Pub Date : 2024-06-24DOI: 10.1109/TIP.2024.3416065
Zhenyu Li;Xuyang Wang;Xianming Liu;Junjun Jiang
Monocular depth estimation (MDE) is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth is estimated via a linear combination of predicted probability distributions and discrete bins. In this paper, we present a novel framework called BinsFormer, tailored for the classification-regression-based depth estimation. It mainly focuses on two crucial components in the specific task: 1) proper generation of adaptive bins; and 2) sufficient interaction between probability distribution and bins predictions. To specify, we employ a Transformer decoder to generate bins, novelly viewing it as a direct set-to-set prediction problem. We further integrate a multi-scale decoder structure to achieve a comprehensive understanding of spatial geometry information and estimate depth maps in a coarse-to-fine manner. Moreover, an extra scene understanding query is proposed to improve the estimation accuracy, which turns out that models can implicitly learn useful information from the auxiliary environment classification task. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that BinsFormer surpasses state-of-the-art MDE methods with prominent margins. Code and pretrained models are made publicly available at https://github.com/zhyever/ Monocular-Depth-Estimation-Toolbox/tree/main/configs/ binsformer.
{"title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","authors":"Zhenyu Li;Xuyang Wang;Xianming Liu;Junjun Jiang","doi":"10.1109/TIP.2024.3416065","DOIUrl":"10.1109/TIP.2024.3416065","url":null,"abstract":"Monocular depth estimation (MDE) is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth is estimated via a linear combination of predicted probability distributions and discrete bins. In this paper, we present a novel framework called BinsFormer, tailored for the classification-regression-based depth estimation. It mainly focuses on two crucial components in the specific task: 1) proper generation of adaptive bins; and 2) sufficient interaction between probability distribution and bins predictions. To specify, we employ a Transformer decoder to generate bins, novelly viewing it as a direct set-to-set prediction problem. We further integrate a multi-scale decoder structure to achieve a comprehensive understanding of spatial geometry information and estimate depth maps in a coarse-to-fine manner. Moreover, an extra scene understanding query is proposed to improve the estimation accuracy, which turns out that models can implicitly learn useful information from the auxiliary environment classification task. Extensive experiments on the KITTI, NYU, and SUN RGB-D datasets demonstrate that BinsFormer surpasses state-of-the-art MDE methods with prominent margins. Code and pretrained models are made publicly available at \u0000<uri>https://github.com/zhyever/</uri>\u0000 Monocular-Depth-Estimation-Toolbox/tree/main/configs/ binsformer.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141447878","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 : 2024-06-24DOI: 10.1109/TIP.2024.3416052
Rui Guo;Zheng Xie;Chencheng Zhang;Xiaohua Qian
Freezing of gait (FoG) is a common disabling symptom of Parkinson’s disease (PD). It is clinically characterized by sudden and transient walking interruptions for specific human body parts, and it presents the localization in time and space. Due to the difficulty in extracting global fine-grained features from lengthy videos, developing an automated five-point FoG scoring system is quite challenging. Therefore, we propose a novel video-based automated five-classification FoG assessment method with a causality-enhanced multiple-instance-learning graph convolutional network (GCN). This method involves developing a temporal segmentation GCN to segment each video into three motion stages for stage-level feature modeling, followed by a multiple-instance-learning framework to divide each stage into short clips for instance-level feature extraction. Subsequently, an uncertainty-driven multiple-instance-learning GCN is developed to capture spatial and temporal fine-grained features through GCN scheme and uncertainty learning, respectively, for acquiring global representations. Finally, a causality-enhanced graph generation strategy is proposed to exploit causal inference for mining and enhancing human structures causally related to clinical assessment, thereby extracting spatial causal features. Extensive experimental results demonstrate the excellent performance of the proposed method on five-classification FoG assessment with an accuracy of 62.72% and an acceptable accuracy of 91.32%, which is confirmed by independent testing. Additionally, it enables temporal and spatial localization of FoG events to a certain extent, facilitating reasonable clinical interpretations. In conclusion, our method provides a valuable tool for automated FoG assessment in PD, and the proposed causality-related component exhibits promising potential for extension to other general and medical fine-grained action recognition tasks.
步态冻结（FoG）是帕金森病（PD）常见的致残症状。它的临床特征是人体特定部位突然出现短暂的行走中断，并呈现出时间和空间上的定位。由于难以从冗长的视频中提取全局精细特征，开发五点 FoG 自动评分系统颇具挑战性。因此，我们利用因果增强多实例学习图卷积网络（GCN）提出了一种新颖的基于视频的 FoG 自动五分类评估方法。该方法包括开发一个时间分割 GCN，将每个视频分割成三个运动阶段，进行阶段级特征建模，然后利用多实例学习框架将每个阶段划分为短片段，进行实例级特征提取。随后，开发了不确定性驱动的多实例学习 GCN，通过 GCN 方案和不确定性学习分别捕捉空间和时间细粒度特征，以获取全局表征。最后，提出了一种因果增强图生成策略，利用因果推理挖掘和增强与临床评估有因果关系的人体结构，从而提取空间因果特征。广泛的实验结果表明，所提出的方法在五分类 FoG 评估中表现出色，准确率达到 62.72%，可接受的准确率为 91.32%，这一点得到了独立测试的证实。此外，它还在一定程度上实现了 FoG 事件的时间和空间定位，为合理的临床解释提供了便利。总之，我们的方法为帕金森病患者的 FoG 自动评估提供了一种有价值的工具，而且所提出的因果关系相关组件在扩展到其他一般和医疗细粒度动作识别任务方面具有广阔的前景。
{"title":"Causality-Enhanced Multiple Instance Learning With Graph Convolutional Networks for Parkinsonian Freezing-of-Gait Assessment","authors":"Rui Guo;Zheng Xie;Chencheng Zhang;Xiaohua Qian","doi":"10.1109/TIP.2024.3416052","DOIUrl":"10.1109/TIP.2024.3416052","url":null,"abstract":"Freezing of gait (FoG) is a common disabling symptom of Parkinson’s disease (PD). It is clinically characterized by sudden and transient walking interruptions for specific human body parts, and it presents the localization in time and space. Due to the difficulty in extracting global fine-grained features from lengthy videos, developing an automated five-point FoG scoring system is quite challenging. Therefore, we propose a novel video-based automated five-classification FoG assessment method with a causality-enhanced multiple-instance-learning graph convolutional network (GCN). This method involves developing a temporal segmentation GCN to segment each video into three motion stages for stage-level feature modeling, followed by a multiple-instance-learning framework to divide each stage into short clips for instance-level feature extraction. Subsequently, an uncertainty-driven multiple-instance-learning GCN is developed to capture spatial and temporal fine-grained features through GCN scheme and uncertainty learning, respectively, for acquiring global representations. Finally, a causality-enhanced graph generation strategy is proposed to exploit causal inference for mining and enhancing human structures causally related to clinical assessment, thereby extracting spatial causal features. Extensive experimental results demonstrate the excellent performance of the proposed method on five-classification FoG assessment with an accuracy of 62.72% and an acceptable accuracy of 91.32%, which is confirmed by independent testing. Additionally, it enables temporal and spatial localization of FoG events to a certain extent, facilitating reasonable clinical interpretations. In conclusion, our method provides a valuable tool for automated FoG assessment in PD, and the proposed causality-related component exhibits promising potential for extension to other general and medical fine-grained action recognition tasks.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141447879","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 : 2024-06-24DOI: 10.1109/TIP.2024.3415963
Zhifeng Xie;Rui Qiu;Sen Wang;Xin Tan;Yuan Xie;Lizhuang Ma
Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled night image datasets, unsupervised domain adaptation (UDA) has become the predominant method for studying night scenes. UDA typically relies on paired day-night image pairs to guide adaptation, but this approach hampers dataset construction and restricts generalization across night scenes in different datasets. Moreover, UDA, focusing on network architecture and training strategies, faces difficulties in handling classes with few domain similarities. In this paper, we leverage Prompt Images Guidance (PIG) to enhance UDA with supplementary night knowledge. We propose a Night-Focused Network (NFNet) to learn night-specific features from both target domain images and prompt images. To generate high-quality pseudo-labels, we propose Pseudo-label Fusion via Domain Similarity Guidance (FDSG). Classes with fewer domain similarities are predicted by NFNet, which excels in parsing night features, while classes with more domain similarities are predicted by UDA, which has rich labeled semantics. Additionally, we propose two data augmentation strategies: the Prompt Mixture Strategy (PMS) and the Alternate Mask Strategy (AMS), aimed at mitigating the overfitting of the NFNet to a few prompt images. We conduct extensive experiments on four night-time datasets: NightCity, NightCity+, Dark Zurich, and ACDC. The results indicate that utilizing PIG can enhance the parsing accuracy of UDA. The code is available at https://github.com/qiurui4shu/PIG .
{"title":"PIG: Prompt Images Guidance for Night-Time Scene Parsing","authors":"Zhifeng Xie;Rui Qiu;Sen Wang;Xin Tan;Yuan Xie;Lizhuang Ma","doi":"10.1109/TIP.2024.3415963","DOIUrl":"10.1109/TIP.2024.3415963","url":null,"abstract":"Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled night image datasets, unsupervised domain adaptation (UDA) has become the predominant method for studying night scenes. UDA typically relies on paired day-night image pairs to guide adaptation, but this approach hampers dataset construction and restricts generalization across night scenes in different datasets. Moreover, UDA, focusing on network architecture and training strategies, faces difficulties in handling classes with few domain similarities. In this paper, we leverage Prompt Images Guidance (PIG) to enhance UDA with supplementary night knowledge. We propose a Night-Focused Network (NFNet) to learn night-specific features from both target domain images and prompt images. To generate high-quality pseudo-labels, we propose Pseudo-label Fusion via Domain Similarity Guidance (FDSG). Classes with fewer domain similarities are predicted by NFNet, which excels in parsing night features, while classes with more domain similarities are predicted by UDA, which has rich labeled semantics. Additionally, we propose two data augmentation strategies: the Prompt Mixture Strategy (PMS) and the Alternate Mask Strategy (AMS), aimed at mitigating the overfitting of the NFNet to a few prompt images. We conduct extensive experiments on four night-time datasets: NightCity, NightCity+, Dark Zurich, and ACDC. The results indicate that utilizing PIG can enhance the parsing accuracy of UDA. The code is available at \u0000<uri>https://github.com/qiurui4shu/PIG</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141447881","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 : 2024-06-24DOI: 10.1109/TIP.2024.3416873
Yibing Liu;Chris Xing Tian;Haoliang Li;Shiqi Wang
Learning invariant representations via contrastive learning has seen state-of-the-art performance in domain generalization (DG). Despite such success, in this paper, we find that its core learning strategy – feature alignment – could heavily hinder model generalization. Drawing insights in neuron interpretability, we characterize this problem from a neuron activation view. Specifically, by treating feature elements as neuron activation states, we show that conventional alignment methods tend to deteriorate the diversity of learned invariant features, as they indiscriminately minimize all neuron activation differences. This instead ignores rich relations among neurons – many of them often identify the same visual concepts despite differing activation patterns. With this finding, we present a simple yet effective approach, Concept Contrast (CoCo), which relaxes element-wise feature alignments by contrasting high-level concepts encoded in neurons. Our CoCo performs in a plug-and-play fashion, thus it can be integrated into any contrastive method in DG. We evaluate CoCo over four canonical contrastive methods, showing that CoCo promotes the diversity of feature representations and consistently improves model generalization capability. By decoupling this success through neuron coverage analysis, we further find that CoCo potentially invokes more meaningful neurons during training, thereby improving model learning.
{"title":"Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning","authors":"Yibing Liu;Chris Xing Tian;Haoliang Li;Shiqi Wang","doi":"10.1109/TIP.2024.3416873","DOIUrl":"10.1109/TIP.2024.3416873","url":null,"abstract":"Learning invariant representations via contrastive learning has seen state-of-the-art performance in domain generalization (DG). Despite such success, in this paper, we find that its core learning strategy – feature alignment – could heavily hinder model generalization. Drawing insights in neuron interpretability, we characterize this problem from a neuron activation view. Specifically, by treating feature elements as neuron activation states, we show that conventional alignment methods tend to deteriorate the diversity of learned invariant features, as they indiscriminately minimize all neuron activation differences. This instead ignores rich relations among neurons – many of them often identify the same visual concepts despite differing activation patterns. With this finding, we present a simple yet effective approach, Concept Contrast (CoCo), which relaxes element-wise feature alignments by contrasting high-level concepts encoded in neurons. Our CoCo performs in a plug-and-play fashion, thus it can be integrated into any contrastive method in DG. We evaluate CoCo over four canonical contrastive methods, showing that CoCo promotes the diversity of feature representations and consistently improves model generalization capability. By decoupling this success through neuron coverage analysis, we further find that CoCo potentially invokes more meaningful neurons during training, thereby improving model learning.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141447880","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 : 2024-06-21DOI: 10.1109/TIP.2024.3409940
Xingyu Hu;Junjun Jiang;Chenyang Wang;Xianming Liu;Jiayi Ma
Multi-focus image fusion can fuse the clear parts of two or more source images captured at the same scene with different focal lengths into an all-in-focus image. On the one hand, previous supervised learning-based multi-focus image fusion methods relying on synthetic datasets have a clear distribution shift with real scenarios. On the other hand, unsupervised learning-based multi-focus image fusion methods can well adapt to the observed images but lack the general knowledge of defocus blur that can be learned from paired data. To avoid the problems of existing methods, this paper presents a novel multi-focus image fusion model by considering both the general knowledge brought by the supervised pretrained backbone and the extrinsic priors optimized on specific testing sample to improve the performance of image fusion. To be specific, the Incremental Network Prior Adaptation (INPA) framework is proposed to incrementally integrate features extracted from the pretrained strong baselines into a tiny prior network (6.9% parameters of the backbone network) to boost the performance for test samples. We evaluate our method on both synthetic and real-world public datasets (Lytro, MFI-WHU, and Real-MFF) and show that our method outperforms existing supervised learning-based methods and unsupervised learning based methods.
{"title":"Incrementally Adapting Pretrained Model Using Network Prior for Multi-Focus Image Fusion","authors":"Xingyu Hu;Junjun Jiang;Chenyang Wang;Xianming Liu;Jiayi Ma","doi":"10.1109/TIP.2024.3409940","DOIUrl":"10.1109/TIP.2024.3409940","url":null,"abstract":"Multi-focus image fusion can fuse the clear parts of two or more source images captured at the same scene with different focal lengths into an all-in-focus image. On the one hand, previous supervised learning-based multi-focus image fusion methods relying on synthetic datasets have a clear distribution shift with real scenarios. On the other hand, unsupervised learning-based multi-focus image fusion methods can well adapt to the observed images but lack the general knowledge of defocus blur that can be learned from paired data. To avoid the problems of existing methods, this paper presents a novel multi-focus image fusion model by considering both the general knowledge brought by the supervised pretrained backbone and the extrinsic priors optimized on specific testing sample to improve the performance of image fusion. To be specific, the Incremental Network Prior Adaptation (INPA) framework is proposed to incrementally integrate features extracted from the pretrained strong baselines into a tiny prior network (6.9% parameters of the backbone network) to boost the performance for test samples. We evaluate our method on both synthetic and real-world public datasets (Lytro, MFI-WHU, and Real-MFF) and show that our method outperforms existing supervised learning-based methods and unsupervised learning based methods.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141437949","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 : 2024-06-20DOI: 10.1109/TIP.2024.3414935
Xuehao Gao;Yang Yang;Yang Wu;Shaoyi Du;Guo-Jun Qi
Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one’s intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven prediction and inferring human motion in isolation from the contextual environment, thus leaving the body location movement in the scene behind. However, real-world human movements are goal-directed and highly influenced by the spatial layout of their surrounding scenes. In this paper, instead of planning future human motion in a “dark” room, we propose a Multi-Condition Latent Diffusion network (MCLD) that reformulates the human motion prediction task as a multi-condition joint inference problem based on the given historical 3D body motion and the current 3D scene contexts. Specifically, instead of directly modeling joint distribution over the raw motion sequences, MCLD performs a conditional diffusion process within the latent embedding space, characterizing the cross-modal mapping from the past body movement and current scene context condition embeddings to the future human motion embedding. Extensive experiments on large-scale human motion prediction datasets demonstrate that our MCLD achieves significant improvements over the state-of-the-art methods on both realistic and diverse predictions.
{"title":"Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction","authors":"Xuehao Gao;Yang Yang;Yang Wu;Shaoyi Du;Guo-Jun Qi","doi":"10.1109/TIP.2024.3414935","DOIUrl":"10.1109/TIP.2024.3414935","url":null,"abstract":"Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one’s intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven prediction and inferring human motion in isolation from the contextual environment, thus leaving the body location movement in the scene behind. However, real-world human movements are goal-directed and highly influenced by the spatial layout of their surrounding scenes. In this paper, instead of planning future human motion in a “dark” room, we propose a Multi-Condition Latent Diffusion network (MCLD) that reformulates the human motion prediction task as a multi-condition joint inference problem based on the given historical 3D body motion and the current 3D scene contexts. Specifically, instead of directly modeling joint distribution over the raw motion sequences, MCLD performs a conditional diffusion process within the latent embedding space, characterizing the cross-modal mapping from the past body movement and current scene context condition embeddings to the future human motion embedding. Extensive experiments on large-scale human motion prediction datasets demonstrate that our MCLD achieves significant improvements over the state-of-the-art methods on both realistic and diverse predictions.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141433611","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 : 2024-06-20DOI: 10.1109/TIP.2024.3414938
Ziyu Wei;Xi Yang;Nannan Wang;Xinbo Gao
Visible infrared person re-identification (VI-ReID) exposes considerable challenges because of the modality gaps between the person images captured by daytime visible cameras and nighttime infrared cameras. Several fully-supervised VI-ReID methods have improved the performance with extensive labeled heterogeneous images. However, the identity of the person is difficult to obtain in real-world situations, especially at night. Limited known identities and large modality discrepancies impede the effectiveness of the model to a great extent. In this paper, we propose a novel Semi-Supervised Learning framework with Heterogeneous Distribution Consistency (HDC-SSL) for VI-ReID. Specifically, through investigating the confidence distribution of heterogeneous images, we introduce a Gaussian Mixture Model-based Pseudo Labeling (GMM-PL) method, which adaptively adjusts different thresholds for each modality to label the identity. Moreover, to facilitate the representation learning of unutilized data whose prediction is lower than the threshold, Modality Consistency Regularization (MCR) is proposed to ensure the prediction consistency of the cross-modality pedestrian images and handle the modality variance. Extensive experiments with different label settings on two VI-ReID datasets demonstrate the effectiveness of our method. Particularly, HDC-SSL achieves competitive performance with state-of-the-art fully-supervised VI-ReID methods on RegDB dataset with only 1 visible label and 1 infrared label per class.
{"title":"Semi-Supervised Learning With Heterogeneous Distribution Consistency for Visible Infrared Person Re-Identification","authors":"Ziyu Wei;Xi Yang;Nannan Wang;Xinbo Gao","doi":"10.1109/TIP.2024.3414938","DOIUrl":"10.1109/TIP.2024.3414938","url":null,"abstract":"Visible infrared person re-identification (VI-ReID) exposes considerable challenges because of the modality gaps between the person images captured by daytime visible cameras and nighttime infrared cameras. Several fully-supervised VI-ReID methods have improved the performance with extensive labeled heterogeneous images. However, the identity of the person is difficult to obtain in real-world situations, especially at night. Limited known identities and large modality discrepancies impede the effectiveness of the model to a great extent. In this paper, we propose a novel Semi-Supervised Learning framework with Heterogeneous Distribution Consistency (HDC-SSL) for VI-ReID. Specifically, through investigating the confidence distribution of heterogeneous images, we introduce a Gaussian Mixture Model-based Pseudo Labeling (GMM-PL) method, which adaptively adjusts different thresholds for each modality to label the identity. Moreover, to facilitate the representation learning of unutilized data whose prediction is lower than the threshold, Modality Consistency Regularization (MCR) is proposed to ensure the prediction consistency of the cross-modality pedestrian images and handle the modality variance. Extensive experiments with different label settings on two VI-ReID datasets demonstrate the effectiveness of our method. Particularly, HDC-SSL achieves competitive performance with state-of-the-art fully-supervised VI-ReID methods on RegDB dataset with only 1 visible label and 1 infrared label per class.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141433612","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 : 2024-06-20DOI: 10.1109/TIP.2024.3403505
Huan Pan;You-Wei Wen;Ya Huang
In this paper, we consider decomposing an image into its cartoon and texture components. Traditional methods, which mainly rely on the gradient amplitude of images to distinguish between these components, often show limitations in decomposing small-scale, high-contrast texture patterns and large-scale, low-contrast structural components. Specifically, these methods tend to decompose the former to the cartoon image and the latter to the texture image, neglecting the scale features inherent in both components. To overcome these challenges, we introduce a new variational model which incorporates an $L_{0}$ -based total variation norm for the cartoon component and an $L_{2}$ norm for the scale space representation of the texture component. We show that the texture component has a small $L_{2}$ norm in the scale space representation. We apply a quadratic penalty function to handle the non-separable $L_{0}$ norm minimization problem. Numerical experiments are given to illustrate the efficiency and effectiveness of our approach.
{"title":"L₀ Gradient-Regularization and Scale Space Representation Model for Cartoon and Texture Decomposition","authors":"Huan Pan;You-Wei Wen;Ya Huang","doi":"10.1109/TIP.2024.3403505","DOIUrl":"10.1109/TIP.2024.3403505","url":null,"abstract":"In this paper, we consider decomposing an image into its cartoon and texture components. Traditional methods, which mainly rely on the gradient amplitude of images to distinguish between these components, often show limitations in decomposing small-scale, high-contrast texture patterns and large-scale, low-contrast structural components. Specifically, these methods tend to decompose the former to the cartoon image and the latter to the texture image, neglecting the scale features inherent in both components. To overcome these challenges, we introduce a new variational model which incorporates an \u0000<inline-formula> <tex-math>$L_{0}$ </tex-math></inline-formula>\u0000-based total variation norm for the cartoon component and an \u0000<inline-formula> <tex-math>$L_{2}$ </tex-math></inline-formula>\u0000 norm for the scale space representation of the texture component. We show that the texture component has a small \u0000<inline-formula> <tex-math>$L_{2}$ </tex-math></inline-formula>\u0000 norm in the scale space representation. We apply a quadratic penalty function to handle the non-separable \u0000<inline-formula> <tex-math>$L_{0}$ </tex-math></inline-formula>\u0000 norm minimization problem. Numerical experiments are given to illustrate the efficiency and effectiveness of our approach.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141433610","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 : 2024-06-19DOI: 10.1109/TIP.2024.3414269
Haoxuan Ding;Junyu Gao;Yuan Yuan;Qi Wang
With the increasing availability of cameras in vehicles, obtaining license plate (LP) information via on-board cameras has become feasible in traffic scenarios. LPs play a pivotal role in vehicle identification, making automatic LP detection (ALPD) a crucial area within traffic analysis. Recent advancements in deep learning have spurred a surge of studies in ALPD. However, the computational limitations of on-board devices hinder the performance of real-time ALPD systems for moving vehicles. Therefore, we propose a real-time frame-by-frame LP detector focusing on real-time accurate LP detection. Specifically, video frames are categorized into keyframes and non-keyframes. Keyframes are processed by a deeper network (high-level stream), while non-keyframes are handled by a lightweight network (low-level stream), significantly enhancing efficiency. To achieve accurate detection, we design a knowledge distillation strategy to boost the performance of low-level stream and a feature propagation method to introduce the temporal clues in video LP detection. Our contributions are: (1) A real-time frame-by-frame LP detector for video LP detection is proposed, achieving a competitive performance with popular one-stage LP detectors. (2) A simple feature-based knowledge distillation strategy is introduced to improve the low-level stream performance. (3) A spatial-temporal attention feature propagation method is designed to refine the features from non-keyframes guided by the memory features from keyframes, leveraging the inherent temporal correlation in videos. The ablation studies show the effectiveness of knowledge distillation strategy and feature propagation method.
{"title":"FF-LPD: A Real-Time Frame-by-Frame License Plate Detector With Knowledge Distillation and Feature Propagation","authors":"Haoxuan Ding;Junyu Gao;Yuan Yuan;Qi Wang","doi":"10.1109/TIP.2024.3414269","DOIUrl":"10.1109/TIP.2024.3414269","url":null,"abstract":"With the increasing availability of cameras in vehicles, obtaining license plate (LP) information via on-board cameras has become feasible in traffic scenarios. LPs play a pivotal role in vehicle identification, making automatic LP detection (ALPD) a crucial area within traffic analysis. Recent advancements in deep learning have spurred a surge of studies in ALPD. However, the computational limitations of on-board devices hinder the performance of real-time ALPD systems for moving vehicles. Therefore, we propose a real-time frame-by-frame LP detector focusing on real-time accurate LP detection. Specifically, video frames are categorized into keyframes and non-keyframes. Keyframes are processed by a deeper network (high-level stream), while non-keyframes are handled by a lightweight network (low-level stream), significantly enhancing efficiency. To achieve accurate detection, we design a knowledge distillation strategy to boost the performance of low-level stream and a feature propagation method to introduce the temporal clues in video LP detection. Our contributions are: (1) A real-time frame-by-frame LP detector for video LP detection is proposed, achieving a competitive performance with popular one-stage LP detectors. (2) A simple feature-based knowledge distillation strategy is introduced to improve the low-level stream performance. (3) A spatial-temporal attention feature propagation method is designed to refine the features from non-keyframes guided by the memory features from keyframes, leveraging the inherent temporal correlation in videos. The ablation studies show the effectiveness of knowledge distillation strategy and feature propagation method.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428585","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}
Semi-supervised learning (SSL), which aims to learn with limited labeled data and massive amounts of unlabeled data, offers a promising approach to exploit the massive amounts of satellite Earth observation images. The fundamental concept underlying most state-of-the-art SSL methods involves generating pseudo-labels for unlabeled data based on image-level predictions. However, complex remote sensing (RS) scene images frequently encounter challenges, such as interference from multiple background objects and significant intra-class differences, resulting in unreliable pseudo-labels. In this paper, we propose the SemiRS-COC, a novel semi-supervised classification method for complex RS scenes. Inspired by the idea that neighboring objects in feature space should share consistent semantic labels, SemiRS-COC utilizes the similarity between foreground objects in RS images to generate reliable object-level pseudo-labels, effectively addressing the issues of multiple background objects and significant intra-class differences in complex RS images. Specifically, we first design a Local Self-Learning Object Perception (LSLOP) mechanism, which transforms multiple background objects interference of RS images into usable annotation information, enhancing the model’s object perception capability. Furthermore, we present a Cross-Object Consistency Pseudo-Labeling (COCPL) strategy, which generates reliable object-level pseudo-labels by comparing the similarity of foreground objects across different RS images, effectively handling significant intra-class differences. Extensive experiments demonstrate that our proposed method achieves excellent performance compared to state-of-the-art methods on three widely-adopted RS datasets.
{"title":"SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes With Cross-Object Consistency","authors":"Qiang Liu;Jun Yue;Yang Kuang;Weiying Xie;Leyuan Fang","doi":"10.1109/TIP.2024.3414122","DOIUrl":"10.1109/TIP.2024.3414122","url":null,"abstract":"Semi-supervised learning (SSL), which aims to learn with limited labeled data and massive amounts of unlabeled data, offers a promising approach to exploit the massive amounts of satellite Earth observation images. The fundamental concept underlying most state-of-the-art SSL methods involves generating pseudo-labels for unlabeled data based on image-level predictions. However, complex remote sensing (RS) scene images frequently encounter challenges, such as interference from multiple background objects and significant intra-class differences, resulting in unreliable pseudo-labels. In this paper, we propose the SemiRS-COC, a novel semi-supervised classification method for complex RS scenes. Inspired by the idea that neighboring objects in feature space should share consistent semantic labels, SemiRS-COC utilizes the similarity between foreground objects in RS images to generate reliable object-level pseudo-labels, effectively addressing the issues of multiple background objects and significant intra-class differences in complex RS images. Specifically, we first design a Local Self-Learning Object Perception (LSLOP) mechanism, which transforms multiple background objects interference of RS images into usable annotation information, enhancing the model’s object perception capability. Furthermore, we present a Cross-Object Consistency Pseudo-Labeling (COCPL) strategy, which generates reliable object-level pseudo-labels by comparing the similarity of foreground objects across different RS images, effectively handling significant intra-class differences. Extensive experiments demonstrate that our proposed method achieves excellent performance compared to state-of-the-art methods on three widely-adopted RS datasets.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141428586","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：