Pub Date : 2024-11-19DOI: 10.1109/TIP.2024.3497795
Qiang Qu;Xiaoming Chen;Yuk Ying Chung;Yiran Shen
Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach’s superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.
{"title":"EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Vision","authors":"Qiang Qu;Xiaoming Chen;Yuk Ying Chung;Yiran Shen","doi":"10.1109/TIP.2024.3497795","DOIUrl":"10.1109/TIP.2024.3497795","url":null,"abstract":"Event-stream representation is the first step for many computer vision tasks using event cameras. It converts the asynchronous event-streams into a formatted structure so that conventional machine learning models can be applied easily. However, most of the state-of-the-art event-stream representations are manually designed and the quality of these representations cannot be guaranteed due to the noisy nature of event-streams. In this paper, we introduce a data-driven approach aiming at enhancing the quality of event-stream representations. Our approach commences with the introduction of a new event-stream representation based on spatial-temporal statistics, denoted as EvRep. Subsequently, we theoretically derive the intrinsic relationship between asynchronous event-streams and synchronous video frames. Building upon this theoretical relationship, we train a representation generator, RepGen, in a self-supervised learning manner accepting EvRep as input. Finally, the event-streams are converted to high-quality representations, termed as EvRepSL, by going through the learned RepGen (without the need of fine-tuning or retraining). Our methodology is rigorously validated through extensive evaluations on a variety of mainstream event-based classification and optical flow datasets (captured with various types of event cameras). The experimental results highlight not only our approach’s superior performance over existing event-stream representations but also its versatility, being agnostic to different event cameras and tasks.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6579-6591"},"PeriodicalIF":0.0,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142673314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-14DOI: 10.1109/TIP.2024.3494600
Hongmin Liu;Canbin Zhang;Bin Fan;Jinglin Xu
Multi-object tracking (MOT) aims to estimate the bounding boxes and ID labels of objects in videos. The challenging issue in this task is to alleviate competitive learning between the detection and tracking subtasks, for which, two-stage Tracking-By-Detection (TBD) optimizes the two subtasks individually, and the single-stage Joint Detection and Tracking (JDT) adjusts the complex network architectures finely in an end-to-end pipeline. In this paper, we propose a new MOT method, i.e., Proposal Propagation via Diffusion Models, called Pro2Diff, which integrates a diffusion model into the proposal propagation in multi-object tracking, focusing on the model training process rather than complex network design. Specifically, using a generative approach, Pro2Diff generates a considerable number of noisy proposals for the tracking image sequence in the forward process, and subsequently, Pro2Diff learns the discrepancies between these noisy proposals and the actual bounding boxes of the tracked objects, gradually optimizing these noisy proposals to obtain the initial sequence of real tracked objects. By introducing the denoising diffusion process into multi-object tracking, we have made three further important findings: 1) Generative methods can effectively handle multi-object tracking tasks; 2) Without the need to modify the model structure, we propose self-conditional proposal propagation to enhance model performance effectively during inference; 3) By adjusting the numbers of proposals and iterations appropriately for different tracking sequences, the optimal performance of the model can be achieved. Extensive experimental results on MOT17 and DanceTrack datasets demonstrate that Pro2Diff outperforms current end-to-end multi-object tracking methods. We achieve 61.9 HOTA on DanceTrack and 57.6 HOTA on MOT17, reaching the competitive result of the JDT approach.
多目标跟踪（MOT）旨在估计视频中物体的边界框和 ID 标签。在这项任务中，具有挑战性的问题是如何缓解检测和跟踪子任务之间的竞争性学习，为此，两阶段跟踪检测（Tracking-By-Detection，TBD）分别对这两个子任务进行优化，而单阶段联合检测和跟踪（Joint Detection and Tracking，JDT）则在端到端流水线中对复杂的网络架构进行精细调整。在本文中，我们提出了一种新的 MOT 方法，即通过扩散模型进行提议传播（Proposal Propagation via Diffusion Models），称为 Pro2Diff，它将扩散模型集成到多目标跟踪的提议传播中，重点关注模型训练过程而非复杂的网络设计。具体来说，Pro2Diff 采用生成式方法，在前向过程中为跟踪图像序列生成相当数量的噪声提议，随后，Pro2Diff 学习这些噪声提议与实际跟踪对象边界框之间的差异，逐步优化这些噪声提议，从而获得真实跟踪对象的初始序列。通过在多目标跟踪中引入去噪扩散过程，我们又有了三个重要发现：1）生成式方法可以有效地处理多目标跟踪任务；2）无需修改模型结构，我们提出了自条件提案传播法，可以在推理过程中有效地提高模型性能；3）通过针对不同的跟踪序列适当调整提案数和迭代数，可以实现模型的最佳性能。在 MOT17 和 DanceTrack 数据集上的大量实验结果表明，Pro2Diff 优于目前的端到端多目标跟踪方法。我们在 DanceTrack 上获得了 61.9 HOTA，在 MOT17 上获得了 57.6 HOTA，达到了 JDT 方法的竞争结果。
{"title":"Pro2Diff: Proposal Propagation for Multi-Object Tracking via the Diffusion Model","authors":"Hongmin Liu;Canbin Zhang;Bin Fan;Jinglin Xu","doi":"10.1109/TIP.2024.3494600","DOIUrl":"10.1109/TIP.2024.3494600","url":null,"abstract":"Multi-object tracking (MOT) aims to estimate the bounding boxes and ID labels of objects in videos. The challenging issue in this task is to alleviate competitive learning between the detection and tracking subtasks, for which, two-stage Tracking-By-Detection (TBD) optimizes the two subtasks individually, and the single-stage Joint Detection and Tracking (JDT) adjusts the complex network architectures finely in an end-to-end pipeline. In this paper, we propose a new MOT method, i.e., Proposal Propagation via Diffusion Models, called Pro2Diff, which integrates a diffusion model into the proposal propagation in multi-object tracking, focusing on the model training process rather than complex network design. Specifically, using a generative approach, Pro2Diff generates a considerable number of noisy proposals for the tracking image sequence in the forward process, and subsequently, Pro2Diff learns the discrepancies between these noisy proposals and the actual bounding boxes of the tracked objects, gradually optimizing these noisy proposals to obtain the initial sequence of real tracked objects. By introducing the denoising diffusion process into multi-object tracking, we have made three further important findings: 1) Generative methods can effectively handle multi-object tracking tasks; 2) Without the need to modify the model structure, we propose self-conditional proposal propagation to enhance model performance effectively during inference; 3) By adjusting the numbers of proposals and iterations appropriately for different tracking sequences, the optimal performance of the model can be achieved. Extensive experimental results on MOT17 and DanceTrack datasets demonstrate that Pro2Diff outperforms current end-to-end multi-object tracking methods. We achieve 61.9 HOTA on DanceTrack and 57.6 HOTA on MOT17, reaching the competitive result of the JDT approach.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6508-6520"},"PeriodicalIF":0.0,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.
{"title":"Enhanced Multispectral Band-to-Band Registration Using Co-Occurrence Scale Space and Spatial Confined RANSAC Guided Segmented Affine Transformation","authors":"Indranil Misra;Mukesh Kumar Rohil;S. Manthira Moorthi;Debajyoti Dhar","doi":"10.1109/TIP.2024.3494555","DOIUrl":"10.1109/TIP.2024.3494555","url":null,"abstract":"Band-to-Band Registration (BBR) is a pre-requisite image processing operation essential for specific remote sensing multispectral sensors. BBR aims to align spectral wavelength channels at sub-pixel level accuracy over each other. The paper presents a novel BBR technique utilizing Co-occurrence Scale Space (CSS) for feature point detection and Spatial Confined RANSAC (SC-RANSAC) for removing outlier matched control points. Additionally, the Segmented Affine Transformation (SAT) model reduces distortion and ensures consistent BBR. The methodology developed is evaluated with Nano-MX multispectral images onboard the Indian Nano Satellite (INS-2B) covering diverse landscapes. BBR performance using the proposed method is also verified visually at a 4X zoom level on satellite scenes dominated by cloud pixels. The band misregistration effect on the Normalized Difference Vegetation Index (NDVI) from INS-2B is analyzed and cross-validated with the closest acquisition Landsat-9 OLI NDVI map before and after BBR correction. The experimental evaluation shows that the proposed BBR approach outperforms the state-of-the-art image registration techniques.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6521-6534"},"PeriodicalIF":0.0,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142637274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1109/TIP.2024.3492724
Huan Liu;Wei Li;Xiang-Gen Xia;Mengmeng Zhang;Zhengqi Guo;Lujie Song
Hyperspectral images (HSIs), with hundreds of narrow spectral bands, are increasingly used for ground object classification in remote sensing. However, many HSI classification models operate pixel-by-pixel, limiting the utilization of spatial information and resulting in increased inference time for the whole image. This paper proposes SegHSI, an effective and efficient end-to-end HSI segmentation model, alongside a novel training strategy. SegHSI adopts a head-free structure with cluster attention modules and spatial-aware feedforward networks (SA-FFN) for multiscale spatial encoding. Cluster attention encodes pixels through constructed clusters within the HSI, while SA-FFN integrates depth-wise convolution to enhance spatial context. Our training strategy utilizes a student-teacher model framework that combines labeled pixel class information with consistency learning on unlabeled pixels. Experiments on three public HSI datasets demonstrate that SegHSI not only surpasses other state-of-the-art models in segmentation accuracy but also achieves inference time at the scale of seconds, even reaching sub-second speeds for full-image classification. Code is available at https://github.com/huanliu233/SegHSI .
{"title":"SegHSI: Semantic Segmentation of Hyperspectral Images With Limited Labeled Pixels","authors":"Huan Liu;Wei Li;Xiang-Gen Xia;Mengmeng Zhang;Zhengqi Guo;Lujie Song","doi":"10.1109/TIP.2024.3492724","DOIUrl":"10.1109/TIP.2024.3492724","url":null,"abstract":"Hyperspectral images (HSIs), with hundreds of narrow spectral bands, are increasingly used for ground object classification in remote sensing. However, many HSI classification models operate pixel-by-pixel, limiting the utilization of spatial information and resulting in increased inference time for the whole image. This paper proposes SegHSI, an effective and efficient end-to-end HSI segmentation model, alongside a novel training strategy. SegHSI adopts a head-free structure with cluster attention modules and spatial-aware feedforward networks (SA-FFN) for multiscale spatial encoding. Cluster attention encodes pixels through constructed clusters within the HSI, while SA-FFN integrates depth-wise convolution to enhance spatial context. Our training strategy utilizes a student-teacher model framework that combines labeled pixel class information with consistency learning on unlabeled pixels. Experiments on three public HSI datasets demonstrate that SegHSI not only surpasses other state-of-the-art models in segmentation accuracy but also achieves inference time at the scale of seconds, even reaching sub-second speeds for full-image classification. Code is available at \u0000<uri>https://github.com/huanliu233/SegHSI</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6469-6482"},"PeriodicalIF":0.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142601116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Unsupervised Domain Adaptation (UDA) has shown promise in Scene Text Recognition (STR) by facilitating knowledge transfer from labeled synthetic text (source) to more challenging unlabeled real scene text (target). However, existing UDA-based STR methods fully rely on the pseudo-labels of target samples, which ignores the impact of domain gaps (inter-domain noise) and various natural environments (intra-domain noise), resulting in poor pseudo-label quality. In this paper, we propose a novel noisy-aware unsupervised domain adaptation framework tailored for STR, which aims to enhance model robustness against both inter- and intra-domain noise, thereby providing more precise pseudo-labels for target samples. Concretely, we propose a reweighting target pseudo-labels by estimating the entropy of refined probability distributions, which mitigates the impact of domain gaps on pseudo-labels. Additionally, a decoupled triple-P-N consistency matching module is proposed, which leverages data augmentation to increase data diversity, enhancing model robustness in diverse natural environments. Within this module, we design a low-confidence-based character negative learning, which is decoupled from high-confidence-based positive learning, thus improving sample utilization under scarce target samples. Furthermore, we extend our framework to the more challenging Source-Free UDA (SFUDA) setting, where only a pre-trained source model is available for adaptation, with no access to source data. Experimental results on benchmark datasets demonstrate the effectiveness of our framework. Under the SFUDA setting, our method exhibits faster convergence and superior performance with less training data than previous UDA-based STR methods. Our method surpasses representative STR methods, establishing new state-of-the-art results across multiple datasets.
{"title":"Noisy-Aware Unsupervised Domain Adaptation for Scene Text Recognition","authors":"Xiao-Qian Liu;Peng-Fei Zhang;Xin Luo;Zi Huang;Xin-Shun Xu","doi":"10.1109/TIP.2024.3492705","DOIUrl":"10.1109/TIP.2024.3492705","url":null,"abstract":"Unsupervised Domain Adaptation (UDA) has shown promise in Scene Text Recognition (STR) by facilitating knowledge transfer from labeled synthetic text (source) to more challenging unlabeled real scene text (target). However, existing UDA-based STR methods fully rely on the pseudo-labels of target samples, which ignores the impact of domain gaps (inter-domain noise) and various natural environments (intra-domain noise), resulting in poor pseudo-label quality. In this paper, we propose a novel noisy-aware unsupervised domain adaptation framework tailored for STR, which aims to enhance model robustness against both inter- and intra-domain noise, thereby providing more precise pseudo-labels for target samples. Concretely, we propose a reweighting target pseudo-labels by estimating the entropy of refined probability distributions, which mitigates the impact of domain gaps on pseudo-labels. Additionally, a decoupled triple-P-N consistency matching module is proposed, which leverages data augmentation to increase data diversity, enhancing model robustness in diverse natural environments. Within this module, we design a low-confidence-based character negative learning, which is decoupled from high-confidence-based positive learning, thus improving sample utilization under scarce target samples. Furthermore, we extend our framework to the more challenging Source-Free UDA (SFUDA) setting, where only a pre-trained source model is available for adaptation, with no access to source data. Experimental results on benchmark datasets demonstrate the effectiveness of our framework. Under the SFUDA setting, our method exhibits faster convergence and superior performance with less training data than previous UDA-based STR methods. Our method surpasses representative STR methods, establishing new state-of-the-art results across multiple datasets.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6550-6563"},"PeriodicalIF":0.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142601119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1109/TIP.2024.3492713
Xu Zhang;Kailun Yang;Jiacheng Lin;Jin Yuan;Zhiyong Li;Shutao Li
Integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation significantly facilitates users’ interaction as well as improves interaction efficiency. However, existing studies primarily encode the position or pixel regions of prompts without considering the contextual areas around them, resulting in insufficient prompt feedback, which is not conducive to performance acceleration. To tackle this problem, this paper proposes a simple yet effective Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation, which allows users to flexibly input diverse visual prompts with the probabilistic prompt encoding and feature post-processing to excavate sufficient and robust prompt features for performance boosting. Specifically, we first propose a Probabilistic Prompt-unified Encoder (PPuE) to generate a unified one-dimensional vector by exploring both prompt and non-prompt contextual information, offering richer feedback cues to accelerate performance improvement. On this basis, we further present a Prompt-to-Pixel Contrastive (P2C) loss to accurately align both prompt and pixel features, bridging the representation gap between them to offer consistent feature representations for mask prediction. Moreover, our approach designs a Dual-cross Merging Attention (DMA) module to implement bidirectional feature interaction between image and prompt features, generating notable features for performance improvement. A comprehensive variety of experiments on several challenging datasets demonstrates that the proposed components achieve consistent improvements, yielding state-of-the-art interactive segmentation performance. Our code is available at https://github.com/XuZhang1211/PVPUFormer .
{"title":"PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentation","authors":"Xu Zhang;Kailun Yang;Jiacheng Lin;Jin Yuan;Zhiyong Li;Shutao Li","doi":"10.1109/TIP.2024.3492713","DOIUrl":"10.1109/TIP.2024.3492713","url":null,"abstract":"Integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation significantly facilitates users’ interaction as well as improves interaction efficiency. However, existing studies primarily encode the position or pixel regions of prompts without considering the contextual areas around them, resulting in insufficient prompt feedback, which is not conducive to performance acceleration. To tackle this problem, this paper proposes a simple yet effective Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation, which allows users to flexibly input diverse visual prompts with the probabilistic prompt encoding and feature post-processing to excavate sufficient and robust prompt features for performance boosting. Specifically, we first propose a Probabilistic Prompt-unified Encoder (PPuE) to generate a unified one-dimensional vector by exploring both prompt and non-prompt contextual information, offering richer feedback cues to accelerate performance improvement. On this basis, we further present a Prompt-to-Pixel Contrastive (P2C) loss to accurately align both prompt and pixel features, bridging the representation gap between them to offer consistent feature representations for mask prediction. Moreover, our approach designs a Dual-cross Merging Attention (DMA) module to implement bidirectional feature interaction between image and prompt features, generating notable features for performance improvement. A comprehensive variety of experiments on several challenging datasets demonstrates that the proposed components achieve consistent improvements, yielding state-of-the-art interactive segmentation performance. Our code is available at \u0000<uri>https://github.com/XuZhang1211/PVPUFormer</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6455-6468"},"PeriodicalIF":0.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142601118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1109/TIP.2024.3492733
Wenlong Yu;Ruonan Liu;Dongyue Chen;Qinghua Hu
Explainability is a pivotal factor in determining whether a deep learning model can be authorized in critical applications. To enhance the explainability of models of end-to-end object DEtection with TRansformer (DETR), we introduce a disentanglement method that constrains the feature learning process, following a divide-and-conquer decoupling paradigm, similar to how people understand complex real-world problems. We first demonstrate the entangled property of the features between the extractor and detector and find that the regression function is a key factor contributing to the deterioration of disentangled feature activation. These highly entangled features always activate the local characteristics, making it difficult to cover the semantic information of an object, which also reduces the interpretability of single-backbone object detection models. Thus, an Explainability Enhanced object detection Transformer with feature Disentanglement (DETD) model is proposed, in which the Tensor Singular Value Decomposition (T-SVD) is used to produce feature bases and the Batch averaged Feature Spectral Penalization (BFSP) loss is introduced to constrain the disentanglement of the feature and balance the semantic activation. The proposed method is applied across three prominent backbones, two DETR variants, and a CNN based model. By combining two optimization techniques, extensive experiments on two datasets consistently demonstrate that the DETD model outperforms the counterpart in terms of object detection performance and feature disentanglement. The Grad-CAM visualizations demonstrate the enhancement of feature learning explainability in the disentanglement view.
{"title":"Explainability Enhanced Object Detection Transformer With Feature Disentanglement","authors":"Wenlong Yu;Ruonan Liu;Dongyue Chen;Qinghua Hu","doi":"10.1109/TIP.2024.3492733","DOIUrl":"10.1109/TIP.2024.3492733","url":null,"abstract":"Explainability is a pivotal factor in determining whether a deep learning model can be authorized in critical applications. To enhance the explainability of models of end-to-end object DEtection with TRansformer (DETR), we introduce a disentanglement method that constrains the feature learning process, following a divide-and-conquer decoupling paradigm, similar to how people understand complex real-world problems. We first demonstrate the entangled property of the features between the extractor and detector and find that the regression function is a key factor contributing to the deterioration of disentangled feature activation. These highly entangled features always activate the local characteristics, making it difficult to cover the semantic information of an object, which also reduces the interpretability of single-backbone object detection models. Thus, an Explainability Enhanced object detection Transformer with feature Disentanglement (DETD) model is proposed, in which the Tensor Singular Value Decomposition (T-SVD) is used to produce feature bases and the Batch averaged Feature Spectral Penalization (BFSP) loss is introduced to constrain the disentanglement of the feature and balance the semantic activation. The proposed method is applied across three prominent backbones, two DETR variants, and a CNN based model. By combining two optimization techniques, extensive experiments on two datasets consistently demonstrate that the DETD model outperforms the counterpart in terms of object detection performance and feature disentanglement. The Grad-CAM visualizations demonstrate the enhancement of feature learning explainability in the disentanglement view.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6439-6454"},"PeriodicalIF":0.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142601130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-12DOI: 10.1109/TIP.2024.3492700
Yu-Xin Zhang;Jie Gui;James Tin-Yau Kwok
Partial point cloud registration aims to align partial scans into a shared coordinate system. While learning-based partial point cloud registration methods have achieved remarkable progress, they often fail to take full advantage of the relative positional relationships both within (intra-) and between (inter-) point clouds. This oversight hampers their ability to accurately identify overlapping regions and search for reliable correspondences. To address these limitations, a diverse inlier consistency (DIC) method has been proposed that adaptively embeds the positional information of a reliable correspondence in the intra- and inter-point cloud. Firstly, a diverse inlier consistency-driven region perception (DICdRP) module is devised, which encodes the positional information of the selected correspondence within the intra-point cloud. This module enhances the sensitivity of all points to overlapping regions by recognizing the position of the selected correspondence. Secondly, a diverse inlier consistency-aware correspondence search (DICaCS) module is developed, which leverages relative positions in the inter-point cloud. This module studies an inter-point cloud DIC weight to supervise correspondence compatibility, allowing for precise identification of correspondences and effective outlier filtration. Thirdly, diverse information is integrated throughout our framework to achieve a more holistic and detailed registration process. Extensive experiments on object-level and scene-level datasets demonstrate the superior performance of the proposed algorithm. The code is available at https://github.com/yxzhang15/DIC .
{"title":"Constructing Diverse Inlier Consistency for Partial Point Cloud Registration","authors":"Yu-Xin Zhang;Jie Gui;James Tin-Yau Kwok","doi":"10.1109/TIP.2024.3492700","DOIUrl":"10.1109/TIP.2024.3492700","url":null,"abstract":"Partial point cloud registration aims to align partial scans into a shared coordinate system. While learning-based partial point cloud registration methods have achieved remarkable progress, they often fail to take full advantage of the relative positional relationships both within (intra-) and between (inter-) point clouds. This oversight hampers their ability to accurately identify overlapping regions and search for reliable correspondences. To address these limitations, a diverse inlier consistency (DIC) method has been proposed that adaptively embeds the positional information of a reliable correspondence in the intra- and inter-point cloud. Firstly, a diverse inlier consistency-driven region perception (DICdRP) module is devised, which encodes the positional information of the selected correspondence within the intra-point cloud. This module enhances the sensitivity of all points to overlapping regions by recognizing the position of the selected correspondence. Secondly, a diverse inlier consistency-aware correspondence search (DICaCS) module is developed, which leverages relative positions in the inter-point cloud. This module studies an inter-point cloud DIC weight to supervise correspondence compatibility, allowing for precise identification of correspondences and effective outlier filtration. Thirdly, diverse information is integrated throughout our framework to achieve a more holistic and detailed registration process. Extensive experiments on object-level and scene-level datasets demonstrate the superior performance of the proposed algorithm. The code is available at \u0000<uri>https://github.com/yxzhang15/DIC</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6535-6549"},"PeriodicalIF":0.0,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142601132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/TIP.2024.3484251
Yun Wang;Longguang Wang;Kunhong Li;Yongjian Zhang;Dapeng Oliver Wu;Yulan Guo
Cost aggregation plays a critical role in existing stereo matching methods. In this paper, we revisit cost aggregation in stereo matching from disparity classification and propose a generic yet efficient Disparity Context Aggregation (DCA) module to improve the performance of CNN-based methods. Our approach is based on an insight that a coarse disparity class prior is beneficial to disparity regression. To obtain such a prior, we first classify pixels in an image into several disparity classes and treat pixels within the same class as homogeneous regions. We then generate homogeneous region representations and incorporate these representations into the cost volume to suppress irrelevant information while enhancing the matching ability for cost aggregation. With the help of homogeneous region representations, efficient and informative cost aggregation can be achieved with only a shallow 3D CNN. Our DCA module is fully-differentiable and well-compatible with different network architectures, which can be seamlessly plugged into existing networks to improve performance with small additional overheads. It is demonstrated that our DCA module can effectively exploit disparity class priors to improve the performance of cost aggregation. Based on our DCA, we design a highly accurate network named DCANet, which achieves state-of-the-art performance on several benchmarks.
{"title":"Cost Volume Aggregation in Stereo Matching Revisited: A Disparity Classification Perspective","authors":"Yun Wang;Longguang Wang;Kunhong Li;Yongjian Zhang;Dapeng Oliver Wu;Yulan Guo","doi":"10.1109/TIP.2024.3484251","DOIUrl":"10.1109/TIP.2024.3484251","url":null,"abstract":"Cost aggregation plays a critical role in existing stereo matching methods. In this paper, we revisit cost aggregation in stereo matching from disparity classification and propose a generic yet efficient Disparity Context Aggregation (DCA) module to improve the performance of CNN-based methods. Our approach is based on an insight that a coarse disparity class prior is beneficial to disparity regression. To obtain such a prior, we first classify pixels in an image into several disparity classes and treat pixels within the same class as homogeneous regions. We then generate homogeneous region representations and incorporate these representations into the cost volume to suppress irrelevant information while enhancing the matching ability for cost aggregation. With the help of homogeneous region representations, efficient and informative cost aggregation can be achieved with only a shallow 3D CNN. Our DCA module is fully-differentiable and well-compatible with different network architectures, which can be seamlessly plugged into existing networks to improve performance with small additional overheads. It is demonstrated that our DCA module can effectively exploit disparity class priors to improve the performance of cost aggregation. Based on our DCA, we design a highly accurate network named DCANet, which achieves state-of-the-art performance on several benchmarks.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6425-6438"},"PeriodicalIF":0.0,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142599222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-11DOI: 10.1109/TIP.2024.3489272
Tongle Wu;Jicong Fan
Low-rank tensor completion (LRTC) has shown promise in processing incomplete visual data, yet it often overlooks the inherent local smooth structures in images and videos. Recent advances in LRTC, integrating total variation regularization to capitalize on the local smoothness, have yielded notable improvements. Nonetheless, these methods are limited to exploiting local smoothness within the original data space, neglecting the latent factor space of tensors. More seriously, there is a lack of theoretical backing for the role of local smoothness in enhancing recovery performance. In response, this paper introduces an innovative tensor completion model that concurrently leverages the global low-rank structure of the original tensor and the local smooth structure of its factor tensors. Our objective is to learn a low-rank tensor that decomposes into two factor tensors, each exhibiting sufficient local smoothness. We propose an efficient alternating direction method of multipliers to optimize our model. Further, we establish generalization error bounds for smooth factor-based tensor completion methods across various decomposition frameworks. These bounds are significantly tighter than existing baselines. We conduct extensive inpainting experiments on color images, multispectral images, and videos, which demonstrate the efficacy and superiority of our method. Additionally, our approach shows a low sensitivity to hyper-parameter settings, enhancing its convenience and reliability for practical applications.
{"title":"Smooth Tensor Product for Tensor Completion","authors":"Tongle Wu;Jicong Fan","doi":"10.1109/TIP.2024.3489272","DOIUrl":"10.1109/TIP.2024.3489272","url":null,"abstract":"Low-rank tensor completion (LRTC) has shown promise in processing incomplete visual data, yet it often overlooks the inherent local smooth structures in images and videos. Recent advances in LRTC, integrating total variation regularization to capitalize on the local smoothness, have yielded notable improvements. Nonetheless, these methods are limited to exploiting local smoothness within the original data space, neglecting the latent factor space of tensors. More seriously, there is a lack of theoretical backing for the role of local smoothness in enhancing recovery performance. In response, this paper introduces an innovative tensor completion model that concurrently leverages the global low-rank structure of the original tensor and the local smooth structure of its factor tensors. Our objective is to learn a low-rank tensor that decomposes into two factor tensors, each exhibiting sufficient local smoothness. We propose an efficient alternating direction method of multipliers to optimize our model. Further, we establish generalization error bounds for smooth factor-based tensor completion methods across various decomposition frameworks. These bounds are significantly tighter than existing baselines. We conduct extensive inpainting experiments on color images, multispectral images, and videos, which demonstrate the efficacy and superiority of our method. Additionally, our approach shows a low sensitivity to hyper-parameter settings, enhancing its convenience and reliability for practical applications.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"6483-6496"},"PeriodicalIF":0.0,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142599221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：