Authors: Wei Ye, Chaoya Jiang, Haiyang Xu, Chenhao Ye, Chenliang Li, Ming Yan, Shikun Zhang, Songhang Huang, Fei Huang
Abstract: Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the efficacy of ViTs, these efforts still struggle with computational inefficiencies caused by lengthy visual sequences. To address this challenge, we introduce an efficient VLP approach called TRIPS, which stands for Text-Relevant Image Patch Selection. TRIPS progressively reduces the visual sequence using a text-guided patch-selection layer in the visual backbone, thereby accelerating both training and inference processes. This patch-selection layer dynamically computes text-dependent visual attention, enabling it to identify attentive image tokens with text guidance and fuse inattentive ones in an end-to-end fashion. Importantly, TRIPS does not add any extra parameters and generalizes to most ViT-based VLP models. We incorporate TRIPS into three representative VLP models covering single-stream, dual-stream, and generative paradigms, and conduct extensive experiments on five widely-used multi-modal benchmark datasets. Our experimental results reveal that TRIPS delivers a 40% speedup, while maintaining competitive or superior performance on downstream tasks.
Authors: Jingnan Jia, Marius Staring, Berend C. Stoel
Abstract: In response to a concerning trend of selectively emphasizing metrics in medical image segmentation (MIS) studies, we introduce \texttt{seg-metrics}, an open-source Python package for standardized MIS model evaluation. Unlike existing packages, \texttt{seg-metrics} offers user-friendly interfaces for various overlap-based and distance-based metrics, providing a comprehensive solution. \texttt{seg-metrics} supports multiple file formats and is easily installable through the Python Package Index (PyPI). With a focus on speed and convenience, \texttt{seg-metrics} stands as a valuable tool for efficient MIS model assessment.
Authors: Sota Moriyama, Koji Watanabe, Katsumi Inoue, Akihiro Takemura
Abstract: We introduce MOD-CL, a multi-label object detection framework that utilizes constrained loss in the training process to produce outputs that better satisfy the given requirements. In this paper, we use $\mathrm{MOD_{YOLO}}$, a multi-label object detection model built upon the state-of-the-art object detection model YOLOv8, which has been published in recent years. In Task 1, we introduce the Corrector Model and Blender Model, two new models that follow after the object detection process, aiming to generate a more constrained output. For Task 2, constrained losses have been incorporated into the $\mathrm{MOD_{YOLO}}$ architecture using Product T-Norm. The results show that these implementations are instrumental to improving the scores for both Task 1 and Task 2.
Authors: Bhishma Dedhia, Niraj K. Jha
Abstract: Object-centric methods have seen significant progress in unsupervised decomposition of raw perception into rich object-like abstractions. However, limited ability to ground object semantics of the real world into the learned abstractions has hindered their adoption in downstream understanding applications. We present the Neural Slot Interpreter (NSI) that learns to ground and generate object semantics via slot representations. At the core of NSI is an XML-like programming language that uses simple syntax rules to organize the object semantics of a scene into object-centric program primitives. Then, an alignment model learns to ground program primitives into slots through a bi-level contrastive learning objective over a shared embedding space. Finally, we formulate the NSI program generator model to use the dense associations inferred from the alignment model to generate object-centric programs from slots. Experiments on bi-modal retrieval tasks demonstrate the efficacy of the learned alignments, surpassing set-matching-based predictors by a significant margin. Moreover, learning the program generator from grounded associations enhances the predictive power of slots. NSI generated programs demonstrate improved performance of object-centric learners on property prediction and object detection, and scale with real-world scene complexity.
Authors: Yijiang Pang, Hoang Bao, Jiayu Zhou
Abstract: Sub-population shift is a specific type of domain shift that highlights changes in data distribution within specific sub-groups or populations between training and testing. Sub-population shift accounts for a significant source of algorithmic bias and calls for distributional robustness. Recent studies found inherent distributional robustness in multi-modality foundation models, such as the vision-language model CLIP, yet this robustness is vulnerable through parameter fine-tuning. In this paper, we propose leveraging the connection of robustness among different modalities and reshaping the distributional robustness of one modality with another. Specifically, in the context of the distributional robustness of CLIP, we propose to leverage natural language inputs to debias the image feature representations, to improve worst-case performance on sub-populations. Our extensive empirical studies show that image representations debiased by natural language can achieve significant performance improvement and reduction of performance instability under sub-population shifts.
Authors: Edgar Gonzalez Fernandez, Ana Lucila Sandoval Orozco, Luis Javier Garcia Villalba
Abstract: Digital images and videos play a very important role in everyday life. Nowadays, people have access the affordable mobile devices equipped with advanced integrated cameras and powerful image processing applications. Technological development facilitates not only the generation of multimedia content, but also the intentional modification of it, either with recreational or malicious purposes. This is where forensic techniques to detect manipulation of images and videos become essential. This paper proposes a forensic technique by analysing compression algorithms used by the H.264 coding. The presence of recompression uses information of macroblocks, a characteristic of the H.264-MPEG4 standard, and motion vectors. A Vector Support Machine is used to create the model that allows to accurately detect if a video has been recompressed.
Authors: Peiheng Zhou, Ming Hu, Xiaofei Xie, Yihao Huang, Kangjie Chen, Mingsong Chen
Abstract: Contrastive Language-Image Pre-training (CLIP) model, as an effective pre-trained multimodal neural network, has been widely used in distributed machine learning tasks, especially Federated Learning (FL). Typically, CLIP-based FL adopts Parameter-Efficient Fine-Tuning (PEFT) for model training, which only fine-tunes adapter parameters or soft prompts rather than the full parameters. Although PEFT is different from the traditional training mode, in this paper, we theoretically analyze that the gradients of adapters or soft prompts can still be used to perform image reconstruction attacks. Based on our theoretical analysis, we propose Multm-In-Parvo (MIP), a proprietary reconstruction attack method targeting CLIP-based distributed machine learning architecture. Specifically, MIP can reconstruct CLIP training images according to the gradients of soft prompts or an adapter. In addition, MIP includes a label prediction strategy to accelerate convergence and an inverse gradient estimation mechanism to avoid the vanishing gradient problem on the text encoder. Experimental results show that MIP can effectively reconstruct training images according to the gradients of soft prompts or adapters of CLIP models.
Authors: Shuaibing Wang, Shunli Wang, Dingkang Yang, Mingcheng Li, Ziyun Qian, Liuzhen Su, Lihua Zhang
Abstract: We propose a robust and accurate method for reconstructing 3D hand mesh from monocular images. This is a very challenging problem, as hands are often severely occluded by objects. Previous works often have disregarded 2D hand pose information, which contains hand prior knowledge that is strongly correlated with occluded regions. Thus, in this work, we propose a novel 3D hand mesh reconstruction network HandGCAT, that can fully exploit hand prior as compensation information to enhance occluded region features. Specifically, we designed the Knowledge-Guided Graph Convolution (KGC) module and the Cross-Attention Transformer (CAT) module. KGC extracts hand prior information from 2D hand pose by graph convolution. CAT fuses hand prior into occluded regions by considering their high correlation. Extensive experiments on popular datasets with challenging hand-object occlusions, such as HO3D v2, HO3D v3, and DexYCB demonstrate that our HandGCAT reaches state-of-the-art performance. The code is available at https://github.com/heartStrive/HandGCAT.
Authors: Yushan Han, Kaer Huang
Abstract: Efficiently modeling spatio-temporal relations of objects is a key challenge in visual object tracking (VOT). Existing methods track by appearance-based similarity or long-term relation modeling, resulting in rich temporal contexts between consecutive frames being easily overlooked. Moreover, training trackers from scratch or fine-tuning large pre-trained models needs more time and memory consumption. In this paper, we present ACTrack, a new tracking framework with additive spatio-temporal conditions. It preserves the quality and capabilities of the pre-trained Transformer backbone by freezing its parameters, and makes a trainable lightweight additive net to model spatio-temporal relations in tracking. We design an additive siamese convolutional network to ensure the integrity of spatial features and perform temporal sequence modeling to simplify the tracking pipeline. Experimental results on several benchmarks prove that ACTrack could balance training efficiency and tracking performance.
Authors: Tingting Zheng, Kui Jiang, Hongxun Yao
Abstract: Multi-Instance Learning (MIL) has shown impressive performance for histopathology whole slide image (WSI) analysis using bags or pseudo-bags. It involves instance sampling, feature representation, and decision-making. However, existing MIL-based technologies at least suffer from one or more of the following problems: 1) requiring high storage and intensive pre-processing for numerous instances (sampling); 2) potential over-fitting with limited knowledge to predict bag labels (feature representation); 3) pseudo-bag counts and prior biases affect model robustness and generalizability (decision-making). Inspired by clinical diagnostics, using the past sampling instances can facilitate the final WSI analysis, but it is barely explored in prior technologies. To break free these limitations, we integrate the dynamic instance sampling and reinforcement learning into a unified framework to improve the instance selection and feature aggregation, forming a novel Dynamic Policy Instance Selection (DPIS) scheme for better and more credible decision-making. Specifically, the measurement of feature distance and reward function are employed to boost continuous instance sampling. To alleviate the over-fitting, we explore the latent global relations among instances for more robust and discriminative feature representation while establishing reward and punishment mechanisms to correct biases in pseudo-bags using contrastive learning. These strategies form the final Dynamic Policy-Driven Adaptive Multi-Instance Learning (PAMIL) method for WSI tasks. Extensive experiments reveal that our PAMIL method outperforms the state-of-the-art by 3.8\% on CAMELYON16 and 4.4\% on TCGA lung cancer datasets.
Authors: Deshun Yang, Luhui Hu, Yu Tian, Zihao Li, Chris Kelly, Bang Yang, Cindy Yang, Yuexian Zou
Abstract: Several text-to-video diffusion models have demonstrated commendable capabilities in synthesizing high-quality video content. However, it remains a formidable challenge pertaining to maintaining temporal consistency and ensuring action smoothness throughout the generated sequences. In this paper, we present an innovative video generation AI agent that harnesses the power of Sora-inspired multimodal learning to build skilled world models framework based on textual prompts and accompanying images. The framework includes two parts: prompt enhancer and full video translation. The first part employs the capabilities of ChatGPT to meticulously distill and proactively construct precise prompts for each subsequent step, thereby guaranteeing the utmost accuracy in prompt communication and accurate execution in following model operations. The second part employ compatible with existing advanced diffusion techniques to expansively generate and refine the key frame at the conclusion of a video. Then we can expertly harness the power of leading and trailing key frames to craft videos with enhanced temporal consistency and action smoothness. The experimental results confirm that our method has strong effectiveness and novelty in constructing world models from text and image inputs over the other methods.
Authors: Jiuniu Wang, Zehua Du, Yuyuan Zhao, Bo Yuan, Kexiang Wang, Jian Liang, Yaxi Zhao, Yihen Lu, Gengliang Li, Junlong Gao, Xin Tu, Zhenyu Guo
Abstract: The Agent and AIGC (Artificial Intelligence Generated Content) technologies have recently made significant progress. We propose AesopAgent, an Agent-driven Evolutionary System on Story-to-Video Production. AesopAgent is a practical application of agent technology for multimodal content generation. The system integrates multiple generative capabilities within a unified framework, so that individual users can leverage these modules easily. This innovative system would convert user story proposals into scripts, images, and audio, and then integrate these multimodal contents into videos. Additionally, the animating units (e.g., Gen-2 and Sora) could make the videos more infectious. The AesopAgent system could orchestrate task workflow for video generation, ensuring that the generated video is both rich in content and coherent. This system mainly contains two layers, i.e., the Horizontal Layer and the Utility Layer. In the Horizontal Layer, we introduce a novel RAG-based evolutionary system that optimizes the whole video generation workflow and the steps within the workflow. It continuously evolves and iteratively optimizes workflow by accumulating expert experience and professional knowledge, including optimizing the LLM prompts and utilities usage. The Utility Layer provides multiple utilities, leading to consistent image generation that is visually coherent in terms of composition, characters, and style. Meanwhile, it provides audio and special effects, integrating them into expressive and logically arranged videos. Overall, our AesopAgent achieves state-of-the-art performance compared with many previous works in visual storytelling. Our AesopAgent is designed for convenient service for individual users, which is available on the following page: https://aesopai.github.io/.
Authors: Zijian Wu, Adam Schmidt, Peter Kazanzides, Septimiu E. Salcudean
Abstract: The Segment Anything Model (SAM) is a powerful vision foundation model that is revolutionizing the traditional paradigm of segmentation. Despite this, a reliance on prompting each frame and large computational cost limit its usage in robotically assisted surgery. Applications, such as augmented reality guidance, require little user intervention along with efficient inference to be usable clinically. In this study, we address these limitations by adopting lightweight SAM variants to meet the speed requirement and employing fine-tuning techniques to enhance their generalization in surgical scenes. Recent advancements in Tracking Any Point (TAP) have shown promising results in both accuracy and efficiency, particularly when points are occluded or leave the field of view. Inspired by this progress, we present a novel framework that combines an online point tracker with a lightweight SAM model that is fine-tuned for surgical instrument segmentation. Sparse points within the region of interest are tracked and used to prompt SAM throughout the video sequence, providing temporal consistency. The quantitative results surpass the state-of-the-art semi-supervised video object segmentation method on the EndoVis 2015 dataset, with an over 25 FPS inference speed running on a single GeForce RTX 4060 GPU.
Authors: Harsh Lunia, Ajoy Mondal, C V Jawahar
Abstract: The importance of Scene Text Recognition (STR) in today's increasingly digital world cannot be overstated. Given the significance of STR, data intensive deep learning approaches that auto-learn feature mappings have primarily driven the development of STR solutions. Several benchmark datasets and substantial work on deep learning models are available for Latin languages to meet this need. On more complex, syntactically and semantically, Indian languages spoken and read by 1.3 billion people, there is less work and datasets available. This paper aims to address the Indian space's lack of a comprehensive dataset by proposing the largest and most comprehensive real dataset - IndicSTR12 - and benchmarking STR performance on 12 major Indian languages. A few works have addressed the same issue, but to the best of our knowledge, they focused on a small number of Indian languages. The size and complexity of the proposed dataset are comparable to those of existing Latin contemporaries, while its multilingualism will catalyse the development of robust text detection and recognition models. It was created specifically for a group of related languages with different scripts. The dataset contains over 27000 word-images gathered from various natural scenes, with over 1000 word-images for each language. Unlike previous datasets, the images cover a broader range of realistic conditions, including blur, illumination changes, occlusion, non-iconic texts, low resolution, perspective text etc. Along with the new dataset, we provide a high-performing baseline on three models - PARSeq, CRNN, and STARNet.
Authors: Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew, Agata M. Wijata, Jakub Nalepa, Nicolas Long\'ep\'e, Przemyslaw Biecek
Abstract: Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for identifying and exposing potential flaws and biases. Since both fields advance independently, there is a notable gap in integrating red teaming strategies into RS. This paper introduces a methodology for examining ML models operating on hyperspectral images within the HYPERVIEW challenge, focusing on soil parameters' estimation. We use post-hoc explanation methods from the Explainable AI (XAI) domain to critically assess the best performing model that won the HYPERVIEW challenge and served as an inspiration for the model deployed on board the INTUITION-1 hyperspectral mission. Our approach effectively red teams the model by pinpointing and validating key shortcomings, constructing a model that achieves comparable performance using just 1% of the input features and a mere up to 5% performance loss. Additionally, we propose a novel way of visualizing explanations that integrate domain-specific information about hyperspectral bands (wavelengths) and data transformations to better suit interpreting models for hyperspectral image analysis.
Authors: Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Abstract: We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses only coordinates from bounding boxes to estimate an affinity score between pairs of tracks extracted from two distinct temporal windows. This module, named TWiX, is trained on sets of tracks with the objective of discriminating pairs of tracks coming from the same object from those which are not. Our module does not use the intersection over union measure, nor does it requires any motion priors or any camera motion compensation technique. By inserting TWiX within an online cascade matching pipeline, our tracker C-TWiX achieves state-of-the-art performance on the DanceTrack and KITTIMOT datasets, and gets competitive results on the MOT17 dataset. The code will be made available upon publication.
Authors: Yuelong Li, Yafei Mao, Raja Bala, Sunil Hadap
Abstract: We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification and renders the 3D object in the classified pose. The second stage performs regression to predict fine-grained residual pose within class. Connecting the two stages is a novel multi-scale residual correlation (MRC) layer that captures high-and-low level correspondences between the input image and rendering from first stage. MRC-Net employs a Siamese network with shared weights between both stages to learn embeddings for input and rendered images. To mitigate ambiguity when predicting discrete pose class labels on symmetric objects, we use soft probabilistic labels to define pose class in the first stage. We demonstrate state-of-the-art accuracy, outperforming all competing RGB-based methods on four challenging BOP benchmark datasets: T-LESS, LM-O, YCB-V, and ITODD. Our method is non-iterative and requires no complex post-processing.
Authors: Pranav Singh Chib, Pravendra Singh
Abstract: Accurate pedestrian trajectory prediction is crucial for various applications, and it requires a deep understanding of pedestrian motion patterns in dynamic environments. However, existing pedestrian trajectory prediction methods still need more exploration to fully leverage these motion patterns. This paper investigates the possibilities of using Large Language Models (LLMs) to improve pedestrian trajectory prediction tasks by inducing motion cues. We introduce LG-Traj, a novel approach incorporating LLMs to generate motion cues present in pedestrian past/observed trajectories. Our approach also incorporates motion cues present in pedestrian future trajectories by clustering future trajectories of training data using a mixture of Gaussians. These motion cues, along with pedestrian coordinates, facilitate a better understanding of the underlying representation. Furthermore, we utilize singular value decomposition to augment the observed trajectories, incorporating them into the model learning process to further enhance representation learning. Our method employs a transformer-based architecture comprising a motion encoder to model motion patterns and a social decoder to capture social interactions among pedestrians. We demonstrate the effectiveness of our approach on popular pedestrian trajectory prediction benchmarks, namely ETH-UCY and SDD, and present various ablation experiments to validate our approach.
Authors: Benjamin D. Killeen, Liam J. Wang, Han Zhang, Mehran Armand, Russell H. Taylor, Greg Osgood, Mathias Unberath
Abstract: Automated X-ray image segmentation would accelerate research and development in diagnostic and interventional precision medicine. Prior efforts have contributed task-specific models capable of solving specific image analysis problems, but the utility of these models is restricted to their particular task domain, and expanding to broader use requires additional data, labels, and retraining efforts. Recently, foundation models (FMs) -- machine learning models trained on large amounts of highly variable data thus enabling broad applicability -- have emerged as promising tools for automated image analysis. Existing FMs for medical image analysis focus on scenarios and modalities where objects are clearly defined by visually apparent boundaries, such as surgical tool segmentation in endoscopy. X-ray imaging, by contrast, does not generally offer such clearly delineated boundaries or structure priors. During X-ray image formation, complex 3D structures are projected in transmission onto the imaging plane, resulting in overlapping features of varying opacity and shape. To pave the way toward an FM for comprehensive and automated analysis of arbitrary medical X-ray images, we develop FluoroSAM, a language-aligned variant of the Segment-Anything Model, trained from scratch on 1.6M synthetic X-ray images. FluoroSAM is trained on data including masks for 128 organ types and 464 non-anatomical objects, such as tools and implants. In real X-ray images of cadaveric specimens, FluoroSAM is able to segment bony anatomical structures based on text-only prompting with 0.51 and 0.79 DICE with point-based refinement, outperforming competing SAM variants for all structures. FluoroSAM is also capable of zero-shot generalization to segmenting classes beyond the training set thanks to its language alignment, which we demonstrate for full lung segmentation on real chest X-rays.
Authors: Morteza Bodaghi, Majid Hosseini, Raju Gottumukkala
Abstract: Multimodal deep learning methods capture synergistic features from multiple modalities and have the potential to improve accuracy for stress detection compared to unimodal methods. However, this accuracy gain typically comes from high computational cost due to the high-dimensional feature spaces, especially for intermediate fusion. Dimensionality reduction is one way to optimize multimodal learning by simplifying data and making the features more amenable to processing and analysis, thereby reducing computational complexity. This paper introduces an intermediate multimodal fusion network with manifold learning-based dimensionality reduction. The multimodal network generates independent representations from biometric signals and facial landmarks through 1D-CNN and 2D-CNN. Finally, these features are fused and fed to another 1D-CNN layer, followed by a fully connected dense layer. We compared various dimensionality reduction techniques for different variations of unimodal and multimodal networks. We observe that the intermediate-level fusion with the Multi-Dimensional Scaling (MDS) manifold method showed promising results with an accuracy of 96.00\% in a Leave-One-Subject-Out Cross-Validation (LOSO-CV) paradigm over other dimensional reduction methods. MDS had the highest computational cost among manifold learning methods. However, while outperforming other networks, it managed to reduce the computational cost of the proposed networks by 25\% when compared to six well-known conventional feature selection methods used in the preprocessing step.
Authors: Daniel C. Stumpp, Himanshu Akolkar, Alan D. George, Ryad Benosman
Abstract: As the use of neuromorphic, event-based vision sensors expands, the need for compression of their output streams has increased. While their operational principle ensures event streams are spatially sparse, the high temporal resolution of the sensors can result in high data rates from the sensor depending on scene dynamics. For systems operating in communication-bandwidth-constrained and power-constrained environments, it is essential to compress these streams before transmitting them to a remote receiver. Therefore, we introduce a flow-based method for the real-time asynchronous compression of event streams as they are generated. This method leverages real-time optical flow estimates to predict future events without needing to transmit them, therefore, drastically reducing the amount of data transmitted. The flow-based compression introduced is evaluated using a variety of methods including spatiotemporal distance between event streams. The introduced method itself is shown to achieve an average compression ratio of 2.81 on a variety of event-camera datasets with the evaluation configuration used. That compression is achieved with a median temporal error of 0.48 ms and an average spatiotemporal event-stream distance of 3.07. When combined with LZMA compression for non-real-time applications, our method can achieve state-of-the-art average compression ratios ranging from 10.45 to 17.24. Additionally, we demonstrate that the proposed prediction algorithm is capable of performing real-time, low-latency event prediction.
Authors: Sudipta Banerjee, Sai Pranaswi Mullangi, Shruti Wagle, Chinmay Hegde, Nasir Memon
Abstract: Facial attribute editing using generative models can impair automated face recognition. This degradation persists even with recent identity-preserving models such as InstantID. To mitigate this issue, we propose two techniques that perform local and global attribute editing. Local editing operates on the finer details via a regularization-free method based on ControlNet conditioned on depth maps and auxiliary semantic segmentation masks. Global editing operates on coarser details via a regularization-based method guided by custom loss and regularization set. In this work, we empirically ablate twenty-six facial semantic, demographic and expression-based attributes altered using state-of-the-art generative models and evaluate them using ArcFace and AdaFace matchers on CelebA, CelebAMaskHQ and LFW datasets. Finally, we use LLaVA, a vision-language framework for attribute prediction to validate our editing techniques. Our methods outperform SoTA (BLIP, InstantID) at facial editing while retaining identity.
Authors: Hanning Chen, Wenjun Huang, Yang Ni, Sanggeon Yun, Fei Wen, Hugo Latapie, Mohsen Imani
Abstract: Task-oriented object detection aims to find objects suitable for accomplishing specific tasks. As a challenging task, it requires simultaneous visual data processing and reasoning under ambiguous semantics. Recent solutions are mainly all-in-one models. However, the object detection backbones are pre-trained without text supervision. Thus, to incorporate task requirements, their intricate models undergo extensive learning on a highly imbalanced and scarce dataset, resulting in capped performance, laborious training, and poor generalizability. In contrast, we propose TaskCLIP, a more natural two-stage design composed of general object detection and task-guided object selection. Particularly for the latter, we resort to the recently successful large Vision-Language Models (VLMs) as our backbone, which provides rich semantic knowledge and a uniform embedding space for images and texts. Nevertheless, the naive application of VLMs leads to sub-optimal quality, due to the misalignment between embeddings of object images and their visual attributes, which are mainly adjective phrases. To this end, we design a transformer-based aligner after the pre-trained VLMs to re-calibrate both embeddings. Finally, we employ a trainable score function to post-process the VLM matching results for object selection. Experimental results demonstrate that our TaskCLIP outperforms the state-of-the-art DETR-based model TOIST by 3.5% and only requires a single NVIDIA RTX 4090 for both training and inference.
Authors: Chensheng Peng, Chenfeng Xu, Yue Wang, Mingyu Ding, Heng Yang, Masayoshi Tomizuka, Kurt Keutzer, Marco Pavone, Wei Zhan
Abstract: Monocular SLAM has long grappled with the challenge of accurately modeling 3D geometries. Recent advances in Neural Radiance Fields (NeRF)-based monocular SLAM have shown promise, yet these methods typically focus on novel view synthesis rather than precise 3D geometry modeling. This focus results in a significant disconnect between NeRF applications, i.e., novel-view synthesis and the requirements of SLAM. We identify that the gap results from the volumetric representations used in NeRF, which are often dense and noisy. In this study, we propose a novel approach that reimagines volumetric representations through the lens of quadric forms. We posit that most scene components can be effectively represented as quadric planes. Leveraging this assumption, we reshape the volumetric representations with million of cubes by several quadric planes, which leads to more accurate and efficient modeling of 3D scenes in SLAM contexts. Our method involves two key steps: First, we use the quadric assumption to enhance coarse depth estimations obtained from tracking modules, e.g., Droid-SLAM. This step alone significantly improves depth estimation accuracy. Second, in the subsequent mapping phase, we diverge from previous NeRF-based SLAM methods that distribute sampling points across the entire volume space. Instead, we concentrate sampling points around quadric planes and aggregate them using a novel quadric-decomposed Transformer. Additionally, we introduce an end-to-end joint optimization strategy that synchronizes pose estimation with 3D reconstruction.
Authors: Alzayat Saleh, Alex Olsen, Jake Wood, Bronson Philippa, Mostafa Rahimi Azghadi
Abstract: Shadows significantly impact computer vision tasks, particularly in outdoor environments. State-of-the-art shadow removal methods are typically too computationally intensive for real-time image processing on edge hardware. We propose ShadowRemovalNet, a novel method designed for real-time image processing on resource-constrained hardware. ShadowRemovalNet achieves significantly higher frame rates compared to existing methods, making it suitable for real-time computer vision pipelines like those used in field robotics. Beyond speed, ShadowRemovalNet offers advantages in efficiency and simplicity, as it does not require a separate shadow mask during inference. ShadowRemovalNet also addresses challenges associated with Generative Adversarial Networks (GANs) for shadow removal, including artefacts, inaccurate mask estimations, and inconsistent supervision between shadow and boundary pixels. To address these limitations, we introduce a novel loss function that substantially reduces shadow removal errors. ShadowRemovalNet's efficiency and straightforwardness make it a robust and effective solution for real-time shadow removal in outdoor robotics and edge computing applications.
Authors: Ali Youssef, Francisco Vasconcelos
Abstract: Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition. While learning-based methods have surpassed traditional handcrafted techniques, their training often relies on simplistic homography-based simulations of multi-view perspectives, limiting model generalisability. This paper introduces a novel approach leveraging neural radiance fields (NeRFs) for realistic multi-view training data generation. We create a diverse multi-view dataset using NeRFs, consisting of indoor and outdoor scenes. Our proposed methodology adapts state-of-the-art feature detectors and descriptors to train on NeRF-synthesised views supervised by perspective projective geometry. Our experiments demonstrate that the proposed methods achieve competitive or superior performance on standard benchmarks for relative pose estimation, point cloud registration, and homography estimation while requiring significantly less training data compared to existing approaches.
Authors: Fuzhi Wu, Jiasong Wu, Youyong Kong, Chunfeng Yang, Guanyu Yang, Huazhong Shu, Guy Carrault, Lotfi Senhadji
Abstract: Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information present obstacles in certain tasks like interpreting global structures or managing smooth transition images. Despite the promising performance of transformer structures in numerous tasks, their intricate optimization complexities highlight the persistent need for refined CNN enhancements using limited resources. Responding to these complexities, we introduce a novel framework, the Multiscale Low-Frequency Memory (MLFM) Network, with the goal to harness the full potential of CNNs while keeping their complexity unchanged. The MLFM efficiently preserves low-frequency information, enhancing performance in targeted computer vision tasks. Central to our MLFM is the Low-Frequency Memory Unit (LFMU), which stores various low-frequency data and forms a parallel channel to the core network. A key advantage of MLFM is its seamless compatibility with various prevalent networks, requiring no alterations to their original core structure. Testing on ImageNet demonstrated substantial accuracy improvements in multiple 2D CNNs, including ResNet, MobileNet, EfficientNet, and ConvNeXt. Furthermore, we showcase MLFM's versatility beyond traditional image classification by successfully integrating it into image-to-image translation tasks, specifically in semantic segmentation networks like FCN and U-Net. In conclusion, our work signifies a pivotal stride in the journey of optimizing the efficacy and efficiency of CNNs with limited resources. This research builds upon the existing CNN foundations and paves the way for future advancements in computer vision. Our codes are available at https://github.com/AlphaWuSeu/ MLFM.
Authors: Zhonglin Sun, Chen Feng, Ioannis Patras, Georgios Tzimiropoulos
Abstract: In this work we focus on learning facial representations that can be adapted to train effective face recognition models, particularly in the absence of labels. Firstly, compared with existing labelled face datasets, a vastly larger magnitude of unlabeled faces exists in the real world. We explore the learning strategy of these unlabeled facial images through self-supervised pretraining to transfer generalized face recognition performance. Moreover, motivated by one recent finding, that is, the face saliency area is critical for face recognition, in contrast to utilizing random cropped blocks of images for constructing augmentations in pretraining, we utilize patches localized by extracted facial landmarks. This enables our method - namely LAndmark-based Facial Self-supervised learning LAFS), to learn key representation that is more critical for face recognition. We also incorporate two landmark-specific augmentations which introduce more diversity of landmark information to further regularize the learning. With learned landmark-based facial representations, we further adapt the representation for face recognition with regularization mitigating variations in landmark positions. Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks, especially on more challenging few-shot scenarios.
Authors: Haibo Zhang, Zhihua Yao, Kouichi Sakurai
Abstract: Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the defense can adapt to new and evolving attacks. Another important factor is the resources involved in terms of time and cost for training defense models and updating the model database. Training many models that are specific to each type of attack can be time-consuming and expensive. Ideally, we should be able to train one single model that can handle a wide range of attacks. It appears that a defense method based on image-to-image translation may be capable of this. The proposed versatile defense approach in this paper only requires training one model to effectively resist various unknown adversarial attacks. The trained model has successfully improved the classification accuracy from nearly zero to an average of 86%, performing better than other defense methods proposed in prior studies. When facing the PGD attack and the MI-FGSM attack, versatile defense model even outperforms the attack-specific models trained based on these two attacks. The robustness check also shows that our versatile defense model performs stably regardless with the attack strength.
Authors: Feng Xiao, Hongbin Xu, Qiuxia Wu, Wenxiong Kang
Abstract: 3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objects especially when multiple referred objects are involved in the description. Experiments show that direct matching of language and visual modal has limited capacity to comprehend complex referential relationships in utterances. It is mainly due to the interference caused by redundant visual information in cross-modal alignment. To strengthen relation-orientated mapping between different modalities, we propose SeCG, a semantic-enhanced relational learning model based on a graph network with our designed memory graph attention layer. Our method replaces original language-independent encoding with cross-modal encoding in visual analysis. More text-related feature expressions are obtained through the guidance of global semantics and implicit relationships. Experimental results on ReferIt3D and ScanRefer benchmarks show that the proposed method outperforms the existing state-of-the-art methods, particularly improving the localization performance for the multi-relation challenges.
Authors: Shuangjian Li, Tao Zhu, Mingxing Nie, Huansheng Ning, Zhenyu Liu, Liming Chen
Abstract: Traditional deep learning methods struggle to simultaneously segment, recognize, and forecast human activities from sensor data. This limits their usefulness in many fields such as healthcare and assisted living, where real-time understanding of ongoing and upcoming activities is crucial. This paper introduces P2LHAP, a novel Patch-to-Label Seq2Seq framework that tackles all three tasks in a efficient single-task model. P2LHAP divides sensor data streams into a sequence of "patches", served as input tokens, and outputs a sequence of patch-level activity labels including the predicted future activities. A unique smoothing technique based on surrounding patch labels, is proposed to identify activity boundaries accurately. Additionally, P2LHAP learns patch-level representation by sensor signal channel-independent Transformer encoders and decoders. All channels share embedding and Transformer weights across all sequences. Evaluated on three public datasets, P2LHAP significantly outperforms the state-of-the-art in all three tasks, demonstrating its effectiveness and potential for real-world applications.
Authors: Sicen Guo, Zhiyuan Wu, Qijun Chen, Ioannis Pitas, Rui Fan
Abstract: Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric prior knowledge acquired by a duplex-encoder teacher model into a single-encoder student model is a practical, albeit less explored research avenue. This paper delves into this topic and resorts to knowledge distillation approaches to address this problem. We introduce the Learning to Infuse "X" (LIX) framework, with novel contributions in both logit distillation and feature distillation aspects. We present a mathematical proof that underscores the limitation of using a single fixed weight in decoupled knowledge distillation and introduce a logit-wise dynamic weight controller as a solution to this issue. Furthermore, we develop an adaptively-recalibrated feature distillation algorithm, including two technical novelties: feature recalibration via kernel regression and in-depth feature consistency quantification via centered kernel alignment. Extensive experiments conducted with intermediate-fusion and late-fusion networks across various public datasets provide both quantitative and qualitative evaluations, demonstrating the superior performance of our LIX framework when compared to other state-of-the-art approaches.
Authors: Ruochen Zheng, Jiahao Hong, Changxin Gao, Nong Sang
Abstract: The presence of noise in acquired data invariably leads to performance degradation in cross-modal matching. Unfortunately, obtaining precise annotations in the multimodal field is expensive, which has prompted some methods to tackle the mismatched data pair issue in cross-modal matching contexts, termed as noisy correspondence. However, most of these existing noisy correspondence methods exhibit the following limitations: a) the problem of self-reinforcing error accumulation, and b) improper handling of noisy data pair. To tackle the two problems, we propose a generalized framework termed as Rank corrElation and noisy Pair hAlf-replacing wIth memoRy (REPAIR), which benefits from maintaining a memory bank for features of matched pairs. Specifically, we calculate the distances between the features in the memory bank and those of the target pair for each respective modality, and use the rank correlation of these two sets of distances to estimate the soft correspondence label of the target pair. Estimating soft correspondence based on memory bank features rather than using a similarity network can avoid the accumulation of errors due to incorrect network identifications. For pairs that are completely mismatched, REPAIR searches the memory bank for the most matching feature to replace one feature of one modality, instead of using the original pair directly or merely discarding the mismatched pair. We conduct experiments on three cross-modal datasets, i.e., Flickr30K, MSCOCO, and CC152K, proving the effectiveness and robustness of our REPAIR on synthetic and real-world noise.
Authors: Yusuke Marumo, Kazuhiko Kawamoto, Hiroshi Kera
Abstract: Not identical but similar objects are everywhere in the world. Examples include four-legged animals such as dogs and cats, cars of different models, akin flowers in various colors, and countless others. In this study, we address a novel task of matching such non-identical objects. We propose a simple weighting scheme of descriptors that enhance various sparse image matching methods, which are originally designed for matching identical objects captured from different perspectives, and achieve semantically robust matching. The experiments show successful matching between non-identical objects in various cases including domain shift. Further, we present a first evaluation of the robustness of the image matching methods under common corruptions, which is a sort of domain shift, and the proposed method improves the matching in this case as well.
Authors: Zezeng Li, Weimin Wang, Ziliang Wang, Na Lei
Abstract: This paper presents a novel point cloud compression method COT-PCC by formulating the task as a constrained optimal transport (COT) problem. COT-PCC takes the bitrate of compressed features as an extra constraint of optimal transport (OT) which learns the distribution transformation between original and reconstructed points. Specifically, the formulated COT is implemented with a generative adversarial network (GAN) and a bitrate loss for training. The discriminator measures the Wasserstein distance between input and reconstructed points, and a generator calculates the optimal mapping between distributions of input and reconstructed point cloud. Moreover, we introduce a learnable sampling module for downsampling in the compression procedure. Extensive results on both sparse and dense point cloud datasets demonstrate that COT-PCC outperforms state-of-the-art methods in terms of both CD and PSNR metrics. Source codes are available at \url{https://github.com/cognaclee/PCC-COT}.
Authors: Jiafu Chen, Wei Xing, Jiakai Sun, Tianyi Chu, Yiling Huang, Boyan Ji, Lei Zhao, Huaizhong Lin, Haibo Chen, Zhizhong Wang
Abstract: 3D scene stylization refers to transform the appearance of a 3D scene to match a given style image, ensuring that images rendered from different viewpoints exhibit the same style as the given style image, while maintaining the 3D consistency of the stylized scene. Several existing methods have obtained impressive results in stylizing 3D scenes. However, the models proposed by these methods need to be re-trained when applied to a new scene. In other words, their models are coupled with a specific scene and cannot adapt to arbitrary other scenes. To address this issue, we propose a novel 3D scene stylization framework to transfer an arbitrary style to an arbitrary scene, without any style-related or scene-related re-training. Concretely, we first map the appearance of the 3D scene into a 2D style pattern space, which realizes complete disentanglement of the geometry and appearance of the 3D scene and makes our model be generalized to arbitrary 3D scenes. Then we stylize the appearance of the 3D scene in the 2D style pattern space via a prompt-based 2D stylization algorithm. Experimental results demonstrate that our proposed framework is superior to SOTA methods in both visual quality and generalization.
Authors: Qing Lin, Jingfeng Zhang, Yew Soon Ong, Mengmi Zhang
Abstract: Despite the rapid progress in image generation, emotional image editing remains under-explored. The semantics, context, and structure of an image can evoke emotional responses, making emotional image editing techniques valuable for various real-world applications, including treatment of psychological disorders, commercialization of products, and artistic design. For the first time, we present a novel challenge of emotion-evoked image generation, aiming to synthesize images that evoke target emotions while retaining the semantics and structures of the original scenes. To address this challenge, we propose a diffusion model capable of effectively understanding and editing source images to convey desired emotions and sentiments. Moreover, due to the lack of emotion editing datasets, we provide a unique dataset consisting of 340,000 pairs of images and their emotion annotations. Furthermore, we conduct human psychophysics experiments and introduce four new evaluation metrics to systematically benchmark all the methods. Experimental results demonstrate that our method surpasses all competitive baselines. Our diffusion model is capable of identifying emotional cues from original images, editing images that elicit desired emotions, and meanwhile, preserving the semantic structure of the original images. All code, model, and data will be made public.
Authors: Minsoo Kim, Gi Pyo Nam, Haksub Kim, Haesol Park, Ig-Jae Kim
Abstract: In the realm of face image quality assesment (FIQA), method based on sample relative classification have shown impressive performance. However, the quality scores used as pseudo-labels assigned from images of classes with low intra-class variance could be unrelated to the actual quality in this method. To address this issue, we present IG-FIQA, a novel approach to guide FIQA training, introducing a weight parameter to alleviate the adverse impact of these classes. This method involves estimating sample intra-class variance at each iteration during training, ensuring minimal computational overhead and straightforward implementation. Furthermore, this paper proposes an on-the-fly data augmentation methodology for improved generalization performance in FIQA. On various benchmark datasets, our proposed method, IG-FIQA, achieved novel state-of-the-art (SOTA) performance.
Authors: Aman Kumar, Khushboo Anand, Shubham Mandloi, Ashutosh Mishra, Avinash Thakur, Neeraj Kasera, Prathosh A P
Abstract: Generative Adversarial Networks (GANs) have proven to exhibit remarkable performance and are widely used across many generative computer vision applications. However, the unprecedented demand for the deployment of GANs on resource-constrained edge devices still poses a challenge due to huge number of parameters involved in the generation process. This has led to focused attention on the area of compressing GANs. Most of the existing works use knowledge distillation with the overhead of teacher dependency. Moreover, there is no ability to control the degree of compression in these methods. Hence, we propose CoroNet-GAN for compressing GAN using the combined strength of differentiable pruning method via hypernetworks. The proposed method provides the advantage of performing controllable compression while training along with reducing training time by a substantial factor. Experiments have been done on various conditional GAN architectures (Pix2Pix and CycleGAN) to signify the effectiveness of our approach on multiple benchmark datasets such as Edges-to-Shoes, Horse-to-Zebra and Summer-to-Winter. The results obtained illustrate that our approach succeeds to outperform the baselines on Zebra-to-Horse and Summer-to-Winter achieving the best FID score of 32.3 and 72.3 respectively, yielding high-fidelity images across all the datasets. Additionally, our approach also outperforms the state-of-the-art methods in achieving better inference time on various smart-phone chipsets and data-types making it a feasible solution for deployment on edge devices.
Authors: Minje Kim, Tae-Kyun Kim
Abstract: Creating personalized hand avatars is important to offer a realistic experience to users on AR / VR platforms. While most prior studies focused on reconstructing 3D hand shapes, some recent work has tackled the reconstruction of hand textures on top of shapes. However, these methods are often limited to capturing pixels on the visible side of a hand, requiring diverse views of the hand in a video or multiple images as input. In this paper, we propose a novel method, BiTT(Bi-directional Texture reconstruction of Two hands), which is the first end-to-end trainable method for relightable, pose-free texture reconstruction of two interacting hands taking only a single RGB image, by three novel components: 1)\ bi-directional (left $\leftrightarrow$ right) texture reconstruction using the texture symmetry of left / right hands, 2) utilizing a texture parametric model for hand texture recovery, and 3)\ the overall coarse-to-fine stage pipeline for reconstructing personalized texture of two interacting hands. BiTT first estimates the scene light condition and albedo image from an input image, then reconstructs the texture of both hands through the texture parametric model and bi-directional texture reconstructor. In experiments using InterHand2.6M and RGB2Hands datasets, our method significantly outperforms state-of-the-art hand texture reconstruction methods quantitatively and qualitatively. The code is available at https://github.com/yunminjin2/BiTT
Authors: Jian Lin, Xueting Liu, Chengze Li, Minshan Xie, Tien-Tsin Wong
Abstract: While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty of generating high-quality shaded high-frequency screentones. The classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. The recent deep learning models enables the automatic generation by learning from a large-scale dataset. However, the state-of-the-art models still fail to generate high-quality shaded screentones due to the lack of a tailored model and high-quality manga training data. In this paper, we propose a novel sketch-to-manga framework that first generates a color illustration from the sketch and then generates a screentoned manga based on the intensity guidance. Our method significantly outperforms existing methods in generating high-quality manga with shaded high-frequency screentones.
Authors: Yue Ma, Yingqing He, Hongfa Wang, Andong Wang, Chenyang Qi, Chengfei Cai, Xiu Li, Zhifeng Li, Heung-Yeung Shum, Wei Liu, Qifeng Chen
Abstract: Despite recent advances in image-to-video generation, better controllability and local animation are less explored. Most existing image-to-video methods are not locally aware and tend to move the entire scene. However, human artists may need to control the movement of different objects or regions. Additionally, current I2V methods require users not only to describe the target motion but also to provide redundant detailed descriptions of frame contents. These two issues hinder the practical utilization of current I2V tools. In this paper, we propose a practical framework, named Follow-Your-Click, to achieve image animation with a simple user click (for specifying what to move) and a short motion prompt (for specifying how to move). Technically, we propose the first-frame masking strategy, which significantly improves the video generation quality, and a motion-augmented module equipped with a short motion prompt dataset to improve the short prompt following abilities of our model. To further control the motion speed, we propose flow-based motion magnitude control to control the speed of target movement more precisely. Our framework has simpler yet precise user control and better generation performance than previous methods. Extensive experiments compared with 7 baselines, including both commercial tools and research methods on 8 metrics, suggest the superiority of our approach. Project Page: https://follow-your-click.github.io/
Authors: Peini Guo, Mengyuan Liu, Hong Liu, Ruijia Fan, Guoquan Wang, Bin He
Abstract: Cloth-Changing Person Re-Identification (CC-ReID) aims to accurately identify the target person in more realistic surveillance scenarios, where pedestrians usually change their clothing. Despite great progress, limited cloth-changing training samples in existing CC-ReID datasets still prevent the model from adequately learning cloth-irrelevant features. In addition, due to the absence of explicit supervision to keep the model constantly focused on cloth-irrelevant areas, existing methods are still hampered by the disruption of clothing variations. To solve the above issues, we propose an Identity-aware Dual-constraint Network (IDNet) for the CC-ReID task. Specifically, to help the model extract cloth-irrelevant clues, we propose a Clothes Diversity Augmentation (CDA), which generates more realistic cloth-changing samples by enriching the clothing color while preserving the texture. In addition, a Multi-scale Constraint Block (MCB) is designed, which extracts fine-grained identity-related features and effectively transfers cloth-irrelevant knowledge. Moreover, a Counterfactual-guided Attention Module (CAM) is presented, which learns cloth-irrelevant features from channel and space dimensions and utilizes the counterfactual intervention for supervising the attention map to highlight identity-related regions. Finally, a Semantic Alignment Constraint (SAC) is designed to facilitate high-level semantic feature interaction. Comprehensive experiments on four CC-ReID datasets indicate that our method outperforms prior state-of-the-art approaches.
Authors: Long Lan, Fengxiang Wang, Shuyan Li, Xiangtao Zheng, Zengmao Wang, Xinwang Liu
Abstract: Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting the effectiveness of traditional supervised classification methods. Recent advancements in large pre-trained Vision-Language Models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning, particularly in understanding image content. This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories, which holds considerable significance in scenarios with restricted data due to cost or privacy constraints. Directly fine-tuning VLMs for RS-FGSC often encounters the challenge of overfitting the seen classes, resulting in suboptimal generalization to unseen classes, which highlights the difficulty in differentiating complex backgrounds and capturing distinct ship features. To address these issues, we introduce a novel prompt tuning technique that employs a hierarchical, multi-granularity prompt design. Our approach integrates remote sensing ship priors through bias terms, learned from a small trainable network. This strategy enhances the model's generalization capabilities while improving its ability to discern intricate backgrounds and learn discriminative ship features. Furthermore, we contribute to the field by introducing a comprehensive dataset, FGSCM-52, significantly expanding existing datasets with more extensive data and detailed annotations for less common ship classes. Extensive experimental evaluations demonstrate the superiority of our proposed method over current state-of-the-art techniques. The source code will be made publicly available.
Authors: Yukun Ma, Zikun Mao
Abstract: In daily life and industrial production, it is crucial to accurately detect changes in liquid level in containers. Traditional contact measurement methods have some limitations, while emerging non-contact image processing technology shows good application prospects. This paper proposes a container dynamic liquid level detection model based on U^2-Net. This model uses the SAM model to generate an initial data set, and then evaluates and filters out high-quality pseudo-label images through the SemiReward framework to build an exclusive data set. The model uses U^2-Net to extract mask images of containers from the data set, and uses morphological processing to compensate for mask defects. Subsequently, the model calculates the grayscale difference between adjacent video frame images at the same position, segments the liquid level change area by setting a difference threshold, and finally uses a lightweight neural network to classify the liquid level state. This approach not only mitigates the impact of intricate surroundings, but also reduces the demand for training data, showing strong robustness and versatility. A large number of experimental results show that the proposed model can effectively detect the dynamic liquid level changes of the liquid in the container, providing a novel and efficient solution for related fields.
Authors: Minsoo Kim, Min-Cheol Sagong, Gi Pyo Nam, Junghyun Cho, Ig-Jae Kim
Abstract: Deep learning-based face recognition continues to face challenges due to its reliance on huge datasets obtained from web crawling, which can be costly to gather and raise significant real-world privacy concerns. To address this issue, we propose VIGFace, a novel framework capable of generating synthetic facial images. Initially, we train the face recognition model using a real face dataset and create a feature space for both real and virtual IDs where virtual prototypes are orthogonal to other prototypes. Subsequently, we generate synthetic images by using the diffusion model based on the feature space. Our proposed framework provides two significant benefits. Firstly, it allows for creating virtual facial images without concerns about portrait rights, guaranteeing that the generated virtual face images are clearly differentiated from existing individuals. Secondly, it serves as an effective augmentation method by incorporating real existing images. Further experiments demonstrate the efficacy of our framework, achieving state-of-the-art results from both perspectives without any external data.
Authors: Zhonghan Zhao, Kewei Chen, Dongxu Guo, Wenhao Chai, Tian Ye, Yanting Zhang, Gaoang Wang
Abstract: Navigating complex environments in Minecraft poses significant challenges for multi-agent systems due to the game's dynamic and unpredictable open-world setting. Agents need to interact with the environment and coordinate their actions with other agents to achieve common objectives. However, traditional approaches often struggle to efficiently manage inter-agent communication and task distribution, which are crucial for effective multi-agent navigation. Furthermore, processing and integrating multi-modal information (such as visual, textual, and auditory data) is essential for agents to fully comprehend their goals and navigate the environment successfully. To address this issue, we design the HAS framework to auto-organize groups of LLM-based agents to complete Navigation tasks. In our approach, we devise a hierarchical auto-organizing navigation system, which is characterized by 1) a hierarchical system for multi-agent organization, ensuring centralized planning and decentralized execution; 2) an auto-organizing and intra-communication mechanism, enabling dynamic group adjustment under subtasks; 3) a multi-modal information platform, facilitating multi-modal perception to perform the three navigation tasks with one system. To assess organizational behavior, we design a series of navigation tasks in the Minecraft environment, which includes searching and exploring. We aim to develop embodied organizations that push the boundaries of embodied AI, moving it towards a more human-like organizational structure.
Authors: Dhruv Toshniwal, Saurabh Loya, Anuj Khot, Yash Marda
Abstract: In the rapidly evolving landscape of transportation, the proliferation of automobiles has made road traffic more complex, necessitating advanced vision-assisted technologies for enhanced safety and navigation. These technologies are imperative for providing critical traffic sign information, influencing driver behavior, and supporting vehicle control, especially for drivers with disabilities and in the burgeoning field of autonomous vehicles. Traffic sign detection and recognition have emerged as key areas of research due to their essential roles in ensuring road safety and compliance with traffic regulations. Traditional computer vision methods have faced challenges in achieving optimal accuracy and speed due to real-world variabilities. However, the advent of deep learning and Convolutional Neural Networks (CNNs) has revolutionized this domain, offering solutions that significantly surpass previous capabilities in terms of speed and reliability. This paper presents an innovative approach leveraging CNNs that achieves an accuracy of nearly 96\%, highlighting the potential for even greater precision through advanced localization techniques. Our findings not only contribute to the ongoing advancement of traffic sign recognition technology but also underscore the critical impact of these developments on road safety and the future of autonomous driving.
Authors: Can Liu, Jin Wang
Abstract: As a new distributed computing framework that can protect data privacy, federated learning (FL) has attracted more and more attention in recent years. It receives gradients from users to train the global model and releases the trained global model to working users. Nonetheless, the gradient inversion (GI) attack reflects the risk of privacy leakage in federated learning. Attackers only need to use gradients through hundreds of thousands of simple iterations to obtain relatively accurate private data stored on users' local devices. For this, some works propose simple but effective strategies to obtain user data under a single-label dataset. However, these strategies induce a satisfactory visual effect of the inversion image at the expense of higher time costs. Due to the semantic limitation of a single label, the image obtained by gradient inversion may have semantic errors. We present a novel gradient inversion strategy based on canny edge detection (MGIC) in both the multi-label and single-label datasets. To reduce semantic errors caused by a single label, we add new convolution layers' blocks in the trained model to obtain the image's multi-label. Through multi-label representation, serious semantic errors in inversion images are reduced. Then, we analyze the impact of parameters on the difficulty of input image reconstruction and discuss how image multi-subjects affect the inversion performance. Our proposed strategy has better visual inversion image results than the most widely used ones, saving more than 78% of time costs in the ImageNet dataset.
Authors: Tianyi Chu, Wei Xing, Jiafu Chen, Zhizhong Wang, Jiakai Sun, Lei Zhao, Haibo Chen, Huaizhong Lin
Abstract: Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or style transfer. On the other hand, GAN-based diverse image generative methods require retraining/fine-tuning the network or designing complex noise injection functions, which is computationally expensive, task-specific, or struggle to generate high-quality results. Given that many deterministic conditional image generative models have been able to produce high-quality yet fixed results, we raise an intriguing question: is it possible for pre-trained deterministic conditional image generative models to generate diverse results without changing network structures or parameters? To answer this question, we re-examine the conditional image generation tasks from the perspective of adversarial attack and propose a simple and efficient plug-in projected gradient descent (PGD) like method for diverse and controllable image generation. The key idea is attacking the pre-trained deterministic generative models by adding a micro perturbation to the input condition. In this way, diverse results can be generated without any adjustment of network structures or fine-tuning of the pre-trained models. In addition, we can also control the diverse results to be generated by specifying the attack direction according to a reference text or image. Our work opens the door to applying adversarial attack to low-level vision tasks, and experiments on various conditional image generation tasks demonstrate the effectiveness and superiority of the proposed method.
Authors: Hongbin Xu, Weitao Chen, Feng Xiao, Baigui Sun, Wenxiong Kang
Abstract: 4D style transfer aims at transferring arbitrary visual style to the synthesized novel views of a dynamic 4D scene with varying viewpoints and times. Existing efforts on 3D style transfer can effectively combine the visual features of style images and neural radiance fields (NeRF) but fail to handle the 4D dynamic scenes limited by the static scene assumption. Consequently, we aim to handle the novel challenging problem of 4D style transfer for the first time, which further requires the consistency of stylized results on dynamic objects. In this paper, we introduce StyleDyRF, a method that represents the 4D feature space by deforming a canonical feature volume and learns a linear style transformation matrix on the feature volume in a data-driven fashion. To obtain the canonical feature volume, the rays at each time step are deformed with the geometric prior of a pre-trained dynamic NeRF to render the feature map under the supervision of pre-trained visual encoders. With the content and style cues in the canonical feature volume and the style image, we can learn the style transformation matrix from their covariance matrices with lightweight neural networks. The learned style transformation matrix can reflect a direct matching of feature covariance from the content volume to the given style pattern, in analogy with the optimization of the Gram matrix in traditional 2D neural style transfer. The experimental results show that our method not only renders 4D photorealistic style transfer results in a zero-shot manner but also outperforms existing methods in terms of visual quality and consistency.
Authors: Hebeizi Li, Hongyu Yang, Di Huang
Abstract: Facial Expression Recognition (FER) has consistently been a focal point in the field of facial analysis. In the context of existing methodologies for 3D FER or 2D+3D FER, the extraction of expression features often gets entangled with identity information, compromising the distinctiveness of these features. To tackle this challenge, we introduce the innovative DrFER method, which brings the concept of disentangled representation learning to the field of 3D FER. DrFER employs a dual-branch framework to effectively disentangle expression information from identity information. Diverging from prior disentanglement endeavors in the 3D facial domain, we have carefully reconfigured both the loss functions and network structure to make the overall framework adaptable to point cloud data. This adaptation enhances the capability of the framework in recognizing facial expressions, even in cases involving varying head poses. Extensive evaluations conducted on the BU-3DFE and Bosphorus datasets substantiate that DrFER surpasses the performance of other 3D FER methods.
Authors: Cheng Cheng, Hang Wang, Hongbin Sun
Abstract: The prevalence of convolution neural networks (CNNs) and vision transformers (ViTs) has markedly revolutionized the area of single-image super-resolution (SISR). To further boost the SR performances, several techniques, such as residual learning and attention mechanism, are introduced, which can be largely attributed to a wider range of activated area, that is, the input pixels that strongly influence the SR results. However, the possibility of further improving SR performance through another versatile vision backbone remains an unresolved challenge. To address this issue, in this paper, we unleash the representation potential of the modern state space model, i.e., Vision Mamba (Vim), in the context of SISR. Specifically, we present three recipes for better utilization of Vim-based models: 1) Integration into a MetaFormer-style block; 2) Pre-training on a larger and broader dataset; 3) Employing complementary attention mechanism, upon which we introduce the MMA. The resulting network MMA is capable of finding the most relevant and representative input pixels to reconstruct the corresponding high-resolution images. Comprehensive experimental analysis reveals that MMA not only achieves competitive or even superior performance compared to state-of-the-art SISR methods but also maintains relatively low memory and computational overheads (e.g., +0.5 dB PSNR elevation on Manga109 dataset with 19.8 M parameters at the scale of 2). Furthermore, MMA proves its versatility in lightweight SR applications. Through this work, we aim to illuminate the potential applications of state space models in the broader realm of image processing rather than SISR, encouraging further exploration in this innovative direction.
Authors: Anton Agafonov, Lihi Zelnik-Manor
Abstract: In various applications, such as virtual reality and gaming, simulating the deformation of soft tissues in the human body during interactions with external objects is essential. Traditionally, Finite Element Methods (FEM) have been employed for this purpose, but they tend to be slow and resource-intensive. In this paper, we propose a unified representation of human body shape and soft tissue with a data-driven simulator of non-rigid deformations. This approach enables rapid simulation of realistic interactions. Our method builds upon the SMPL model, which generates human body shapes considering rigid transformations. We extend SMPL by incorporating a soft tissue layer and an intuitive representation of external forces applied to the body during object interactions. Specifically, we mapped the 3D body shape and soft tissue and applied external forces to 2D UV maps. Leveraging a UNET architecture designed for 2D data, our approach achieves high-accuracy inference in real time. Our experiment shows that our method achieves plausible deformation of the soft tissue layer, even for unseen scenarios.
Authors: Cheng Chen, Junchen Zhu, Xu Luo, Hengtao Shen, Lianli Gao, Jingkuan Song
Abstract: Instruction tuning represents a prevalent strategy employed by Multimodal Large Language Models (MLLMs) to align with human instructions and adapt to new tasks. Nevertheless, MLLMs encounter the challenge of adapting to users' evolving knowledge and demands. Therefore, how to retain existing skills while acquiring new knowledge needs to be investigated. In this paper, we present a comprehensive benchmark, namely Continual Instruction tuNing (CoIN), to assess existing MLLMs in the sequential instruction tuning paradigm. CoIN comprises 10 commonly used datasets spanning 8 task categories, ensuring a diverse range of instructions and tasks. Besides, the trained model is evaluated from two aspects: Instruction Following and General Knowledge, which assess the alignment with human intention and knowledge preserved for reasoning, respectively. Experiments on CoIN demonstrate that current powerful MLLMs still suffer catastrophic forgetting, and the failure in intention alignment assumes the main responsibility, instead of the knowledge forgetting. To this end, we introduce MoELoRA to MLLMs which is effective to retain the previous instruction alignment. Experimental results consistently illustrate the forgetting decreased from this method on CoIN.
Authors: Luyuan Peng, Hari Vishnu, Mandar Chitre, Yuen Min Too, Bharath Kalyan, Rajat Mishra
Abstract: We investigate the performance of image-based pose regressor models in underwater environments for relocalization. Leveraging PoseNet and PoseLSTM, we regress a 6-degree-of-freedom pose from single RGB images with high accuracy. Additionally, we explore data augmentation with stereo camera images to improve model accuracy. Experimental results demonstrate that the models achieve high accuracy in both simulated and clear waters, promising effective real-world underwater navigation and inspection applications.
Authors: L. Papa, P. Russo, I. Amerini
Abstract: Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years, owing to the potential benefits of this methodology in overcoming the limitations of active depth sensing systems. Moreover, due to the low cost and size of monocular cameras, researchers have focused their attention on monocular depth estimation (MDE), which consists in estimating a dense depth map from a single RGB video frame. State of the art MDE models typically rely on vision transformers (ViT) architectures that are highly deep and complex, making them unsuitable for fast inference on devices with hardware constraints. Purposely, in this paper, we address the problem of exploiting ViT in MDE on embedded devices. Those systems are usually characterized by limited memory capabilities and low-power CPU/GPU. We propose METER, a novel lightweight vision transformer architecture capable of achieving state of the art estimations and low latency inference performances on the considered embedded hardwares: NVIDIA Jetson TX1 and NVIDIA Jetson Nano. We provide a solution consisting of three alternative configurations of METER, a novel loss function to balance pixel estimation and reconstruction of image details, and a new data augmentation strategy to improve the overall final predictions. The proposed method outperforms previous lightweight works over the two benchmark datasets: the indoor NYU Depth v2 and the outdoor KITTI.
Authors: Lu Jiang, Qi Wang, Yuhang Chang, Jianing Song, Haoyue Fu
Abstract: Category imbalance is one of the most popular and important issues in the domain of classification. In this paper, we present a new generalized framework with Adaptive Weight function for soft-margin Weighted SVM (AW-WSVM), which aims to enhance the issue of imbalance and outlier sensitivity in standard support vector machine (SVM) for classifying two-class data. The weight coefficient is introduced into the unconstrained soft-margin support vector machines, and the sample weights are updated before each training. The Adaptive Weight function (AW function) is constructed from the distance between the samples and the decision hyperplane, assigning different weights to each sample. A weight update method is proposed, taking into account the proximity of the support vectors to the decision hyperplane. Before training, the weights of the corresponding samples are initialized according to different categories. Subsequently, the samples close to the decision hyperplane are identified and assigned more weights. At the same time, lower weights are assigned to samples that are far from the decision hyperplane. Furthermore, we also put forward an effective way to eliminate noise. To evaluate the strength of the proposed generalized framework, we conducted experiments on standard datasets and emotion classification datasets with different imbalanced ratios (IR). The experimental results prove that the proposed generalized framework outperforms in terms of accuracy, recall metrics and G-mean, validating the effectiveness of the weighted strategy provided in this paper in enhancing support vector machines.
Authors: Haoqing Li, Jinfu Yang, Yifei Xu, Runshi Wang
Abstract: Infrared Small Target Detection (IRSTD) aims to segment small targets from infrared clutter background. Existing methods mainly focus on discriminative approaches, i.e., a pixel-level front-background binary segmentation. Since infrared small targets are small and low signal-to-clutter ratio, empirical risk has few disturbances when a certain false alarm and missed detection exist, which seriously affect the further improvement of such methods. Motivated by the dense prediction generative methods, in this paper, we propose a diffusion model framework for Infrared Small Target Detection which compensates pixel-level discriminant with mask posterior distribution modeling. Furthermore, we design a Low-frequency Isolation in the wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets. Code are available at https://github.com/Li-Haoqing/IRSTD-Diff.
Authors: Pengze Zhang, Hubery Yin, Chen Li, Xiaohua Xie
Abstract: Most diffusion models assume that the reverse process adheres to a Gaussian distribution. However, this approximation has not been rigorously validated, especially at singularities, where t=0 and t=1. Improperly dealing with such singularities leads to an average brightness issue in applications, and limits the generation of images with extreme brightness or darkness. We primarily focus on tackling singularities from both theoretical and practical perspectives. Initially, we establish the error bounds for the reverse process approximation, and showcase its Gaussian characteristics at singularity time steps. Based on this theoretical insight, we confirm the singularity at t=1 is conditionally removable while it at t=0 is an inherent property. Upon these significant conclusions, we propose a novel plug-and-play method SingDiffusion to address the initial singular time step sampling, which not only effectively resolves the average brightness issue for a wide range of diffusion models without extra training efforts, but also enhances their generation capability in achieving notable lower FID scores. Code and models are released at https://github.com/PangzeCheung/SingDiffusion.
Authors: Can Liu, Jin Wang, Dongyang Yu
Abstract: Federated learning (FL) empowers privacy-preservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to the gradient inversion (GI) attack which can reconstruct ground-truth training data such as images based on model gradients. However, reconstructing high-resolution images by existing GI attack works faces two challenges: inferior accuracy and slow-convergence, especially when the context is complicated, e.g., the training batch size is much greater than 1 on each FL user. To address these challenges, we present a Robust, Accurate and Fast-convergent GI attack algorithm, called RAF-GI, with two components: 1) Additional Convolution Block (ACB) which can restore labels with up to 20% improvement compared with existing works; 2) Total variance, three-channel mEan and cAnny edge detection regularization term (TEA), which is a white-box attack strategy to reconstruct images based on labels inferred by ACB. Moreover, RAF-GI is robust that can still accurately reconstruct ground-truth data when the users' training batch size is no more than 48. Our experimental results manifest that RAF-GI can diminish 94% time costs while achieving superb inversion quality in ImageNet dataset. Notably, with a batch size of 1, RAF-GI exhibits a 7.89 higher Peak Signal-to-Noise Ratio (PSNR) compared to the state-of-the-art baselines.
Authors: M Rakesh Reddy, Shubham Mandloi, Aman Kumar
Abstract: Moire pattern frequently appears in photographs captured with mobile devices and digital cameras, potentially degrading image quality. Despite recent advancements in computer vision, image demoire'ing remains a challenging task due to the dynamic textures and variations in colour, shape, and frequency of moire patterns. Most existing methods struggle to generalize to unseen datasets, limiting their effectiveness in removing moire patterns from real-world scenarios. In this paper, we propose a novel lightweight architecture, AADNet (Attention Aware Demoireing Network), for high-resolution image demoire'ing that effectively works across different frequency bands and generalizes well to unseen datasets. Extensive experiments conducted on the UHDM dataset validate the effectiveness of our approach, resulting in high-fidelity images.
Authors: Shuhan Li, Yi Lin, Hao Chen, Kwang-Ting Cheng
Abstract: Accurate and robust classification of diseases is important for proper diagnosis and treatment. However, medical datasets often face challenges related to limited sample sizes and inherent imbalanced distributions, due to difficulties in data collection and variations in disease prevalence across different types. In this paper, we introduce an Iterative Online Image Synthesis (IOIS) framework to address the class imbalance problem in medical image classification. Our framework incorporates two key modules, namely Online Image Synthesis (OIS) and Accuracy Adaptive Sampling (AAS), which collectively target the imbalance classification issue at both the instance level and the class level. The OIS module alleviates the data insufficiency problem by generating representative samples tailored for online training of the classifier. On the other hand, the AAS module dynamically balances the synthesized samples among various classes, targeting those with low training accuracy. To evaluate the effectiveness of our proposed method in addressing imbalanced classification, we conduct experiments on the HAM10000 and APTOS datasets. The results obtained demonstrate the superiority of our approach over state-of-the-art methods as well as the effectiveness of each component. The source code will be released upon acceptance.
Authors: Wensheng Liang, Ruiyan Zhuang, Xianwei Shi, Shuai Li, Zhicheng Wang, Xiaoguang Ma
Abstract: Industrial managements, including quality control, cost and safety optimization, etc., heavily rely on high quality industrial human action recognitions (IHARs) which were hard to be implemented in large-scale industrial scenes due to their high costs and poor real-time performance. In this paper, we proposed a large-scale foundation model(LSFM)-based IHAR method, wherein various LSFMs and lightweight methods were jointly used, for the first time, to fulfill low-cost dataset establishment and real-time IHARs. Comprehensive tests on in-situ large-scale industrial manufacturing lines elucidated that the proposed method realized great reduction on employment costs, superior real-time performance, and satisfactory accuracy and generalization capabilities, indicating its great potential as a backbone IHAR method, especially for large-scale industrial applications.
Authors: Zicheng Zhang, Tong Zhang, Yi Zhu, Jianzhuang Liu, Xiaodan Liang, QiXiang Ye, Wei Ke
Abstract: The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness, prevailing methods within this paradigm encounter challenges, including overfitting on seen classes and small fragmentation in masks. To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information.Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Moreover, to circumvent noisy alignments from the vision part due to its redundant nature, we introduce route attention into self-attention for finding visual consensus, thereby enhancing semantic consistency within the same object. Equipped with a vision-language prompting strategy, our approach significantly boosts the generalization capacity of segmentation models for unseen classes. Experimental results underscore the effectiveness of our approach, showcasing mIoU gains of 4.5 on the PASCAL VOC 2012 and 3.6 on the COCO-Stuff 164k for unseen classes compared with the state-of-the-art methods.
Authors: Yuxin Tian, Mouxing Yang, Yunfan Li, Dayiheng Liu, Xingzhang Ren, Xi Peng, Jiancheng Lv
Abstract: Recent studies applied Parameter Efficient Fine-Tuning techniques (PEFTs) to efficiently narrow the performance gap between pre-training and downstream. There are two important factors for various PEFTs, namely, the accessible data size and fine-tunable parameter size. A natural expectation for PEFTs is that the performance of various PEFTs is positively related to the data size and fine-tunable parameter size. However, according to the evaluation of five PEFTs on two downstream vision-language (VL) tasks, we find that such an intuition holds only if the downstream data and task are not consistent with pre-training. For downstream fine-tuning consistent with pre-training, data size no longer affects the performance, while the influence of fine-tunable parameter size is not monotonous. We believe such an observation could guide the choice of training strategy for various PEFTs.
Authors: Tuomas Varanka, Tapani Toivonen, Soumya Tripathy, Guoying Zhao, Erman Acar
Abstract: Recent developments in face restoration have achieved remarkable results in producing high-quality and lifelike outputs. The stunning results however often fail to be faithful with respect to the identity of the person as the models lack necessary context. In this paper, we explore the potential of personalized face restoration with diffusion models. In our approach a restoration model is personalized using a few images of the identity, leading to tailored restoration with respect to the identity while retaining fine-grained details. By using independent trainable blocks for personalization, the rich prior of a base restoration model can be exploited to its fullest. To avoid the model relying on parts of identity left in the conditioning low-quality images, a generative regularizer is employed. With a learnable parameter, the model learns to balance between the details generated based on the input image and the degree of personalization. Moreover, we improve the training pipeline of face restoration models to enable an alignment-free approach. We showcase the robust capabilities of our approach in several real-world scenarios with multiple identities, demonstrating our method's ability to generate fine-grained details with faithful restoration. In the user study we evaluate the perceptual quality and faithfulness of the genereated details, with our method being voted best 61% of the time compared to the second best with 25% of the votes.
Authors: Xuanpu Zhang, Dan Song, Pengxin Zhan, Qingguo Chen, Kuilong Liu, Anan Liu
Abstract: Image-based virtual try-on aims to transfer target in-shop clothing to a dressed model image, the objectives of which are totally taking off original clothing while preserving the contents outside of the try-on area, naturally wearing target clothing and correctly inpainting the gap between target clothing and original clothing. Tremendous efforts have been made to facilitate this popular research area, but cannot keep the type of target clothing with the try-on area affected by original clothing. In this paper, we focus on the unpaired virtual try-on situation where target clothing and original clothing on the model are different, i.e., the practical scenario. To break the correlation between the try-on area and the original clothing and make the model learn the correct information to inpaint, we propose an adaptive mask training paradigm that dynamically adjusts training masks. It not only improves the alignment and fit of clothing but also significantly enhances the fidelity of virtual try-on experience. Furthermore, we for the first time propose two metrics for unpaired try-on evaluation, the Semantic-Densepose-Ratio (SDR) and Skeleton-LPIPS (S-LPIPS), to evaluate the correctness of clothing type and the accuracy of clothing texture. For unpaired try-on validation, we construct a comprehensive cross-try-on benchmark (Cross-27) with distinctive clothing items and model physiques, covering a broad try-on scenarios. Experiments demonstrate the effectiveness of the proposed methods, contributing to the advancement of virtual try-on technology and offering new insights and tools for future research in the field. The code, model and benchmark will be publicly released.
Authors: Ruibin Zhang, Donglai Xue, Yuhan Wang, Ruixu Geng, Fei Gao
Abstract: Millimeter wave (mmWave) radars have attracted significant attention from both academia and industry due to their capability to operate in extreme weather conditions. However, they face challenges in terms of sparsity and noise interference, which hinder their application in the field of micro aerial vehicle (MAV) autonomous navigation. To this end, this paper proposes a novel approach to dense and accurate mmWave radar point cloud construction via cross-modal learning. Specifically, we introduce diffusion models, which possess state-of-the-art performance in generative modeling, to predict LiDAR-like point clouds from paired raw radar data. We also incorporate the most recent diffusion model inference accelerating techniques to ensure that the proposed method can be implemented on MAVs with limited computing resources.We validate the proposed method through extensive benchmark comparisons and real-world experiments, demonstrating its superior performance and generalization ability. Code and pretrained models will be available at https://github.com/ZJU-FAST-Lab/Radar-Diffusion.
Authors: Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying Wei
Abstract: Conventional wisdom suggests parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the best of both worlds, meta-tuning introduces a subsequent optimization stage of foundation models but has so far only shown limited success and crucially tends to underperform on out-of-domain (OOD) tasks. In this paper, we introduce Sparse MetA-Tuning (SMAT), a method inspired by sparse mixture-of-experts approaches and trained to isolate subsets of pre-trained parameters automatically for meta-tuning on each task. SMAT successfully overcomes OOD sensitivity and delivers on the promise of enhancing the transfer abilities of vision foundation models beyond parameter-efficient finetuning. We establish new state-of-the-art results on a challenging combination of Meta-Dataset augmented with additional OOD tasks in both zero-shot and gradient-based adaptation settings. In addition, we provide a thorough analysis of the superiority of learned over hand-designed sparsity patterns for sparse expert methods and the pivotal importance of the sparsity level in balancing between in-domain and out-of-domain generalization. Our code is publicly available.
Authors: Xiaomeng Fu, Xi Wang, Qiao Li, Jin Liu, Jiao Dai, Jizhong Han
Abstract: Diffusion models pose risks of privacy breaches and copyright disputes, primarily stemming from the potential utilization of unauthorized data during the training phase. The Training Membership Inference (TMI) task aims to determine whether a specific sample has been used in the training process of a target model, representing a critical tool for privacy violation verification. However, the increased stochasticity inherent in diffusion renders traditional shadow-model-based or metric-based methods ineffective when applied to diffusion models. Moreover, existing methods only yield binary classification labels which lack necessary comprehensibility in practical applications. In this paper, we explore a novel perspective for the TMI task by leveraging the intrinsic generative priors within the diffusion model. Compared with unseen samples, training samples exhibit stronger generative priors within the diffusion model, enabling the successful reconstruction of substantially degraded training images. Consequently, we propose the Degrade Restore Compare (DRC) framework. In this framework, an image undergoes sequential degradation and restoration, and its membership is determined by comparing it with the restored counterpart. Experimental results verify that our approach not only significantly outperforms existing methods in terms of accuracy but also provides comprehensible decision criteria, offering evidence for potential privacy violations.
Authors: Abhishek Saroha, Mariia Gladkova, Cecilia Curreli, Tarun Yenamandra, Daniel Cremers
Abstract: Scene stylization extends the work of neural style transfer to three spatial dimensions. A vital challenge in this problem is to maintain the uniformity of the stylized appearance across a multi-view setting. A vast majority of the previous works achieve this by optimizing the scene with a specific style image. In contrast, we propose a novel architecture trained on a collection of style images, that at test time produces high quality stylized novel views. Our work builds up on the framework of 3D Gaussian splatting. For a given scene, we take the pretrained Gaussians and process them using a multi resolution hash grid and a tiny MLP to obtain the conditional stylised views. The explicit nature of 3D Gaussians give us inherent advantages over NeRF-based methods including geometric consistency, along with having a fast training and rendering regime. This enables our method to be useful for vast practical use cases such as in augmented or virtual reality applications. Through our experiments, we show our methods achieve state-of-the-art performance with superior visual quality on various indoor and outdoor real-world data.
Authors: Zongqing Qi, Danqing Ma, Jingyu Xu, Ao Xiang, Hedi Qu
Abstract: In recent years, there have been frequent incidents of foreign objects intruding into railway and Airport runways. These objects can include pedestrians, vehicles, animals, and debris. This paper introduces an improved YOLOv5 architecture incorporating FasterNet and attention mechanisms to enhance the detection of foreign objects on railways and Airport runways. This study proposes a new dataset, AARFOD (Aero and Rail Foreign Object Detection), which combines two public datasets for detecting foreign objects in aviation and railway systems.The dataset aims to improve the recognition capabilities of foreign object targets. Experimental results on this large dataset have demonstrated significant performance improvements of the proposed model over the baseline YOLOv5 model, reducing computational requirements.Improved YOLO model shows a significant improvement in precision by 1.2%, recall rate by 1.0%, and mAP@.5 by 0.6%, while mAP@.5-.95 remained unchanged. The parameters were reduced by approximately 25.12%, and GFLOPs were reduced by about 10.63%. In the ablation experiment, it is found that the FasterNet module can significantly reduce the number of parameters of the model, and the reference of the attention mechanism can slow down the performance loss caused by lightweight.
Authors: Christos Papadimitriou, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou
Abstract: Story Visualization (SV) is a challenging generative vision task, that requires both visual quality and consistency between different frames in generated image sequences. Previous approaches either employ some kind of memory mechanism to maintain context throughout an auto-regressive generation of the image sequence, or model the generation of the characters and their background separately, to improve the rendering of characters. On the contrary, we embrace a completely parallel transformer-based approach, exclusively relying on Cross-Attention with past and future captions to achieve consistency. Additionally, we propose a Character Guidance technique to focus on the generation of characters in an implicit manner, by forming a combination of text-conditional and character-conditional logits in the logit space. We also employ a caption-augmentation technique, carried out by a Large Language Model (LLM), to enhance the robustness of our approach. The combination of these methods culminates into state-of-the-art (SOTA) results over various metrics in the most prominent SV benchmark (Pororo-SV), attained with constraint resources while achieving superior computational complexity compared to previous arts. The validity of our quantitative results is supported by a human survey.
Authors: Hao Shi, Song Wang, Jiaming Zhang, Xiaoting Yin, Zhongdao Wang, Zhijian Zhao, Guangming Wang, Jianke Zhu, Kailun Yang, Kaiwei Wang
Abstract: Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation, continuity across varying viewpoints, and single-view occlusion. Our paper introduces OccFiner, a novel offboard framework designed to enhance the accuracy of vision-based occupancy predictions. OccFiner operates in two hybrid phases: 1) a multi-to-multi local propagation network that implicitly aligns and processes multiple local frames for correcting onboard model errors and consistently enhancing occupancy accuracy across all distances. 2) the region-centric global propagation, focuses on refining labels using explicit multi-view geometry and integrating sensor bias, especially to increase the accuracy of distant occupied voxels. Extensive experiments demonstrate that OccFiner improves both geometric and semantic accuracy across various types of coarse occupancy, setting a new state-of-the-art performance on the SemanticKITTI dataset. Notably, OccFiner elevates vision-based SSC models to a level even surpassing that of LiDAR-based onboard SSC models.
Authors: Ao Xiang, Zongqing Qi, Han Wang, Qin Yang, Danqing Ma
Abstract: In recent years, there have been frequent incidents of foreign objects intruding into railway and Airport runways. These objects can include pedestrians, vehicles, animals, and debris. This paper introduces an improved YOLOv5 architecture incorporating FasterNet and attention mechanisms to enhance the detection of foreign objects on railways and Airport runways. This study proposes a new dataset, AARFOD (Aero and Rail Foreign Object Detection), which combines two public datasets for detecting foreign objects in aviation and railway systems. The dataset aims to improve the recognition capabilities of foreign object targets. Experimental results on this large dataset have demonstrated significant performance improvements of the proposed model over the baseline YOLOv5 model, reducing computational requirements. improved YOLO model shows a significant improvement in precision by 1.2%, recall rate by 1.0%, and mAP@.5 by 0.6%, while mAP@.5-.95 remained unchanged. The parameters were reduced by approximately 25.12%, and GFLOPs were reduced by about 10.63%. In the ablation experiment, it is found that the FasterNet module can significantly reduce the number of parameters of the model, and the reference of the attention mechanism can slow down the performance loss caused by lightweight.
Authors: Zikun Xu, Jianqiang Wang, Shaobing Xu
Abstract: LiDAR-based 3D perception algorithms have evolved rapidly alongside the emergence of large datasets. Nonetheless, considerable performance degradation often ensues when models trained on a specific dataset are applied to other datasets or real-world scenarios with different LiDAR. This paper aims to develop a unified model capable of handling different LiDARs, enabling continual learning across diverse LiDAR datasets and seamless deployment across heterogeneous platforms. We observe that the gaps among datasets primarily manifest in geometric disparities (such as variations in beams and point counts) and semantic inconsistencies (taxonomy conflicts). To this end, this paper proposes UniLiDAR, an occupancy prediction pipeline that leverages geometric realignment and semantic label mapping to facilitate multiple datasets training and mitigate performance degradation during deployment on heterogeneous platforms. Moreover, our method can be easily combined with existing 3D perception models. The efficacy of the proposed approach in bridging LiDAR domain gaps is verified by comprehensive experiments on two prominent datasets: OpenOccupancy-nuScenes and SemanticKITTI. UniLiDAR elevates the mIoU of occupancy prediction by 15.7% and 12.5%, respectively, compared to the model trained on the directly merged dataset. Moreover, it outperforms several SOTA methods trained on individual datasets. We expect our research to facilitate further study of 3D generalization, the code will be available soon.
Authors: Junior Silva Souza, Eduardo Bedin, Gabriel Toshio Hirokawa Higa, Newton Loebens, Hemerson Pistori
Abstract: The development of techniques that can be used to analyze and detect animal behavior is a crucial activity for the livestock sector, as it is possible to monitor the stress and animal welfare and contributes to decision making in the farm. Thus, the development of applications can assist breeders in making decisions to improve production performance and reduce costs, once the animal behavior is analyzed by humans and this can lead to susceptible errors and time consumption. Aggressiveness in pigs is an example of behavior that is studied to reduce its impact through animal classification and identification. However, this process is laborious and susceptible to errors, which can be reduced through automation by visually classifying videos captured in controlled environment. The captured videos can be used for training and, as a result, for classification through computer vision and artificial intelligence, employing neural network techniques. The main techniques utilized in this study are variants of transformers: STAM, TimeSformer, and ViViT, as well as techniques using convolutions, such as ResNet3D2, Resnet(2+1)D, and CnnLstm. These techniques were employed for pig video classification with the objective of identifying aggressive and non-aggressive behaviors. In this work, various techniques were compared to analyze the contribution of using transformers, in addition to the effectiveness of the convolution technique in video classification. The performance was evaluated using accuracy, precision, and recall. The TimerSformer technique showed the best results in video classification, with median accuracy of 0.729.
Authors: Francesco Dibitonto, Fabio Garcea, Andr\'e Panisson, Alan Perotti, Lia Morra
Abstract: Convolutional Neural Networks (CNNs) are nowadays the model of choice in Computer Vision, thanks to their ability to automatize the feature extraction process in visual tasks. However, the knowledge acquired during training is fully subsymbolic, and hence difficult to understand and explain to end users. In this paper, we propose a new technique called HOLMES (HOLonym-MEronym based Semantic inspection) that decomposes a label into a set of related concepts, and provides component-level explanations for an image classification model. Specifically, HOLMES leverages ontologies, web scraping and transfer learning to automatically construct meronym (parts)-based detectors for a given holonym (class). Then, it produces heatmaps at the meronym level and finally, by probing the holonym CNN with occluded images, it highlights the importance of each part on the classification output. Compared to state-of-the-art saliency methods, HOLMES takes a step further and provides information about both where and what the holonym CNN is looking at, without relying on densely annotated datasets and without forcing concepts to be associated to single computational units. Extensive experimental evaluation on different categories of objects (animals, tools and vehicles) shows the feasibility of our approach. On average, HOLMES explanations include at least two meronyms, and the ablation of a single meronym roughly halves the holonym model confidence. The resulting heatmaps were quantitatively evaluated using the deletion/insertion/preservation curves. All metrics were comparable to those achieved by GradCAM, while offering the advantage of further decomposing the heatmap in human-understandable concepts, thus highlighting both the relevance of meronyms to object classification, as well as HOLMES ability to capture it. The code is available at https://github.com/FrancesC0de/HOLMES.
Authors: Yifei Gao, Jiaqi Wang, Zhiyu Lin, Jitao Sang
Abstract: The evolution of Artificial Intelligence Generated Contents (AIGCs) is advancing towards higher quality. The growing interactions with AIGCs present a new challenge to the data-driven AI community: While AI-generated contents have played a crucial role in a wide range of AI models, the potential hidden risks they introduce have not been thoroughly examined. Beyond human-oriented forgery detection, AI-generated content poses potential issues for AI models originally designed to process natural data. In this study, we underscore the exacerbated hallucination phenomena in Large Vision-Language Models (LVLMs) caused by AI-synthetic images. Remarkably, our findings shed light on a consistent AIGC \textbf{hallucination bias}: the object hallucinations induced by synthetic images are characterized by a greater quantity and a more uniform position distribution, even these synthetic images do not manifest unrealistic or additional relevant visual features compared to natural images. Moreover, our investigations on Q-former and Linear projector reveal that synthetic images may present token deviations after visual projection, thereby amplifying the hallucination bias.
Authors: Yihao Liu, Feng Xue, Anlong Ming
Abstract: The generalization of monocular metric depth estimation (MMDE) has been a longstanding challenge. Recent methods made progress by combining relative and metric depth or aligning input image focal length. However, they are still beset by challenges in camera, scene, and data levels: (1) Sensitivity to different cameras; (2) Inconsistent accuracy across scenes; (3) Reliance on massive training data. This paper proposes SM4Depth, a seamless MMDE method, to address all the issues above within a single network. First, we reveal that a consistent field of view (FOV) is the key to resolve ``metric ambiguity'' across cameras, which guides us to propose a more straightforward preprocessing unit. Second, to achieve consistently high accuracy across scenes, we explicitly model the metric scale determination as discretizing the depth interval into bins and propose variation-based unnormalized depth bins. This method bridges the depth gap of diverse scenes by reducing the ambiguity of the conventional metric bin. Third, to reduce the reliance on massive training data, we propose a ``divide and conquer" solution. Instead of estimating directly from the vast solution space, the correct metric bins are estimated from multiple solution sub-spaces for complexity reduction. Finally, with just 150K RGB-D pairs and a consumer-grade GPU for training, SM4Depth achieves state-of-the-art performance on most previously unseen datasets, especially surpassing ZoeDepth and Metric3D on mRI$_\theta$. The code can be found at https://github.com/1hao-Liu/SM4Depth.
Authors: Zhihao Chen, Yiyuan Ge
Abstract: Cloth-changing person re-identification aims to retrieve and identify spe-cific pedestrians by using cloth-irrelevant features in person cloth-changing scenarios. However, pedestrian images captured by surveillance probes usually contain occlusions in real-world scenarios. The perfor-mance of existing cloth-changing re-identification methods is significantly degraded due to the reduction of discriminative cloth-irrelevant features caused by occlusion. We define cloth-changing person re-identification in occlusion scenarios as occluded cloth-changing person re-identification (Occ-CC-ReID), and to the best of our knowledge, we are the first to pro-pose occluded cloth-changing person re-identification as a new task. We constructed two occluded cloth-changing person re-identification datasets for different occlusion scenarios: Occluded-PRCC and Occluded-LTCC. The datasets can be obtained from the following link: https://github.com/1024AILab/Occluded-Cloth-Changing-Person- Re-Identification.
URLs: https://github.com/1024AILab/Occluded-Cloth-Changing-Person-
Authors: Zhanxin Gao, Jun Cen, Xiaobin Chang
Abstract: Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts and classifiers efficiently. Existing prompt-based methods are inconsistent between training and testing, limiting their effectiveness. Two types of inconsistency are revealed. Test predictions are made from all classifiers while training only focuses on the current task classifier without holistic alignment, leading to Classifier inconsistency. Prompt inconsistency indicates that the prompt selected during testing may not correspond to the one associated with this task during training. In this paper, we propose a novel prompt-based method, Consistent Prompting (CPrompt), for more aligned training and testing. Specifically, all existing classifiers are exposed to prompt training, resulting in classifier consistency learning. In addition, prompt consistency learning is proposed to enhance prediction robustness and boost prompt selection accuracy. Our Consistent Prompting surpasses its prompt-based counterparts and achieves state-of-the-art performance on multiple continual learning benchmarks. Detailed analysis shows that improvements come from more consistent training and testing.
Authors: Yuxing Han, Yunan Ding, Chen Ye Gan, Jiangtao Wen
Abstract: Classifying videos into distinct categories, such as Sport and Music Video, is crucial for multimedia understanding and retrieval, especially when an immense volume of video content is being constantly generated. Traditional methods require video decompression to extract pixel-level features like color, texture, and motion, thereby increasing computational and storage demands. Moreover, these methods often suffer from performance degradation in low-quality videos. We present a novel approach that examines only the post-compression bitstream of a video to perform classification, eliminating the need for bitstream decoding. To validate our approach, we built a comprehensive data set comprising over 29,000 YouTube video clips, totaling 6,000 hours and spanning 11 distinct categories. Our evaluations indicate precision, accuracy, and recall rates consistently above 80%, many exceeding 90%, and some reaching 99%. The algorithm operates approximately 15,000 times faster than real-time for 30fps videos, outperforming traditional Dynamic Time Warping (DTW) algorithm by seven orders of magnitude.
Authors: Matteo Taiana, Matteo Toso, Stuart James, Alessio Del Bue
Abstract: Robustly estimating camera poses from a set of images is a fundamental task which remains challenging for differentiable methods, especially in the case of small and sparse camera pose graphs. To overcome this challenge, we propose Pose-refined Rotation Averaging Graph Optimization (PRAGO). From a set of objectness detections on unordered images, our method reconstructs the rotational pose, and in turn, the absolute pose, in a differentiable manner benefiting from the optimization of a sequence of geometrical tasks. We show how our objectness pose-refinement module in PRAGO is able to refine the inherent ambiguities in pairwise relative pose estimation without removing edges and avoiding making early decisions on the viability of graph edges. PRAGO then refines the absolute rotations through iterative graph construction, reweighting the graph edges to compute the final rotational pose, which can be converted into absolute poses using translation averaging. We show that PRAGO is able to outperform non-differentiable solvers on small and sparse scenes extracted from 7-Scenes achieving a relative improvement of 21% for rotations while achieving similar translation estimates.
Authors: Lei Shi, Paul B\"urkner, Andreas Bulling
Abstract: We present ActionDiffusion -- a novel diffusion model for procedure planning in instructional videos that is the first to take temporal inter-dependencies between actions into account in a diffusion model for procedure planning. This approach is in stark contrast to existing methods that fail to exploit the rich information content available in the particular order in which actions are performed. Our method unifies the learning of temporal dependencies between actions and denoising of the action plan in the diffusion process by projecting the action information into the noise space. This is achieved 1) by adding action embeddings in the noise masks in the noise-adding phase and 2) by introducing an attention mechanism in the noise prediction network to learn the correlations between different action steps. We report extensive experiments on three instructional video benchmark datasets (CrossTask, Coin, and NIV) and show that our method outperforms previous state-of-the-art methods on all metrics on CrossTask and NIV and all metrics except accuracy on Coin dataset. We show that by adding action embeddings into the noise mask the diffusion model can better learn action temporal dependencies and increase the performances on procedure planning.
Authors: Nan Jiang, Zhiyuan Zhang, Hongjie Li, Xiaoxuan Ma, Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Siyuan Huang
Abstract: Confronting the challenges of data scarcity and advanced motion synthesis in human-scene interaction modeling, we introduce the TRUMANS dataset alongside a novel HSI motion synthesis method. TRUMANS stands as the most comprehensive motion-captured HSI dataset currently available, encompassing over 15 hours of human interactions across 100 indoor scenes. It intricately captures whole-body human motions and part-level object dynamics, focusing on the realism of contact. This dataset is further scaled up by transforming physical environments into exact virtual models and applying extensive augmentations to appearance and motion for both humans and objects while maintaining interaction fidelity. Utilizing TRUMANS, we devise a diffusion-based autoregressive model that efficiently generates HSI sequences of any length, taking into account both scene context and intended actions. In experiments, our approach shows remarkable zero-shot generalizability on a range of 3D scene datasets (e.g., PROX, Replica, ScanNet, ScanNet++), producing motions that closely mimic original motion-captured sequences, as confirmed by quantitative experiments and human studies.
Authors: Zhuang Liu, Kaiming He
Abstract: We revisit the "dataset classification" experiment suggested by Torralba and Efros a decade ago, in the new era with large-scale, diverse, and hopefully less biased datasets as well as more capable neural network architectures. Surprisingly, we observe that modern neural networks can achieve excellent accuracy in classifying which dataset an image is from: e.g., we report 84.7% accuracy on held-out validation data for the three-way classification problem consisting of the YFCC, CC, and DataComp datasets. Our further experiments show that such a dataset classifier could learn semantic features that are generalizable and transferable, which cannot be simply explained by memorization. We hope our discovery will inspire the community to rethink the issue involving dataset bias and model capabilities.
Authors: Yi Zhou, Hui Zhang, Jiaqian Yu, Yifan Yang, Sangil Jung, Seung-In Park, ByungIn Yoo
Abstract: Vectorized High-Definition (HD) map construction requires predictions of the category and point coordinates of map elements (e.g. road boundary, lane divider, pedestrian crossing, etc.). State-of-the-art methods are mainly based on point-level representation learning for regressing accurate point coordinates. However, this pipeline has limitations in obtaining element-level information and handling element-level failures, e.g. erroneous element shape or entanglement between elements. To tackle the above issues, we propose a simple yet effective HybrId framework named HIMap to sufficiently learn and interact both point-level and element-level information. Concretely, we introduce a hybrid representation called HIQuery to represent all map elements, and propose a point-element interactor to interactively extract and encode the hybrid information of elements, e.g. point position and element shape, into the HIQuery. Additionally, we present a point-element consistency constraint to enhance the consistency between the point-level and element-level information. Finally, the output point-element integrated HIQuery can be directly converted into map elements' class, point coordinates, and mask. We conduct extensive experiments and consistently outperform previous methods on both nuScenes and Argoverse2 datasets. Notably, our method achieves $77.8$ mAP on the nuScenes dataset, remarkably superior to previous SOTAs by $8.3$ mAP at least.
Authors: Mengkun She, Felix Seegr\"aber, David Nakath, Kevin K\"oser
Abstract: In this paper, we present a complete refractive Structure-from-Motion (RSfM) framework for underwater 3D reconstruction using refractive camera setups (for both, flat- and dome-port underwater housings). Despite notable achievements in refractive multi-view geometry over the past decade, a robust, complete and publicly available solution for such tasks is not available at present, and often practical applications have to resort to approximating refraction effects by the intrinsic (distortion) parameters of a pinhole camera model. To fill this gap, we have integrated refraction considerations throughout the entire SfM process within the state-of-the-art, open-source SfM framework COLMAP. Numerical simulations and reconstruction results on synthetically generated but photo-realistic images with ground truth validate that enabling refraction does not compromise accuracy or robustness as compared to in-air reconstructions. Finally, we demonstrate the capability of our approach for large-scale refractive scenarios using a dataset consisting of nearly 6000 images. The implementation is released as open-source at: https://cau-git.rz.uni-kiel.de/inf-ag-koeser/colmap_underwater.
URLs: https://cau-git.rz.uni-kiel.de/inf-ag-koeser/colmap_underwater.
Authors: Liang Chen, Yong Zhang, Yibing Song, Zhen Zhang, Lingqiao Liu
Abstract: Learning domain-invariant semantic representations is crucial for achieving domain generalization (DG), where a model is required to perform well on unseen target domains. One critical challenge is that standard training often results in entangled semantic and domain-specific features. Previous works suggest formulating the problem from a causal perspective and solving the entanglement problem by enforcing marginal independence between the causal (\ie semantic) and non-causal (\ie domain-specific) features. Despite its simplicity, the basic marginal independent-based idea alone may be insufficient to identify the causal feature. By d-separation, we observe that the causal feature can be further characterized by being independent of the domain conditioned on the object, and we propose the following two strategies as complements for the basic framework. First, the observation implicitly implies that for the same object, the causal feature should not be associated with the non-causal feature, revealing that the common practice of obtaining the two features with a shared base feature extractor and two lightweight prediction heads might be inappropriate. To meet the constraint, we propose a simple early-branching structure, where the causal and non-causal feature obtaining branches share the first few blocks while diverging thereafter, for better structure design; Second, the observation implies that the causal feature remains invariant across different domains for the same object. To this end, we suggest that augmentation should be incorporated into the framework to better characterize the causal feature, and we further suggest an effective random domain sampling scheme to fulfill the task. Theoretical and experimental results show that the two strategies are beneficial for the basic marginal independent-based framework. Code is available at \url{https://github.com/liangchen527/CausEB}.
Authors: Wentao Jiang, Yige Zhang, Shaozhong Zheng, Si Liu, Shuicheng Yan
Abstract: This survey presents a comprehensive analysis of data augmentation techniques in human-centric vision tasks, a first of its kind in the field. It delves into a wide range of research areas including person ReID, human parsing, human pose estimation, and pedestrian detection, addressing the significant challenges posed by overfitting and limited training data in these domains. Our work categorizes data augmentation methods into two main types: data generation and data perturbation. Data generation covers techniques like graphic engine-based generation, generative model-based generation, and data recombination, while data perturbation is divided into image-level and human-level perturbations. Each method is tailored to the unique requirements of human-centric tasks, with some applicable across multiple areas. Our contributions include an extensive literature review, providing deep insights into the influence of these augmentation techniques in human-centric vision and highlighting the nuances of each method. We also discuss open issues and future directions, such as the integration of advanced generative models like Latent Diffusion Models, for creating more realistic and diverse training data. This survey not only encapsulates the current state of data augmentation in human-centric vision but also charts a course for future research, aiming to develop more robust, accurate, and efficient human-centric vision systems.
Authors: Jianan Jiang, Xinglin Li, Weiren Yu, Di Wu
Abstract: In the realm of fashion design, sketches serve as the canvas for expressing an artist's distinctive drawing style and creative vision, capturing intricate details like stroke variations and texture nuances. The advent of sketch-to-image cross-modal translation technology has notably aided designers. However, existing methods often compromise these sketch details during image generation, resulting in images that deviate from the designer's intended concept. This limitation hampers the ability to offer designers a precise preview of the final output. To overcome this challenge, we introduce HAIFIT, a novel approach that transforms sketches into high-fidelity, lifelike clothing images by integrating multi-scale features and capturing extensive feature map dependencies from diverse perspectives. Through extensive qualitative and quantitative evaluations conducted on our self-collected dataset, our method demonstrates superior performance compared to existing methods in generating photorealistic clothing images. Our method excels in preserving the distinctive style and intricate details essential for fashion design applications.
Authors: Wanyun Li, Pinxue Guo, Xinyu Zhou, Lingyi Hong, Yangji He, Xiangyu Zheng, Wei Zhang, Wenqiang Zhang
Abstract: Contemporary Video Object Segmentation (VOS) approaches typically consist stages of feature extraction, matching, memory management, and multiple objects aggregation. Recent advanced models either employ a discrete modeling for these components in a sequential manner, or optimize a combined pipeline through substructure aggregation. However, these existing explicit staged approaches prevent the VOS framework from being optimized as a unified whole, leading to the limited capacity and suboptimal performance in tackling complex videos. In this paper, we propose OneVOS, a novel framework that unifies the core components of VOS with All-in-One Transformer. Specifically, to unify all aforementioned modules into a vision transformer, we model all the features of frames, masks and memory for multiple objects as transformer tokens, and integrally accomplish feature extraction, matching and memory management of multiple objects through the flexible attention mechanism. Furthermore, a Unidirectional Hybrid Attention is proposed through a double decoupling of the original attention operation, to rectify semantic errors and ambiguities of stored tokens in OneVOS framework. Finally, to alleviate the storage burden and expedite inference, we propose the Dynamic Token Selector, which unveils the working mechanism of OneVOS and naturally leads to a more efficient version of OneVOS. Extensive experiments demonstrate the superiority of OneVOS, achieving state-of-the-art performance across 7 datasets, particularly excelling in complex LVOS and MOSE datasets with 70.1% and 66.4% $J \& F$ scores, surpassing previous state-of-the-art methods by 4.2% and 7.0%, respectively. And our code will be available for reproducibility and further research.
Authors: Daniel Kovac, Jan Mucha, Jon Alvarez Justo, Jiri Mekyska, Zoltan Galaz, Krystof Novotny, Radoslav Pitonak, Jan Knezik, Jonas Herec, Tor Arne Johansen
Abstract: This article explores the latest Convolutional Neural Networks (CNNs) for cloud detection aboard hyperspectral satellites. The performance of the latest 1D CNN (1D-Justo-LiuNet) and two recent 2D CNNs (nnU-net and 2D-Justo-UNet-Simple) for cloud segmentation and classification is assessed. Evaluation criteria include precision and computational efficiency for in-orbit deployment. Experiments utilize NASA's EO-1 Hyperion data, with varying spectral channel numbers after Principal Component Analysis. Results indicate that 1D-Justo-LiuNet achieves the highest accuracy, outperforming 2D CNNs, while maintaining compactness with larger spectral channel sets, albeit with increased inference times. However, the performance of 1D CNN degrades with significant channel reduction. In this context, the 2D-Justo-UNet-Simple offers the best balance for in-orbit deployment, considering precision, memory, and time costs. While nnU-net is suitable for on-ground processing, deployment of lightweight 1D-Justo-LiuNet is recommended for high-precision applications. Alternatively, lightweight 2D-Justo-UNet-Simple is recommended for balanced costs between timing and precision in orbit.
Authors: Syrine Kalleli, Scott Trigg, S\'egol\`ene Albouy, Mathieu Husson, Mathieu Aubry
Abstract: Automatically extracting the geometric content from the hundreds of thousands of diagrams drawn in historical manuscripts would enable historians to study the diffusion of astronomical knowledge on a global scale. However, state-of-the-art vectorization methods, often designed to tackle modern data, are not adapted to the complexity and diversity of historical astronomical diagrams. Our contribution is thus twofold. First, we introduce a unique dataset of 303 astronomical diagrams from diverse traditions, ranging from the XIIth to the XVIIIth century, annotated with more than 3000 line segments, circles and arcs. Second, we develop a model that builds on DINO-DETR to enable the prediction of multiple geometric primitives. We show that it can be trained solely on synthetic data and accurately predict primitives on our challenging dataset. Our approach widely improves over the LETR baseline, which is restricted to lines, by introducing a meaningful parametrization for multiple primitives, jointly training for detection and parameter refinement, using deformable attention and training on rich synthetic data. Our dataset and code are available on our webpage.
Authors: Asad Aali, Giannis Daras, Brett Levac, Sidharth Kumar, Alexandros G. Dimakis, Jonathan I. Tamir
Abstract: We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data. Our method, Ambient Diffusion Posterior Sampling (A-DPS), leverages a generative model pre-trained on one type of corruption (e.g. image inpainting) to perform posterior sampling conditioned on measurements from a potentially different forward process (e.g. image blurring). We test the efficacy of our approach on standard natural image datasets (CelebA, FFHQ, and AFHQ) and we show that A-DPS can sometimes outperform models trained on clean data for several image restoration tasks in both speed and performance. We further extend the Ambient Diffusion framework to train MRI models with access only to Fourier subsampled multi-coil MRI measurements at various acceleration factors (R=2, 4, 6, 8). We again observe that models trained on highly subsampled data are better priors for solving inverse problems in the high acceleration regime than models trained on fully sampled data. We open-source our code and the trained Ambient Diffusion MRI models: https://github.com/utcsilab/ambient-diffusion-mri .
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: Dinh-Khoi Vo, Duy-Nam Ly, Khanh-Duy Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
Abstract: Creating thematic collections in industries demands innovative designs and cohesive concepts. Designers may face challenges in maintaining thematic consistency when drawing inspiration from existing objects, landscapes, or artifacts. While AI-powered graphic design tools offer help, they often fail to generate cohesive sets based on specific thematic concepts. In response, we introduce iCONTRA, an interactive CONcept TRAnsfer system. With a user-friendly interface, iCONTRA enables both experienced designers and novices to effortlessly explore creative design concepts and efficiently generate thematic collections. We also propose a zero-shot image editing algorithm, eliminating the need for fine-tuning models, which gradually integrates information from initial objects, ensuring consistency in the generation process without influencing the background. A pilot study suggests iCONTRA's potential to reduce designers' efforts. Experimental results demonstrate its effectiveness in producing consistent and high-quality object concept transfers. iCONTRA stands as a promising tool for innovation and creative exploration in thematic collection design. The source code will be available at: https://github.com/vdkhoi20/iCONTRA.
Authors: Feng Cheng, Ziyang Wang, Yi-Lin Sung, Yan-Bo Lin, Mohit Bansal, Gedas Bertasius
Abstract: We present a parameter-efficient method for continual video question-answering (VidQA) learning. Our method, named DAM, uses the proposed Dynamic Adapter Merging to (i) mitigate catastrophic forgetting, (ii) enable efficient adaptation to continually arriving datasets, (iii) handle inputs from unknown datasets during inference, and (iv) enable knowledge sharing across similar dataset domains. Given a set of continually streaming VidQA datasets, we sequentially train dataset-specific adapters for each dataset while freezing the parameters of a large pretrained video-language backbone. During inference, given a video-question sample from an unknown domain, our method first uses the proposed non-parametric router function to compute a probability for each adapter, reflecting how relevant that adapter is to the current video-question input instance. Subsequently, the proposed dynamic adapter merging scheme aggregates all the adapter weights into a new adapter instance tailored for that particular test sample to compute the final VidQA prediction, mitigating the impact of inaccurate router predictions and facilitating knowledge sharing across domains. Our DAM model outperforms prior state-of-the-art continual learning approaches by 9.1% while exhibiting 1.9% less forgetting on 6 VidQA datasets spanning various domains. We further extend DAM to continual image classification and image QA and outperform prior methods by a large margin. The code is publicly available at: https://github.com/klauscc/DAM
Authors: Jialv Zou, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang
Abstract: Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D annotations, limiting the scalability, or focus on single-frame or monocular inputs, neglecting the temporal information. We propose MIM4D, a novel pre-training paradigm based on dual masked image modeling (MIM). MIM4D leverages both spatial and temporal relations by training on masked multi-view video inputs. It constructs pseudo-3D features using continuous scene flow and projects them onto 2D plane for supervision. To address the lack of dense 3D supervision, MIM4D reconstruct pixels by employing 3D volumetric differentiable rendering to learn geometric representations. We demonstrate that MIM4D achieves state-of-the-art performance on the nuScenes dataset for visual representation learning in autonomous driving. It significantly improves existing methods on multiple downstream tasks, including BEV segmentation (8.7% IoU), 3D object detection (3.5% mAP), and HD map construction (1.4% mAP). Our work offers a new choice for learning representation at scale in autonomous driving. Code and models are released at https://github.com/hustvl/MIM4D
Authors: Enric Corona, Andrei Zanfir, Eduard Gabriel Bazavan, Nikos Kolotouros, Thiemo Alldieck, Cristian Sminchisescu
Abstract: We propose VLOGGER, a method for audio-driven human video generation from a single input image of a person, which builds on the success of recent generative diffusion models. Our method consists of 1) a stochastic human-to-3d-motion diffusion model, and 2) a novel diffusion-based architecture that augments text-to-image models with both spatial and temporal controls. This supports the generation of high quality video of variable length, easily controllable through high-level representations of human faces and bodies. In contrast to previous work, our method does not require training for each person, does not rely on face detection and cropping, generates the complete image (not just the face or the lips), and considers a broad spectrum of scenarios (e.g. visible torso or diverse subject identities) that are critical to correctly synthesize humans who communicate. We also curate MENTOR, a new and diverse dataset with 3d pose and expression annotations, one order of magnitude larger than previous ones (800,000 identities) and with dynamic gestures, on which we train and ablate our main technical contributions. VLOGGER outperforms state-of-the-art methods in three public benchmarks, considering image quality, identity preservation and temporal consistency while also generating upper-body gestures. We analyze the performance of VLOGGER with respect to multiple diversity metrics, showing that our architectural choices and the use of MENTOR benefit training a fair and unbiased model at scale. Finally we show applications in video editing and personalization.
Authors: Yupeng Zheng, Xiang Li, Pengfei Li, Yuhang Zheng, Bu Jin, Chengliang Zhong, Xiaoxiao Long, Hao Zhao, Qichao Zhang
Abstract: Monocular Semantic Occupancy Prediction aims to infer the complete 3D geometry and semantic information of scenes from only 2D images. It has garnered significant attention, particularly due to its potential to enhance the 3D perception of autonomous vehicles. However, existing methods rely on a complex cascaded framework with relatively limited information to restore 3D scenes, including a dependency on supervision solely on the whole network's output, single-frame input, and the utilization of a small backbone. These challenges, in turn, hinder the optimization of the framework and yield inferior prediction results, particularly concerning smaller and long-tailed objects. To address these issues, we propose MonoOcc. In particular, we (i) improve the monocular occupancy prediction framework by proposing an auxiliary semantic loss as supervision to the shallow layers of the framework and an image-conditioned cross-attention module to refine voxel features with visual clues, and (ii) employ a distillation module that transfers temporal information and richer knowledge from a larger image backbone to the monocular semantic occupancy prediction framework with low cost of hardware. With these advantages, our method yields state-of-the-art performance on the camera-based SemanticKITTI Scene Completion benchmark. Codes and models can be accessed at https://github.com/ucaszyp/MonoOcc
Authors: Linyi Jin, Nilesh Kulkarni, David Fouhey
Abstract: This paper introduces 3DFIRES, a novel system for scene-level 3D reconstruction from posed images. Designed to work with as few as one view, 3DFIRES reconstructs the complete geometry of unseen scenes, including hidden surfaces. With multiple view inputs, our method produces full reconstruction within all camera frustums. A key feature of our approach is the fusion of multi-view information at the feature level, enabling the production of coherent and comprehensive 3D reconstruction. We train our system on non-watertight scans from large-scale real scene dataset. We show it matches the efficacy of single-view reconstruction methods with only one input and surpasses existing techniques in both quantitative and qualitative measures for sparse-view 3D reconstruction.
Authors: Yifei Zhang, Hao Zhao, Hongyang Li, Siheng Chen
Abstract: 3D correspondence, i.e., a pair of 3D points, is a fundamental concept in computer vision. A set of 3D correspondences, when equipped with compatibility edges, forms a correspondence graph. This graph is a critical component in several state-of-the-art 3D point cloud registration approaches, e.g., the one based on maximal cliques (MAC). However, its properties have not been well understood. So we present the first study that introduces graph signal processing into the domain of correspondence graph. We exploit the generalized degree signal on correspondence graph and pursue sampling strategies that preserve high-frequency components of this signal. To address time-consuming singular value decomposition in deterministic sampling, we resort to a stochastic approximate sampling strategy. As such, the core of our method is the stochastic spectral sampling of correspondence graph. As an application, we build a complete 3D registration algorithm termed as FastMAC, that reaches real-time speed while leading to little to none performance drop. Through extensive experiments, we validate that FastMAC works for both indoor and outdoor benchmarks. For example, FastMAC can accelerate MAC by 80 times while maintaining high registration success rate on KITTI. Codes are publicly available at https://github.com/Forrest-110/FastMAC.
Authors: Daniel Fernandes Gomes, Wenxuan Mou, Paolo Paoletti, Shan Luo
Abstract: End-to-end self-supervised models have been proposed for estimating the success of future candidate grasps and video predictive models for generating future observations. However, none have yet studied these two strategies side-by-side for addressing the aforementioned grasping problem. We investigate and compare a model-free approach, to estimate the success of a candidate grasp, against a model-based alternative that exploits a self-supervised learnt predictive model that generates a future observation of the gripper about to grasp an object. Our experiments demonstrate that despite the end-to-end model-free model obtaining a best accuracy of 72%, the proposed model-based pipeline yields a significantly higher accuracy of 82%.
Authors: Shentong Mo, Jing Shi, Yapeng Tian
Abstract: In recent times, the focus on text-to-audio (TTA) generation has intensified, as researchers strive to synthesize audio from textual descriptions. However, most existing methods, though leveraging latent diffusion models to learn the correlation between audio and text embeddings, fall short when it comes to maintaining a seamless synchronization between the produced audio and its video. This often results in discernible audio-visual mismatches. To bridge this gap, we introduce a groundbreaking benchmark for Text-to-Audio generation that aligns with Videos, named T2AV-Bench. This benchmark distinguishes itself with three novel metrics dedicated to evaluating visual alignment and temporal consistency. To complement this, we also present a simple yet effective video-aligned TTA generation model, namely T2AV. Moving beyond traditional methods, T2AV refines the latent diffusion approach by integrating visual-aligned text embeddings as its conditional foundation. It employs a temporal multi-head attention transformer to extract and understand temporal nuances from video data, a feat amplified by our Audio-Visual ControlNet that adeptly merges temporal visual representations with text embeddings. Further enhancing this integration, we weave in a contrastive learning objective, designed to ensure that the visual-aligned text embeddings resonate closely with the audio features. Extensive evaluations on the AudioCaps and T2AV-Bench demonstrate that our T2AV sets a new standard for video-aligned TTA generation in ensuring visual alignment and temporal consistency.
Authors: Kavita Sultanpure, Bhairavi Shirsath, Bhakti Bhande, Harshada Sawai, Srushti Gawade, Suraj Samgir
Abstract: In recent years, there has been a notable advancement in the integration of healthcare and technology, particularly evident in the field of medical image analysis. This paper introduces a pioneering approach in dermatology, presenting a robust method for the detection of hair and scalp diseases using state-of-the-art deep learning techniques. Our methodology relies on Convolutional Neural Networks (CNNs), well-known for their efficacy in image recognition, to meticulously analyze images for various dermatological conditions affecting the hair and scalp. Our proposed system represents a significant advancement in dermatological diagnostics, offering a non-invasive and highly efficient means of early detection and diagnosis. By leveraging the capabilities of CNNs, our model holds the potential to revolutionize dermatology, providing accessible and timely healthcare solutions. Furthermore, the seamless integration of our trained model into a web-based platform developed with the Django framework ensures broad accessibility and usability, democratizing advanced medical diagnostics. The integration of machine learning algorithms into web applications marks a pivotal moment in healthcare delivery, promising empowerment for both healthcare providers and patients. Through the synergy between technology and healthcare, our paper outlines the meticulous methodology, technical intricacies, and promising future prospects of our system. With a steadfast commitment to advancing healthcare frontiers, our goal is to significantly contribute to leveraging technology for improved healthcare outcomes globally. This endeavor underscores the profound impact of technological innovation in shaping the future of healthcare delivery and patient care, highlighting the transformative potential of our approach.
Authors: Chenxing Gao, Hang Zhou, Junqing Yu, YuTeng Ye, Jiale Cai, Junle Wang, Wei Yang
Abstract: Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications. Existing ViT adversarial attackers rely on la bels to calculate the gradient for perturbation, and exhibit low transferability to other structures and tasks. In this paper, we present a label-free white-box attack approach for ViT-based models that exhibits strong transferability to various black box models, including most ViT variants, CNNs, and MLPs, even for models developed for other modalities. Our inspira tion comes from the feature collapse phenomenon in ViTs, where the critical attention mechanism overly depends on the low-frequency component of features, causing the features in middle-to-end layers to become increasingly similar and eventually collapse. We propose the feature diversity attacker to naturally accelerate this process and achieve remarkable performance and transferability.
Authors: Yiran Wang, Li Xiao
Abstract: It has been shown that traditional deep learning methods for electronic microscopy segmentation usually suffer from low transferability when samples and annotations are limited, while large-scale vision foundation models are more robust when transferring between different domains but facing sub-optimal improvement under fine-tuning. In this work, we present a new few-shot domain adaptation framework SAMDA, which combines the Segment Anything Model(SAM) with nnUNet in the embedding space to achieve high transferability and accuracy. Specifically, we choose the Unet-based network as the "expert" component to learn segmentation features efficiently and design a SAM-based adaptation module as the "generic" component for domain transfer. By amalgamating the "generic" and "expert" components, we mitigate the modality imbalance in the complex pre-training knowledge inherent to large-scale Vision Foundation models and the challenge of transferability inherent to traditional neural networks. The effectiveness of our model is evaluated on two electron microscopic image datasets with different modalities for mitochondria segmentation, which improves the dice coefficient on the target domain by 6.7%. Also, the SAM-based adaptor performs significantly better with only a single annotated image than the 10-shot domain adaptation on nnUNet. We further verify our model on four MRI datasets from different sources to prove its generalization ability.
Authors: Juan Manuel Zambrano Chaves, Shih-Cheng Huang, Yanbo Xu, Hanwen Xu, Naoto Usuyama, Sheng Zhang, Fei Wang, Yujia Xie, Mahmoud Khademi, Ziyi Yang, Hany Awadalla, Julia Gong, Houdong Hu, Jianwei Yang, Chunyuan Li, Jianfeng Gao, Yu Gu, Cliff Wong, Mu Wei, Tristan Naumann, Muhao Chen, Matthew P. Lungren, Serena Yeung-Levy, Curtis P. Langlotz, Sheng Wang, Hoifung Poon
Abstract: The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such large models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world applications. Frontier models such as GPT-4V still have major competency gaps in multimodal capabilities for biomedical applications. Moreover, pragmatic issues such as access, cost, latency, and compliance make it hard for clinicians to use privately-hosted state-of-the-art large models directly on private patient data. In this paper, we explore training open-source small multimodal models (SMMs) to bridge biomedical competency gaps for unmet clinical needs. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space. We conduct a comprehensive study of this approach on radiology imaging. For training, we assemble a large dataset with over 1 million image-text pairs. For evaluation, we propose a clinically driven novel approach using GPT-4 and demonstrate its parity with expert evaluation. We also study grounding qualitatively using attention. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LLaVA-Rad (7B) model attains state-of-the-art results on radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). LLaVA-Rad is fast and can be run on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
Authors: Rodrigo Santos, Jo\~ao Silva, Ant\'onio Branco
Abstract: The combination of language processing and image processing keeps attracting increased interest given recent impressive advances that leverage the combined strengths of both domains of research. Among these advances, the task of editing an image on the basis solely of a natural language instruction stands out as a most challenging endeavour. While recent approaches for this task resort, in one way or other, to some form of preliminary preparation, training or fine-tuning, this paper explores a novel approach: We propose a preparation-free method that permits instruction-guided image editing on the fly. This approach is organized along three steps properly orchestrated that resort to image captioning and DDIM inversion, followed by obtaining the edit direction embedding, followed by image editing proper. While dispensing with preliminary preparation, our approach demonstrates to be effective and competitive, outperforming recent, state of the art models for this task when evaluated on the MAGICBRUSH dataset.
Authors: Micheli Nayara de Oliveira Vicente, Gabriel Toshio Hirokawa Higa, Jo\~ao Vitor de Andrade Porto, Higor Henrique, Picoli Nucci, Asser Botelho Santana, Karla Rejane de Andrade Porto, Antonia Railda Roel, Hemerson Pistori
Abstract: Aedes aegypti is still one of the main concerns when it comes to disease vectors. Among the many ways to deal with it, there are important protocols that make use of egg numbers in ovitraps to calculate indices, such as the LIRAa and the Breteau Index, which can provide information on predictable outbursts and epidemics. Also, there are many research lines that require egg numbers, specially when mass production of mosquitoes is needed. Egg counting is a laborious and error-prone task that can be automated via computer vision-based techniques, specially deep learning-based counting with object detection. In this work, we propose a new dataset comprising field and laboratory eggs, along with test results of three neural networks applied to the task: Faster R-CNN, Side-Aware Boundary Localization and FoveaBox.
Authors: Amel Imene Hadj Bouzid, Baudouin Denis de Senneville, Fabien Baldacci, Pascal Desbarats, Patrick Berger, Ilyes Benlala, Ga\"el Dournes
Abstract: This research embarked on a comparative exploration of the holistic segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized data from two CF reference centers, covering five major CF structural changes. Initially, it compared the 2D and 3D models, highlighting the 3D model's superior capability in capturing complex features like mucus plugs and consolidations. To improve the 2D model's performance, a loss adapted to fine structures segmentation was implemented and evaluated, significantly enhancing its accuracy, though not surpassing the 3D model's performance. The models underwent further validation through external evaluation against pulmonary function tests (PFTs), confirming the robustness of the findings. Moreover, this study went beyond comparing metrics; it also included comprehensive assessments of the models' interpretability and reliability, providing valuable insights for their clinical application.
Authors: Mohammad Nazeri, Junzhe Wang, Amirreza Payandeh, Xuesu Xiao
Abstract: Humans excel at efficiently navigating through crowds without collision by focusing on specific visual regions relevant to navigation. However, most robotic visual navigation methods rely on deep learning models pre-trained on vision tasks, which prioritize salient objects -- not necessarily relevant to navigation and potentially misleading. Alternative approaches train specialized navigation models from scratch, requiring significant computation. On the other hand, self-supervised learning has revolutionized computer vision and natural language processing, but its application to robotic navigation remains underexplored due to the difficulty of defining effective self-supervision signals. Motivated by these observations, in this work, we propose a Self-Supervised Vision-Action Model for Visual Navigation Pre-Training (VANP). Instead of detecting salient objects that are beneficial for tasks such as classification or detection, VANP learns to focus only on specific visual regions that are relevant to the navigation task. To achieve this, VANP uses a history of visual observations, future actions, and a goal image for self-supervision, and embeds them using two small Transformer Encoders. Then, VANP maximizes the information between the embeddings by using a mutual information maximization objective function. We demonstrate that most VANP-extracted features match with human navigation intuition. VANP achieves comparable performance as models learned end-to-end with half the training time and models trained on a large-scale, fully supervised dataset, i.e., ImageNet, with only 0.08% data.
Authors: Shuang Guo, Guillermo Gallego
Abstract: Event cameras are bio-inspired visual sensors that capture pixel-wise intensity changes and output asynchronous event streams. They show great potential over conventional cameras to handle challenging scenarios in robotics and computer vision, such as high-speed and high dynamic range. This paper considers the problem of rotational motion estimation using event cameras. Several event-based rotation estimation methods have been developed in the past decade, but their performance has not been evaluated and compared under unified criteria yet. In addition, these prior works do not consider a global refinement step. To this end, we conduct a systematic study of this problem with two objectives in mind: summarizing previous works and presenting our own solution. First, we compare prior works both theoretically and experimentally. Second, we propose the first event-based rotation-only bundle adjustment (BA) approach. We formulate it leveraging the state-of-the-art Contrast Maximization (CMax) framework, which is principled and avoids the need to convert events into frames. Third, we use the proposed BA to build CMax-SLAM, the first event-based rotation-only SLAM system comprising a front-end and a back-end. Our BA is able to run both offline (trajectory smoothing) and online (CMax-SLAM back-end). To demonstrate the performance and versatility of our method, we present comprehensive experiments on synthetic and real-world datasets, including indoor, outdoor and space scenarios. We discuss the pitfalls of real-world evaluation and propose a proxy for the reprojection error as the figure of merit to evaluate event-based rotation BA methods. We release the source code and novel data sequences to benefit the community. We hope this work leads to a better understanding and fosters further research on event-based ego-motion estimation. Project page: https://github.com/tub-rip/cmax_slam
Authors: Lintao Zhang, Mengqi Wu, Lihong Wang, David C. Steffens, Guy G. Potter, Mingxia Liu
Abstract: Image noise and motion artifacts greatly affect the quality of brain MRI and negatively influence downstream medical image analysis. Previous studies often focus on 2D methods that process each volumetric MR image slice-by-slice, thus losing important 3D anatomical information. Additionally, these studies generally treat image denoising and artifact correction as two standalone tasks, without considering their potential relationship, especially on low-quality images where severe noise and motion artifacts occur simultaneously. To address these issues, we propose a Joint image Denoising and motion Artifact Correction (JDAC) framework via iterative learning to handle noisy MRIs with motion artifacts, consisting of an adaptive denoising model and an anti-artifact model. In the adaptive denoising model, we first design a novel noise level estimation strategy, and then adaptively reduce the noise through a U-Net backbone with feature normalization conditioning on the estimated noise variance. The anti-artifact model employs another U-Net for eliminating motion artifacts, incorporating a novel gradient-based loss function designed to maintain the integrity of brain anatomy during the motion correction process. These two models are iteratively employed for joint image denoising and artifact correction through an iterative learning framework. An early stopping strategy depending on noise level estimation is applied to accelerate the iteration process. The denoising model is trained with 9,544 T1-weighted MRIs with manually added Gaussian noise as supervision. The anti-artifact model is trained on 552 T1-weighted MRIs with motion artifacts and paired motion-free images. Experimental results on a public dataset and a clinical study suggest the effectiveness of JDAC in both tasks of denoising and motion artifact correction, compared with several state-of-the-art methods.
Authors: Siqi Li, Jun Chen, Jingyang Xiang, Chengrui Zhu, Yong Liu
Abstract: Structured pruning methods are developed to bridge the gap between the massive scale of neural networks and the limited hardware resources. Most current structured pruning methods rely on training datasets to fine-tune the compressed model, resulting in high computational burdens and being inapplicable for scenarios with stringent requirements on privacy and security. As an alternative, some data-free methods have been proposed, however, these methods often require handcraft parameter tuning and can only achieve inflexible reconstruction. In this paper, we propose the Automatic Data-Free Pruning (AutoDFP) method that achieves automatic pruning and reconstruction without fine-tuning. Our approach is based on the assumption that the loss of information can be partially compensated by retaining focused information from similar channels. Specifically, We formulate data-free pruning as an optimization problem, which can be effectively addressed through reinforcement learning. AutoDFP assesses the similarity of channels for each layer and provides this information to the reinforcement learning agent, guiding the pruning and reconstruction process of the network. We evaluate AutoDFP with multiple networks on multiple datasets, achieving impressive compression results. For instance, on the CIFAR-10 dataset, AutoDFP demonstrates a 2.87\% reduction in accuracy loss compared to the recently proposed data-free pruning method DFPC with fewer FLOPs on VGG-16. Furthermore, on the ImageNet dataset, AutoDFP achieves 43.17\% higher accuracy than the SOTA method with the same 80\% preserved ratio on MobileNet-V1.
Authors: Khondoker Murad Hossain, Tim Oates
Abstract: In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that can be exploited by malicious actors. Our approach leverages advanced tensor decomposition algorithms Independent Vector Analysis (IVA), Multiset Canonical Correlation Analysis (MCCA), and Parallel Factor Analysis (PARAFAC2) to meticulously analyze the weights of pre-trained DNNs and distinguish between backdoored and clean models effectively. The key strengths of our method lie in its domain independence, adaptability to various network architectures, and ability to operate without access to the training data of the scrutinized models. This not only ensures versatility across different application scenarios but also addresses the challenge of identifying backdoors without prior knowledge of the specific triggers employed to alter network behavior. We have applied our detection pipeline to three distinct computer vision datasets, encompassing both image classification and object detection tasks. The results demonstrate a marked improvement in both accuracy and efficiency over existing backdoor detection methods. This advancement enhances the security of deep learning and AI in networked systems, providing essential cybersecurity against evolving threats in emerging technologies.
Authors: Qinglong Meng, Chongkun Xia, Xueqian Wang
Abstract: Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues, which are manifold and discrete data. If the target distribution is a manifold, which means the dimension of the latent target distribution and the dimension of the data distribution are unmatched, flow-based models might perform badly. Discrete data makes flow-based models collapse into a degenerate mixture of point masses. In this paper, to sidestep such two issues we propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. PaddingFlow is easy to implement, computationally cheap, widely suitable for various tasks, and generates samples that are unbiased estimations of the data. Especially, our method can overcome the limitation of existing dequantization methods that have to change the data distribution, which might degrade performance. We validate our method on the main benchmarks of unconditional density estimation, including five tabular datasets and four image datasets for VAE models, and the IK experiments which are conditional density estimation. The results show that PaddingFlow can provide improvement on all tasks in this paper.
Authors: Kento Kawaharazuka, Naoaki Kanazawa, Yoshiki Obinata, Kei Okada, Masayuki Inaba
Abstract: The state recognition of the environment and objects by robots is generally based on the judgement of the current state as a classification problem. On the other hand, state changes of food in cooking happen continuously and need to be captured not only at a certain time point but also continuously over time. In addition, the state changes of food are complex and cannot be easily described by manual programming. Therefore, we propose a method to recognize the continuous state changes of food for cooking robots through the spoken language using pre-trained large-scale vision-language models. By using models that can compute the similarity between images and texts continuously over time, we can capture the state changes of food while cooking. We also show that by adjusting the weighting of each text prompt based on fitting the similarity changes to a sigmoid function and then performing black-box optimization, more accurate and robust continuous state recognition can be achieved. We demonstrate the effectiveness and limitations of this method by performing the recognition of water boiling, butter melting, egg cooking, and onion stir-frying.
Authors: Hongyang Zhu, Xin Lu, Yanwei Qin, Xinran Yu, Tianjiao Sun, Yunsong Zhao
Abstract: Ring artifacts in computed tomography images, arising from the undesirable responses of detector units, significantly degrade image quality and diagnostic reliability. To address this challenge, we propose a dual-domain regularization model to effectively remove ring artifacts, while maintaining the integrity of the original CT image. The proposed model corrects the vertical stripe artifacts on the sinogram by innovatively updating the response inconsistency compensation coefficients of detector units, which is achieved by employing the group sparse constraint and the projection-view direction sparse constraint on the stripe artifacts. Simultaneously, we apply the sparse constraint on the reconstructed image to further rectified ring artifacts in the image domain. The key advantage of the proposed method lies in considering the relationship between the response inconsistency compensation coefficients of the detector units and the projection views, which enables a more accurate correction of the response of the detector units. An alternating minimization method is designed to solve the model. Comparative experiments on real photon counting detector data demonstrate that the proposed method not only surpasses existing methods in removing ring artifacts but also excels in preserving structural details and image fidelity.
Authors: Katerina Deike-Hofmann, Dorottya Dancs, Daniel Paech, Heinz-Peter Schlemmer, Klaus Maier-Hein, Philipp B\"aumer, Alexander Radbruch, Michael G\"otz
Abstract: Materials and methods: First, a dual-time approach was assessed, for which the CNN was provided sequences of the MRI that initially depicted new MM (diagnosis MRI) as well as of a prediagnosis MRI: inclusion of only contrast-enhanced T1-weighted images (CNNdual_ce) was compared with inclusion of also the native T1-weighted images, T2-weighted images, and FLAIR sequences of both time points (CNNdual_all).Second, results were compared with the corresponding single time approaches, in which the CNN was provided exclusively the respective sequences of the diagnosis MRI.Casewise diagnostic performance parameters were calculated from 5-fold cross-validation. Results: In total, 94 cases with 494 MMs were included. Overall, the highest diagnostic performance was achieved by inclusion of only the contrast-enhanced T1-weighted images of the diagnosis and of a prediagnosis MRI (CNNdual_ce, sensitivity = 73%, PPV = 25%, F1-score = 36%). Using exclusively contrast-enhanced T1-weighted images as input resulted in significantly less false-positives (FPs) compared with inclusion of further sequences beyond contrast-enhanced T1-weighted images (FPs = 5/7 for CNNdual_ce/CNNdual_all, P < 1e-5). Comparison of contrast-enhanced dual and mono time approaches revealed that exclusion of prediagnosis MRI significantly increased FPs (FPs = 5/10 for CNNdual_ce/CNNce, P < 1e-9).Approaches with only native sequences were clearly inferior to CNNs that were provided contrast-enhanced sequences. Conclusions: Automated MM detection on contrast-enhanced T1-weighted images performed with high sensitivity. Frequent FPs due to artifacts and vessels were significantly reduced by additional inclusion of prediagnosis MRI, but not by inclusion of further sequences beyond contrast-enhanced T1-weighted images. Future studies might investigate different change detection architectures for computer-aided detection.
Authors: Guanxing Lu, Shiyi Zhang, Ziwei Wang, Changliu Liu, Jiwen Lu, Yansong Tang
Abstract: Performing language-conditioned robotic manipulation tasks in unstructured environments is highly demanded for general intelligent robots. Conventional robotic manipulation methods usually learn semantic representation of the observation for action prediction, which ignores the scene-level spatiotemporal dynamics for human goal completion. In this paper, we propose a dynamic Gaussian Splatting method named ManiGaussian for multi-task robotic manipulation, which mines scene dynamics via future scene reconstruction. Specifically, we first formulate the dynamic Gaussian Splatting framework that infers the semantics propagation in the Gaussian embedding space, where the semantic representation is leveraged to predict the optimal robot action. Then, we build a Gaussian world model to parameterize the distribution in our dynamic Gaussian Splatting framework, which provides informative supervision in the interactive environment via future scene reconstruction. We evaluate our ManiGaussian on 10 RLBench tasks with 166 variations, and the results demonstrate our framework can outperform the state-of-the-art methods by 13.1\% in average success rate.
Authors: Alhassan Mumuni, Fuseini Mumuni
Abstract: Data augmentation is arguably the most important regularization technique commonly used to improve generalization performance of machine learning models. It primarily involves the application of appropriate data transformation operations to create new data samples with desired properties. Despite its effectiveness, the process is often challenging because of the time-consuming trial and error procedures for creating and testing different candidate augmentations and their hyperparameters manually. Automated data augmentation methods aim to automate the process. State-of-the-art approaches typically rely on automated machine learning (AutoML) principles. This work presents a comprehensive survey of AutoML-based data augmentation techniques. We discuss various approaches for accomplishing data augmentation with AutoML, including data manipulation, data integration and data synthesis techniques. We present extensive discussion of techniques for realizing each of the major subtasks of the data augmentation process: search space design, hyperparameter optimization and model evaluation. Finally, we carried out an extensive comparison and analysis of the performance of automated data augmentation techniques and state-of-the-art methods based on classical augmentation approaches. The results show that AutoML methods for data augmentation currently outperform state-of-the-art techniques based on conventional approaches.
Authors: Ran Xu, Yan Shen, Xiaoqi Li, Ruihai Wu, Hao Dong
Abstract: Enabling home-assistant robots to perceive and manipulate a diverse range of 3D objects based on human language instructions is a pivotal challenge. Prior research has predominantly focused on simplistic and task-oriented instructions, i.e., "Slide the top drawer open". However, many real-world tasks demand intricate multi-step reasoning, and without human instructions, these will become extremely difficult for robot manipulation. To address these challenges, we introduce a comprehensive benchmark, NrVLM, comprising 15 distinct manipulation tasks, containing over 4500 episodes meticulously annotated with fine-grained language instructions. We split the long-term task process into several steps, with each step having a natural language instruction. Moreover, we propose a novel learning framework that completes the manipulation task step-by-step according to the fine-grained instructions. Specifically, we first identify the instruction to execute, taking into account visual observations and the end-effector's current state. Subsequently, our approach facilitates explicit learning through action-prompts and perception-prompts to promote manipulation-aware cross-modality alignment. Leveraging both visual observations and linguistic guidance, our model outputs a sequence of actionable predictions for manipulation, including contact points and end-effector poses. We evaluate our method and baselines using the proposed benchmark NrVLM. The experimental results demonstrate the effectiveness of our approach. For additional details, please refer to https://sites.google.com/view/naturalvlm.
Authors: Lao-Tzu Allan-Blitz, Sithira Ambepitiya, Raghavendra Tirupathi, Jeffrey D. Klausner, Yudara Kularathne
Abstract: Machine-learning algorithms can facilitate low-cost, user-guided visual diagnostic platforms for addressing disparities in access to sexual health services. We developed a clinical image dataset using original and augmented images for five penile diseases: herpes eruption, syphilitic chancres, penile candidiasis, penile cancer, and genital warts. We used a U-net architecture model for semantic pixel segmentation into background or subject image, the Inception-ResNet version 2 neural architecture to classify each pixel as diseased or non-diseased, and a salience map using GradCAM++. We trained the model on a random 91% sample of the image database using 150 epochs per image, and evaluated the model on the remaining 9% of images, assessing recall (or sensitivity), precision, specificity, and F1-score (accuracy). Of the 239 images in the validation dataset, 45 (18.8%) were of genital warts, 43 (18.0%) were of HSV infection, 29 (12.1%) were of penile cancer, 40 (16.7%) were of penile candidiasis, 37 (15.5%) were of syphilitic chancres, and 45 (18.8%) were of non-diseased penises. The overall accuracy of the model for correctly classifying the diseased image was 0.944. Between July 1st and October 1st 2023, there were 2,640 unique users of the mobile platform. Among a random sample of submissions (n=437), 271 (62.0%) were from the United States, 64 (14.6%) from Singapore, 41 (9.4%) from Candia, 40 (9.2%) from the United Kingdom, and 21 (4.8%) from Vietnam. The majority (n=277 [63.4%]) were between 18 and 30 years old. We report on the development of a machine-learning model for classifying five penile diseases, which demonstrated excellent performance on a validation dataset. That model is currently in use globally and has the potential to improve access to diagnostic services for penile diseases.
Authors: Cosmin I. Bercea, Benedikt Wiestler, Daniel Rueckert, Julia A. Schnabel
Abstract: Diffusion models have advanced unsupervised anomaly detection by improving the transformation of pathological images into pseudo-healthy equivalents. Nonetheless, standard approaches may compromise critical information during pathology removal, leading to restorations that do not align with unaffected regions in the original scans. Such discrepancies can inadvertently increase false positive rates and reduce specificity, complicating radiological evaluations. This paper introduces Temporal Harmonization for Optimal Restoration (THOR), which refines the de-noising process by integrating implicit guidance through temporal anomaly maps. THOR aims to preserve the integrity of healthy tissue in areas unaffected by pathology. Comparative evaluations show that THOR surpasses existing diffusion-based methods in detecting and segmenting anomalies in brain MRIs and wrist X-rays. Code: https://github.com/ci-ber/THOR_DDPM.
Authors: Linjie Fu, Xia Li, Xiuding Cai, Yingkai Wang, Xueyao Wang, Yali Shen, Yu Yao
Abstract: Radiation therapy is crucial in cancer treatment. Experienced experts typically iteratively generate high-quality dose distribution maps, forming the basis for excellent radiation therapy plans. Therefore, automated prediction of dose distribution maps is significant in expediting the treatment process and providing a better starting point for developing radiation therapy plans. With the remarkable results of diffusion models in predicting high-frequency regions of dose distribution maps, dose prediction methods based on diffusion models have been extensively studied. However, existing methods mainly utilize CNNs or Transformers as denoising networks. CNNs lack the capture of global receptive fields, resulting in suboptimal prediction performance. Transformers excel in global modeling but face quadratic complexity with image size, resulting in significant computational overhead. To tackle these challenges, we introduce a novel diffusion model, MD-Dose, based on the Mamba architecture for predicting radiation therapy dose distribution in thoracic cancer patients. In the forward process, MD-Dose adds Gaussian noise to dose distribution maps to obtain pure noise images. In the backward process, MD-Dose utilizes a noise predictor based on the Mamba to predict the noise, ultimately outputting the dose distribution maps. Furthermore, We develop a Mamba encoder to extract structural information and integrate it into the noise predictor for localizing dose regions in the planning target volume (PTV) and organs at risk (OARs). Through extensive experiments on a dataset of 300 thoracic tumor patients, we showcase the superiority of MD-Dose in various metrics and time consumption.
Authors: Xinjie Zhang, Shenyuan Gao, Zhening Liu, Xingtong Ge, Dailan He, Tongda Xu, Yan Wang, Jun Zhang
Abstract: Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model to capture both spatial and disparity dependencies, by introducing a novel content-aware masked image modeling (MIM) technique. Our content-aware MIM facilitates efficient bidirectional interaction between prior information and estimated tokens, which naturally obviates the need for an extra Transformer decoder. Experiments show that our stereo image codec achieves state-of-the-art rate-distortion performance on two stereo image datasets Cityscapes and InStereo2K with fast encoding and decoding speed.
Authors: Sikai Bai, Jie Zhang, Shuaicheng Li, Song Guo, Jingcai Guo, Jun Hou, Tao Han, Xiaocheng Lu
Abstract: Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target domain) is absent from the decentralized training data (source domains). However, most existing FL methods assume that domain labels are provided during training, and their evaluation imposes explicit constraints on the number of domains, which must strictly match the number of clients. Because of the underutilization of numerous edge devices and additional cross-client domain annotations in the real world, such restrictions may be impractical and involve potential privacy leaks. In this paper, we propose an efficient and novel approach, called Disentangled Prompt Tuning (DiPrompT), a method that tackles the above restrictions by learning adaptive prompts for domain generalization in a distributed manner. Specifically, we first design two types of prompts, i.e., global prompt to capture general knowledge across all clients and domain prompts to capture domain-specific knowledge. They eliminate the restriction on the one-to-one mapping between source domains and local clients. Furthermore, a dynamic query metric is introduced to automatically search the suitable domain label for each sample, which includes two-substep text-image alignments based on prompt tuning without labor-intensive annotation. Extensive experiments on multiple datasets demonstrate that our DiPrompT achieves superior domain generalization performance over state-of-the-art FL methods when domain labels are not provided, and even outperforms many centralized learning methods using domain labels.
Authors: Maik Dannecker, Vanessa Kyriakopoulou, Lucilio Cordero-Grande, Anthony N. Price, Joseph V. Hajnal, Daniel Rueckert
Abstract: We introduce a conditional implicit neural atlas (CINA) for spatio-temporal atlas generation from Magnetic Resonance Images (MRI) of the neurotypical and pathological fetal brain, that is fully independent of affine or non-rigid registration. During training, CINA learns a general representation of the fetal brain and encodes subject specific information into latent code. After training, CINA can construct a faithful atlas with tissue probability maps of the fetal brain for any gestational age (GA) and anatomical variation covered within the training domain. Thus, CINA is competent to represent both, neurotypical and pathological brains. Furthermore, a trained CINA model can be fit to brain MRI of unseen subjects via test-time optimization of the latent code. CINA can then produce probabilistic tissue maps tailored to a particular subject. We evaluate our method on a total of 198 T2 weighted MRI of normal and abnormal fetal brains from the dHCP and FeTA datasets. We demonstrate CINA's capability to represent a fetal brain atlas that can be flexibly conditioned on GA and on anatomical variations like ventricular volume or degree of cortical folding, making it a suitable tool for modeling both neurotypical and pathological brains. We quantify the fidelity of our atlas by means of tissue segmentation and age prediction and compare it to an established baseline. CINA demonstrates superior accuracy for neurotypical brains and pathological brains with ventriculomegaly. Moreover, CINA scores a mean absolute error of 0.23 weeks in fetal brain age prediction, further confirming an accurate representation of fetal brain development.
Authors: Xinjie Zhang, Xingtong Ge, Tongda Xu, Dailan He, Yan Wang, Hongwei Qin, Guo Lu, Jing Geng, Jun Zhang
Abstract: Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. However, this requirement often hinders their use on low-end devices with limited memory. In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage. We first introduce 2D Gaussian to represent the image, where each Gaussian has 8 parameters including position, covariance and color. Subsequently, we unveil a novel rendering algorithm based on accumulated summation. Remarkably, our method with a minimum of 3$\times$ lower GPU memory usage and 5$\times$ faster fitting time not only rivals INRs (e.g., WIRE, I-NGP) in representation performance, but also delivers a faster rendering speed of 1500-2000 FPS regardless of parameter size. Furthermore, we integrate existing vector quantization technique to build an image codec. Experimental results demonstrate that our codec attains rate-distortion performance comparable to compression-based INRs such as COIN and COIN++, while facilitating decoding speeds of approximately 1000 FPS. Additionally, preliminary proof of concept shows that our codec surpasses COIN and COIN++ in performance when using partial bits-back coding.
Authors: Armin Sheibanifard, Hongchuan Yu
Abstract: The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the compression rate for volumetric medical images. Most of the INR techniques need a huge amount of GPU memory and a long training time for high-quality medical volume rendering. In this paper, we present a novel implicit neural representation to compress volume data using our proposed architecture, that is, the Lanczos downsampling scheme, SIREN deep network, and SRDenseNet high-resolution scheme. Our architecture can effectively reduce training time, and gain a high compression rate while retaining the final rendering quality. Moreover, it can save GPU memory in comparison with the existing works. The experiments show that the quality of reconstructed images and training speed using our architecture is higher than current works which use the SIREN only. Besides, the GPU memory cost is evidently decreased
Authors: Tiange Xiang, Yixiao Zhang, Yongyi Lu, Alan Yuille, Chaoyi Zhang, Weidong Cai, Zongwei Zhou
Abstract: Radiography imaging protocols focus on particular body regions, therefore producing images of great similarity and yielding recurrent anatomical structures across patients. Exploiting this structured information could potentially ease the detection of anomalies from radiography images. To this end, we propose a Simple Space-Aware Memory Matrix for In-painting and Detecting anomalies from radiography images (abbreviated as SimSID). We formulate anomaly detection as an image reconstruction task, consisting of a space-aware memory matrix and an in-painting block in the feature space. During the training, SimSID can taxonomize the ingrained anatomical structures into recurrent visual patterns, and in the inference, it can identify anomalies (unseen/modified visual patterns) from the test image. Our SimSID surpasses the state of the arts in unsupervised anomaly detection by +8.0%, +5.0%, and +9.9% AUC scores on ZhangLab, COVIDx, and CheXpert benchmark datasets, respectively. Code: https://github.com/MrGiovanni/SimSID
Authors: Paraskevas Pegios, Manxi Lin, Nina Weng, Morten Bo S{\o}ndergaard Svendsen, Zahra Bashir, Siavash Bigdeli, Anders Nymark Christensen, Martin Tolsgaard, Aasa Feragen
Abstract: Obstetric ultrasound image quality is crucial for accurate diagnosis and monitoring of fetal health. However, producing high-quality standard planes is difficult, influenced by the sonographer's expertise and factors like the maternal BMI or the fetus dynamics. In this work, we propose using diffusion-based counterfactual explainable AI to generate realistic high-quality standard planes from low-quality non-standard ones. Through quantitative and qualitative evaluation, we demonstrate the effectiveness of our method in producing plausible counterfactuals of increased quality. This shows future promise both for enhancing training of clinicians by providing visual feedback, as well as for improving image quality and, consequently, downstream diagnosis and monitoring.
Authors: Renjie Pi, Tianyang Han, Wei Xiong, Jipeng Zhang, Runtao Liu, Rui Pan, Tong Zhang
Abstract: Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual information. We treat this bias as a "preference" for pretraining statistics, which hinders the model's grounding in visual input. To mitigate this issue, we propose Bootstrapped Preference Optimization (BPO), which conducts preference learning with datasets containing negative responses bootstrapped from the model itself. Specifically, we propose the following two strategies: 1) using distorted image inputs to the MLLM for eliciting responses that contain signified pretraining bias; 2) leveraging text-based LLM to explicitly inject erroneous but common elements into the original response. Those undesirable responses are paired with original annotated responses from the datasets to construct the preference dataset, which is subsequently utilized to perform preference learning. Our approach effectively suppresses pretrained LLM bias, enabling enhanced grounding in visual inputs. Extensive experimentation demonstrates significant performance improvements across multiple benchmarks, advancing the state-of-the-art in multimodal conversational systems.
Authors: Samuel Sze, Lars Kunze
Abstract: In autonomous vehicles, understanding the surrounding 3D environment of the ego vehicle in real-time is essential. A compact way to represent scenes while encoding geometric distances and semantic object information is via 3D semantic occupancy maps. State of the art 3D mapping methods leverage transformers with cross-attention mechanisms to elevate 2D vision-centric camera features into the 3D domain. However, these methods encounter significant challenges in real-time applications due to their high computational demands during inference. This limitation is particularly problematic in autonomous vehicles, where GPU resources must be shared with other tasks such as localization and planning. In this paper, we introduce an approach that extracts features from front-view 2D camera images and LiDAR scans, then employs a sparse convolution network (Minkowski Engine), for 3D semantic occupancy prediction. Given that outdoor scenes in autonomous driving scenarios are inherently sparse, the utilization of sparse convolution is particularly apt. By jointly solving the problems of 3D scene completion of sparse scenes and 3D semantic segmentation, we provide a more efficient learning framework suitable for real-time applications in autonomous vehicles. We also demonstrate competitive accuracy on the nuScenes dataset.
Authors: Shihan Qiu, Shaoyan Pan, Yikang Liu, Lin Zhao, Jian Xu, Qi Liu, Terrence Chen, Eric Z. Chen, Xiao Chen, Shanhui Sun
Abstract: The currently limited quality of accelerated cardiac cine reconstruction may potentially be improved by the emerging diffusion models, but the clinically unacceptable long processing time poses a challenge. We aim to develop a clinically feasible diffusion-model-based reconstruction pipeline to improve the image quality of cine MRI. A multi-in multi-out diffusion enhancement model together with fast inference strategies were developed to be used in conjunction with a reconstruction model. The diffusion reconstruction reduced spatial and temporal blurring in prospectively undersampled clinical data, as validated by experts inspection. The 1.5s per video processing time enabled the approach to be applied in clinical scenarios.
Authors: Shihan Qiu, Shaoyan Pan, Yikang Liu, Lin Zhao, Jian Xu, Qi Liu, Terrence Chen, Eric Z. Chen, Xiao Chen, Shanhui Sun
Abstract: Current deep learning reconstruction for accelerated cardiac cine MRI suffers from spatial and temporal blurring. We aim to improve image sharpness and motion delineation for cine MRI under high undersampling rates. A spatiotemporal diffusion enhancement model conditional on an existing deep learning reconstruction along with a novel paired sampling strategy was developed. The diffusion model provided sharper tissue boundaries and clearer motion than the original reconstruction in experts evaluation on clinical data. The innovative paired sampling strategy substantially reduced artificial noises in the generative results.
Authors: Yun Xin Teoh, Alice Othmani, Siew Li Goh, Juliana Usman, Khin Wee Lai
Abstract: Knee osteoarthritis is a degenerative joint disease that induces chronic pain and disability. Bone morphological analysis is a promising tool to understand the mechanical aspect of this disorder. This study proposes a 2D bone morphological analysis using manually segmented bones to explore morphological features related to distinct pain conditions. Furthermore, six semantic segmentation algorithms are assessed for extracting femur and tibia bones from X-ray images. Our analysis reveals that the morphology of the femur undergoes significant changes in instances where pain worsens. Conversely, improvements in pain may not manifest pronounced alterations in bone shape. The few-shot-learning-based algorithm, UniverSeg, demonstrated superior segmentation results with Dice scores of 99.69% for femur and 99.60% for tibia. Regarding pain condition classification, the zero-shot-learning-based algorithm, CP-SAM, achieved the highest accuracy at 66% among all models. UniverSeg is recommended for automatic knee bone segmentation, while SAM models show potential with prompt encoder modifications for optimized outcomes. These findings highlight the effectiveness of few-shot learning for semantic segmentation and the potential of zero-shot learning in enhancing classification models for knee osteoarthritis diagnosis.
Authors: Chenhao Lin, Jingyi Deng, Pengbin Hu, Chao Shen, Qian Wang, Qi Li
Abstract: Deepfake detection automatically recognizes the manipulated medias through the analysis of the difference between manipulated and non-altered videos. It is natural to ask which are the top performers among the existing deepfake detection approaches to identify promising research directions and provide practical guidance. Unfortunately, it's difficult to conduct a sound benchmarking comparison of existing detection approaches using the results in the literature because evaluation conditions are inconsistent across studies. Our objective is to establish a comprehensive and consistent benchmark, to develop a repeatable evaluation procedure, and to measure the performance of a range of detection approaches so that the results can be compared soundly. A challenging dataset consisting of the manipulated samples generated by more than 13 different methods has been collected, and 11 popular detection approaches (9 algorithms) from the existing literature have been implemented and evaluated with 6 fair-minded and practical evaluation metrics. Finally, 92 models have been trained and 644 experiments have been performed for the evaluation. The results along with the shared data and evaluation methodology constitute a benchmark for comparing deepfake detection approaches and measuring progress.
Authors: Abol Basher, Jani Boutellier
Abstract: Dense point cloud generation from a sparse or incomplete point cloud is a crucial and challenging problem in 3D computer vision and computer graphics. So far, the existing methods are either computationally too expensive, suffer from limited resolution, or both. In addition, some methods are strictly limited to watertight surfaces -- another major obstacle for a number of applications. To address these issues, we propose a lightweight Convolutional Neural Network that learns and predicts the unsigned distance field for arbitrary 3D shapes for dense point cloud generation using the recently emerged concept of implicit function learning. Experiments demonstrate that the proposed architecture outperforms the state of the art by 7.8x less model parameters, 2.4x faster inference time and up to 24.8% improved generation quality compared to the state-of-the-art.
Authors: Mat\'eo Mahaut, Francesca Franzon, Roberto Dess\`i, Marco Baroni
Abstract: As large pre-trained image-processing neural networks are being embedded in autonomous agents such as self-driving cars or robots, the question arises of how such systems can communicate with each other about the surrounding world, despite their different architectures and training regimes. As a first step in this direction, we systematically explore the task of \textit{referential communication} in a community of heterogeneous state-of-the-art pre-trained visual networks, showing that they can develop, in a self-supervised way, a shared protocol to refer to a target object among a set of candidates. This shared protocol can also be used, to some extent, to communicate about previously unseen object categories of different granularity. Moreover, a visual network that was not initially part of an existing community can learn the community's protocol with remarkable ease. Finally, we study, both qualitatively and quantitatively, the properties of the emergent protocol, providing some evidence that it is capturing high-level semantic features of objects.
Authors: George Stoica, Daniel Bolya, Jakob Bjorner, Pratik Ramesh, Taylor Hearn, Judy Hoffman
Abstract: Typical deep visual recognition models are capable of performing the one task they were trained on. In this paper, we tackle the extremely difficult problem of combining distinct models with different initializations, each solving a separate task, into one multi-task model without any additional training. Prior work in model merging permutes one model to the space of the other then averages them together. While this works for models trained on the same task, we find that this fails to account for the differences in models trained on disjoint tasks. Thus, we introduce "ZipIt!", a general method for merging two arbitrary models of the same architecture that incorporates two simple strategies. First, in order to account for features that aren't shared between models, we expand the model merging problem to allow for merging features within each model by defining a general "zip" operation. Second, we add support for partially zipping the models up until a specified layer, naturally creating a multi-head model. We find that these two changes combined account for 20-60% improvement over prior work, making it more feasible to merge models trained on disjoint tasks without retraining.
Authors: Maoxun Yuan, Xingxing Wei
Abstract: Object detection on visible (RGB) and infrared (IR) images, as an emerging solution to facilitate robust detection for around-the-clock applications, has received extensive attention in recent years. With the help of IR images, object detectors have been more reliable and robust in practical applications by using RGB-IR combined information. However, existing methods still suffer from modality miscalibration and fusion imprecision problems. Since transformer has the powerful capability to model the pairwise correlations between different features, in this paper, we propose a novel Calibrated and Complementary Transformer called $\mathrm{C}^2$Former to address these two problems simultaneously. In $\mathrm{C}^2$Former, we design an Inter-modality Cross-Attention (ICA) module to obtain the calibrated and complementary features by learning the cross-attention relationship between the RGB and IR modality. To reduce the computational cost caused by computing the global attention in ICA, an Adaptive Feature Sampling (AFS) module is introduced to decrease the dimension of feature maps. Because $\mathrm{C}^2$Former performs in the feature domain, it can be embedded into existed RGB-IR object detectors via the backbone network. Thus, one single-stage and one two-stage object detector both incorporating our $\mathrm{C}^2$Former are constructed to evaluate its effectiveness and versatility. With extensive experiments on the DroneVehicle and KAIST RGB-IR datasets, we verify that our method can fully utilize the RGB-IR complementary information and achieve robust detection results. The code is available at https://github.com/yuanmaoxun/Calibrated-and-Complementary-Transformer-for-RGB-Infrared-Object-Detection.git.
Authors: Qin Zhang, Linghan Xu, Qingming Tang, Jun Fang, Ying Nian Wu, Joe Tighe, Yifan Xing
Abstract: Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice of using a fixed threshold to declare a match, this gives rise to significant performance variations in terms of false accept rate (FAR) and false reject rate (FRR) across test classes and data distributions. We define this issue in DML as threshold inconsistency. In real-world applications, such inconsistency often complicates the threshold selection process when deploying commercial image retrieval systems. To measure this inconsistency, we propose a novel variance-based metric called Operating-Point-Inconsistency-Score (OPIS) that quantifies the variance in the operating characteristics across classes. Using the OPIS metric, we find that achieving high accuracy levels in a DML model does not automatically guarantee threshold consistency. In fact, our investigation reveals a Pareto frontier in the high-accuracy regime, where existing methods to improve accuracy often lead to degradation in threshold consistency. To address this trade-off, we introduce the Threshold-Consistent Margin (TCM) loss, a simple yet effective regularization technique that promotes uniformity in representation structures across classes by selectively penalizing hard sample pairs. Extensive experiments demonstrate TCM's effectiveness in enhancing threshold consistency while preserving accuracy, simplifying the threshold selection process in practical DML settings.
Authors: Yiming Wu, Ruixiang Li, Zequn Qin, Xinhai Zhao, Xi Li
Abstract: Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into all previous BEV representation generation methods, we found that most of them fall into two types: modeling depths in image views or modeling heights in the BEV space, mostly in an implicit way. In this work, we propose to explicitly model heights in the BEV space, which needs no extra data like LiDAR and can fit arbitrary camera rigs and types compared to modeling depths. Theoretically, we give proof of the equivalence between height-based methods and depth-based methods. Considering the equivalence and some advantages of modeling heights, we propose HeightFormer, which models heights and uncertainties in a self-recursive way. Without any extra data, the proposed HeightFormer could estimate heights in BEV accurately. Benchmark results show that the performance of HeightFormer achieves SOTA compared with those camera-only methods.
Authors: Marwane Hariat, Olivier Laurent, R\'emi Kazmierczak, Shihao Zhang, Andrei Bursuc, Angela Yao, Gianni Franchi
Abstract: Semantic segmentation methods have advanced significantly. Still, their robustness to real-world perturbations and object types not seen during training remains a challenge, particularly in safety-critical applications. We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models. Specifically, we design Robusta, a novel robust conditional generative adversarial network to generate realistic and plausible perturbed images that can be used to train reliable segmentation models. We conduct in-depth studies of the proposed generative model, assess the performance and robustness of the downstream segmentation network, and demonstrate that our approach can significantly enhance the robustness in the face of real-world perturbations, distribution shifts, and out-of-distribution samples. Our results suggest that this approach could be valuable in safety-critical applications, where the reliability of perception modules such as semantic segmentation is of utmost importance and comes with a limited computational budget in inference. We release our code at https://github.com/ENSTA-U2IS-AI/robusta.
Authors: Kaixin Cai, Pengzhen Ren, Yi Zhu, Hang Xu, Jianzhuang Liu, Changlin Li, Guangrun Wang, Xiaodan Liang
Abstract: Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face difficulties in learning fine-grained semantic alignment at the pixel level and predicting accurate object masks. To address this issue, we propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model's ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence. Our approach involves generating fine-grained patch-text pairs data by mixing image patches while preserving the correspondence between patches and text. The model is then trained to minimize the segmentation loss of the mixed images and the two contrastive losses of the original and restored features. With MixReorg as a mask learner, conventional text-supervised semantic segmentation models can achieve highly generalizable pixel-semantic alignment ability, which is crucial for open-world segmentation. After training with large-scale image-text data, MixReorg models can be applied directly to segment visual objects of arbitrary categories, without the need for further fine-tuning. Our proposed framework demonstrates strong performance on popular zero-shot semantic segmentation benchmarks, outperforming GroupViT by significant margins of 5.0%, 6.2%, 2.5%, and 3.4% mIoU on PASCAL VOC2012, PASCAL Context, MS COCO, and ADE20K, respectively.
Authors: Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Mengmeng Wang, Jingdong Wang
Abstract: Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and complex scene images from user-specified layouts, has risen to prominence. However, existing methods transform layout information into tokens or RGB images for conditional control in the generative process, leading to insufficient spatial and semantic controllability of individual instances. To address these limitations, we propose a novel Spatial-Semantic Map Guided (SSMG) diffusion model that adopts the feature map, derived from the layout, as guidance. Owing to rich spatial and semantic information encapsulated in well-designed feature maps, SSMG achieves superior generation quality with sufficient spatial and semantic controllability compared to previous works. Additionally, we propose the Relation-Sensitive Attention (RSA) and Location-Sensitive Attention (LSA) mechanisms. The former aims to model the relationships among multiple objects within scenes while the latter is designed to heighten the model's sensitivity to the spatial information embedded in the guidance. Extensive experiments demonstrate that SSMG achieves highly promising results, setting a new state-of-the-art across a range of metrics encompassing fidelity, diversity, and controllability.
Authors: Giuseppe Vecchio, Renato Sortino, Simone Palazzo, Concetto Spampinato
Abstract: Creating high-quality materials in computer graphics is a challenging and time-consuming task, which requires great expertise. To simplify this process, we introduce MatFuse, a unified approach that harnesses the generative power of diffusion models for creation and editing of 3D materials. Our method integrates multiple sources of conditioning, including color palettes, sketches, text, and pictures, enhancing creative possibilities and granting fine-grained control over material synthesis. Additionally, MatFuse enables map-level material editing capabilities through latent manipulation by means of a multi-encoder compression model which learns a disentangled latent representation for each map. We demonstrate the effectiveness of MatFuse under multiple conditioning settings and explore the potential of material editing. Finally, we assess the quality of the generated materials both quantitatively in terms of CLIP-IQA and FID scores and qualitatively by conducting a user study. Source code for training MatFuse and supplemental materials are publicly available at https://gvecchio.com/matfuse.
Authors: Himanshu Pahadia, Duo Lu, Bharatesh Chakravarthi, Yezhou Yang
Abstract: Intelligent transportation systems (ITS) have revolutionized modern road infrastructure, providing essential functionalities such as traffic monitoring, road safety assessment, congestion reduction, and law enforcement. Effective vehicle detection and accurate vehicle pose estimation are crucial for ITS, particularly using monocular cameras installed on the road infrastructure. One fundamental challenge in vision-based vehicle monitoring is keypoint detection, which involves identifying and localizing specific points on vehicles (such as headlights, wheels, taillights, etc.). However, this task is complicated by vehicle model and shape variations, occlusion, weather, and lighting conditions. Furthermore, existing traffic perception datasets for keypoint detection predominantly focus on frontal views from ego vehicle-mounted sensors, limiting their usability in traffic monitoring. To address these issues, we propose SKoPe3D, a unique synthetic vehicle keypoint dataset generated using the CARLA simulator from a roadside perspective. This comprehensive dataset includes generated images with bounding boxes, tracking IDs, and 33 keypoints for each vehicle. Spanning over 25k images across 28 scenes, SKoPe3D contains over 150k vehicle instances and 4.9 million keypoints. To demonstrate its utility, we trained a keypoint R-CNN model on our dataset as a baseline and conducted a thorough evaluation. Our experiments highlight the dataset's applicability and the potential for knowledge transfer between synthetic and real-world data. By leveraging the SKoPe3D dataset, researchers and practitioners can overcome the limitations of existing datasets, enabling advancements in vehicle keypoint detection for ITS.
Authors: Chengyou Jia, Minnan Luo, Zhuohang Dang, Guang Dai, Xiaojun Chang, Jingdong Wang
Abstract: Dominant Person Search methods aim to localize and recognize query persons in a unified network, which jointly optimizes two sub-tasks, \ie, pedestrian detection and Re-IDentification (ReID). Despite significant progress, current methods face two primary challenges: 1) the pedestrian candidates learned within detectors are suboptimal for the ReID task. 2) the potential for collaboration between two sub-tasks is overlooked. To address these issues, we present a novel Person Search framework based on the Diffusion model, PSDiff. PSDiff formulates the person search as a dual denoising process from noisy boxes and ReID embeddings to ground truths. Distinct from the conventional Detection-to-ReID approach, our denoising paradigm discards prior pedestrian candidates generated by detectors, thereby avoiding the local optimum problem of the ReID task. Following the new paradigm, we further design a new Collaborative Denoising Layer (CDL) to optimize detection and ReID sub-tasks in an iterative and collaborative way, which makes two sub-tasks mutually beneficial. Extensive experiments on the standard benchmarks show that PSDiff achieves state-of-the-art performance with fewer parameters and elastic computing overhead.
Authors: Shiyu Xuan, Qingpei Guo, Ming Yang, Shiliang Zhang
Abstract: Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referring-expression-bounding-box pairs. These methods enable the generation of high-quality instruction data which includes a wide range of fundamental abilities essential for fine-grained image perception. Moreover, we argue that the visual encoder should be tuned during instruction tuning to mitigate the gap between full image perception and fine-grained image perception. Experimental results demonstrate the superior performance of our method. For instance, our model exhibits a 5.2% accuracy improvement over Qwen-VL on GQA and surpasses the accuracy of Kosmos-2 by 24.7% on RefCOCO_val. We have also attained the top rank on the leaderboard of MMBench. This promising performance is achieved by training on only publicly available data, making it easily reproducible. The models, datasets, and codes are publicly available at https://github.com/SY-Xuan/Pink.
Authors: Xiaoxiao Sun, Xingjian Leng, Zijian Wang, Yang Yang, Zi Huang, Liang Zheng
Abstract: Analyzing model performance in various unseen environments is a critical research problem in the machine learning community. To study this problem, it is important to construct a testbed with out-of-distribution test sets that have broad coverage of environmental discrepancies. However, existing testbeds typically either have a small number of domains or are synthesized by image corruptions, hindering algorithm design that demonstrates real-world effectiveness. In this paper, we introduce CIFAR-10-Warehouse, consisting of 180 datasets collected by prompting image search engines and diffusion models in various ways. Generally sized between 300 and 8,000 images, the datasets contain natural images, cartoons, certain colors, or objects that do not naturally appear. With CIFAR-10-W, we aim to enhance the evaluation and deepen the understanding of two generalization tasks: domain generalization and model accuracy prediction in various out-of-distribution environments. We conduct extensive benchmarking and comparison experiments and show that CIFAR-10-W offers new and interesting insights inherent to these tasks. We also discuss other fields that would benefit from CIFAR-10-W.
Authors: Xiaoxiao Sun, Yue Yao, Shengjin Wang, Hongdong Li, Liang Zheng
Abstract: For object re-identification (re-ID), learning from synthetic data has become a promising strategy to cheaply acquire large-scale annotated datasets and effective models, with few privacy concerns. Many interesting research problems arise from this strategy, e.g., how to reduce the domain gap between synthetic source and real-world target. To facilitate developing more new approaches in learning from synthetic data, we introduce the Alice benchmarks, large-scale datasets providing benchmarks as well as evaluation protocols to the research community. Within the Alice benchmarks, two object re-ID tasks are offered: person and vehicle re-ID. We collected and annotated two challenging real-world target datasets: AlicePerson and AliceVehicle, captured under various illuminations, image resolutions, etc. As an important feature of our real target, the clusterability of its training set is not manually guaranteed to make it closer to a real domain adaptation test scenario. Correspondingly, we reuse existing PersonX and VehicleX as synthetic source domains. The primary goal is to train models from synthetic data that can work effectively in the real world. In this paper, we detail the settings of Alice benchmarks, provide an analysis of existing commonly-used domain adaptation methods, and discuss some interesting future directions. An online server has been set up for the community to evaluate methods conveniently and fairly. Datasets and the online server details are available at https://sites.google.com/view/alice-benchmarks.
Authors: Bohan Zeng, Shanglin Li, Yutang Feng, Hong Li, Sicheng Gao, Jiaming Liu, Huaxia Li, Xu Tang, Jianzhuang Liu, Baochang Zhang
Abstract: Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to supervise 3D generation. These methods enable the synthesis of detailed and photorealistic textured objects. However, the appearance of 3D objects produced by these text-to-3D methods is unpredictable, and it is hard for the single-image-to-3D methods to deal with complex images, thus posing a challenge in generating appearance-controllable 3D objects. To achieve controllable complex 3D object synthesis, we introduce IPDreamer, a novel approach that incorporates $\textbf{I}$mage $\textbf{P}$rompts to provide specific and comprehensive appearance information for 3D object generation. Our results demonstrate that IPDreamer effectively generates high-quality 3D objects that are consistent with both the provided text and the appearance of complex image prompts, demonstrating its promising capability in appearance-controllable 3D object generation. Our code is avaliable at https://github.com/zengbohan0217/IPDreamer.
Authors: Lijun Yu, Jos\'e Lezama, Nitesh B. Gundavarapu, Luca Versari, Kihyuk Sohn, David Minnen, Yong Cheng, Vighnesh Birodkar, Agrim Gupta, Xiuye Gu, Alexander G. Hauptmann, Boqing Gong, Ming-Hsuan Yang, Irfan Essa, David A. Ross, Lu Jiang
Abstract: While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.
Authors: Fei Shen, Hu Ye, Jun Zhang, Cong Wang, Xiao Han, Wei Yang
Abstract: Recent work has showcased the significant potential of diffusion models in pose-guided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose information, remains a formidable challenge. This paper presents Progressive Conditional Diffusion Models (PCDMs) that incrementally bridge the gap between person images under the target and source poses through three stages. Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance. Then, the second stage establishes a dense correspondence between the source and target images using the global features from the previous stage, and an inpainting conditional diffusion model is proposed to further align and enhance the contextual features, generating a coarse-grained person image. In the third stage, we propose a refining conditional diffusion model to utilize the coarsely generated image from the previous stage as a condition, achieving texture restoration and enhancing fine-detail consistency. The three-stage PCDMs work progressively to generate the final high-quality and high-fidelity synthesized image. Both qualitative and quantitative results demonstrate the consistency and photorealism of our proposed PCDMs under challenging scenarios.The code and model will be available at https://github.com/tencent-ailab/PCDMs.
Authors: Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip Torr
Abstract: Neural surface reconstruction is sensitive to the camera pose noise, even if state-of-the-art pose estimators like COLMAP or ARKit are used. More importantly, existing Pose-NeRF joint optimisation methods have struggled to improve pose accuracy in challenging real-world scenarios. To overcome the challenges, we introduce the pose residual field (PoRF), a novel implicit representation that uses an MLP for regressing pose updates. This is more robust than the conventional pose parameter optimisation due to parameter sharing that leverages global information over the entire sequence. Furthermore, we propose an epipolar geometry loss to enhance the supervision that leverages the correspondences exported from COLMAP results without the extra computational overhead. Our method yields promising results. On the DTU dataset, we reduce the rotation error by 78\% for COLMAP poses, leading to the decreased reconstruction Chamfer distance from 3.48mm to 0.85mm. On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69.18 to 75.67, outperforming that with the dataset provided ground-truth pose (75.14). These achievements demonstrate the efficacy of our approach in refining camera poses and improving the accuracy of neural surface reconstruction in real-world scenarios.
Authors: Jiarong Wei, Yancong Lin, Holger Caesar
Abstract: Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then training a model from these samples. We identify two problems with existing active learning methods for LiDAR semantic segmentation. First, they overlook the severe class imbalance inherent in LiDAR semantic segmentation datasets. Second, to bootstrap the active learning loop when there is no labeled data available, they train their initial model from randomly selected data samples, leading to low performance. This situation is referred to as the cold start problem. To address these problems we propose BaSAL, a size-balanced warm start active learning model, based on the observation that each object class has a characteristic size. By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced. Furthermore, in contrast to existing information measures like entropy or CoreSet, size-based sampling does not require a pretrained model, thus addressing the cold start problem effectively. Results show that we are able to improve the performance of the initial model by a large margin. Combining warm start and size-balanced sampling with established information measures, our approach achieves comparable performance to training on the entire SemanticKITTI dataset, despite using only 5% of the annotations, outperforming existing active learning methods. We also match the existing state-of-the-art in active learning on nuScenes. Our code is available at: https://github.com/Tony-WJR/BaSAL.
Authors: Chenyangguang Zhang, Guanlong Jiao, Yan Di, Gu Wang, Ziqin Huang, Ruida Zhang, Fabian Manhardt, Bowen Fu, Federico Tombari, Xiangyang Ji
Abstract: Previous works concerning single-view hand-held object reconstruction typically rely on supervision from 3D ground-truth models, which are hard to collect in real world. In contrast, readily accessible hand-object videos offer a promising training data source, but they only give heavily occluded object observations. In this paper, we present a novel synthetic-to-real framework to exploit Multi-view Occlusion-aware supervision from hand-object videos for Hand-held Object reconstruction (MOHO) from a single image, tackling two predominant challenges in such setting: hand-induced occlusion and object's self-occlusion. First, in the synthetic pre-training stage, we render a large-scaled synthetic dataset SOMVideo with hand-object images and multi-view occlusion-free supervisions, adopted to address hand-induced occlusion in both 2D and 3D spaces. Second, in the real-world finetuning stage, MOHO leverages the amodal-mask-weighted geometric supervision to mitigate the unfaithful guidance caused by the hand-occluded supervising views in real world. Moreover, domain-consistent occlusion-aware features are amalgamated in MOHO to resist object's self-occlusion for inferring the complete object shape. Extensive experiments on HO3D and DexYCB datasets demonstrate 2D-supervised MOHO gains superior results against 3D-supervised methods by a large margin.
Authors: Haoran Wang, Qiuye Jin, Shiman Li, Siyu Liu, Manning Wang, Zhijian Song
Abstract: Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets. Yet, the high cost of annotating medical images severely hampers the development of deep learning in this field. To reduce annotation costs, active learning aims to select the most informative samples for annotation and train high-performance models with as few labeled samples as possible. In this survey, we review the core methods of active learning, including the evaluation of informativeness and sampling strategy. For the first time, we provide a detailed summary of the integration of active learning with other label-efficient techniques, such as semi-supervised, self-supervised learning, and so on. We also summarize active learning works that are specifically tailored to medical image analysis. Additionally, we conduct a thorough comparative analysis of the performance of different AL methods in medical image analysis with experiments. In the end, we offer our perspectives on the future trends and challenges of active learning and its applications in medical image analysis.
Authors: Zeren Chen, Ziqin Wang, Zhen Wang, Huayang Liu, Zhenfei Yin, Si Liu, Lu Sheng, Wanli Ouyang, Yu Qiao, Jing Shao
Abstract: Recent studies have demonstrated Large Language Models (LLMs) can extend their zero-shot generalization capabilities to multimodal learning through instruction tuning. As more modalities and downstream tasks are introduced, negative conflicts and interference may have a worse impact on performance. While this phenomenon has been overlooked in previous work, we propose a novel and extensible framework, called Octavius, for comprehensive studies and experimentation on multimodal learning with Multimodal Large Language Models (MLLMs). Specifically, we combine the well-known Mixture-of-Experts (MoE) and one of the representative PEFT techniques, i.e., LoRA, designing a novel LLM-based decoder, called LoRA-MoE, for multimodal learning. To the best of our knowledge, we are one of the pioneering efforts to introduce MoE into MLLMs to address this problem. The experimental results (about 20% improvement) have shown the effectiveness and versatility of our design in various 2D and 3D downstream tasks. Code and datasets are available at https://openlamm.github.io/paper_list/Octavius.
Authors: Xingzhe He, Zhiwen Cao, Nicholas Kolkin, Lantao Yu, Helge Rhodin, Ratheesh Kalarot
Abstract: Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to interest in how to personalize a text-to-image model. Despite significant progress, this task remains a formidable challenge, particularly in preserving the subject's identity. Most researchers attempt to address this issue by modifying model architectures. These methods are capable of keeping the subject structure and color but fail to preserve identity details. Towards this issue, our approach takes a data-centric perspective. We introduce a novel regularization dataset generation strategy on both the text and image level. This strategy enables the model to preserve fine details of the desired subjects, such as text and logos. Our method is architecture-agnostic and can be flexibly applied on various text-to-image models. We show on established benchmarks that our data-centric approach forms the new state of the art in terms of identity preservation and text alignment.
Authors: Peng Wu, Xuerong Zhou, Guansong Pang, Yujia Sun, Jing Liu, Peng Wang, Yanning Zhang
Abstract: Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. However, current approaches are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. However, such a setting focuses on predicting frame anomaly scores, having no ability to recognize the specific categories of anomalies, despite the fact that this ability is essential for building more informed video surveillance systems. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies. To this end, we propose a model that decouples OVVAD into two mutually complementary tasks -- class-agnostic detection and class-specific classification -- and jointly optimizes both tasks. Particularly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task. These semantic knowledge and synthesis anomalies substantially extend our model's capability in detecting and categorizing a variety of seen and unseen anomalies. Extensive experiments on three widely-used benchmarks demonstrate our model achieves state-of-the-art performance on OVVAD task.
Authors: Yan Li, Weiwei Guo, Xue Yang, Ning Liao, Dunyun He, Jiaqi Zhou, Wenxian Yu
Abstract: An increasingly massive number of remote-sensing images spurs the development of extensible object detectors that can detect objects beyond training categories without costly collecting new labeled data. In this paper, we aim to develop open-vocabulary object detection (OVD) technique in aerial images that scales up object vocabulary size beyond training data. The fundamental challenges hinder open vocabulary object detection performance: the qualities of the class-agnostic region proposals and the pseudo-labels that can generalize well to novel object categories. To simultaneously generate high-quality proposals and pseudo-labels, we propose CastDet, a CLIP-activated student-teacher open-vocabulary object Detection framework. Our end-to-end framework following the student-teacher self-learning mechanism employs the RemoteCLIP model as an extra omniscient teacher with rich knowledge. By doing so, our approach boosts not only novel object proposals but also classification. Furthermore, we devise a dynamic label queue strategy to maintain high-quality pseudo labels during batch training. We conduct extensive experiments on multiple existing aerial object detection datasets, which are set up for the OVD task. Experimental results demonstrate our CastDet achieving superior open-vocabulary detection performance, e.g., reaching 40.5\% mAP, which outperforms previous methods Detic/ViLD by 23.7%/14.9% on the VisDroneZSD dataset. To our best knowledge, this is the first work to apply and develop the open-vocabulary object detection technique for aerial images.
Authors: McKell Woodland, Austin Castelo, Mais Al Taie, Jessica Albuquerque Marques Silva, Mohamed Eltaher, Frank Mohn, Alexander Shieh, Austin Castelo, Suprateek Kundu, Joshua P. Yung, Ankit B. Patel, Kristy K. Brock
Abstract: Fr\'echet Inception Distance (FID) is a widely used metric for assessing synthetic image quality. It relies on an ImageNet-based feature extractor, making its applicability to medical imaging unclear. A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images. Our study challenges this practice by demonstrating that ImageNet-based extractors are more consistent and aligned with human judgment than their RadImageNet counterparts. We evaluated sixteen StyleGAN2 networks across four medical imaging modalities and four data augmentation techniques with Fr\'echet distances (FDs) computed using eleven ImageNet or RadImageNet-trained feature extractors. Comparison with human judgment via visual Turing tests revealed that ImageNet-based extractors produced rankings consistent with human judgment, with the FD derived from the ImageNet-trained SwAV extractor significantly correlating with expert evaluations. In contrast, RadImageNet-based rankings were volatile and inconsistent with human judgment. Our findings challenge prevailing assumptions, providing novel evidence that medical image-trained feature extractors do not inherently improve FDs and can even compromise their reliability. Our code is available at https://github.com/mckellwoodland/fid-med-eval.
Authors: Pingyi Chen, Honglin Li, Chenglu Zhu, Sunyi Zheng, Zhongyi Shui, Lin Yang
Abstract: Whole slide images are the foundation of digital pathology for the diagnosis and treatment of carcinomas. Writing pathology reports is laborious and error-prone for inexperienced pathologists. To reduce the workload and improve clinical automation, we investigate how to generate pathology reports given whole slide images. On the data end, we curated the largest WSI-text dataset (TCGA-PathoText). In specific, we collected nearly 10000 high-quality WSI-text pairs for visual-language models by recognizing and cleaning pathology reports which narrate diagnostic slides in TCGA. On the model end, we propose the multiple instance generative model (MI-Gen) which can produce pathology reports for gigapixel WSIs. We benchmark our model on the largest subset of TCGA-PathoText. Experimental results show our model can generate pathology reports which contain multiple clinical clues and achieve competitive performance on certain slide-level tasks. We observe that simple semantic extraction from the pathology reports can achieve the best performance (0.838 of F1 score) on BRCA subtyping surpassing previous state-of-the-art approaches. Our collected dataset and related code are available.
Authors: Xinyu Tian, Shu Zou, Zhaoyuan Yang, Jing Zhang
Abstract: Although soft prompt tuning is effective in efficiently adapting Vision-Language (V&L) models for downstream tasks, it shows limitations in dealing with distribution shifts. We address this issue with Attribute-Guided Prompt Tuning (ArGue), making three key contributions. 1) In contrast to the conventional approach of directly appending soft prompts preceding class names, we align the model with primitive visual attributes generated by Large Language Models (LLMs). We posit that a model's ability to express high confidence in these attributes signifies its capacity to discern the correct class rationales. 2) We introduce attribute sampling to eliminate disadvantageous attributes, thus only semantically meaningful attributes are preserved. 3) We propose negative prompting, explicitly enumerating class-agnostic attributes to activate spurious correlations and encourage the model to generate highly orthogonal probability distributions in relation to these negative features. In experiments, our method significantly outperforms current state-of-the-art prompt tuning methods on both novel class prediction and out-of-distribution generalization tasks.
Authors: Song Tang, Wenxin Su, Mao Ye, Xiatian Zhu
Abstract: Source-Free Domain Adaptation (SFDA) aims to adapt a source model for a target domain, with only access to unlabeled target training data and the source model pre-trained on a supervised source domain. Relying on pseudo labeling and/or auxiliary supervision, conventional methods are inevitably error-prone. To mitigate this limitation, in this work we for the first time explore the potentials of off-the-shelf vision-language (ViL) multimodal models (e.g.,CLIP) with rich whilst heterogeneous knowledge. We find that directly applying the ViL model to the target domain in a zero-shot fashion is unsatisfactory, as it is not specialized for this particular task but largely generic. To make it task specific, we propose a novel Distilling multimodal Foundation model(DIFO)approach. Specifically, DIFO alternates between two steps during adaptation: (i) Customizing the ViL model by maximizing the mutual information with the target model in a prompt learning manner, (ii) Distilling the knowledge of this customized ViL model to the target model. For more fine-grained and reliable distillation, we further introduce two effective regularization terms, namely most-likely category encouragement and predictive consistency. Extensive experiments show that DIFO significantly outperforms the state-of-the-art alternatives. Code is here
Authors: Siyuan Huang, Yifan Zhou, Ram Prabhakar, Xijun Liu, Yuxiang Guo, Hongrui Yi, Cheng Peng, Rama Chellappa, Chun Pong Lau
Abstract: Person Re-Identification (ReID) is a challenging problem, focusing on identifying individuals across diverse settings. However, previous ReID methods primarily concentrated on a single domain or modality, such as Clothes-Changing ReID (CC-ReID) and video ReID. Real-world ReID is not constrained by factors like clothes or input types. Recent approaches emphasize on learning semantics through pre-training to enhance ReID performance but are hindered by coarse granularity, on-clothes focus and pre-defined areas. To address these limitations, we propose a Local Semantic Extraction (LSE) module inspired by Interactive Segmentation Models. The LSE module captures fine-grained, biometric, and flexible local semantics, enhancing ReID accuracy. Additionally, we introduce Semantic ReID (SemReID), a pre-training method that leverages LSE to learn effective semantics for seamless transfer across various ReID domains and modalities. Extensive evaluations across nine ReID datasets demonstrates SemReID's robust performance across multiple domains, including clothes-changing ReID, video ReID, unconstrained ReID, and short-term ReID. Our findings highlight the importance of effective semantics in ReID, as SemReID can achieve great performances without domain-specific designs.
Authors: Hantao Yao, Rui Zhang, Changsheng Xu
Abstract: Prompt tuning represents a valuable technique for adapting pre-trained visual-language models (VLM) to various downstream tasks. Recent advancements in CoOp-based methods propose a set of learnable domain-shared or image-conditional textual tokens to facilitate the generation of task-specific textual classifiers. However, those textual tokens have a limited generalization ability regarding unseen domains, as they cannot dynamically adjust to the distribution of testing classes. To tackle this issue, we present a novel Textual-based Class-aware Prompt tuning(TCP) that explicitly incorporates prior knowledge about classes to enhance their discriminability. The critical concept of TCP involves leveraging Textual Knowledge Embedding (TKE) to map the high generalizability of class-level textual knowledge into class-aware textual tokens. By seamlessly integrating these class-aware prompts into the Text Encoder, a dynamic class-aware classifier is generated to enhance discriminability for unseen domains. During inference, TKE dynamically generates class-aware prompts related to the unseen classes. Comprehensive evaluations demonstrate that TKE serves as a plug-and-play module effortlessly combinable with existing methods. Furthermore, TCP consistently achieves superior performance while demanding less training time. Code:https://github.com/htyao89/Textual-based_Class-aware_prompt_tuning/
URLs: https://github.com/htyao89/Textual-based_Class-aware_prompt_tuning/
Authors: Yanqing Liu, Kai Wang, Wenqi Shao, Ping Luo, Yu Qiao, Mike Zheng Shou, Kaipeng Zhang, Yang You
Abstract: Visual-language pre-training has achieved remarkable success in many multi-modal tasks, largely attributed to the availability of large-scale image-text datasets. In this work, we demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning by establishing richer image-text associations for image-text datasets. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. To prevent the bias introduced by MLLMs' hallucinations and monotonous language styles, we propose "text shearing" to maintain the quality and availability of extended captions. In image-text retrieval, without introducing additional training cost, our method consistently obtains 5.6 ~ 35.0 and 16.8 ~ 46.1 improvement on Recall@1 under the fine-tuning and zero-shot settings, respectively. Notably, we obtain zero-shot results that are comparable to fine-tuning on target datasets, which encourages more exploration of the versatile use of MLLMs.
Authors: Yanlong Li, Chamara Madarasingha, Kanchana Thilakarathna
Abstract: Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges, particularly in terms of high bandwidth consumption and large storage capacity. Despite various solutions proposed thus far, with a focus on point cloud compression, upsampling, and completion, these reconstruction-related methods continue to fall short in delivering high fidelity point cloud output. As a solution, in DiffPMAE, we propose an effective point cloud reconstruction architecture. Inspired by self-supervised learning concepts, we combine Masked Auto-Encoding and Diffusion Model mechanism to remotely reconstruct point cloud data. By the nature of this reconstruction process, DiffPMAE can be extended to many related downstream tasks including point cloud compression, upsampling and completion. Leveraging ShapeNet-55 and ModelNet datasets with over 60000 objects, we validate the performance of DiffPMAE exceeding many state-of-the-art methods in-terms of auto-encoding and downstream tasks considered.
Authors: Tianhong Li, Dina Katabi, Kaiming He
Abstract: Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale unlabeled data. In the literature, the generation quality of an unconditional method has been much worse than that of its conditional counterpart. This gap can be attributed to the lack of semantic information provided by labels. In this work, we show that one can close this gap by generating semantic representations in the representation space produced by a self-supervised encoder. These representations can be used to condition the image generator. This framework, called Representation-Conditioned Generation (RCG), provides an effective solution to the unconditional generation problem without using labels. Through comprehensive experiments, we observe that RCG significantly improves unconditional generation quality: e.g., it achieves a new state-of-the-art FID of 2.15 on ImageNet 256x256, largely reducing the previous best of 5.91 by a relative 64%. Our unconditional results are situated in the same tier as the leading class-conditional ones. We hope these encouraging observations will attract the community's attention to the fundamental problem of unconditional generation. Code is available at https://github.com/LTH14/rcg.
Authors: Qian Wang, Yaoyao Liu, Hefei Ling, Yingwei Li, Qihao Liu, Ping Li, Jiazhong Chen, Alan Yuille, Ning Yu
Abstract: In response to the rapidly evolving nature of adversarial attacks against visual classifiers on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes to all types of attacks is not realistic because the environment in which defense systems operate is dynamic and comprises various unique attacks that emerge as time goes on. The defense system must gather online few-shot defense feedback to promptly enhance itself, leveraging efficient memory utilization. Therefore, we propose the first continual adversarial defense (CAD) framework that adapts to any attacks in a dynamic scenario, where various attacks emerge stage by stage. In practice, CAD is modeled under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial images. We explore and integrate cutting-edge continual learning, few-shot learning, and ensemble learning techniques to qualify the principles. Experiments conducted on CIFAR-10 and ImageNet-100 validate the effectiveness of our approach against multiple stages of modern adversarial attacks and demonstrate significant improvements over numerous baseline methods. In particular, CAD is capable of quickly adapting with minimal feedback and a low cost of defense failure, while maintaining good performance against previous attacks. Our research sheds light on a brand-new paradigm for continual defense adaptation against dynamic and evolving attacks.
Authors: Yuming Huang, Yingpin Chen, Changhui Wu, Hanrong Xie, Binhui Song, Hui Wang
Abstract: The Swin Transformer image super-resolution reconstruction network only relies on the long-range relationship of window attention and shifted window attention to explore features. This mechanism has two limitations. On the one hand, it only focuses on global features while ignoring local features. On the other hand, it is only concerned with spatial feature interactions while ignoring channel features and channel interactions, thus limiting its non-linear mapping ability. To address the above limitations, this paper proposes enhanced Swin Transformer modules via alternating aggregation of local-global features. In the local feature aggregation stage, we introduce a shift convolution to realize the interaction between local spatial information and channel information. Then, a block sparse global perception module is introduced in the global feature aggregation stage. In this module, we reorganize the spatial information first, then send the recombination information into a multi-layer perceptron unit to implement the global perception. After that, a multi-scale self-attention module and a low-parameter residual channel attention module are introduced to realize information aggregation at different scales. Finally, the proposed network is validated on five publicly available datasets. The experimental results show that the proposed network outperforms the other state-of-the-art super-resolution networks.
Authors: Huan Liu, Julia Qi, Zhenhao Li, Mohammad Hassanpour, Yang Wang, Konstantinos Plataniotis, Yuanhao Yu
Abstract: Despite the recent remarkable achievement in gaze estimation, efficient and accurate personalization of gaze estimation without labels is a practical problem but rarely touched on in the literature. To achieve efficient personalization, we take inspiration from the recent advances in Natural Language Processing (NLP) by updating a negligible number of parameters, "prompts", at the test time. Specifically, the prompt is additionally attached without perturbing original network and can contain less than 1% of a ResNet-18's parameters. Our experiments show high efficiency of the prompt tuning approach. The proposed one can be 10 times faster in terms of adaptation speed than the methods compared. However, it is non-trivial to update the prompt for personalized gaze estimation without labels. At the test time, it is essential to ensure that the minimizing of particular unsupervised loss leads to the goals of minimizing gaze estimation error. To address this difficulty, we propose to meta-learn the prompt to ensure that its updates align with the goal. Our experiments show that the meta-learned prompt can be effectively adapted even with a simple symmetry loss. In addition, we experiment on four cross-dataset validations to show the remarkable advantages of the proposed method. Code is available at https://github.com/hmarkamcan/TPGaze.
Authors: Idit Diamant, Amir Rosenfeld, Idan Achituve, Jacob Goldberger, Arnon Netzer
Abstract: Source-free domain adaptation (SFDA) aims to adapt a source-trained model to an unlabeled target domain without access to the source data. SFDA has attracted growing attention in recent years, where existing approaches focus on self-training that usually includes pseudo-labeling techniques. In this paper, we introduce a novel noise-learning approach tailored to address noise distribution in domain adaptation settings and learn to de-confuse the pseudo-labels. More specifically, we learn a noise transition matrix of the pseudo-labels to capture the label corruption of each class and learn the underlying true label distribution. Estimating the noise transition matrix enables a better true class-posterior estimation, resulting in better prediction accuracy. We demonstrate the effectiveness of our approach when combined with several SFDA methods: SHOT, SHOT++, and AaD. We obtain state-of-the-art results on three domain adaptation datasets: VisDA, DomainNet, and OfficeHome.
Authors: Jiahao Nie, Yun Xing, Gongjie Zhang, Pei Yan, Aoran Xiao, Yap-Peng Tan, Alex C. Kot, Shijian Lu
Abstract: Cross-Domain Few-Shot Segmentation (CD-FSS) poses the challenge of segmenting novel categories from a distinct domain using only limited exemplars. In this paper, we undertake a comprehensive study of CD-FSS and uncover two crucial insights: (i) the necessity of a fine-tuning stage to effectively transfer the learned meta-knowledge across domains, and (ii) the overfitting risk during the na\"ive fine-tuning due to the scarcity of novel category examples. With these insights, we propose a novel cross-domain fine-tuning strategy that addresses the challenging CD-FSS tasks. We first design Bi-directional Few-shot Prediction (BFP), which establishes support-query correspondence in a bi-directional manner, crafting augmented supervision to reduce the overfitting risk. Then we further extend BFP into Iterative Few-shot Adaptor (IFA), which is a recursive framework to capture the support-query correspondence iteratively, targeting maximal exploitation of supervisory signals from the sparse novel category samples. Extensive empirical evaluations show that our method significantly outperforms the state-of-the-arts (+7.8\%), which verifies that IFA tackles the cross-domain challenges and mitigates the overfitting simultaneously. The code is available at: https://github.com/niejiahao1998/IFA.
Authors: Tao Guo, Yinuo Wang, Shihao Shu, Diansheng Chen, Zhouping Tang, Cai Meng, Xiangzhi Bai
Abstract: Capturing voxel-wise spatial correspondence across distinct modalities is crucial for medical image analysis. However, current registration approaches are not practical enough in terms of registration accuracy and clinical applicability. In this paper, we introduce MambaMorph, a novel multi-modality deformable registration framework. Specifically, MambaMorph utilizes a Mamba-based registration module and a fine-grained, yet simple, feature extractor for efficient long-range correspondence modeling and high-dimensional feature learning, respectively. Additionally, we develop a well-annotated brain MR-CT registration dataset, SR-Reg, to address the scarcity of data in multi-modality registration. To validate MambaMorph's multi-modality registration capabilities, we conduct quantitative experiments on both our SR-Reg dataset and a public T1-T2 dataset. The experimental results on both datasets demonstrate that MambaMorph significantly outperforms the current state-of-the-art learning-based registration methods in terms of registration accuracy. Further study underscores the efficiency of the Mamba-based registration module and the lightweight feature extractor, which achieve notable registration quality while maintaining reasonable computational costs and speeds. We believe that MambaMorph holds significant potential for practical applications in medical image registration. The code for MambaMorph is available at: https://github.com/Guo-Stone/MambaMorph.
Authors: Mingrui Li, Shuhong Liu, Heng Zhou, Guohao Zhu, Na Cheng, Tianchen Deng, Hongyu Wang
Abstract: We present SGS-SLAM, the first semantic visual SLAM system based on Gaussian Splatting. It incorporates appearance, geometry, and semantic features through multi-channel optimization, addressing the oversmoothing limitations of neural implicit SLAM systems in high-quality rendering, scene understanding, and object-level geometry. We introduce a unique semantic feature loss that effectively compensates for the shortcomings of traditional depth and color losses in object optimization. Through a semantic-guided keyframe selection strategy, we prevent erroneous reconstructions caused by cumulative errors. Extensive experiments demonstrate that SGS-SLAM delivers state-of-the-art performance in camera pose estimation, map reconstruction, precise semantic segmentation, and object-level geometric accuracy, while ensuring real-time rendering capabilities.
Authors: Shufan Li, Harkanwar Singh, Aditya Grover
Abstract: In recent years, Transformers have become the de-facto architecture for sequence modeling on text and a variety of multi-dimensional data, such as images and video. However, the use of self-attention layers in a Transformer incurs prohibitive compute and memory complexity that scales quadratically w.r.t. the sequence length. A recent architecture, Mamba, based on state space models has been shown to achieve comparable performance for modeling text sequences, while scaling linearly with the sequence length. In this work, we present Mamba-ND, a generalized design extending the Mamba architecture to arbitrary multi-dimensional data. Our design alternatively unravels the input data across different dimensions following row-major orderings. We provide a systematic comparison of Mamba-ND with several other alternatives, based on prior multi-dimensional extensions such as Bi-directional LSTMs and S4ND. Empirically, we show that Mamba-ND demonstrates performance competitive with the state-of-the-art on a variety of multi-dimensional benchmarks, including ImageNet-1K classification, HMDB-51 action recognition, and ERA5 weather forecasting.
Authors: Shaojie Zhang, Yinghui Wang, Peixuan Liu, Yukai Wang, Liangyi Huang, Mingfeng Wang, Ibragim R. Atadjanov
Abstract: This paper presents, for the first time, an image enhancement methodology designed to enhance the clarity of small intestinal villi in Wireless Capsule Endoscopy (WCE) images. This method first separates the low-frequency and high-frequency components of small intestinal villi images using guided filtering. Subsequently, an adaptive light gain factor is generated based on the low-frequency component, and an adaptive gradient gain factor is derived from the convolution results of the Laplacian operator in different regions of small intestinal villi images. The obtained light gain factor and gradient gain factor are then combined to enhance the high-frequency components. Finally, the enhanced high-frequency component is fused with the original image to achieve adaptive sharpening of the edges of WCE small intestinal villi images. The experiments affirm that, compared to established WCE image enhancement methods, our approach not only accentuates the edge details of WCE small intestine villi images but also skillfully suppresses noise amplification, thereby preventing the occurrence of edge overshooting.
Authors: Chao Wu, Xiaobin Chang, Ruixuan Wang
Abstract: Deep neural networks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and achieved substantial improvements. In this paper, a novel two-branch continual learning framework is proposed to further enhance most existing CL methods. Specifically, the main branch can be any existing CL model and the newly introduced side branch is a lightweight convolutional network. The output of each main branch block is modulated by the output of the corresponding side branch block. Such a simple two-branch model can then be easily implemented and learned with the vanilla optimization setting without whistles and bells. Extensive experiments with various settings on multiple image datasets show that the proposed framework yields consistent improvements over state-of-the-art methods.
Authors: Dongliang Cao, Marvin Eisenberger, Nafie El Amrani, Daniel Cremers, Florian Bernard
Abstract: Although 3D shape matching and interpolation are highly interrelated, they are often studied separately and applied sequentially to relate different 3D shapes, thus resulting in sub-optimal performance. In this work we present a unified framework to predict both point-wise correspondences and shape interpolation between 3D shapes. To this end, we combine the deep functional map framework with classical surface deformation models to map shapes in both spectral and spatial domains. On the one hand, by incorporating spatial maps, our method obtains more accurate and smooth point-wise correspondences compared to previous functional map methods for shape matching. On the other hand, by introducing spectral maps, our method gets rid of commonly used but computationally expensive geodesic distance constraints that are only valid for near-isometric shape deformations. Furthermore, we propose a novel test-time adaptation scheme to capture both pose-dominant and shape-dominant deformations. Using different challenging datasets, we demonstrate that our method outperforms previous state-of-the-art methods for both shape matching and interpolation, even compared to supervised approaches.
Authors: Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Stewart Worrall
Abstract: This paper introduces OccFusion, a straightforward and efficient sensor fusion framework for predicting 3D occupancy. A comprehensive understanding of 3D scenes is crucial in autonomous driving, and recent models for 3D semantic occupancy prediction have successfully addressed the challenge of describing real-world objects with varied shapes and classes. However, existing methods for 3D occupancy prediction heavily rely on surround-view camera images, making them susceptible to changes in lighting and weather conditions. By integrating features from additional sensors, such as lidar and surround view radars, our framework enhances the accuracy and robustness of occupancy prediction, resulting in top-tier performance on the nuScenes benchmark. Furthermore, extensive experiments conducted on the nuScenes dataset, including challenging night and rainy scenarios, confirm the superior performance of our sensor fusion strategy across various perception ranges. The code for this framework will be made available at https://github.com/DanielMing123/OCCFusion.
Authors: Amariah Condon, Bailey Buscarino, Eric Moch, William J. Sehnert, Owen Miles, Patrick K. Herring, Peter M. Attia
Abstract: Battery technology is increasingly important for global electrification efforts. However, batteries are highly sensitive to small manufacturing variations that can induce reliability or safety issues. An important technology for battery quality control is computed tomography (CT) scanning, which is widely used for non-destructive 3D inspection across a variety of clinical and industrial applications. Historically, however, the utility of CT scanning for high-volume manufacturing has been limited by its low throughput as well as the difficulty of handling its large file sizes. In this work, we present a dataset of over one thousand CT scans of as-produced commercially available batteries. The dataset spans various chemistries (lithium-ion and sodium-ion) as well as various battery form factors (cylindrical, pouch, and prismatic). We evaluate seven different battery types in total. The manufacturing variability and the presence of battery defects can be observed via this dataset. This dataset may be of interest to scientists and engineers working on battery technology, computer vision, or both.
Authors: Deepanway Ghosal, Vernon Toh Yan Han, Chia Yew Ken, Soujanya Poria
Abstract: This paper introduces the novel task of multimodal puzzle solving, framed within the context of visual question-answering. We present a new dataset, AlgoPuzzleVQA designed to challenge and evaluate the capabilities of multimodal language models in solving algorithmic puzzles that necessitate both visual understanding, language understanding, and complex algorithmic reasoning. We create the puzzles to encompass a diverse array of mathematical and algorithmic topics such as boolean logic, combinatorics, graph theory, optimization, search, etc., aiming to evaluate the gap between visual data interpretation and algorithmic problem-solving skills. The dataset is generated automatically from code authored by humans. All our puzzles have exact solutions that can be found from the algorithm without tedious human calculations. It ensures that our dataset can be scaled up arbitrarily in terms of reasoning complexity and dataset size. Our investigation reveals that large language models (LLMs) such as GPT4V and Gemini exhibit limited performance in puzzle-solving tasks. We find that their performance is near random in a multi-choice question-answering setup for a significant number of puzzles. The findings emphasize the challenges of integrating visual, language, and algorithmic knowledge for solving complex reasoning problems.
Authors: R. Gnana Praveen, Jahangir Alam
Abstract: Person or identity verification has been recently gaining a lot of attention using audio-visual fusion as faces and voices share close associations with each other. Conventional approaches based on audio-visual fusion rely on score-level or early feature-level fusion techniques. Though existing approaches showed improvement over unimodal systems, the potential of audio-visual fusion for person verification is not fully exploited. In this paper, we have investigated the prospect of effectively capturing both the intra- and inter-modal relationships across audio and visual modalities, which can play a crucial role in significantly improving the fusion performance over unimodal systems. In particular, we introduce a recursive fusion of a joint cross-attentional model, where a joint audio-visual feature representation is employed in the cross-attention framework in a recursive fashion to progressively refine the feature representations that can efficiently capture the intra-and inter-modal relationships. To further enhance the audio-visual feature representations, we have also explored BLSTMs to improve the temporal modeling of audio-visual feature representations. Extensive experiments are conducted on the Voxceleb1 dataset to evaluate the proposed model. Results indicate that the proposed model shows promising improvement in fusion performance by adeptly capturing the intra-and inter-modal relationships across audio and visual modalities.
Authors: R. Gnana Praveen, Jahangir Alam
Abstract: Although person or identity verification has been predominantly explored using individual modalities such as face and voice, audio-visual fusion has recently shown immense potential to outperform unimodal approaches. Audio and visual modalities are often expected to pose strong complementary relationships, which plays a crucial role in effective audio-visual fusion. However, they may not always strongly complement each other, they may also exhibit weak complementary relationships, resulting in poor audio-visual feature representations. In this paper, we propose a Dynamic Cross-Attention (DCA) model that can dynamically select the cross-attended or unattended features on the fly based on the strong or weak complementary relationships, respectively, across audio and visual modalities. In particular, a conditional gating layer is designed to evaluate the contribution of the cross-attention mechanism and choose cross-attended features only when they exhibit strong complementary relationships, otherwise unattended features. Extensive experiments are conducted on the Voxceleb1 dataset to demonstrate the robustness of the proposed model. Results indicate that the proposed model consistently improves the performance on multiple variants of cross-attention while outperforming the state-of-the-art methods.
Authors: Qihao Zhao, Yalun Dai, Hao Li, Wei Hu, Fan Zhang, Jun Liu
Abstract: Long-tail recognition is challenging because it requires the model to learn good representations from tail categories and address imbalances across all categories. In this paper, we propose a novel generative and fine-tuning framework, LTGC, to handle long-tail recognition via leveraging generated content. Firstly, inspired by the rich implicit knowledge in large-scale models (e.g., large language models, LLMs), LTGC leverages the power of these models to parse and reason over the original tail data to produce diverse tail-class content. We then propose several novel designs for LTGC to ensure the quality of the generated data and to efficiently fine-tune the model using both the generated and original data. The visualization demonstrates the effectiveness of the generation module in LTGC, which produces accurate and diverse tail data. Additionally, the experimental results demonstrate that our LTGC outperforms existing state-of-the-art methods on popular long-tailed benchmarks.
Authors: Yanyi Zhang, Qi Jia, Xin Fan, Yu Liu, Ran He
Abstract: Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods based on disentangled representation learning lose sight of the contextual dependency between the A-O primitive pairs. Inspired by this, we propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet). The key insight is to firstly classify one primitive and then specifies the predicted class as a priori for guiding another primitive recognition in a cascaded fashion. To this end, CSCNet constructs Attribute-to-Object and Object-to-Attribute cascaded branches, in addition to a composition branch modeling the two primitives as a whole. Notably, we devise a parametric classifier (ParamCls) to improve the matching between visual and semantic embeddings. By improving the A-O disentanglement, our framework achieves superior results than previous competitive methods.
Authors: Minjie Zhu, Yichen Zhu, Xin Liu, Ning Liu, Zhiyuan Xu, Chaomin Shen, Yaxin Peng, Zhicai Ou, Feifei Feng, Jian Tang
Abstract: Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models, and optimization strategies. We show that without increasing the volume of training data, our Mipha-3B outperforms the state-of-the-art large MLLMs, especially LLaVA-1.5-13B, on multiple benchmarks. Through detailed discussion, we provide insights and guidelines for developing strong MSLMs that rival the capabilities of MLLMs. Our code is available at https://github.com/zhuyiche/Mipha.
Authors: Xingyi Li, Zhiguo Cao, Yizheng Wu, Kewei Wang, Ke Xian, Zhe Wang, Guosheng Lin
Abstract: Current 3D stylization methods often assume static scenes, which violates the dynamic nature of our real world. To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields. However, stylizing dynamic 3D scenes is inherently challenging due to the limited availability of stylized reference images along the temporal axis. Our key insight lies in introducing additional temporal cues besides the provided reference. To this end, we generate temporal pseudo-references from the given stylized reference. These pseudo-references facilitate the propagation of style information from the reference to the entire dynamic 3D scene. For coarse style transfer, we enforce novel views and times to mimic the style details present in pseudo-references at the feature level. To preserve high-frequency details, we create a collection of stylized temporal pseudo-rays from temporal pseudo-references. These pseudo-rays serve as detailed and explicit stylization guidance for achieving fine style transfer. Experiments on both synthetic and real-world datasets demonstrate that our method yields plausible stylized results of space-time view synthesis on dynamic 3D scenes.
Authors: Shuai Tan, Bin Ji, Yu Ding, Ye Pan
Abstract: Generating stylized talking head with diverse head motions is crucial for achieving natural-looking videos but still remains challenging. Previous works either adopt a regressive method to capture the speaking style, resulting in a coarse style that is averaged across all training data, or employ a universal network to synthesize videos with different styles which causes suboptimal performance. To address these, we propose a novel dynamic-weight method, namely Say Anything withAny Style (SAAS), which queries the discrete style representation via a generative model with a learned style codebook. Specifically, we develop a multi-task VQ-VAE that incorporates three closely related tasks to learn a style codebook as a prior for style extraction. This discrete prior, along with the generative model, enhances the precision and robustness when extracting the speaking styles of the given style clips. By utilizing the extracted style, a residual architecture comprising a canonical branch and style-specific branch is employed to predict the mouth shapes conditioned on any driving audio while transferring the speaking style from the source to any desired one. To adapt to different speaking styles, we steer clear of employing a universal network by exploring an elaborate HyperStyle to produce the style-specific weights offset for the style branch. Furthermore, we construct a pose generator and a pose codebook to store the quantized pose representation, allowing us to sample diverse head motions aligned with the audio and the extracted style. Experiments demonstrate that our approach surpasses state-of-theart methods in terms of both lip-synchronization and stylized expression. Besides, we extend our SAAS to video-driven style editing field and achieve satisfactory performance.
Authors: Rukhshanda Hussain, Hui Xian Grace Lim, Borchun Chen, Mubarak Shah, Ser Nam Lim
Abstract: Novel view synthesis has observed tremendous developments since the arrival of NeRFs. However, Nerf models overfit on a single scene, lacking generalization to out of distribution objects. Recently, diffusion models have exhibited remarkable performance on introducing generalization in view synthesis. Inspired by these advancements, we explore the capabilities of a pretrained stable diffusion model for view synthesis without explicit 3D priors. Specifically, we base our method on a personalized text to image model, Dreambooth, given its strong ability to adapt to specific novel objects with a few shots. Our research reveals two interesting findings. First, we observe that Dreambooth can learn the high level concept of a view, compared to arguably more complex strategies which involve finetuning diffusions on large amounts of multi-view data. Second, we establish that the concept of a view can be disentangled and transferred to a novel object irrespective of the original object's identify from which the views are learnt. Motivated by this, we introduce a learning strategy, FSViewFusion, which inherits a specific view through only one image sample of a single scene, and transfers the knowledge to a novel object, learnt from few shots, using low rank adapters. Through extensive experiments we demonstrate that our method, albeit simple, is efficient in generating reliable view samples for in the wild images. Code and models will be released.
Authors: Guangyang Wu, Xiaohong Liu, Jun Jia, Xuehao Cui, Guangtao Zhai
Abstract: In the digital era, QR codes serve as a linchpin connecting virtual and physical realms. Their pervasive integration across various applications highlights the demand for aesthetically pleasing codes without compromised scannability. However, prevailing methods grapple with the intrinsic challenge of balancing customization and scannability. Notably, stable-diffusion models have ushered in an epoch of high-quality, customizable content generation. This paper introduces Text2QR, a pioneering approach leveraging these advancements to address a fundamental challenge: concurrently achieving user-defined aesthetics and scanning robustness. To ensure stable generation of aesthetic QR codes, we introduce the QR Aesthetic Blueprint (QAB) module, generating a blueprint image exerting control over the entire generation process. Subsequently, the Scannability Enhancing Latent Refinement (SELR) process refines the output iteratively in the latent space, enhancing scanning robustness. This approach harnesses the potent generation capabilities of stable-diffusion models, navigating the trade-off between image aesthetics and QR code scannability. Our experiments demonstrate the seamless fusion of visual appeal with the practical utility of aesthetic QR codes, markedly outperforming prior methods. Codes are available at \url{https://github.com/mulns/Text2QR}
Authors: Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu
Abstract: Radiance fields have demonstrated impressive performance in synthesizing novel views from sparse input views, yet prevailing methods suffer from high training costs and slow inference speed. This paper introduces DNGaussian, a depth-regularized framework based on 3D Gaussian radiance fields, offering real-time and high-quality few-shot novel view synthesis at low costs. Our motivation stems from the highly efficient representation and surprising quality of the recent 3D Gaussian Splatting, despite it will encounter a geometry degradation when input views decrease. In the Gaussian radiance fields, we find this degradation in scene geometry primarily lined to the positioning of Gaussian primitives and can be mitigated by depth constraint. Consequently, we propose a Hard and Soft Depth Regularization to restore accurate scene geometry under coarse monocular depth supervision while maintaining a fine-grained color appearance. To further refine detailed geometry reshaping, we introduce Global-Local Depth Normalization, enhancing the focus on small local depth changes. Extensive experiments on LLFF, DTU, and Blender datasets demonstrate that DNGaussian outperforms state-of-the-art methods, achieving comparable or better results with significantly reduced memory cost, a $25 \times$ reduction in training time, and over $3000 \times$ faster rendering speed.
Authors: Xianzu Wu, Xianfeng Wu, Tianyu Luan, Yajing Bai, Zhongyuan Lai, Junsong Yuan
Abstract: While previous studies have demonstrated successful 3D object shape completion with a sufficient number of points, they often fail in scenarios when a few points, e.g. tens of points, are observed. Surprisingly, via entropy analysis, we find that even a few points, e.g. 64 points, could retain substantial information to help recover the 3D shape of the object. To address the challenge of shape completion with very sparse point clouds, we then propose Few-point Shape Completion (FSC) model, which contains a novel dual-branch feature extractor for handling extremely sparse inputs, coupled with an extensive branch for maximal point utilization with a saliency branch for dynamic importance assignment. This model is further bolstered by a two-stage revision network that refines both the extracted features and the decoder output, enhancing the detail and authenticity of the completed point cloud. Our experiments demonstrate the feasibility of recovering 3D shapes from a few points. The proposed Few-point Shape Completion (FSC) model outperforms previous methods on both few-point inputs and many-point inputs, and shows good generalizability to different object categories.
Authors: Weijia Wu, Zhuang Li, Yuchao Gu, Rui Zhao, Yefei He, David Junhao Zhang, Mike Zheng Shou, Yan Li, Tingting Gao, Di Zhang
Abstract: We introduce DragAnything, which utilizes a entity representation to achieve motion control for any object in controllable video generation. Comparison to existing motion control methods, DragAnything offers several advantages. Firstly, trajectory-based is more userfriendly for interaction, when acquiring other guidance signals (e.g., masks, depth maps) is labor-intensive. Users only need to draw a line (trajectory) during interaction. Secondly, our entity representation serves as an open-domain embedding capable of representing any object, enabling the control of motion for diverse entities, including background. Lastly, our entity representation allows simultaneous and distinct motion control for multiple objects. Extensive experiments demonstrate that our DragAnything achieves state-of-the-art performance for FVD, FID, and User Study, particularly in terms of object motion control, where our method surpasses the previous methods (e.g., DragNUWA) by 26% in human voting.
Authors: J. J. Cabrera, A. Santo, A. Gil, C. Viegas, L. Pay\'a
Abstract: This paper presents MinkUNeXt, an effective and efficient architecture for place-recognition from point clouds entirely based on the new 3D MinkNeXt Block, a residual block composed of 3D sparse convolutions that follows the philosophy established by recent Transformers but purely using simple 3D convolutions. Feature extraction is performed at different scales by a U-Net encoder-decoder network and the feature aggregation of those features into a single descriptor is carried out by a Generalized Mean Pooling (GeM). The proposed architecture demonstrates that it is possible to surpass the current state-of-the-art by only relying on conventional 3D sparse convolutions without making use of more complex and sophisticated proposals such as Transformers, Attention-Layers or Deformable Convolutions. A thorough assessment of the proposal has been carried out using the Oxford RobotCar and the In-house datasets. As a result, MinkUNeXt proves to outperform other methods in the state-of-the-art.
Authors: Jumin Lee, Sebin Lee, Changho Jo, Woobin Im, Juhyeong Seon, Sung-Eui Yoon
Abstract: We present "SemCity," a 3D diffusion model for semantic scene generation in real-world outdoor environments. Most 3D diffusion models focus on generating a single object, synthetic indoor scenes, or synthetic outdoor scenes, while the generation of real-world outdoor scenes is rarely addressed. In this paper, we concentrate on generating a real-outdoor scene through learning a diffusion model on a real-world outdoor dataset. In contrast to synthetic data, real-outdoor datasets often contain more empty spaces due to sensor limitations, causing challenges in learning real-outdoor distributions. To address this issue, we exploit a triplane representation as a proxy form of scene distributions to be learned by our diffusion model. Furthermore, we propose a triplane manipulation that integrates seamlessly with our triplane diffusion model. The manipulation improves our diffusion model's applicability in a variety of downstream tasks related to outdoor scene generation such as scene inpainting, scene outpainting, and semantic scene completion refinements. In experimental results, we demonstrate that our triplane diffusion model shows meaningful generation results compared with existing work in a real-outdoor dataset, SemanticKITTI. We also show our triplane manipulation facilitates seamlessly adding, removing, or modifying objects within a scene. Further, it also enables the expansion of scenes toward a city-level scale. Finally, we evaluate our method on semantic scene completion refinements where our diffusion model enhances predictions of semantic scene completion networks by learning scene distribution. Our code is available at https://github.com/zoomin-lee/SemCity.
Authors: Marco Jiralerspong, Avishek Joey Bose, Ian Gemp, Chongli Qin, Yoram Bachrach, Gauthier Gidel
Abstract: The past few years have seen impressive progress in the development of deep generative models capable of producing high-dimensional, complex, and photo-realistic data. However, current methods for evaluating such models remain incomplete: standard likelihood-based metrics do not always apply and rarely correlate with perceptual fidelity, while sample-based metrics, such as FID, are insensitive to overfitting, i.e., inability to generalize beyond the training set. To address these limitations, we propose a new metric called the Feature Likelihood Divergence (FLD), a parametric sample-based metric that uses density estimation to provide a comprehensive trichotomic evaluation accounting for novelty (i.e., different from the training samples), fidelity, and diversity of generated samples. We empirically demonstrate the ability of FLD to identify overfitting problem cases, even when previously proposed metrics fail. We also extensively evaluate FLD on various image datasets and model classes, demonstrating its ability to match intuitions of previous metrics like FID while offering a more comprehensive evaluation of generative models. Code is available at https://github.com/marcojira/fld.
Authors: Chuang Niu, Qing Lyu, Christopher D. Carothers, Parisa Kaviani, Josh Tan, Pingkun Yan, Mannudeep K. Kalra, Christopher T. Whitlow, Ge Wang
Abstract: Patient management requires multitasking interaction with multimodal data. While today's AI, particularly large foundation models, promises unprecedented opportunities, progress remains relatively slow in developing medical multimodal multitask foundation models. There are two main challenges along this direction: the data challenge -- the high bar to curate medical multimodal multitask datasets including 3D medical tomographic images in alignment with other clinical datasets, and the model challenge -- the unavailability of a scalable and adaptable foundation model architecture to synergize multimodal datasets for diverse clinical tasks. Here we propose the first-of-its-kind medical multimodal-multitask foundation model (M3FM) with an emphasis on lung cancer screening. To train our M3FM, we first curated a comprehensive multimodal multitask dataset consisting of 163,725 3D chest CT exams, 48 clinical data types, and 17 medical tasks on lung, heart, and other chest diseases. Then, we created and applied a multimodal question-answering framework as a unified training strategy to effectively integrate multimodal information and naturally perform multiple tasks with free-text prompting. Extensive experimental results demonstrate that M3FM consistently outperforms the previous state-of-the-art models. M3FM can identify informative multimodal data elements that are relevant to specific clinical tasks, being instrumental in building AI models and gaining insights into correlations among multimodal data and diseases. M3FM can be adapted to boost the performance of new tasks with a small out-of-distribution dataset. M3FM has enabled superior volumetric CT imaging performance for lung cancer screening, cardiac disease prediction, and other CT-related tasks. M3FM can be extended to incorporate more data types and improve other medical tasks, towards AI-empowered precise and efficient medicine.
Authors: Mehdi Ounissi, Morwena Latouche, Daniel Racoceanu
Abstract: Quantifying the phagocytosis of dynamic, unstained cells is essential for evaluating neurodegenerative diseases. However, measuring rapid cell interactions and distinguishing cells from background make this task very challenging when processing time-lapse phase-contrast video microscopy. In this study, we introduce an end-to-end, scalable, and versatile real-time framework for quantifying and analyzing phagocytic activity. Our proposed pipeline is able to process large data-sets and includes a data quality verification module to counteract perturbations such as microscope movements and frame blurring. We also propose an explainable cell segmentation module to improve the interpretability of DL methods compared to black-box algorithms. This includes two interpretable DL capabilities: visual explanation and model simplification. We demonstrate that interpretability in DL is not the opposite of high performance, by additionally providing essential DL algorithm optimization insights and solutions. Besides, incorporating interpretable modules results in an efficient architecture design and optimized execution time. We apply our pipeline to analyze microglial cell phagocytosis in FTD and obtain statistically reliable results showing that FTD mutant cells are larger and more aggressive than control cells. The method has been tested and validated on public benchmarks by generating state-of-the art performances. To stimulate translational approaches and future studies, we release an open-source end-to-end pipeline and a unique microglial cells phagocytosis dataset for immune system characterization in neurodegenerative diseases research. This pipeline and the associated dataset will consistently crystallize future advances in this field, promoting the development of interpretable algorithms dedicated to the domain of neurodegenerative diseases' characterization. github.com/ounissimehdi/PhagoStat
Authors: Emanuel Sanchez Aimar, Hannah Helgesen, Yonghao Xu, Marco Kuhlmann, Michael Felsberg
Abstract: Long-tailed semi-supervised learning (LTSSL) represents a practical scenario for semi-supervised applications, challenged by skewed labeled distributions that bias classifiers. This problem is often aggravated by discrepancies between labeled and unlabeled class distributions, leading to biased pseudo-labels, neglect of rare classes, and poorly calibrated probabilities. To address these issues, we introduce Flexible Distribution Alignment (FlexDA), a novel adaptive logit-adjusted loss framework designed to dynamically estimate and align predictions with the actual distribution of unlabeled data and achieve a balanced classifier by the end of training. FlexDA is further enhanced by a distillation-based consistency loss, promoting fair data usage across classes and effectively leveraging underconfident samples. This method, encapsulated in ADELLO (Align and Distill Everything All at Once), proves robust against label shift, significantly improves model calibration in LTSSL contexts, and surpasses previous state-of-of-art approaches across multiple benchmarks, including CIFAR100-LT, STL10-LT, and ImageNet127, addressing class imbalance challenges in semi-supervised learning. Our code will be made available upon paper acceptance.
Authors: Anna Bair, Hongxu Yin, Maying Shen, Pavlo Molchanov, Jose Alvarez
Abstract: Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains, while the process of compression exploits specificity in one domain. We introduce Adaptive Sharpness-Aware Pruning (AdaSAP), which unifies these goals through the lens of network sharpness. The AdaSAP method produces sparse networks that are robust to input variations which are unseen at training time. We achieve this by strategically incorporating weight perturbations in order to optimize the loss landscape. This allows the model to be both primed for pruning and regularized for improved robustness. AdaSAP improves the robust accuracy of pruned models on image classification by up to +6% on ImageNet C and +4% on ImageNet V2, and on object detection by +4% on a corrupted Pascal VOC dataset, over a wide range of compression ratios, pruning criteria, and network architectures, outperforming recent pruning art by large margins.
Authors: Hossein Shakibania, Sina Raoufi, Behnam Pourafkham, Hassan Khotanlou, Muharram Mansoorizadeh
Abstract: Diabetic retinopathy is a severe complication of diabetes that can lead to permanent blindness if not treated promptly. Early and accurate diagnosis of the disease is essential for successful treatment. This paper introduces a deep learning method for the detection and stage grading of diabetic retinopathy, using a single fundus retinal image. Our model utilizes transfer learning, employing two state-of-the-art pre-trained models as feature extractors and fine-tuning them on a new dataset. The proposed model is trained on a large multi-center dataset, including the APTOS 2019 dataset, obtained from publicly available sources. It achieves remarkable performance in diabetic retinopathy detection and stage classification on the APTOS 2019, outperforming the established literature. For binary classification, the proposed approach achieves an accuracy of 98.50, a sensitivity of 99.46, and a specificity of 97.51. In stage grading, it achieves a quadratic weighted kappa of 93.00, an accuracy of 89.60, a sensitivity of 89.60, and a specificity of 97.72. The proposed approach serves as a reliable screening and stage grading tool for diabetic retinopathy, offering significant potential to enhance clinical decision-making and patient care.
Authors: Haowei Lin, Yijia Shao, Weinan Qian, Ningxin Pan, Yiduo Guo, Bing Liu
Abstract: Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is that no task identifier (or task-id) is provided at test time. Predicting the task-id for each test sample is a challenging problem. An emerging theory-guided approach (called TIL+OOD) is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with catastrophic forgetting. The model for each task is an out-of-distribution (OOD) detector rather than a conventional classifier. The OOD detector can perform both within-task (in-distribution (IND)) class prediction and OOD detection. The OOD detection capability is the key to task-id prediction during inference. However, this paper argues that using a traditional OOD detector for task-id prediction is sub-optimal because additional information (e.g., the replay data and the learned tasks) available in CIL can be exploited to design a better and principled method for task-id prediction. We call the new method TPL (Task-id Prediction based on Likelihood Ratio). TPL markedly outperforms strong CIL baselines and has negligible catastrophic forgetting. The code of TPL is publicly available at https://github.com/linhaowei1/TPL.
Authors: Dongjun Kim, Chieh-Hsin Lai, Wei-Hsiang Liao, Naoki Murata, Yuhta Takida, Toshimitsu Uesaka, Yutong He, Yuki Mitsufuji, Stefano Ermon
Abstract: Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion process. CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance and achieves new state-of-the-art FIDs for single-step diffusion model sampling on CIFAR-10 (FID 1.73) and ImageNet at 64x64 resolution (FID 1.92). CTM also enables a new family of sampling schemes, both deterministic and stochastic, involving long jumps along the ODE solution trajectories. It consistently improves sample quality as computational budgets increase, avoiding the degradation seen in CM. Furthermore, unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods from the diffusion community. This access also enables the computation of likelihood. The code is available at https://github.com/sony/ctm.
Authors: Zhixuan Liang, Yao Mu, Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo
Abstract: Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent trajectories from high-level instructions remains challenging, especially for long-range composition tasks requiring multiple sequential skills. We propose SkillDiffuser, an end-to-end hierarchical planning framework integrating interpretable skill learning with conditional diffusion planning to address this problem. At the higher level, the skill abstraction module learns discrete, human-understandable skill representations from visual observations and language instructions. These learned skill embeddings are then used to condition the diffusion model to generate customized latent trajectories aligned with the skills. This allows generating diverse state trajectories that adhere to the learnable skills. By integrating skill learning with conditional trajectory generation, SkillDiffuser produces coherent behavior following abstract instructions across diverse tasks. Experiments on multi-task robotic manipulation benchmarks like Meta-World and LOReL demonstrate state-of-the-art performance and human-interpretable skill representations from SkillDiffuser. More visualization results and information could be found on our website.
Authors: Galib Muhammad Shahriar Himel
Abstract: Traditionally, pathological analysis and diagnosis are performed by manually eyeballing glass slide specimens under a microscope by an expert. The whole slide image is the digital specimen produced from the glass slide. Whole slide image enabled specimens to be observed on a computer screen and led to computational pathology where computer vision and artificial intelligence are utilized for automated analysis and diagnosis. With the current computational advancement, the entire whole slide image can be analyzed autonomously without human supervision. However, the analysis could fail or lead to wrong diagnosis if the whole slide image is affected by tissue artifacts such as tissue fold or air bubbles depending on the severity. Existing artifact detection methods rely on experts for severity assessment to eliminate artifact affected regions from the analysis. This process is time consuming, exhausting and undermines the goal of automated analysis or removal of artifacts without evaluating their severity, which could result in the loss of diagnostically important data. Therefore, it is necessary to detect artifacts and then assess their severity automatically. In this paper, we propose a system that incorporates severity evaluation with artifact detection utilizing convolutional neural networks. The proposed system uses DoubleUNet to segment artifacts and an ensemble network of six fine tuned convolutional neural network models to determine severity. This method outperformed current state of the art in accuracy by 9 percent for artifact segmentation and achieved a strong correlation of 97 percent with the evaluation of pathologists for severity assessment. The robustness of the system was demonstrated using our proposed heterogeneous dataset and practical usability was ensured by integrating it with an automated analysis system.
Authors: Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, Yu Su
Abstract: The recent development on large multimodal models (LMMs), especially GPT-4V(ision) and Gemini, has been quickly expanding the capability boundaries of multimodal models beyond traditional tasks like image captioning and visual question answering. In this work, we explore the potential of LMMs like GPT-4V as a generalist web agent that can follow natural language instructions to complete tasks on any given website. We propose SEEACT, a generalist web agent that harnesses the power of LMMs for integrated visual understanding and acting on the web. We evaluate on the recent MIND2WEB benchmark. In addition to standard offline evaluation on cached websites, we enable a new online evaluation setting by developing a tool that allows running web agents on live websites. We show that GPT-4V presents a great potential for web agents -- it can successfully complete 51.1 of the tasks on live websites if we manually ground its textual plans into actions on the websites. This substantially outperforms text-only LLMs like GPT-4 or smaller models (FLAN-T5 and BLIP-2) specifically fine-tuned for web agents. However, grounding still remains a major challenge. Existing LMM grounding strategies like set-of-mark prompting turns out to be not effective for web agents, and the best grounding strategy we develop in this paper leverages both the HTML structure and visuals. Yet, there is still a substantial gap with oracle grounding, leaving ample room for further improvement. All code, data, and evaluation tools are available at https://github.com/OSU-NLP-Group/SeeAct.
Authors: Jos\'e Morano, Guilherme Aresta, Hrvoje Bogunovi\'c
Abstract: The caliber and configuration of retinal blood vessels serve as important biomarkers for various diseases and medical conditions. A thorough analysis of the retinal vasculature requires the segmentation of the blood vessels and their classification into arteries and veins, typically performed on color fundus images obtained by retinography. However, manually performing these tasks is labor-intensive and prone to human error. While several automated methods have been proposed to address this task, the current state of art faces challenges due to manifest classification errors affecting the topological consistency of segmentation maps. In this work, we introduce RRWNet, a novel end-to-end deep learning framework that addresses this limitation. The framework consists of a fully convolutional neural network that recursively refines semantic segmentation maps, correcting manifest classification errors and thus improving topological consistency. In particular, RRWNet is composed of two specialized subnetworks: a Base subnetwork that generates base segmentation maps from the input images, and a Recursive Refinement subnetwork that iteratively and recursively improves these maps. Evaluation on three different public datasets demonstrates the state-of-the-art performance of the proposed method, yielding more topologically consistent segmentation maps with fewer manifest classification errors than existing approaches. In addition, the Recursive Refinement module within RRWNet proves effective in post-processing segmentation maps from other methods, further demonstrating its potential. The model code, weights, and predictions will be publicly available at https://github.com/j-morano/rrwnet.
Authors: Jiequan Cui, Beier Zhu, Xin Wen, Xiaojuan Qi, Bei Yu, Hanwang Zhang
Abstract: In this paper, we present an empirical study on image recognition fairness, i.e., extreme class accuracy disparity on balanced data like ImageNet. We experimentally demonstrate that classes are not equal and the fairness issue is prevalent for image classification models across various datasets, network architectures, and model capacities. Moreover, several intriguing properties of fairness are identified. First, the unfairness lies in problematic representation rather than classifier bias. Second, with the proposed concept of Model Prediction Bias, we investigate the origins of problematic representation during optimization. Our findings reveal that models tend to exhibit greater prediction biases for classes that are more challenging to recognize. It means that more other classes will be confused with harder classes. Then the False Positives (FPs) will dominate the learning in optimization, thus leading to their poor accuracy. Further, we conclude that data augmentation and representation learning algorithms improve overall performance by promoting fairness to some degree in image classification. The Code is available at https://github.com/dvlab-research/Parametric-Contrastive-Learning.
URLs: https://github.com/dvlab-research/Parametric-Contrastive-Learning.
Authors: Wen Wen, Mu Li, Yabin Zhang, Yiting Liao, Junlin Li, Li Zhang, Kede Ma
Abstract: Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Specifically, our model comprises a base quality predictor, a spatial rectifier, and a temporal rectifier, responding to the visual content and distortion, spatial resolution, and frame rate changes on video quality, respectively. During training, spatial and temporal rectifiers are dropped out with some probabilities so as to make the base quality predictor a standalone BVQA model, which should work better with the rectifiers. Extensive experiments on both professionally-generated content and user generated content video databases show that our quality model achieves superior or comparable performance to current methods. Furthermore, the modularity of our model offers a great opportunity to analyze existing video quality databases in terms of their spatial and temporal complexities. Last, our BVQA model is cost-effective to add other quality-relevant video attributes such as dynamic range and color gamut as additional rectifiers.
Authors: Yameng Peng, Andy Song, Haytham M. Fayek, Vic Ciesielski, Xiaojun Chang
Abstract: Training-free metrics (a.k.a. zero-cost proxies) are widely used to avoid resource-intensive neural network training, especially in Neural Architecture Search (NAS). Recent studies show that existing training-free metrics have several limitations, such as limited correlation and poor generalisation across different search spaces and tasks. Hence, we propose Sample-Wise Activation Patterns and its derivative, SWAP-Score, a novel high-performance training-free metric. It measures the expressivity of networks over a batch of input samples. The SWAP-Score is strongly correlated with ground-truth performance across various search spaces and tasks, outperforming 15 existing training-free metrics on NAS-Bench-101/201/301 and TransNAS-Bench-101. The SWAP-Score can be further enhanced by regularisation, which leads to even higher correlations in cell-based search space and enables model size control during the search. For example, Spearman's rank correlation coefficient between regularised SWAP-Score and CIFAR-100 validation accuracies on NAS-Bench-201 networks is 0.90, significantly higher than 0.80 from the second-best metric, NWOT. When integrated with an evolutionary algorithm for NAS, our SWAP-NAS achieves competitive performance on CIFAR-10 and ImageNet in approximately 6 minutes and 9 minutes of GPU time respectively.
Authors: Amir Aghabiglou, Chung San Chu, Arwa Dabbech, Yves Wiaux
Abstract: Radio-interferometric (RI) imaging entails solving high-resolution high-dynamic range inverse problems from large data volumes. Recent image reconstruction techniques grounded in optimization theory have demonstrated remarkable capability for imaging precision, well beyond CLEAN's capability. These range from advanced proximal algorithms propelled by handcrafted regularization operators, such as the SARA family, to hybrid plug-and-play (PnP) algorithms propelled by learned regularization denoisers, such as AIRI. Optimization and PnP structures are however highly iterative, which hinders their ability to handle the extreme data sizes expected from future instruments. To address this scalability challenge, we introduce a novel deep learning approach, dubbed ``Residual-to-Residual DNN series for high-Dynamic range imaging''. R2D2's reconstruction is formed as a series of residual images, iteratively estimated as outputs of Deep Neural Networks (DNNs) taking the previous iteration's image estimate and associated data residual as inputs. It thus takes a hybrid structure between a PnP algorithm and a learned version of the matching pursuit algorithm that underpins CLEAN. We present a comprehensive study of our approach, featuring its multiple incarnations distinguished by their DNN architectures. We provide a detailed description of its training process, targeting a telescope-specific approach. R2D2's capability to deliver high precision is demonstrated in simulation, across a variety of image and observation settings using the Very Large Array (VLA). Its reconstruction speed is also demonstrated: with only few iterations required to clean data residuals at dynamic ranges up to 100000, R2D2 opens the door to fast precision imaging. R2D2 codes are available in the BASPLib library on GitHub.
Authors: Junyong Shin, Yujin Kang, Yo-Seb Jeon
Abstract: This paper presents a finite-rate deep-learning (DL)-based channel state information (CSI) feedback method for massive multiple-input multiple-output (MIMO) systems. The presented method provides a finite-bit representation of the latent vector based on a vector-quantized variational autoencoder (VQ-VAE) framework while reducing its computational complexity based on shape-gain vector quantization. In this method, the magnitude of the latent vector is quantized using a non-uniform scalar codebook with a proper transformation function, while the direction of the latent vector is quantized using a trainable Grassmannian codebook. A multi-rate codebook design strategy is also developed by introducing a codeword selection rule for a nested codebook along with the design of a loss function. Simulation results demonstrate that the proposed method reduces the computational complexity associated with VQ-VAE while improving CSI reconstruction performance under a given feedback overhead.
Authors: Neel Kanwal, Farbod Khoraminia, Umay Kiraz, Andres Mosquera-Zamudio, Carlos Monteagudo, Emiel A. M. Janssen, Tahlita C. M. Zuiverloon, Chunmig Rong, Kjersti Engan
Abstract: Histopathology is a gold standard for cancer diagnosis under a microscopic examination. However, histological tissue processing procedures result in artifacts, which are ultimately transferred to the digitized version of glass slides, known as whole slide images (WSIs). Artifacts are diagnostically irrelevant areas and may result in wrong deep learning (DL) algorithms predictions. Therefore, detecting and excluding artifacts in the computational pathology (CPATH) system is essential for reliable automated diagnosis. In this paper, we propose a mixture of experts (MoE) scheme for detecting five notable artifacts, including damaged tissue, blur, folded tissue, air bubbles, and histologically irrelevant blood from WSIs. First, we train independent binary DL models as experts to capture particular artifact morphology. Then, we ensemble their predictions using a fusion mechanism. We apply probabilistic thresholding over the final probability distribution to improve the sensitivity of the MoE. We developed DL pipelines using two MoEs and two multiclass models of state-of-the-art deep convolutional neural networks (DCNNs) and vision transformers (ViTs). DCNNs-based MoE and ViTs-based MoE schemes outperformed simpler multiclass models and were tested on datasets from different hospitals and cancer types, where MoE using DCNNs yielded the best results. The proposed MoE yields 86.15% F1 and 97.93% sensitivity scores on unseen data, retaining less computational cost for inference than MoE using ViTs. This best performance of MoEs comes with relatively higher computational trade-offs than multiclass models. The proposed artifact detection pipeline will not only ensure reliable CPATH predictions but may also provide quality control.