral domain translation is a formidable task due to the inherent spectral mapping ambiguities within NIR inputs and RGB outputs. Thus, existing methods fail to reconcile the tension between maintaining texture detail fidelity and achieving diverse color variations. In this paper, we propose a Multi-scale HSV Color Feature Embedding Network (MCFNet) that decomposes the mapping process into three sub-tasks, including NIR texture maintenance, coarse geometry reconstruction, and RGB color prediction. Thus, we propose three key modules for each corresponding sub-task: the Texture Preserving Block (TPB), the HSV Color Feature Embedding Module (HSV-CFEM), and the Geometry Reconstruction Module (GRM). These modules contribute to our MCFNet methodically tackling spectral translation through a series of escalating resolutions, progressively enriching images with color and texture fidelity in a scale-coherent fashion. The proposed MCFNet demonstrates substantial performance gains over the NIR image colorization task. Code is released at: https://github.com/AlexYangxx/MCFNet.
Authors: Xiaohong Liu, Xiongkuo Min, Guangtao Zhai, Chunyi Li, Tengchuan Kou, Wei Sun, Haoning Wu, Yixuan Gao, Yuqin Cao, Zicheng Zhang, Xiele Wu, Radu Timofte
Abstract: This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.
Authors: Mazda Moayeri, Michael Rabbat, Mark Ibrahim, Diane Bouchacourt
Abstract: Vision-language models enable open-world classification of objects without the need for any retraining. While this zero-shot paradigm marks a significant advance, even today's best models exhibit skewed performance when objects are dissimilar from their typical depiction. Real world objects such as pears appear in a variety of forms -- from diced to whole, on a table or in a bowl -- yet standard VLM classifiers map all instances of a class to a \it{single vector based on the class label}. We argue that to represent this rich diversity within a class, zero-shot classification should move beyond a single vector. We propose a method to encode and account for diversity within a class using inferred attributes, still in the zero-shot setting without retraining. We find our method consistently outperforms standard zero-shot classification over a large suite of datasets encompassing hierarchies, diverse object states, and real-world geographic diversity, as well finer-grained datasets where intra-class diversity may be less prevalent. Importantly, our method is inherently interpretable, offering faithful explanations for each inference to facilitate model debugging and enhance transparency. We also find our method scales efficiently to a large number of attributes to account for diversity -- leading to more accurate predictions for atypical instances. Finally, we characterize a principled trade-off between overall and worst class accuracy, which can be tuned via a hyperparameter of our method. We hope this work spurs further research into the promise of zero-shot classification beyond a single class vector for capturing diversity in the world, and building transparent AI systems without compromising performance.
Authors: Nitin Kumar, Manisha
Abstract: Cancelable Biometric is a challenging research field in which security of an original biometric image is ensured by transforming the original biometric into another irreversible domain. Several approaches have been suggested in literature for generating cancelable biometric templates. In this paper, two novel and simple cancelable biometric template generation methods based on Random Walk (CBRW) have been proposed. By employing random walk and other steps given in the proposed two algorithms viz. CBRW-BitXOR and CBRW-BitCMP, the original biometric is transformed into a cancellable template. The performance of the proposed methods is compared with other state-of-the-art methods. Experiments have been performed on eight publicly available gray and color datasets i.e. CP (ear) (gray and color), UTIRIS (iris) (gray and color), ORL (face) (gray), IIT Delhi (iris) (gray and color), and AR (face) (color). Performance of the generated templates is measured in terms of Correlation Coefficient (Cr), Root Mean Square Error (RMSE), Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), Mean Absolute Error (MAE), Number of Pixel Change Rate (NPCR), and Unified Average Changing Intensity (UACI). By experimental results, it has been proved that proposed methods are superior than other state-of-the-art methods in qualitative as well as quantitative analysis. Furthermore, CBRW performs better on both gray as well as color images.
Authors: Junting Dong, Qi Fang, Zehuan Huang, Xudong Xu, Jingbo Wang, Sida Peng, Bo Dai
Abstract: This paper addresses the task of 3D clothed human generation from textural descriptions. Previous works usually encode the human body and clothes as a holistic model and generate the whole model in a single-stage optimization, which makes them struggle for clothing editing and meanwhile lose fine-grained control over the whole generation process. To solve this, we propose a layer-wise clothed human representation combined with a progressive optimization strategy, which produces clothing-disentangled 3D human models while providing control capacity for the generation process. The basic idea is progressively generating a minimal-clothed human body and layer-wise clothes. During clothing generation, a novel stratified compositional rendering method is proposed to fuse multi-layer human models, and a new loss function is utilized to help decouple the clothing model from the human body. The proposed method achieves high-quality disentanglement, which thereby provides an effective way for 3D garment generation. Extensive experiments demonstrate that our approach achieves state-of-the-art 3D clothed human generation while also supporting cloth editing applications such as virtual try-on. Project page: http://jtdong.com/tela_layer/
Authors: Sai Kumar Dwivedi, Yu Sun, Priyanka Patel, Yao Feng, Michael J. Black
Abstract: We address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy. The current best methods leverage large datasets of 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust performance. With such methods, we observe a paradoxical decline in 3D pose accuracy with increasing 2D accuracy. This is caused by biases in the p-GT and the use of an approximate camera projection model. We quantify the error induced by current camera models and show that fitting 2D keypoints and p-GT accurately causes incorrect 3D poses. Our analysis defines the invalid distances within which minimizing 2D and p-GT losses is detrimental. We use this to formulate a new loss Threshold-Adaptive Loss Scaling (TALS) that penalizes gross 2D and p-GT losses but not smaller ones. With such a loss, there are many 3D poses that could equally explain the 2D evidence. To reduce this ambiguity we need a prior over valid human poses but such priors can introduce unwanted bias. To address this, we exploit a tokenized representation of human pose and reformulate the problem as token prediction. This restricts the estimated poses to the space of valid poses, effectively providing a uniform prior. Extensive experiments on the EMDB and 3DPW datasets show that our reformulated keypoint loss and tokenization allows us to train on in-the-wild data while improving 3D accuracy over the state-of-the-art. Our models and code are available for research at https://tokenhmr.is.tue.mpg.de.
Authors: Xiaoman Zhang, Chaoyi Wu, Ziheng Zhao, Jiayu Lei, Ya Zhang, Yanfeng Wang, Weidi Xie
Abstract: Developing generalist foundation model has recently attracted tremendous attention among researchers in the field of AI for Medicine (AI4Medicine). A pivotal insight in developing these models is their reliance on dataset scaling, which emphasizes the requirements on developing open-source medical image datasets that incorporate diverse supervision signals across various imaging modalities. In this paper, we introduce RadGenome-Chest CT, a comprehensive, large-scale, region-guided 3D chest CT interpretation dataset based on CT-RATE. Specifically, we leverage the latest powerful universal segmentation and large language models, to extend the original datasets (over 25,692 non-contrast 3D chest CT volume and reports from 20,000 patients) from the following aspects: (i) organ-level segmentation masks covering 197 categories, which provide intermediate reasoning visual clues for interpretation; (ii) 665 K multi-granularity grounded reports, where each sentence of the report is linked to the corresponding anatomical region of CT volume in the form of a segmentation mask; (iii) 1.3 M grounded VQA pairs, where questions and answers are all linked with reference segmentation masks, enabling models to associate visual evidence with textual explanations. All grounded reports and VQA pairs in the validation set have gone through manual verification to ensure dataset quality. We believe that RadGenome-Chest CT can significantly advance the development of multimodal medical foundation models, by training to generate texts based on given segmentation regions, which is unattainable with previous relevant datasets. We will release all segmentation masks, grounded reports, and VQA pairs to facilitate further research and development in this field.
Authors: Jiehui Huang, Xiao Dong, Wenhui Song, Hanhui Li, Jun Zhou, Yuhao Cheng, Shutao Liao, Long Chen, Yiqiang Yan, Shengcai Liao, Xiaodan Liang
Abstract: Diffusion-based technologies have made significant strides, particularly in personalized and customized facialgeneration. However, existing methods face challenges in achieving high-fidelity and detailed identity (ID)consistency, primarily due to insufficient fine-grained control over facial areas and the lack of a comprehensive strategy for ID preservation by fully considering intricate facial details and the overall face. To address these limitations, we introduce ConsistentID, an innovative method crafted for diverseidentity-preserving portrait generation under fine-grained multimodal facial prompts, utilizing only a single reference image. ConsistentID comprises two key components: a multimodal facial prompt generator that combines facial features, corresponding facial descriptions and the overall facial context to enhance precision in facial details, and an ID-preservation network optimized through the facial attention localization strategy, aimed at preserving ID consistency in facial regions. Together, these components significantly enhance the accuracy of ID preservation by introducing fine-grained multimodal ID information from facial regions. To facilitate training of ConsistentID, we present a fine-grained portrait dataset, FGID, with over 500,000 facial images, offering greater diversity and comprehensiveness than existing public facial datasets. % such as LAION-Face, CelebA, FFHQ, and SFHQ. Experimental results substantiate that our ConsistentID achieves exceptional precision and diversity in personalized facial generation, surpassing existing methods in the MyStyle dataset. Furthermore, while ConsistentID introduces more multimodal ID information, it maintains a fast inference speed during generation.
Authors: David Rivas-Villar, \'Alvaro S. Hervella, Jos\'e Rouco, Jorge Novo
Abstract: Self-supervised contrastive learning has emerged as one of the most successful deep learning paradigms. In this regard, it has seen extensive use in image registration and, more recently, in the particular field of medical image registration. In this work, we propose to test and extend and improve a state-of-the-art framework for color fundus image registration, ConKeD. Using the ConKeD framework we test multiple loss functions, adapting them to the framework and the application domain. Furthermore, we evaluate our models using the standarized benchmark dataset FIRE as well as several datasets that have never been used before for color fundus registration, for which we are releasing the pairing data as well as a standardized evaluation approach. Our work demonstrates state-of-the-art performance across all datasets and metrics demonstrating several advantages over current SOTA color fundus registration methods
Authors: Karthik Gopinath, Xiaoling Hu, Malte Hoffmann, Oula Puonti, Juan Eugenio Iglesias
Abstract: In human neuroimaging studies, atlas registration enables mapping MRI scans to a common coordinate frame, which is necessary to aggregate data from multiple subjects. Machine learning registration methods have achieved excellent speed and accuracy but lack interpretability. More recently, keypoint-based methods have been proposed to tackle this issue, but their accuracy is still subpar, particularly when fitting nonlinear transforms. Here we propose Registration by Regression (RbR), a novel atlas registration framework that is highly robust and flexible, conceptually simple, and can be trained with cheaply obtained data. RbR predicts the (x,y,z) atlas coordinates for every voxel of the input scan (i.e., every voxel is a keypoint), and then uses closed-form expressions to quickly fit transforms using a wide array of possible deformation models, including affine and nonlinear (e.g., Bspline, Demons, invertible diffeomorphic models, etc.). Robustness is provided by the large number of voxels informing the registration and can be further increased by robust estimators like RANSAC. Experiments on independent public datasets show that RbR yields more accurate registration than competing keypoint approaches, while providing full control of the deformation model.
Authors: Bohao Li, Yuying Ge, Yi Chen, Yixiao Ge, Ruimao Zhang, Ying Shan
Abstract: Comprehending text-rich visual content is paramount for the practical application of Multimodal Large Language Models (MLLMs), since text-rich scenarios are ubiquitous in the real world, which are characterized by the presence of extensive texts embedded within images. Recently, the advent of MLLMs with impressive versatility has raised the bar for what we can expect from MLLMs. However, their proficiency in text-rich scenarios has yet to be comprehensively and objectively assessed, since current MLLM benchmarks primarily focus on evaluating general visual comprehension. In this work, we introduce SEED-Bench-2-Plus, a benchmark specifically designed for evaluating \textbf{text-rich visual comprehension} of MLLMs. Our benchmark comprises 2.3K multiple-choice questions with precise human annotations, spanning three broad categories: Charts, Maps, and Webs, each of which covers a wide spectrum of text-rich scenarios in the real world. These categories, due to their inherent complexity and diversity, effectively simulate real-world text-rich environments. We further conduct a thorough evaluation involving 34 prominent MLLMs (including GPT-4V, Gemini-Pro-Vision and Claude-3-Opus) and emphasize the current limitations of MLLMs in text-rich visual comprehension. We hope that our work can serve as a valuable addition to existing MLLM benchmarks, providing insightful observations and inspiring further research in the area of text-rich visual comprehension with MLLMs. The dataset and evaluation code can be accessed at https://github.com/AILab-CVC/SEED-Bench.
Authors: Gahyeon Kim, Sohee Kim, Seokju Lee
Abstract: Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where context within a prompt is replaced with learnable vectors, leading to significant improvements over manually crafted prompts. However, the performance improvement for unseen classes is still marginal, and to tackle this problem, data augmentation has been frequently used in traditional zero-shot learning techniques. Through our experiments, we have identified important issues in CoOp and CoCoOp: the context learned through traditional image augmentation is biased toward seen classes, negatively impacting generalization to unseen classes. To address this problem, we propose adversarial token embedding to disentangle low-level visual augmentation features from high-level class information when inducing bias in learnable prompts. Through our novel mechanism called "Adding Attributes to Prompt Learning", AAPL, we guide the learnable context to effectively extract text features by focusing on high-level features for unseen classes. We have conducted experiments across 11 datasets, and overall, AAPL shows favorable performances compared to the existing methods in few-shot learning, zero-shot learning, cross-dataset, and domain generalization tasks.
Authors: Zeynep \"Ozdemir, Hacer Yalim Keles, \"Omer \"Ozg\"ur Tanr{\i}\"over
Abstract: Addressing the challenges of rare diseases is difficult, especially with the limited number of reference images and a small patient population. This is more evident in rare skin diseases, where we encounter long-tailed data distributions that make it difficult to develop unbiased and broadly effective models. The diverse ways in which image datasets are gathered and their distinct purposes also add to these challenges. Our study conducts a detailed examination of the benefits and drawbacks of episodic and conventional training methodologies, adopting a few-shot learning approach alongside transfer learning. We evaluated our models using the ISIC2018, Derm7pt, and SD-198 datasets. With minimal labeled examples, our models showed substantial information gains and better performance compared to previously trained models. Our research emphasizes the improved ability to represent features in DenseNet121 and MobileNetV2 models, achieved by using pre-trained models on ImageNet to increase similarities within classes. Moreover, our experiments, ranging from 2-way to 5-way classifications with up to 10 examples, showed a growing success rate for traditional transfer learning methods as the number of examples increased. The addition of data augmentation techniques significantly improved our transfer learning based model performance, leading to higher performances than existing methods, especially in the SD-198 and ISIC2018 datasets. All source code related to this work will be made publicly available soon at the provided URL.
Authors: Oliver Hahn, Nikita Araslanov, Simone Schaub-Meyer, Stefan Roth
Abstract: Unsupervised semantic segmentation aims to automatically partition images into semantically meaningful regions by identifying global categories within an image corpus without any form of annotation. Building upon recent advances in self-supervised representation learning, we focus on how to leverage these large pre-trained models for the downstream task of unsupervised segmentation. We present PriMaPs - Principal Mask Proposals - decomposing images into semantically meaningful masks based on their feature representation. This allows us to realize unsupervised semantic segmentation by fitting class prototypes to PriMaPs with a stochastic expectation-maximization algorithm, PriMaPs-EM. Despite its conceptual simplicity, PriMaPs-EM leads to competitive results across various pre-trained backbone models, including DINO and DINOv2, and across datasets, such as Cityscapes, COCO-Stuff, and Potsdam-3. Importantly, PriMaPs-EM is able to boost results when applied orthogonally to current state-of-the-art unsupervised semantic segmentation pipelines.
Authors: Olivia Wiles, Chuhan Zhang, Isabela Albuquerque, Ivana Kaji\'c, Su Wang, Emanuele Bugliarello, Yasumasa Onoe, Chris Knutsen, Cyrus Rashtchian, Jordi Pont-Tuset, Aida Nematzadeh
Abstract: While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for collecting human judgements, the quality of these components is not systematically measured. Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated. We address this gap by performing an extensive study evaluating auto-eval metrics and human templates. We provide three main contributions: (1) We introduce a comprehensive skills-based benchmark that can discriminate models across different human templates. This skills-based benchmark categorises prompts into sub-skills, allowing a practitioner to pinpoint not only which skills are challenging, but at what level of complexity a skill becomes challenging. (2) We gather human ratings across four templates and four T2I models for a total of >100K annotations. This allows us to understand where differences arise due to inherent ambiguity in the prompt and where they arise due to differences in metric and model quality. (3) Finally, we introduce a new QA-based auto-eval metric that is better correlated with human ratings than existing metrics for our new dataset, across different human templates, and on TIFA160.
Authors: Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, Ji Ma, Jiaqi Wang, Xiaoyi Dong, Hang Yan, Hewei Guo, Conghui He, Zhenjiang Jin, Chao Xu, Bin Wang, Xingjian Wei, Wei Li, Wenjian Zhang, Lewei Lu, Xizhou Zhu, Tong Lu, Dahua Lin, Yu Qiao
Abstract: In this report, we introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple improvements: (1) Strong Vision Encoder: we explored a continuous learning strategy for the large-scale vision foundation model -- InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs. (2) Dynamic High-Resolution: we divide images into tiles ranging from 1 to 40 of 448$\times$448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input. (3) High-Quality Bilingual Dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images, and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in OCR- and Chinese-related tasks. We evaluate InternVL 1.5 through a series of benchmarks and comparative studies. Compared to both open-source and proprietary models, InternVL 1.5 shows competitive performance, achieving state-of-the-art results in 8 of 18 benchmarks. Code has been released at https://github.com/OpenGVLab/InternVL.
Authors: Xuanyu Zhang, Youmin Xu, Runyi Li, Jiwen Yu, Weiqi Li, Zhipei Xu, Jian Zhang
Abstract: AI-generated video has revolutionized short video production, filmmaking, and personalized media, making video local editing an essential tool. However, this progress also blurs the line between reality and fiction, posing challenges in multimedia forensics. To solve this urgent issue, V2A-Mark is proposed to address the limitations of current video tampering forensics, such as poor generalizability, singular function, and single modality focus. Combining the fragility of video-into-video steganography with deep robust watermarking, our method can embed invisible visual-audio localization watermarks and copyright watermarks into the original video frames and audio, enabling precise manipulation localization and copyright protection. We also design a temporal alignment and fusion module and degradation prompt learning to enhance the localization accuracy and decoding robustness. Meanwhile, we introduce a sample-level audio localization method and a cross-modal copyright extraction mechanism to couple the information of audio and video frames. The effectiveness of V2A-Mark has been verified on a visual-audio tampering dataset, emphasizing its superiority in localization precision and copyright accuracy, crucial for the sustainable development of video editing in the AIGC video era.
Authors: Weiqi Li, Shijie Zhao, Bin Chen, Xinhua Cheng, Junlin Li, Li Zhang, Jian Zhang
Abstract: With the advent of virtual reality technology, omnidirectional image (ODI) rescaling techniques are increasingly embraced for reducing transmitted and stored file sizes while preserving high image quality. Despite this progress, current ODI rescaling methods predominantly focus on enhancing the quality of images in equirectangular projection (ERP) format, which overlooks the fact that the content viewed on head mounted displays (HMDs) is actually a rendered viewport instead of an ERP image. In this work, we emphasize that focusing solely on ERP quality results in inferior viewport visual experiences for users. Thus, we propose ResVR, which is the first comprehensive framework for the joint Rescaling and Viewport Rendering of ODIs. ResVR allows obtaining LR ERP images for transmission while rendering high-quality viewports for users to watch on HMDs. In our ResVR, a novel discrete pixel sampling strategy is developed to tackle the complex mapping between the viewport and ERP, enabling end-to-end training of ResVR pipeline. Furthermore, a spherical pixel shape representation technique is innovatively derived from spherical differentiation to significantly improve the visual quality of rendered viewports. Extensive experiments demonstrate that our ResVR outperforms existing methods in viewport rendering tasks across different fields of view, resolutions, and view directions while keeping a low transmission overhead.
Authors: Charig Yang, Weidi Xie, Andrew Zisserman
Abstract: Our objective is to discover and localize monotonic temporal changes in a sequence of images. To achieve this, we exploit a simple proxy task of ordering a shuffled image sequence, with `time' serving as a supervisory signal since only changes that are monotonic with time can give rise to the correct ordering. We also introduce a flexible transformer-based model for general-purpose ordering of image sequences of arbitrary length with built-in attribution maps. After training, the model successfully discovers and localizes monotonic changes while ignoring cyclic and stochastic ones. We demonstrate applications of the model in multiple video settings covering different scene and object types, discovering both object-level and environmental changes in unseen sequences. We also demonstrate that the attention-based attribution maps function as effective prompts for segmenting the changing regions, and that the learned representations can be used for downstream applications. Finally, we show that the model achieves the state of the art on standard benchmarks for ordering a set of images.
Authors: Ye Fang, Zeyi Sun, Tong Wu, Jiaqi Wang, Ziwei Liu, Gordon Wetzstein, Dahua Lin
Abstract: Physically realistic materials are pivotal in augmenting the realism of 3D assets across various applications and lighting conditions. However, existing 3D assets and generative models often lack authentic material properties. Manual assignment of materials using graphic software is a tedious and time-consuming task. In this paper, we exploit advancements in Multimodal Large Language Models (MLLMs), particularly GPT-4V, to present a novel approach, Make-it-Real: 1) We demonstrate that GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material library. 2) Utilizing a combination of visual cues and hierarchical text prompts, GPT-4V precisely identifies and aligns materials with the corresponding components of 3D objects. 3) The correctly matched materials are then meticulously applied as reference for the new SVBRDF material generation according to the original diffuse map, significantly enhancing their visual authenticity. Make-it-Real offers a streamlined integration into the 3D content creation workflow, showcasing its utility as an essential tool for developers of 3D assets.
Authors: Jaime Spencer, Fabio Tosi, Matteo Poggi, Ripudaman Singh Arora, Chris Russell, Simon Hadfield, Richard Bowden, GuangYuan Zhou, ZhengXin Li, Qiang Rao, YiPing Bao, Xiao Liu, Dohyeong Kim, Jinseong Kim, Myunghyun Kim, Mykola Lavreniuk, Rui Li, Qing Mao, Jiang Wu, Yu Zhu, Jinqiu Sun, Yanning Zhang, Suraj Patni, Aradhye Agarwal, Chetan Arora, Pihai Sun, Kui Jiang, Gang Wu, Jian Liu, Xianming Liu, Junjun Jiang, Xidan Zhang, Jianing Wei, Fangjun Wang, Zhiming Tan, Jiabao Wang, Albert Luginov, Muhammad Shahzad, Seyed Hosseini, Aleksander Trajcevski, James H. Elder
Abstract: This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.
Authors: Dominek Winecki (Dept. of Computer Science and Engineeering, The Ohio State University), Christopher S. Kochanek (Dept. of Astronomy, The Ohio State University)
Abstract: We develop a deep neural network (DNN) to obtain photometry of saturated stars in the All-Sky Automated Survey for Supernovae (ASAS-SN). The DNN can obtain unbiased photometry for stars from g=4 to 14 mag with a dispersion (15%-85% 1sigma range around median) of 0.12 mag for saturated (g<11.5 mag) stars. More importantly, the light curve of a non-variable saturated star has a median dispersion of only 0.037 mag. The DNN light curves are, in many cases, spectacularly better than provided by the standard ASAS-SN pipelines. While the network was trained on g band data from only one of ASAS-SN's 20 cameras, initial experiments suggest that it can be used for any camera and the older ASAS-SN V band data as well. The dominant problems seem to be associated with correctable issues in the ASAS-SN data reduction pipeline for saturated stars more than the DNN itself. The method is publicly available as a light curve option on ASAS-SN Sky Patrol v1.0.
Authors: Felipe M. Dias, Diego A. C. Cardenas, Marcelo A. F. Toledo, Filipe A. C. Oliveira, Estela Ribeiro, Jose E. Krieger, Marco A. Gutierrez
Abstract: Hypertension, a leading contributor to cardiovascular morbidity, underscores the need for accurate and continuous blood pressure (BP) monitoring. Photoplethysmography (PPG) presents a promising approach to this end. However, the precision of BP estimates derived from PPG signals has been the subject of ongoing debate, necessitating a comprehensive evaluation of their effectiveness and constraints. We developed a calibration-based Siamese ResNet model for BP estimation, using a signal input paired with a reference BP reading. We compared the use of normalized PPG (N-PPG) against the normalized Invasive Arterial Blood Pressure (N-IABP) signals as input. The N-IABP signals do not directly present systolic and diastolic values but theoretically provide a more accurate BP measure than PPG signals since it is a direct pressure sensor inside the body. Our strategy establishes a critical benchmark for PPG performance, realistically calibrating expectations for PPG's BP estimation capabilities. Nonetheless, we compared the performance of our models using different signal-filtering conditions to evaluate the impact of filtering on the results. We evaluated our method using the AAMI and the BHS standards employing the VitalDB dataset. The N-IABP signals meet with AAMI standards for both Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP), with errors of 1.29+-6.33mmHg for systolic pressure and 1.17+-5.78mmHg for systolic and diastolic pressure respectively for the raw N-IABP signal. In contrast, N-PPG signals, in their best setup, exhibited inferior performance than N-IABP, presenting 1.49+-11.82mmHg and 0.89+-7.27mmHg for systolic and diastolic pressure respectively. Our findings highlight the potential and limitations of employing PPG for BP estimation, showing that these signals contain information correlated to BP but may not be sufficient for predicting it accurately.
Authors: Hong-Jun Yoon, Chris Keum, Alexander Witkowski, Joanna Ludzik, Tracy Petrie, Heidi A. Hanson, Sancy A. Leachman
Abstract: Reflectance Confocal Microscopy (RCM) is a non-invasive imaging technique used in biomedical research and clinical dermatology. It provides virtual high-resolution images of the skin and superficial tissues, reducing the need for physical biopsies. RCM employs a laser light source to illuminate the tissue, capturing the reflected light to generate detailed images of microscopic structures at various depths. Recent studies explored AI and machine learning, particularly CNNs, for analyzing RCM images. Our study proposes a segmentation strategy based on textural features to identify clinically significant regions, empowering dermatologists in effective image interpretation and boosting diagnostic confidence. This approach promises to advance dermatological diagnosis and treatment.
Authors: Badri Narayana Patro, Vijay Srinivas Agneeswaran
Abstract: Sequence modeling is a crucial area across various domains, including Natural Language Processing (NLP), speech recognition, time series forecasting, music generation, and bioinformatics. Recurrent Neural Networks (RNNs) and Long Short Term Memory Networks (LSTMs) have historically dominated sequence modeling tasks like Machine Translation, Named Entity Recognition (NER), etc. However, the advancement of transformers has led to a shift in this paradigm, given their superior performance. Yet, transformers suffer from $O(N^2)$ attention complexity and challenges in handling inductive bias. Several variations have been proposed to address these issues which use spectral networks or convolutions and have performed well on a range of tasks. However, they still have difficulty in dealing with long sequences. State Space Models(SSMs) have emerged as promising alternatives for sequence modeling paradigms in this context, especially with the advent of S4 and its variants, such as S4nd, Hippo, Hyena, Diagnol State Spaces (DSS), Gated State Spaces (GSS), Linear Recurrent Unit (LRU), Liquid-S4, Mamba, etc. In this survey, we categorize the foundational SSMs based on three paradigms namely, Gating architectures, Structural architectures, and Recurrent architectures. This survey also highlights diverse applications of SSMs across domains such as vision, video, audio, speech, language (especially long sequence modeling), medical (including genomics), chemical (like drug design), recommendation systems, and time series analysis, including tabular data. Moreover, we consolidate the performance of SSMs on benchmark datasets like Long Range Arena (LRA), WikiText, Glue, Pile, ImageNet, Kinetics-400, sstv2, as well as video datasets such as Breakfast, COIN, LVU, and various time series datasets. The project page for Mamba-360 work is available on this webpage.\url{https://github.com/badripatro/mamba360}.
Authors: Grace Guo, Lifu Deng, Animesh Tandon, Alex Endert, Bum Chul Kwon
Abstract: The recent prevalence of publicly accessible, large medical imaging datasets has led to a proliferation of artificial intelligence (AI) models for cardiovascular image classification and analysis. At the same time, the potentially significant impacts of these models have motivated the development of a range of explainable AI (XAI) methods that aim to explain model predictions given certain image inputs. However, many of these methods are not developed or evaluated with domain experts, and explanations are not contextualized in terms of medical expertise or domain knowledge. In this paper, we propose a novel framework and python library, MiMICRI, that provides domain-centered counterfactual explanations of cardiovascular image classification models. MiMICRI helps users interactively select and replace segments of medical images that correspond to morphological structures. From the counterfactuals generated, users can then assess the influence of each segment on model predictions, and validate the model against known medical facts. We evaluate this library with two medical experts. Our evaluation demonstrates that a domain-centered XAI approach can enhance the interpretability of model explanations, and help experts reason about models in terms of relevant domain knowledge. However, concerns were also surfaced about the clinical plausibility of the counterfactuals generated. We conclude with a discussion on the generalizability and trustworthiness of the MiMICRI framework, as well as the implications of our findings on the development of domain-centered XAI methods for model interpretability in healthcare contexts.
Authors: Cuong Nhat Ha, Shima Asaadi, Sanjeev Kumar Karn, Oladimeji Farri, Tobias Heimann, Thomas Runkler
Abstract: Vision-language models, while effective in general domains and showing strong performance in diverse multi-modal applications like visual question-answering (VQA), struggle to maintain the same level of effectiveness in more specialized domains, e.g., medical. We propose a medical vision-language model that integrates large vision and language models adapted for the medical domain. This model goes through three stages of parameter-efficient training using three separate biomedical and radiology multi-modal visual and text datasets. The proposed model achieves state-of-the-art performance on the SLAKE 1.0 medical VQA (MedVQA) dataset with an overall accuracy of 87.5% and demonstrates strong performance on another MedVQA dataset, VQA-RAD, achieving an overall accuracy of 73.2%.
Authors: Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala, Bimal Viswanath
Abstract: Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly available deepfake datasets. In this work, we study 8 state-of-the-art detectors and argue that they are far from being ready for deployment due to two recent developments. First, the emergence of lightweight methods to customize large generative models, can enable an attacker to create many customized generators (to create deepfakes), thereby substantially increasing the threat surface. We show that existing defenses fail to generalize well to such \emph{user-customized generative models} that are publicly available today. We discuss new machine learning approaches based on content-agnostic features, and ensemble modeling to improve generalization performance against user-customized models. Second, the emergence of \textit{vision foundation models} -- machine learning models trained on broad data that can be easily adapted to several downstream tasks -- can be misused by attackers to craft adversarial deepfakes that can evade existing defenses. We propose a simple adversarial attack that leverages existing foundation models to craft adversarial samples \textit{without adding any adversarial noise}, through careful semantic manipulation of the image content. We highlight the vulnerabilities of several defenses against our attack, and explore directions leveraging advanced foundation models and adversarial training to defend against this new threat.
Authors: Bharat Yalavarthi, Arjun Ramesh Kaushik, Arun Ross, Vishnu Boddeti, Nalini Ratha
Abstract: Modern face recognition systems utilize deep neural networks to extract salient features from a face. These features denote embeddings in latent space and are often stored as templates in a face recognition system. These embeddings are susceptible to data leakage and, in some cases, can even be used to reconstruct the original face image. To prevent compromising identities, template protection schemes are commonly employed. However, these schemes may still not prevent the leakage of soft biometric information such as age, gender and race. To alleviate this issue, we propose a novel technique that combines Fully Homomorphic Encryption (FHE) with an existing template protection scheme known as PolyProtect. We show that the embeddings can be compressed and encrypted using FHE and transformed into a secure PolyProtect template using polynomial transformation, for additional protection. We demonstrate the efficacy of the proposed approach through extensive experiments on multiple datasets. Our proposed approach ensures irreversibility and unlinkability, effectively preventing the leakage of soft biometric attributes from face embeddings without compromising recognition accuracy.
Authors: Arman Maesumi, Dylan Hu, Krishi Saripalli, Vladimir G. Kim, Matthew Fisher, S\"oren Pirk, Daniel Ritchie
Abstract: Procedural noise is a fundamental component of computer graphics pipelines, offering a flexible way to generate textures that exhibit "natural" random variation. Many different types of noise exist, each produced by a separate algorithm. In this paper, we present a single generative model which can learn to generate multiple types of noise as well as blend between them. In addition, it is capable of producing spatially-varying noise blends despite not having access to such data for training. These features are enabled by training a denoising diffusion model using a novel combination of data augmentation and network conditioning techniques. Like procedural noise generators, the model's behavior is controllable via interpretable parameters and a source of randomness. We use our model to produce a variety of visually compelling noise textures. We also present an application of our model to improving inverse procedural material design; using our model in place of fixed-type noise nodes in a procedural material graph results in higher-fidelity material reconstructions without needing to know the type of noise in advance.
Authors: Nico Schiavone, Xingyu Li
Abstract: Foundation models contain a wealth of information from their vast number of training samples. However, most prior arts fail to extract this information in a precise and efficient way for small sample sizes. In this work, we propose a framework utilizing reinforcement learning as a control for foundation models, allowing for the granular generation of small, focused synthetic support sets to augment the performance of neural network models on real data classification tasks. We first allow a reinforcement learning agent access to a novel context based dictionary; the agent then uses this dictionary with a novel prompt structure to form and optimize prompts as inputs to generative models, receiving feedback based on a reward function combining the change in validation accuracy and entropy. A support set is formed this way over several exploration steps. Our framework produced excellent results, increasing classification accuracy by significant margins for no additional labelling or data cost.
Authors: Xiaoling Zhou, Wei Ye, Zhemg Lee, Rui Xie, Shikun Zhang
Abstract: Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To address this, we propose to augment the deep features of samples by incorporating their adversarial and anti-adversarial perturbation distributions, enabling adaptive adjustment in the learning difficulty tailored to each sample's specific characteristics. We then theoretically reveal that our augmentation process approximates the optimization of a surrogate loss function as the number of augmented copies increases indefinitely. This insight leads us to develop a meta-learning-based framework for optimizing classifiers with this novel loss, introducing the effects of augmentation while bypassing the explicit augmentation process. We conduct extensive experiments across four common biased learning scenarios: long-tail learning, generalized long-tail learning, noisy label learning, and subpopulation shift learning. The empirical results demonstrate that our method consistently achieves state-of-the-art performance, highlighting its broad adaptability.
Authors: Changjuan Ran, Yeting Guo, Fang Liu, Shenglan Cui, Yunfan Ye
Abstract: The unique artistic style is crucial to artists' occupational competitiveness, yet prevailing Art Commission Platforms rarely support style-based retrieval. Meanwhile, the fast-growing generative AI techniques aggravate artists' concerns about releasing personal artworks to public platforms. To achieve artistic style-based retrieval without exposing personal artworks, we propose FedStyle, a style-based federated learning crowdsourcing framework. It allows artists to train local style models and share model parameters rather than artworks for collaboration. However, most artists possess a unique artistic style, resulting in severe model drift among them. FedStyle addresses such extreme data heterogeneity by having artists learn their abstract style representations and align with the server, rather than merely aggregating model parameters lacking semantics. Besides, we introduce contrastive learning to meticulously construct the style representation space, pulling artworks with similar styles closer and keeping different ones apart in the embedding space. Extensive experiments on the proposed datasets demonstrate the superiority of FedStyle.
Authors: Xiang He, Weiye Song, Yiming Wang, Fabio Poiesi, Ji Yi, Manishi Desai, Quanqing Xu, Kongzheng Yang, Yi Wan
Abstract: Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as an important tool for diagnosing ophthalmic diseases. However, it is challenging to achieve accurate segmentation due to low contrast and blood flow noises presented in the images. In addition, the algorithm should be light-weight to be deployed for practical clinical applications. Therefore, it is desired to design a light-weight network with high performance for retinal layer segmentation. In this paper, we propose LightReSeg for retinal layer segmentation which can be applied to OCT images. Specifically, our approach follows an encoder-decoder structure, where the encoder part employs multi-scale feature extraction and a Transformer block for fully exploiting the semantic information of feature maps at all scales and making the features have better global reasoning capabilities, while the decoder part, we design a multi-scale asymmetric attention (MAA) module for preserving the semantic information at each encoder scale. The experiments show that our approach achieves a better segmentation performance compared to the current state-of-the-art method TransUnet with 105.7M parameters on both our collected dataset and two other public datasets, with only 3.3M parameters.
Authors: Tiago Gon\c{c}alves, Dagoberto Pulido-Arias, Julian Willett, Katharina V. Hoebel, Mason Cleveland, Syed Rakin Ahmed, Elizabeth Gerstner, Jayashree Kalpathy-Cramer, Jaime S. Cardoso, Christopher P. Bridge, Albert E. Kim
Abstract: The interactions between tumor cells and the tumor microenvironment (TME) dictate therapeutic efficacy of radiation and many systemic therapies in breast cancer. However, to date, there is not a widely available method to reproducibly measure tumor and immune phenotypes for each patient's tumor. Given this unmet clinical need, we applied multiple instance learning (MIL) algorithms to assess activity of ten biologically relevant pathways from the hematoxylin and eosin (H&E) slide of primary breast tumors. We employed different feature extraction approaches and state-of-the-art model architectures. Using binary classification, our models attained area under the receiver operating characteristic (AUROC) scores above 0.70 for nearly all gene expression pathways and on some cases, exceeded 0.80. Attention maps suggest that our trained models recognize biologically relevant spatial patterns of cell sub-populations from H&E. These efforts represent a first step towards developing computational H&E biomarkers that reflect facets of the TME and hold promise for augmenting precision oncology.
Authors: Chen Wei, Jiachen Zou, Dietmar Heinke, Quanying Liu
Abstract: A central question for cognitive science is to understand how humans process visual objects, i.e, to uncover human low-dimensional concept representation space from high-dimensional visual stimuli. Generating visual stimuli with controlling concepts is the key. However, there are currently no generative models in AI to solve this problem. Here, we present the Concept based Controllable Generation (CoCoG) framework. CoCoG consists of two components, a simple yet efficient AI agent for extracting interpretable concept and predicting human decision-making in visual similarity judgment tasks, and a conditional generation model for generating visual stimuli given the concepts. We quantify the performance of CoCoG from two aspects, the human behavior prediction accuracy and the controllable generation ability. The experiments with CoCoG indicate that 1) the reliable concept embeddings in CoCoG allows to predict human behavior with 64.07\% accuracy in the THINGS-similarity dataset; 2) CoCoG can generate diverse objects through the control of concepts; 3) CoCoG can manipulate human similarity judgment behavior by intervening key concepts. CoCoG offers visual objects with controlling concepts to advance our understanding of causality in human cognition. The code of CoCoG is available at \url{https://github.com/ncclab-sustech/CoCoG}.
Authors: Shaocong Dong, Lihe Ding, Zhanpeng Huang, Zibin Wang, Tianfan Xue, Dan Xu
Abstract: 3D object generation has undergone significant advancements, yielding high-quality results. However, fall short of achieving precise user control, often yielding results that do not align with user expectations, thus limiting their applicability. User-envisioning 3D object generation faces significant challenges in realizing its concepts using current generative models due to limited interaction capabilities. Existing methods mainly offer two approaches: (i) interpreting textual instructions with constrained controllability, or (ii) reconstructing 3D objects from 2D images. Both of them limit customization to the confines of the 2D reference and potentially introduce undesirable artifacts during the 3D lifting process, restricting the scope for direct and versatile 3D modifications. In this work, we introduce Interactive3D, an innovative framework for interactive 3D generation that grants users precise control over the generative process through extensive 3D interaction capabilities. Interactive3D is constructed in two cascading stages, utilizing distinct 3D representations. The first stage employs Gaussian Splatting for direct user interaction, allowing modifications and guidance of the generative direction at any intermediate step through (i) Adding and Removing components, (ii) Deformable and Rigid Dragging, (iii) Geometric Transformations, and (iv) Semantic Editing. Subsequently, the Gaussian splats are transformed into InstantNGP. We introduce a novel (v) Interactive Hash Refinement module to further add details and extract the geometry in the second stage. Our experiments demonstrate that Interactive3D markedly improves the controllability and quality of 3D generation. Our project webpage is available at \url{https://interactive-3d.github.io/}.
Authors: Daniel Schober, Ronja G\"uldenring, James Love, Lazaros Nalpantidis
Abstract: Laboratory processes involving small volumes of solutions and active ingredients are often performed manually due to challenges in automation, such as high initial costs, semi-structured environments and protocol variability. In this work, we develop a flexible and cost-effective approach to address this gap by introducing a vision-based system for liquid volume estimation and a simulation-driven pouring method particularly designed for containers with small openings. We evaluate both components individually, followed by an applied real-world integration of cell culture automation using a UR5 robotic arm. Our work is fully reproducible: we share our code at at \url{https://github.com/DaniSchober/LabLiquidVision} and the newly introduced dataset LabLiquidVolume is available at https://data.dtu.dk/articles/dataset/LabLiquidVision/25103102.
URLs: https://github.com/DaniSchober/LabLiquidVision, https://data.dtu.dk/articles/dataset/LabLiquidVision/25103102.
Authors: Abbas Khan, Muhammad Asad, Martin Benning, Caroline Roney, Gregory Slabaugh
Abstract: We propose a novel multi-stage trans-dimensional architecture for multi-view cardiac image segmentation. Our method exploits the relationship between long-axis (2D) and short-axis (3D) magnetic resonance (MR) images to perform a sequential 3D-to-2D-to-3D segmentation, segmenting the long-axis and short-axis images. In the first stage, 3D segmentation is performed using the short-axis image, and the prediction is transformed to the long-axis view and used as a segmentation prior in the next stage. In the second step, the heart region is localized and cropped around the segmentation prior using a Heart Localization and Cropping (HLC) module, focusing the subsequent model on the heart region of the image, where a 2D segmentation is performed. Similarly, we transform the long-axis prediction to the short-axis view, localize and crop the heart region and again perform a 3D segmentation to refine the initial short-axis segmentation. We evaluate our proposed method on the Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI (M&Ms-2) dataset, where our method outperforms state-of-the-art methods in segmenting cardiac regions of interest in both short-axis and long-axis images. The pre-trained models, source code, and implementation details will be publicly available.
Authors: Arina Varlamova, Valery Belotsky, Grigory Novikov, Anton Konushin, Evgeny Sidorov
Abstract: Detection of malignant lesions on mammography images is extremely important for early breast cancer diagnosis. In clinical practice, images are acquired from two different angles, and radiologists can fully utilize information from both views, simultaneously locating the same lesion. However, for automatic detection approaches such information fusion remains a challenge. In this paper, we propose a new model called MAMM-Net, which allows the processing of both mammography views simultaneously by sharing information not only on an object level, as seen in existing works, but also on a feature level. MAMM-Net's key component is the Fusion Layer, based on deformable attention and designed to increase detection precision while keeping high recall. Our experiments show superior performance on the public DDSM dataset compared to the previous state-of-the-art model, while introducing new helpful features such as lesion annotation on pixel-level and classification of lesions malignancy.
Authors: Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kiant\'e Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun
Abstract: While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications including the fine-tuning of generative models. Unfortunately, PPO requires multiple heuristics to enable stable convergence (e.g. value networks, clipping) and is notorious for its sensitivity to the precise implementation of these components. In response, we take a step back and ask what a minimalist RL algorithm for the era of generative models would look like. We propose REBEL, an algorithm that cleanly reduces the problem of policy optimization to regressing the relative rewards via a direct policy parameterization between two completions to a prompt, enabling strikingly lightweight implementation. In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL, which allows us to match the strongest known theoretical guarantees in terms of convergence and sample complexity in the RL literature. REBEL can also cleanly incorporate offline data and handle the intransitive preferences we frequently see in practice. Empirically, we find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO, all while being simpler to implement and more computationally tractable than PPO.
Authors: Toru Lin, Yu Zhang, Qiyang Li, Haozhi Qi, Brent Yi, Sergey Levine, Jitendra Malik
Abstract: Aiming to replicate human-like dexterity, perceptual experiences, and motion patterns, we explore learning from human demonstrations using a bimanual system with multifingered hands and visuotactile data. Two significant challenges exist: the lack of an affordable and accessible teleoperation system suitable for a dual-arm setup with multifingered hands, and the scarcity of multifingered hand hardware equipped with touch sensing. To tackle the first challenge, we develop HATO, a low-cost hands-arms teleoperation system that leverages off-the-shelf electronics, complemented with a software suite that enables efficient data collection; the comprehensive software suite also supports multimodal data processing, scalable policy learning, and smooth policy deployment. To tackle the latter challenge, we introduce a novel hardware adaptation by repurposing two prosthetic hands equipped with touch sensors for research. Using visuotactile data collected from our system, we learn skills to complete long-horizon, high-precision tasks which are difficult to achieve without multifingered dexterity and touch feedback. Furthermore, we empirically investigate the effects of dataset size, sensing modality, and visual input preprocessing on policy learning. Our results mark a promising step forward in bimanual multifingered manipulation from visuotactile data. Videos, code, and datasets can be found at https://toruowo.github.io/hato/ .
Authors: Zhicheng Ding, Zhixin Lai, Siyang Li, Panfeng Li, Qikai Yang, Edward Wong
Abstract: Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods. In this paper, we propose Confidence-Triggered Detection (CTD), an innovative approach that strategically bypasses object detection for frames closely resembling intermediate states, leveraging tracker confidence scores. CTD not only enhances tracking speed but also preserves accuracy, surpassing existing tracking algorithms. Through extensive evaluation across various tracker confidence thresholds, we identify an optimal trade-off between tracking speed and accuracy, providing crucial insights for parameter fine-tuning and enhancing CTD's practicality in real-world scenarios. Our experiments across diverse detection models underscore the robustness and versatility of the CTD framework, demonstrating its potential to enable real-time tracking in resource-constrained environments.
Authors: Le Xue, Ning Yu, Shu Zhang, Junnan Li, Roberto Mart\'in-Mart\'in, Jiajun Wu, Caiming Xiong, Ran Xu, Juan Carlos Niebles, Silvio Savarese
Abstract: Recent advancements in multimodal pre-training have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts, and language descriptions. However, the methods used by existing frameworks to curate such multimodal data, in particular language descriptions for 3D shapes, are not scalable, and the collected language descriptions are not diverse. To address this, we introduce ULIP-2, a simple yet effective tri-modal pre-training framework that leverages large multimodal models to automatically generate holistic language descriptions for 3D shapes. It only needs 3D data as input, eliminating the need for any manual 3D annotations, and is therefore scalable to large datasets. ULIP-2 is also equipped with scaled-up backbones for better multimodal representation learning. We conduct experiments on two large-scale 3D datasets, Objaverse and ShapeNet, and augment them with tri-modal datasets of 3D point clouds, images, and language for training ULIP-2. Experiments show that ULIP-2 demonstrates substantial benefits in three downstream tasks: zero-shot 3D classification, standard 3D classification with fine-tuning, and 3D captioning (3D-to-language generation). It achieves a new SOTA of 50.6% (top-1) on Objaverse-LVIS and 84.7% (top-1) on ModelNet40 in zero-shot classification. In the ScanObjectNN benchmark for standard fine-tuning, ULIP-2 reaches an overall accuracy of 91.5% with a compact model of only 1.4 million parameters. ULIP-2 sheds light on a new paradigm for scalable multimodal 3D representation learning without human annotations and shows significant improvements over existing baselines. The code and datasets are released at https://github.com/salesforce/ULIP.
Authors: Xuehai He, Weixi Feng, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Eric Wang
Abstract: Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified in text prompts, can we leverage the powerful representations learned by pre-trained diffusion models for discriminative tasks such as image-text matching? To answer this question, we propose a novel approach, Discriminative Stable Diffusion (DSD), which turns pre-trained text-to-image diffusion models into few-shot discriminative learners. Our approach mainly uses the cross-attention score of a Stable Diffusion model to capture the mutual influence between visual and textual information and fine-tune the model via efficient attention-based prompt learning to perform image-text matching. By comparing DSD with state-of-the-art methods on several benchmark datasets, we demonstrate the potential of using pre-trained diffusion models for discriminative tasks with superior results on few-shot image-text matching.
Authors: Le Zhang, Rabiul Awal, Aishwarya Agrawal
Abstract: Vision-Language Models (VLMs), such as CLIP, exhibit strong image-text comprehension abilities, facilitating advances in several downstream tasks such as zero-shot image classification, image-text retrieval, and text-to-image generation. However, the compositional reasoning abilities of existing VLMs remains subpar. The root of this limitation lies in the inadequate alignment between the images and captions in the pretraining datasets. Additionally, the current contrastive learning objective fails to focus on fine-grained grounding components like relations, actions, and attributes, resulting in "bag-of-words" representations. We introduce a simple and effective method to improve compositional reasoning in VLMs. Our method better leverages available datasets by refining and expanding the standard image-text contrastive learning framework. Our approach does not require specific annotations and does not incur extra parameters. When integrated with CLIP, our technique yields notable improvement over state-of-the-art baselines across five vision-language compositional benchmarks. We open-source our code at https://github.com/lezhang7/Enhance-FineGrained.
Authors: Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Abstract: Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data augmentation to create two views of the same instance (i.e., positive pairs) and encourage the model to learn good representations by attracting these views closer in the embedding space without collapsing to the trivial solution. However, data augmentation is limited in representing positive pairs, and the repulsion process between the instances during contrastive learning may discard important features for instances that have similar categories. To address this issue, we propose an approach to identify those images with similar semantic content and treat them as positive instances, thereby reducing the chance of discarding important features during representation learning and increasing the richness of the latent representation. Our approach is generic and could work with any self-supervised instance discrimination frameworks such as MoCo and SimSiam. To evaluate our method, we run experiments on three benchmark datasets: ImageNet, STL-10 and CIFAR-10 with different instance discrimination SSL approaches. The experimental results show that our approach consistently outperforms the baseline methods across all three datasets; for instance, we improve upon the vanilla MoCo-v2 by 4.1% on ImageNet under a linear evaluation protocol over 800 epochs. We also report results on semi-supervised learning, transfer learning on downstream tasks, and object detection.
Authors: Moon Ye-Bin, Nam Hyeon-Woo, Wonseok Choi, Nayeong Kim, Suha Kwak, Tae-Hyun Oh
Abstract: Data imbalance in training data often leads to biased predictions from trained models, which in turn causes ethical and social issues. A straightforward solution is to carefully curate training data, but given the enormous scale of modern neural networks, this is prohibitively labor-intensive and thus impractical. Inspired by recent developments in generative models, this paper explores the potential of synthetic data to address the data imbalance problem. To be specific, our method, dubbed SYNAuG, leverages synthetic data to equalize the unbalanced distribution of training data. Our experiments demonstrate that, although a domain gap between real and synthetic data exists, training with SYNAuG followed by fine-tuning with a few real samples allows to achieve impressive performance on diverse tasks with different data imbalance issues, surpassing existing task-specific methods for the same purpose.
Authors: Jiayuan Wang, Q. M. Jonathan Wu, Ning Zhang
Abstract: High precision, lightweight, and real-time responsiveness are three essential requirements for implementing autonomous driving. In this study, we incorporate A-YOLOM, an adaptive, real-time, and lightweight multi-task model designed to concurrently address object detection, drivable area segmentation, and lane line segmentation tasks. Specifically, we develop an end-to-end multi-task model with a unified and streamlined segmentation structure. We introduce a learnable parameter that adaptively concatenates features between necks and backbone in segmentation tasks, using the same loss function for all segmentation tasks. This eliminates the need for customizations and enhances the model's generalization capabilities. We also introduce a segmentation head composed only of a series of convolutional layers, which reduces the number of parameters and inference time. We achieve competitive results on the BDD100k dataset, particularly in visualization outcomes. The performance results show a mAP50 of 81.1% for object detection, a mIoU of 91.0% for drivable area segmentation, and an IoU of 28.8% for lane line segmentation. Additionally, we introduce real-world scenarios to evaluate our model's performance in a real scene, which significantly outperforms competitors. This demonstrates that our model not only exhibits competitive performance but is also more flexible and faster than existing multi-task models. The source codes and pre-trained models are released at https://github.com/JiayuanWang-JW/YOLOv8-multi-task
Authors: Neha Gianchandani, Mahsa Dibaji, Johanna Ospel, Fernando Vega, Mariana Bento, M. Ethan MacDonald, Roberto Souza
Abstract: Brain aging is a regional phenomenon, a facet that remains relatively under-explored within the realm of brain age prediction research using machine learning methods. Voxel-level predictions can provide localized brain age estimates that can provide granular insights into the regional aging processes. This is essential to understand the differences in aging trajectories in healthy versus diseased subjects. In this work, a deep learning-based multitask model is proposed for voxel-level brain age prediction from T1-weighted magnetic resonance images. The proposed model outperforms the models existing in the literature and yields valuable clinical insights when applied to both healthy and diseased populations. Regional analysis is performed on the voxel-level brain age predictions to understand aging trajectories of known anatomical regions in the brain and show that there exist disparities in regional aging trajectories of healthy subjects compared to ones with underlying neurological disorders such as Dementia and more specifically, Alzheimer's disease. Our code is available at https://github.com/nehagianchandani/Voxel-level-brain-age-prediction.
URLs: https://github.com/nehagianchandani/Voxel-level-brain-age-prediction.
Authors: Nico Schiavone, Jingyi Wang, Shuangzhi Li, Roger Zemp, Xingyu Li
Abstract: Active Learning (AL) and Few Shot Learning (FSL) are two label-efficient methods which have achieved excellent results recently. However, most prior arts in both learning paradigms fail to explore the wealth of the vast unlabelled data. In this study, we address this issue in the scenario where the annotation budget is very limited, yet a large amount of unlabelled data for the target task is available. We frame this work in the context of histopathology where labelling is prohibitively expensive. To this end, we introduce an active few shot learning framework, Myriad Active Learning (MAL), including a contrastive-learning encoder, pseudo-label generation, and novel query sample selection in the loop. Specifically, we propose to massage unlabelled data in a self-supervised manner, where the obtained data representations and clustering knowledge form the basis to activate the AL loop. With feedback from the oracle in each AL cycle, the pseudo-labels of the unlabelled data are refined by optimizing a shallow task-specific net on top of the encoder. These updated pseudo-labels serve to inform and improve the active learning query selection process. Furthermore, we introduce a novel recipe to combine existing uncertainty measures and utilize the entire uncertainty list to reduce sample redundancy in AL. Extensive experiments on two public histopathology datasets show that MAL has superior test accuracy, macro F1-score, and label efficiency compared to prior works, and can achieve a comparable test accuracy to a fully supervised algorithm while labelling only 5% of the dataset.
Authors: Chang Liu, Yuanhe Tian, Yan Song
Abstract: Radiology report generation (RRG) aims to automatically generate free-text descriptions from clinical radiographs, e.g., chest X-Ray images. RRG plays an essential role in promoting clinical automation and presents significant help to provide practical assistance for inexperienced doctors and alleviate radiologists' workloads. Therefore, consider these meaningful potentials, research on RRG is experiencing explosive growth in the past half-decade, especially with the rapid development of deep learning approaches. Existing studies perform RRG from the perspective of enhancing different modalities, provide insights on optimizing the report generation process with elaborated features from both visual and textual information, and further facilitate RRG with the cross-modal interactions among them. In this paper, we present a comprehensive review of deep learning-based RRG from various perspectives. Specifically, we firstly cover pivotal RRG approaches based on the task-specific features of radiographs, reports, and the cross-modal relations between them, and then illustrate the benchmark datasets conventionally used for this task with evaluation metrics, subsequently analyze the performance of different approaches and finally offer our summary on the challenges and the trends in future directions. Overall, the goal of this paper is to serve as a tool for understanding existing literature and inspiring potential valuable research in the field of RRG.
Authors: Xiang Xu, Lingdong Kong, Hui Shuai, Qingshan Liu
Abstract: LiDAR segmentation has become a crucial component in advanced autonomous driving systems. Recent range-view LiDAR segmentation approaches show promise for real-time processing. However, they inevitably suffer from corrupted contextual information and rely heavily on post-processing techniques for prediction refinement. In this work, we propose FRNet, a simple yet powerful method aimed at restoring the contextual information of range image pixels using corresponding frustum LiDAR points. Firstly, a frustum feature encoder module is used to extract per-point features within the frustum region, which preserves scene consistency and is crucial for point-level predictions. Next, a frustum-point fusion module is introduced to update per-point features hierarchically, enabling each point to extract more surrounding information via the frustum features. Finally, a head fusion module is used to fuse features at different levels for final semantic prediction. Extensive experiments conducted on four popular LiDAR segmentation benchmarks under various task setups demonstrate the superiority of FRNet. Notably, FRNet achieves 73.3% and 82.5% mIoU scores on the testing sets of SemanticKITTI and nuScenes. While achieving competitive performance, FRNet operates 5 times faster than state-of-the-art approaches. Such high efficiency opens up new possibilities for more scalable LiDAR segmentation. The code has been made publicly available at https://github.com/Xiangxu-0103/FRNet.
Authors: Sharath Girish, Kamal Gupta, Abhinav Shrivastava
Abstract: Recently, 3D Gaussian splatting (3D-GS) has gained popularity in novel-view scene synthesis. It addresses the challenges of lengthy training times and slow rendering speeds associated with Neural Radiance Fields (NeRFs). Through rapid, differentiable rasterization of 3D Gaussians, 3D-GS achieves real-time rendering and accelerated training. They, however, demand substantial memory resources for both training and storage, as they require millions of Gaussians in their point cloud representation for each scene. We present a technique utilizing quantized embeddings to significantly reduce per-point memory storage requirements and a coarse-to-fine training strategy for a faster and more stable optimization of the Gaussian point clouds. Our approach develops a pruning stage which results in scene representations with fewer Gaussians, leading to faster training times and rendering speeds for real-time rendering of high resolution scenes. We reduce storage memory by more than an order of magnitude all while preserving the reconstruction quality. We validate the effectiveness of our approach on a variety of datasets and scenes preserving the visual quality while consuming 10-20x lesser memory and faster training/inference speed. Project page and code is available https://efficientgaussian.github.io
Authors: Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou
Abstract: Instruction tuning data is essential for training the Multimodal Large Language Models (MLLMs). However, the creation of high-quality instruction tuning data presents significant challenges. Asking the human to label the instruction tuning data is label-intensive and time-consuming. Some works prompted to GPT-4 for data generation were not only costly but also lacked satisfactory performance in complex tasks (i.e., grounding-based reasoning tasks). To address the challenges of data creation, we are the first to explore the potential of empowering MLLMs with the ability to generate instruction-tuning data by following user instructions. Specifically, we developed an innovative data generation pipeline Genixer to generate various high-quality instruction tuning data, including nine representative tasks, e.g., Common VQA, REC, REG, and PointQ. Genixer provides a unified solution for data generation with four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLM, and (iv) data generation and filtering. To validate the effectiveness of generated data, we conducted the human evaluation and user preference study to assess the quality of generated data. Subsequently, we generated two instruction-tuning datasets for the training of two representative MLLMs, LLaVA1.5 and Shikra, and noted consistent improvements across various VQA tasks and multimodal benchmarks. For instance, performance on the VizWiz benchmark improved from 50.0% to 53.8%, and on ScienceQA, it increased from 66.8% to 69.7%, reconfirming the quality of the generated instruction tuning data. The data, code, and models will be released.
Authors: Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, Saining Xie
Abstract: Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visual component typically depends only on the instance-level contrastive language-image pre-training (CLIP). Our research reveals that the visual capabilities in recent multimodal LLMs (MLLMs) still exhibit systematic shortcomings. To understand the roots of these errors, we explore the gap between the visual embedding space of CLIP and vision-only self-supervised learning. We identify ''CLIP-blind pairs'' - images that CLIP perceives as similar despite their clear visual differences. With these pairs, we construct the Multimodal Visual Patterns (MMVP) benchmark. MMVP exposes areas where state-of-the-art systems, including GPT-4V, struggle with straightforward questions across nine basic visual patterns, often providing incorrect answers and hallucinated explanations. We further evaluate various CLIP-based vision-and-language models and found a notable correlation between visual patterns that challenge CLIP models and those problematic for multimodal LLMs. As an initial effort to address these issues, we propose a Mixture of Features (MoF) approach, demonstrating that integrating vision self-supervised learning features with MLLMs can significantly enhance their visual grounding capabilities. Together, our research suggests visual representation learning remains an open challenge, and accurate visual grounding is crucial for future successful multimodal systems.
Authors: Fengfan Zhou, Qianyu Zhou, Bangjie Yin, Hui Zheng, Xuequan Lu, Lizhuang Ma, Hefei Ling
Abstract: Face Recognition (FR) systems can be easily deceived by adversarial examples that manipulate benign face images through imperceptible perturbations. Adversarial attacks on FR encompass two types: impersonation (targeted) attacks and dodging (untargeted) attacks. Previous methods often achieve a successful impersonation attack on FR; However, it does not necessarily guarantee a successful dodging attack on FR in the black-box setting. In this paper, our key insight is that the generation of adversarial examples should perform both impersonation and dodging attacks simultaneously. To this end, we propose a novel attack method termed as Adversarial Pruning (Adv-Pruning), to fine-tune existing adversarial examples to enhance their dodging capabilities while preserving their impersonation capabilities. Adv-Pruning consists of Priming, Pruning, and Restoration stages. Concretely, we propose Adversarial Priority Quantification to measure the region-wise priority of original adversarial perturbations, identifying and releasing those with minimal impact on absolute model output variances. Then, Biased Gradient Adaptation is presented to adapt the adversarial examples to traverse the decision boundaries of both the attacker and victim by adding perturbations favoring dodging attacks on the vacated regions, preserving the prioritized features of the original perturbations while boosting dodging performance. As a result, we can maintain the impersonation capabilities of original adversarial examples while effectively enhancing dodging capabilities. Comprehensive experiments demonstrate the superiority of our method compared with state-of-the-art adversarial attacks.
Authors: Juan Hu, Xin Liao, Difei Gao, Satoshi Tsutsui, Qian Wang, Zheng Qin, Mike Zheng Shou
Abstract: Deepfake videos are becoming increasingly realistic, showing subtle tampering traces on facial areasthat vary between frames. Consequently, many existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address thislimitation, we propose Delocate, a novel Deepfake detection model that can both recognize andlocalize unknown domain Deepfake videos. Ourmethod consists of two stages named recoveringand localization. In the recovering stage, the modelrandomly masks regions of interest (ROIs) and reconstructs real faces without tampering traces, resulting in a relatively good recovery effect for realfaces and a poor recovery effect for fake faces. Inthe localization stage, the output of the recoveryphase and the forgery ground truth mask serve assupervision to guide the forgery localization process. This process strategically emphasizes the recovery phase of fake faces with poor recovery, facilitating the localization of tampered regions. Ourextensive experiments on four widely used benchmark datasets demonstrate that Delocate not onlyexcels in localizing tampered areas but also enhances cross-domain detection performance.
Authors: Jingyu Zhuang, Di Kang, Yan-Pei Cao, Guanbin Li, Liang Lin, Ying Shan
Abstract: Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the inherent limitations of the text description. To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region. With the image prompt, users can conveniently specify the detailed appearance/style of the target content in complement to the text description, enabling accurate control of the appearance. Specifically, TIP-Editor employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image, in which a localization loss is proposed to encourage correct object placement as specified by the bounding box. Additionally, TIPEditor utilizes explicit and flexible 3D Gaussian splatting as the 3D representation to facilitate local editing while keeping the background unchanged. Extensive experiments have demonstrated that TIP-Editor conducts accurate editing following the text and image prompts in the specified bounding box region, consistently outperforming the baselines in editing quality, and the alignment to the prompts, qualitatively and quantitatively.
Authors: Soufiane Belharbi, Marco Pedersoli, Alessandro Lameiras Koerich, Simon Bacon, Eric Granger
Abstract: Although state-of-the-art classifiers for facial expression recognition (FER) can achieve a high level of accuracy, they lack interpretability, an important feature for end-users. Experts typically associate spatial action units (\aus) from a codebook to facial regions for the visual interpretation of expressions. In this paper, the same expert steps are followed. A new learning strategy is proposed to explicitly incorporate \au cues into classifier training, allowing to train deep interpretable models. During training, this \au codebook is used, along with the input image expression label, and facial landmarks, to construct a \au heatmap that indicates the most discriminative image regions of interest w.r.t the facial expression. This valuable spatial cue is leveraged to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with \au heatmaps. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with \au maps, simulating the expert decision process. Our strategy only relies on image class expression for supervision, without additional manual annotations. Our new strategy is generic, and can be applied to any deep CNN- or transformer-based classifier without requiring any architectural change or significant additional training time. Our extensive evaluation on two public benchmarks \rafdb, and \affectnet datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on class activation mapping (CAM) methods, and show that our approach can also improve CAM interpretability.
Authors: Rui Song, Chenwei Liang, Hu Cao, Zhiran Yan, Walter Zimmer, Markus Gross, Andreas Festag, Alois Knoll
Abstract: Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or bird's eye views as representations of the environment. However, these approaches fall short in offering a comprehensive 3D environmental prediction. To bridge this gap, we introduce the first method for collaborative 3D semantic occupancy prediction. Particularly, it improves local 3D semantic occupancy predictions by hybrid fusion of (i) semantic and occupancy task features, and (ii) compressed orthogonal attention features shared between vehicles. Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation. The experimental findings highlight that: (i) our collaborative semantic occupancy predictions excel above the results from single vehicles by over 30%, and (ii) models anchored on semantic occupancy outpace state-of-the-art collaborative 3D detection techniques in subsequent perception applications, showcasing enhanced accuracy and enriched semantic-awareness in road environments.
Authors: Abdullah Nazhat Abdullah, Tarkan Aydin
Abstract: The Attention mechanism is the main component of the Transformer architecture, and since its introduction, it has led to significant advancements in Deep Learning that span many domains and multiple tasks. The Attention Mechanism was utilized in Computer Vision as the Vision Transformer ViT, and its usage has expanded into many tasks in the vision domain, such as classification, segmentation, object detection, and image generation. While this mechanism is very expressive and capable, it comes with the drawback of being computationally expensive and requiring datasets of considerable size for effective optimization. To address these shortcomings, many designs have been proposed in the literature to reduce the computational burden and alleviate the data size requirements. Examples of such attempts in the vision domain are the MLP-Mixer, the Conv-Mixer, the Perciver-IO, and many more. This paper introduces a new computational block as an alternative to the standard ViT block that reduces the compute burdens by replacing the normal Attention layers with a Network in Network structure that enhances the static approach of the MLP Mixer with a dynamic system of learning an element-wise gating function by a token mixing process. Extensive experimentation shows that the proposed design provides better performance than the baseline architectures on multiple datasets applied in the image classification task of the vision domain.
Authors: Zhengyi Luo, Jinkun Cao, Rawal Khirodkar, Alexander Winkler, Jing Huang, Kris Kitani, Weipeng Xu
Abstract: We present SimXR, a method for controlling a simulated avatar from information (headset pose and cameras) obtained from AR / VR headsets. Due to the challenging viewpoint of head-mounted cameras, the human body is often clipped out of view, making traditional image-based egocentric pose estimation challenging. On the other hand, headset poses provide valuable information about overall body motion, but lack fine-grained details about the hands and feet. To synergize headset poses with cameras, we control a humanoid to track headset movement while analyzing input images to decide body movement. When body parts are seen, the movements of hands and feet will be guided by the images; when unseen, the laws of physics guide the controller to generate plausible motion. We design an end-to-end method that does not rely on any intermediate representations and learns to directly map from images and headset poses to humanoid control signals. To train our method, we also propose a large-scale synthetic dataset created using camera configurations compatible with a commercially available VR headset (Quest 2) and show promising results on real-world captures. To demonstrate the applicability of our framework, we also test it on an AR headset with a forward-facing camera.
Authors: Youngmin Chung, Ji Hun Ha, Kyeong Chan Im, Joo Sang Lee
Abstract: Recent advancements in Spatial Transcriptomics (ST) technology have facilitated detailed gene expression analysis within tissue contexts. However, the high costs and methodological limitations of ST necessitate a more robust predictive model. In response, this paper introduces TRIPLEX, a novel deep learning framework designed to predict spatial gene expression from Whole Slide Images (WSIs). TRIPLEX uniquely harnesses multi-resolution features, capturing cellular morphology at individual spots, the local context around these spots, and the global tissue organization. By integrating these features through an effective fusion strategy, TRIPLEX achieves accurate gene expression prediction. Our comprehensive benchmark study, conducted on three public ST datasets and supplemented with Visium data from 10X Genomics, demonstrates that TRIPLEX outperforms current state-of-the-art models in Mean Squared Error (MSE), Mean Absolute Error (MAE), and Pearson Correlation Coefficient (PCC). The model's predictions align closely with ground truth gene expression profiles and tumor annotations, underscoring TRIPLEX's potential in advancing cancer diagnosis and treatment.
Authors: Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu
Abstract: We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS). Our method first renders a collection of images by using the 3DGS and edits them by using a pre-trained 2D diffusion model (ControlNet) based on the input prompt, which is then used to optimise the 3D model. Our key contribution is multi-view consistent editing, which enables editing all images together instead of iteratively editing one image while updating the 3D model as in previous works. It leads to faster editing as well as higher visual quality. This is achieved by the two terms: (a) depth-conditioned editing that enforces geometric consistency across multi-view images by leveraging naturally consistent depth maps. (b) attention-based latent code alignment that unifies the appearance of edited images by conditioning their editing to several reference views through self and cross-view attention between images' latent representations. Experiments demonstrate that our method achieves faster editing and better visual results than previous state-of-the-art methods.
Authors: Badri N. Patro, Vijay S. Agneeswaran
Abstract: Transformers have widely adopted attention networks for sequence mixing and MLPs for channel mixing, playing a pivotal role in achieving breakthroughs across domains. However, recent literature highlights issues with attention networks, including low inductive bias and quadratic complexity concerning input sequence length. State Space Models (SSMs) like S4 and others (Hippo, Global Convolutions, liquid S4, LRU, Mega, and Mamba), have emerged to address the above issues to help handle longer sequence lengths. Mamba, while being the state-of-the-art SSM, has a stability issue when scaled to large networks for computer vision datasets. We propose SiMBA, a new architecture that introduces Einstein FFT (EinFFT) for channel modeling by specific eigenvalue computations and uses the Mamba block for sequence modeling. Extensive performance studies across image and time-series benchmarks demonstrate that SiMBA outperforms existing SSMs, bridging the performance gap with state-of-the-art transformers. Notably, SiMBA establishes itself as the new state-of-the-art SSM on ImageNet and transfer learning benchmarks such as Stanford Car and Flower as well as task learning benchmarks as well as seven time series benchmark datasets. The project page is available on this website ~\url{https://github.com/badripatro/Simba}.
Authors: Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi
Abstract: Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagation-based approaches to handle this. Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data. Our model uses a two-stream architecture to maintain knowledge about the source domain as well as complementary target-domain-specific information. The backpropagation-free property of our model helps address the well-known forgetting problem and mitigates the error accumulation issue. The proposed method also eliminates the need for the usually noisy process of pseudo-labeling and reliance on costly self-supervised training. Moreover, our method leverages subspace learning, effectively reducing the distribution variance between the two domains. Furthermore, the source-domain-specific and the target-domain-specific streams are aligned using a novel entropy-based adaptive fusion strategy. Extensive experiments on popular benchmarks demonstrate the effectiveness of our method. The code will be available at \url{https://github.com/abie-e/BFTT3D}.
Authors: Yang Luo, Zhineng Chen, Peng Zhou, Zuxuan Wu, Xieping Gao, Yu-Gang Jiang
Abstract: Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods rely on supervisory signals. They may compel models to preserve content that aligns with labeled categories and discard content belonging to unlabeled categories. This categorical inductive bias makes these methods less effective in real-world scenarios. To address this issue, we propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches (LTRP). We observe that image reconstruction of masked image modeling models is sensitive to the removal of visible patches when the masking ratio is high (e.g., 90\%). Building upon it, we implement LTRP via two steps: inferring the semantic density score of each patch by quantifying variation between reconstructions with and without this patch, and learning to rank the patches with the pseudo score. The entire process is self-supervised, thus getting out of the dilemma of categorical inductive bias. We design extensive experiments on different datasets and tasks. The results demonstrate that LTRP outperforms both supervised and other self-supervised methods due to the fair assessment of image content.
Authors: Andrea Atzori, Fadi Boutros, Naser Damer, Gianni Fenu, Mirko Marras
Abstract: Recent advances in deep face recognition have spurred a growing demand for large, diverse, and manually annotated face datasets. Acquiring authentic, high-quality data for face recognition has proven to be a challenge, primarily due to privacy concerns. Large face datasets are primarily sourced from web-based images, lacking explicit user consent. In this paper, we examine whether and how synthetic face data can be used to train effective face recognition models with reduced reliance on authentic images, thereby mitigating data collection concerns. First, we explored the performance gap among recent state-of-the-art face recognition models, trained with synthetic data only and authentic (scarce) data only. Then, we deepened our analysis by training a state-of-the-art backbone with various combinations of synthetic and authentic data, gaining insights into optimizing the limited use of the latter for verification accuracy. Finally, we assessed the effectiveness of data augmentation approaches on synthetic and authentic data, with the same goal in mind. Our results highlighted the effectiveness of FR trained on combined datasets, particularly when combined with appropriate augmentation techniques.
Authors: Yingtao Tian
Abstract: Chinese, Japanese, and Korean (CJK), with a vast number of native speakers, have profound influence on society and culture. The typesetting of CJK languages carries a wide range of requirements due to the complexity of their scripts and unique literary traditions. A critical aspect of this typesetting process is that CJK fonts need to provide a set of consistent-looking glyphs for approximately one hundred thousand characters. However, creating such a font is inherently labor-intensive and expensive, which significantly hampers the development of new CJK fonts for typesetting, historical, aesthetic, or artistic purposes. To bridge this gap, we are motivated by recent advancements in diffusion-based generative models and propose a novel diffusion method for generating glyphs in a targeted style from a single conditioned, standard glyph form. Our experiments show that our method is capable of generating fonts of both printed and hand-written styles, the latter of which presents a greater challenge. Moreover, our approach shows remarkable zero-shot generalization capabilities for non-CJK but Chinese-inspired scripts. We also show our method facilitates smooth style interpolation and generates bitmap images suitable for vectorization, which is crucial in the font creation process. In summary, our proposed method opens the door to high-quality, generative model-assisted font creation for CJK characters, for both typesetting and artistic endeavors.
Authors: Jinyue Chen, Lingyu Kong, Haoran Wei, Chenglong Liu, Zheng Ge, Liang Zhao, Jianjian Sun, Chunrui Han, Xiangyu Zhang
Abstract: Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of parameters struggle to handle such tasks satisfactorily. To address this, we propose OneChart: a reliable agent specifically devised for the structural extraction of chart information. Similar to popular LVLMs, OneChart incorporates an autoregressive main body. Uniquely, to enhance the reliability of the numerical parts of the output, we introduce an auxiliary token placed at the beginning of the total tokens along with an additional decoder. The numerically optimized (auxiliary) token allows subsequent tokens for chart parsing to capture enhanced numerical features through causal attention. Furthermore, with the aid of the auxiliary token, we have devised a self-evaluation mechanism that enables the model to gauge the reliability of its chart parsing results by providing confidence scores for the generated content. Compared to current state-of-the-art (SOTA) chart parsing models, e.g., DePlot, ChartVLM, ChartAst, OneChart significantly outperforms in Average Precision (AP) for chart structural extraction across multiple public benchmarks, despite enjoying only 0.2 billion parameters. Moreover, as a chart parsing agent, it also brings 10%+ accuracy gains for the popular LVLM (LLaVA-1.6) in the downstream ChartQA benchmark.
Authors: Qi Han, Zhibo Tian, Chengwei Xia, Kun Zhan
Abstract: Semi-supervised image classification, leveraging pseudo supervision and consistency regularization, has demonstrated remarkable success. However, the ongoing challenge lies in fully exploiting the potential of unlabeled data. To address this, we employ information entropy neural estimation to utilize the potential of unlabeled samples. Inspired by contrastive learning, the entropy is estimated by maximizing a lower bound on mutual information across different augmented views. Moreover, we theoretically analyze that the information entropy of the posterior of an image classifier is approximated by maximizing the likelihood function of the softmax predictions. Guided by these insights, we optimize our model from both perspectives to ensure that the predicted probability distribution closely aligns with the ground-truth distribution. Given the theoretical connection to information entropy, we name our method InfoMatch. Through extensive experiments, we show its superior performance. The source code is available at https://github.com/kunzhan/InfoMatch.
Authors: Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A. Smith, Wei-Chiu Ma, Ranjay Krishna
Abstract: We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the Blink tasks can be solved by humans "within a blink" (e.g., relative depth estimation, visual correspondence, forensics detection, and multi-view reasoning). However, we find these perception-demanding tasks cast significant challenges for current multimodal LLMs because they resist mediation through natural language. Blink reformats 14 classic computer vision tasks into 3,807 multiple-choice questions, paired with single or multiple images and visual prompting. While humans get 95.70% accuracy on average, Blink is surprisingly challenging for existing multimodal LLMs: even the best-performing GPT-4V and Gemini achieve accuracies of 51.26% and 45.72%, only 13.17% and 7.63% higher than random guessing, indicating that such perception abilities have not "emerged" yet in recent multimodal LLMs. Our analysis also highlights that specialist CV models could solve these problems much better, suggesting potential pathways for future improvements. We believe Blink will stimulate the community to help multimodal LLMs catch up with human-level visual perception.
Authors: Yuchi Liu, Lei Wang, Yuli Zou, James Zou, Liang Zheng
Abstract: Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE loss has intrinsic limitations. For example, for a narrow misclassification, a calibrator trained by the CE loss often produces high confidence on the wrongly predicted class (e.g., a test sample is wrongly classified and its softmax score on the ground truth class is around 0.4), which is undesirable. In this paper, we propose a new post-hoc calibration objective derived from the aim of calibration. Intuitively, the proposed objective function asks that the calibrator decrease model confidence on wrongly predicted samples and increase confidence on correctly predicted samples. Because a sample itself has insufficient ability to indicate correctness, we use its transformed versions (e.g., rotated, greyscaled and color-jittered) during calibrator training. Trained on an in-distribution validation set and tested with isolated, individual test samples, our method achieves competitive calibration performance on both in-distribution and out-of-distribution test sets compared with the state of the art. Further, our analysis points out the difference between our method and commonly used objectives such as CE loss and mean square error loss, where the latters sometimes deviates from the calibration aim.
Authors: Yifan Jiang, Jiarui Zhang, Kexuan Sun, Zhivar Sourati, Kian Ahrabian, Kaixin Ma, Filip Ilievski, Jay Pujara
Abstract: While multi-modal large language models (MLLMs) have shown significant progress on many popular visual reasoning benchmarks, whether they possess abstract visual reasoning abilities remains an open question. Similar to the Sudoku puzzles, abstract visual reasoning (AVR) problems require finding high-level patterns (e.g., repetition constraints) that control the input shapes (e.g., digits) in a specific task configuration (e.g., matrix). However, existing AVR benchmarks only considered a limited set of patterns (addition, conjunction), input shapes (rectangle, square), and task configurations (3 by 3 matrices). To evaluate MLLMs' reasoning abilities comprehensively, we introduce MARVEL, a multidimensional AVR benchmark with 770 puzzles composed of six core knowledge patterns, geometric and abstract shapes, and five different task configurations. To inspect whether the model accuracy is grounded in perception and reasoning, MARVEL complements the general AVR question with perception questions in a hierarchical evaluation framework. We conduct comprehensive experiments on MARVEL with nine representative MLLMs in zero-shot and few-shot settings. Our experiments reveal that all models show near-random performance on the AVR question, with significant performance gaps (40%) compared to humans across all patterns and task configurations. Further analysis of perception questions reveals that MLLMs struggle to comprehend the visual features (near-random performance) and even count the panels in the puzzle ( <45%), hindering their ability for abstract reasoning. We release our entire code and dataset.
Authors: Tahmim Hossain, Faisal Sayed, Solehin Islam
Abstract: The shortage of nephrologists and the growing public health concern over renal failure have spurred the demand for AI systems capable of autonomously detecting kidney abnormalities. Renal failure, marked by a gradual decline in kidney function, can result from factors like cysts, stones, and tumors. Chronic kidney disease may go unnoticed initially, leading to untreated cases until they reach an advanced stage. The dataset, comprising 12,427 images from multiple hospitals in Dhaka, was categorized into four groups: cyst, tumor, stone, and normal. Our methodology aims to enhance CT scan image quality using Cropping, Resizing, and CALHE techniques, followed by feature extraction with our proposed Adaptive Local Binary Pattern (A-LBP) feature extraction method compared with the state-of-the-art local binary pattern (LBP) method. Our proposed features fed into classifiers such as Random Forest, Decision Tree, Naive Bayes, K-Nearest Neighbor, and SVM. We explored an ensemble model with soft voting to get a more robust model for our task. We got the highest of more than 99% in accuracy using our feature descriptor and ensembling five classifiers (Random Forest, Decision Tree, Naive Bayes, K-Nearest Neighbor, Support Vector Machine) with the soft voting method.
Authors: Yugan Chen, Lin Zhao, Yalong Xu, Honglei Zu, Xiaoqi An, Guangyu Li
Abstract: Domain adaptive pose estimation aims to enable deep models trained on source domain (synthesized) datasets produce similar results on the target domain (real-world) datasets. The existing methods have made significant progress by conducting image-level or feature-level alignment. However, only aligning at a single level is not sufficient to fully bridge the domain gap and achieve excellent domain adaptive results. In this paper, we propose a multi-level domain adaptation aproach, which aligns different domains at the image, feature, and pose levels. Specifically, we first utilize image style transer to ensure that images from the source and target domains have a similar distribution. Subsequently, at the feature level, we employ adversarial training to make the features from the source and target domains preserve domain-invariant characeristics as much as possible. Finally, at the pose level, a self-supervised approach is utilized to enable the model to learn diverse knowledge, implicitly addressing the domain gap. Experimental results demonstrate that significant imrovement can be achieved by the proposed multi-level alignment method in pose estimation, which outperforms previous state-of-the-art in human pose by up to 2.4% and animal pose estimation by up to 3.1% for dogs and 1.4% for sheep.
Authors: Anahita Fathi Kazerooni, Nastaran Khalili, Deep Gandhi, Xinyang Liu, Zhifan Jiang, Syed Muhammed Anwar, Jake Albrecht, Maruf Adewole, Udunna Anazodo, Hannah Anderson, Sina Bagheri, Ujjwal Baid, Timothy Bergquist, Austin J. Borja, Evan Calabrese, Verena Chung, Gian-Marco Conte, Farouk Dako, James Eddy, Ivan Ezhov, Ariana Familiar, Keyvan Farahani, Anurag Gottipati, Debanjan Haldar, Shuvanjan Haldar, Juan Eugenio Iglesias, Anastasia Janas, Elaine Johansen, Blaise V Jones, Neda Khalili, Florian Kofler, Dominic LaBella, Hollie Anne Lai, Koen Van Leemput, Hongwei Bran Li, Nazanin Maleki, Aaron S McAllister, Zeke Meier, Bjoern Menze, Ahmed W Moawad, Khanak K Nandolia, Julija Pavaine, Marie Piraud, Tina Poussaint, Sanjay P Prabhu, Zachary Reitman, Andres Rodriguez, Jeffrey D Rudie, Mariana Sanchez-Montano, Ibraheem Salman Shaikh, Lubdha M. Shah, Nakul Sheth, Russel Taki Shinohara, Wenxin Tu, Karthik Viswanathan, Chunhao Wang, Jeffrey B Ware, Benedikt Wiestler, Walter Wiggins, Anna Zapaishchykova, Mariam Aboian, Miriam Bornhorst, Peter de Blank, Michelle Deutsch, Maryam Fouladi, Lindsey Hoffman, Benjamin Kann, Margot Lazow, Leonie Mikael, Ali Nabavizadeh, Roger Packer, Spyridon Bakas, Adam Resnick, Brian Rood, Arastoo Vossough, Marius George Linguraru
Abstract: Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge, focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.
Authors: Jinfu Liu, Baiqiao Yin, Jiaying Lin, Jiajun Wen, Yue Li, Mengyuan Liu
Abstract: Skeleton-based action recognition has gained considerable traction thanks to its utilization of succinct and robust skeletal representations. Nonetheless, current methodologies often lean towards utilizing a solitary backbone to model skeleton modality, which can be limited by inherent flaws in the network backbone. To address this and fully leverage the complementary characteristics of various network architectures, we propose a novel Hybrid Dual-Branch Network (HDBN) for robust skeleton-based action recognition, which benefits from the graph convolutional network's proficiency in handling graph-structured data and the powerful modeling capabilities of Transformers for global information. In detail, our proposed HDBN is divided into two trunk branches: MixGCN and MixFormer. The two branches utilize GCNs and Transformers to model both 2D and 3D skeletal modalities respectively. Our proposed HDBN emerged as one of the top solutions in the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) of 2024 ICME Grand Challenge, achieving accuracies of 47.95% and 75.36% on two benchmarks of the UAV-Human dataset by outperforming most existing methods. Our code will be publicly available at: https://github.com/liujf69/ICMEW2024-Track10.
Authors: Folco Bertini Baldassini, Mustafa Shukor, Matthieu Cord, Laure Soulier, Benjamin Piwowarski
Abstract: Large Language Models have demonstrated remarkable performance across various tasks, exhibiting the capacity to swiftly acquire new skills, such as through In-Context Learning (ICL) with minimal demonstration examples. In this work, we present a comprehensive framework for investigating Multimodal ICL (M-ICL) in the context of Large Multimodal Models. We consider the best open-source multimodal models (e.g., IDEFICS, OpenFlamingo) and a wide range of multimodal tasks. Our study unveils several noteworthy findings: (1) M-ICL primarily relies on text-driven mechanisms, showing little to no influence from the image modality. (2) When used with advanced-ICL strategy (like RICES), M-ICL is not better than a simple strategy based on majority voting over context examples. Moreover, we identify several biases and limitations of M-ICL that warrant consideration prior to deployment. Code available at https://gitlab.com/folbaeni/multimodal-icl
Authors: Eunsu Baek, Keondo Park, Jiyoon Kim, Hyung-Sin Kim
Abstract: Computer vision applications predict on digital images acquired by a camera from physical scenes through light. However, conventional robustness benchmarks rely on perturbations in digitized images, diverging from distribution shifts occurring in the image acquisition process. To bridge this gap, we introduce a new distribution shift dataset, ImageNet-ES, comprising variations in environmental and camera sensor factors by directly capturing 202k images with a real camera in a controllable testbed. With the new dataset, we evaluate out-of-distribution (OOD) detection and model robustness. We find that existing OOD detection methods do not cope with the covariate shifts in ImageNet-ES, implying that the definition and detection of OOD should be revisited to embrace real-world distribution shifts. We also observe that the model becomes more robust in both ImageNet-C and -ES by learning environment and sensor variations in addition to existing digital augmentations. Lastly, our results suggest that effective shift mitigation via camera sensor control can significantly improve performance without increasing model size. With these findings, our benchmark may aid future research on robustness, OOD, and camera sensor control for computer vision. Our code and dataset are available at https://github.com/Edw2n/ImageNet-ES.
Authors: Lizhi Wang, Feng Zhou, Jianqin Yin
Abstract: Recent advancements in 3D reconstruction technologies have paved the way for high-quality and real-time rendering of complex 3D scenes. Despite these achievements, a notable challenge persists: it is difficult to precisely reconstruct specific objects from large scenes. Current scene reconstruction techniques frequently result in the loss of object detail textures and are unable to reconstruct object portions that are occluded or unseen in views. To address this challenge, we delve into the meticulous 3D reconstruction of specific objects within large scenes and propose a framework termed OMEGAS: Object Mesh Extraction from Large Scenes Guided by GAussian Segmentation. OMEGAS employs a multi-step approach, grounded in several excellent off-the-shelf methodologies. Specifically, initially, we utilize the Segment Anything Model (SAM) to guide the segmentation of 3D Gaussian Splatting (3DGS), thereby creating a basic 3DGS model of the target object. Then, we leverage large-scale diffusion priors to further refine the details of the 3DGS model, especially aimed at addressing invisible or occluded object portions from the original scene views. Subsequently, by re-rendering the 3DGS model onto the scene views, we achieve accurate object segmentation and effectively remove the background. Finally, these target-only images are used to improve the 3DGS model further and extract the definitive 3D object mesh by the SuGaR model. In various scenarios, our experiments demonstrate that OMEGAS significantly surpasses existing scene reconstruction methods. Our project page is at: https://github.com/CrystalWlz/OMEGAS
Authors: Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn, Seungryong Kim
Abstract: We propose GaussianTalker, a novel framework for real-time generation of pose-controllable talking heads. It leverages the fast rendering capabilities of 3D Gaussian Splatting (3DGS) while addressing the challenges of directly controlling 3DGS with speech audio. GaussianTalker constructs a canonical 3DGS representation of the head and deforms it in sync with the audio. A key insight is to encode the 3D Gaussian attributes into a shared implicit feature representation, where it is merged with audio features to manipulate each Gaussian attribute. This design exploits the spatial-aware features and enforces interactions between neighboring points. The feature embeddings are then fed to a spatial-audio attention module, which predicts frame-wise offsets for the attributes of each Gaussian. It is more stable than previous concatenation or multiplication approaches for manipulating the numerous Gaussians and their intricate parameters. Experimental results showcase GaussianTalker's superiority in facial fidelity, lip synchronization accuracy, and rendering speed compared to previous methods. Specifically, GaussianTalker achieves a remarkable rendering speed up to 120 FPS, surpassing previous benchmarks. Our code is made available at https://github.com/KU-CVLAB/GaussianTalker/ .
Authors: Jianan Liu, Hao Li, Tao Huang, Euijoon Ahn, Kang Han, Adeel Razi, Wei Xiang, Jinman Kim, David Dagan Feng
Abstract: High-resolution (HR) magnetic resonance imaging is critical in aiding doctors in their diagnoses and image-guided treatments. However, acquiring HR images can be time-consuming and costly. Consequently, deep learning-based super-resolution reconstruction (SRR) has emerged as a promising solution for generating super-resolution (SR) images from low-resolution (LR) images. Unfortunately, training such neural networks requires aligned authentic HR and LR image pairs, which are challenging to obtain due to patient movements during and between image acquisitions. While rigid movements of hard tissues can be corrected with image registration, aligning deformed soft tissues is complex, making it impractical to train neural networks with authentic HR and LR image pairs. Previous studies have focused on SRR using authentic HR images and down-sampled synthetic LR images. However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images. To address this issue, we propose a novel Unsupervised Degradation Adaptation Network (UDEAN). Our network consists of a degradation learning network and an SRR network. The degradation learning network downsamples the HR images using the degradation representation learned from the misaligned or unpaired LR images. The SRR network then learns the mapping from the down-sampled HR images to the original ones. Experimental results show that our method outperforms state-of-the-art networks and is a promising solution to the challenges in clinical settings.
Authors: Ilayda Yaman, Guoda Tian, Erik Tegler, Jens Gulin, Nikhil Challa, Fredrik Tufvesson, Ove Edfors, Kalle Astrom, Steffen Malkowsky, Liang Liu
Abstract: We present a unique comparative analysis, and evaluation of vision, radio, and audio based localization algorithms. We create the first baseline for the aforementioned sensors using the recently published Lund University Vision, Radio, and Audio (LuViRA) dataset, where all the sensors are synchronized and measured in the same environment. Some of the challenges of using each specific sensor for indoor localization tasks are highlighted. Each sensor is paired with a current state-of-the-art localization algorithm and evaluated for different aspects: localization accuracy, reliability and sensitivity to environment changes, calibration requirements, and potential system complexity. Specifically, the evaluation covers the ORB-SLAM3 algorithm for vision-based localization with an RGB-D camera, a machine-learning algorithm for radio-based localization with massive MIMO technology, and the SFS2 algorithm for audio-based localization with distributed microphones. The results can serve as a guideline and basis for further development of robust and high-precision multi-sensory localization systems, e.g., through sensor fusion, context, and environment-aware adaptation.
Authors: Caixin Wang, Jie Zhang, Matthew A. Wilson, Ralph Etienne-Cummings
Abstract: Accurately capturing dynamic scenes with wide-ranging motion and light intensity is crucial for many vision applications. However, acquiring high-speed high dynamic range (HDR) video is challenging because the camera's frame rate restricts its dynamic range. Existing methods sacrifice speed to acquire multi-exposure frames. Yet, misaligned motion in these frames can still pose complications for HDR fusion algorithms, resulting in artifacts. Instead of frame-based exposures, we sample the videos using individual pixels at varying exposures and phase offsets. Implemented on a monochrome pixel-wise programmable image sensor, our sampling pattern simultaneously captures fast motion at a high dynamic range. We then transform pixel-wise outputs into an HDR video using end-to-end learned weights from deep neural networks, achieving high spatiotemporal resolution with minimized motion blurring. We demonstrate aliasing-free HDR video acquisition at 1000 FPS, resolving fast motion under low-light conditions and against bright backgrounds - both challenging conditions for conventional cameras. By combining the versatility of pixel-wise sampling patterns with the strength of deep neural networks at decoding complex scenes, our method greatly enhances the vision system's adaptability and performance in dynamic conditions.
Authors: Aojun Lu, Tao Feng, Hangjie Yuan, Xiaotian Song, Yanan Sun
Abstract: Efforts to overcome catastrophic forgetting have primarily centered around developing more effective Continual Learning (CL) methods. In contrast, less attention was devoted to analyzing the role of network architecture design (e.g., network depth, width, and components) in contributing to CL. This paper seeks to bridge this gap between network architecture design and CL, and to present a holistic study on the impact of network architectures on CL. This work considers architecture design at the network scaling level, i.e., width and depth, and also at the network components, i.e., skip connections, global pooling layers, and down-sampling. In both cases, we first derive insights through systematically exploring how architectural designs affect CL. Then, grounded in these insights, we craft a specialized search space for CL and further propose a simple yet effective ArchCraft method to steer a CL-friendly architecture, namely, this method recrafts AlexNet/ResNet into AlexAC/ResAC. Experimental validation across various CL settings and scenarios demonstrates that improved architectures are parameter-efficient, achieving state-of-the-art performance of CL while being 86%, 61%, and 97% more compact in terms of parameters than the naive CL architecture in Task IL and Class IL. Code is available at https://github.com/byyx666/ArchCraft.