IR cameras are widely used for temperature measurements in various applications, including agriculture, medicine, and security. Low-cost IR cameras have the immense potential to replace expensive radiometric cameras in these applications; however, low-cost microbolometer-based IR cameras are prone to spatially variant nonuniformity and to drift in temperature measurements, which limit their usability in practical scenarios. To address these limitations, we propose a novel approach for simultaneous temperature estimation and nonuniformity correction (NUC) from multiple frames captured by low-cost microbolometer-based IR cameras. We leverage the camera’s physical image-acquisition model and incorporate it into a deep-learning architecture termed kernel prediction network (KPN), which enables us to combine multiple frames despite imperfect registration between them. We also propose a novel offset block that incorporates the ambient temperature into the model and enables us to estimate the offset of the camera, which is a key factor in temperature estimation. Our findings demonstrate that the number of frames has a significant impact on the accuracy of the temperature estimation and NUC. Moreover, introduction of the offset block results in significantly improved performance compared to vanilla KPN. The method was tested on real data collected by a low-cost IR camera mounted on an unmanned aerial vehicle, showing only a small average error of $0.27-0.54^{circ } C$ relative to costly scientific-grade radiometric cameras. Real data collected horizontally resulted in similar errors of $0.48-0.68^{circ } C$ . Our method provides an accurate and efficient solution for simultaneous temperature estimation and NUC, which has important implications for a wide range of practical applications.
{"title":"Simultaneous Temperature Estimation and Nonuniformity Correction From Multiple Frames","authors":"Navot Oz;Omri Berman;Nir Sochen;David Mendlovic;Iftach Klapp","doi":"10.1109/TIP.2024.3458861","DOIUrl":"10.1109/TIP.2024.3458861","url":null,"abstract":"IR cameras are widely used for temperature measurements in various applications, including agriculture, medicine, and security. Low-cost IR cameras have the immense potential to replace expensive radiometric cameras in these applications; however, low-cost microbolometer-based IR cameras are prone to spatially variant nonuniformity and to drift in temperature measurements, which limit their usability in practical scenarios. To address these limitations, we propose a novel approach for simultaneous temperature estimation and nonuniformity correction (NUC) from multiple frames captured by low-cost microbolometer-based IR cameras. We leverage the camera’s physical image-acquisition model and incorporate it into a deep-learning architecture termed kernel prediction network (KPN), which enables us to combine multiple frames despite imperfect registration between them. We also propose a novel offset block that incorporates the ambient temperature into the model and enables us to estimate the offset of the camera, which is a key factor in temperature estimation. Our findings demonstrate that the number of frames has a significant impact on the accuracy of the temperature estimation and NUC. Moreover, introduction of the offset block results in significantly improved performance compared to vanilla KPN. The method was tested on real data collected by a low-cost IR camera mounted on an unmanned aerial vehicle, showing only a small average error of \u0000<inline-formula> <tex-math>$0.27-0.54^{circ } C$ </tex-math></inline-formula>\u0000 relative to costly scientific-grade radiometric cameras. Real data collected horizontally resulted in similar errors of \u0000<inline-formula> <tex-math>$0.48-0.68^{circ } C$ </tex-math></inline-formula>\u0000. Our method provides an accurate and efficient solution for simultaneous temperature estimation and NUC, which has important implications for a wide range of practical applications.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5246-5259"},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10682482","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-16DOI: 10.1109/TIP.2024.3457236
Binhui Liu;Tianchu Guo;Bin Luo;Zhen Cui;Jian Yang
Defect detection from images is a crucial and challenging topic of industry scenarios due to the scarcity and unpredictability of anomalous samples. However, existing defect detection methods exhibit low detection performance when it comes to small-size defects. In this work, we propose a Cross-Attention Regression Flow (CARF) framework to model a compact distribution of normal visual patterns for separating outliers. To retain rich scale information of defects, we build an interactive cross-attention pattern flow module to jointly transform and align distributions of multi-layer features, which is beneficial for detecting small-size defects that may be annihilated in high-level features. To handle the complexity of multi-layer feature distributions, we introduce a layer-conditional autoregression module to improve the fitting capacity of data likelihoods on multi-layer features. By transforming the multi-layer feature distributions into a latent space, we can better characterize normal visual patterns. Extensive experiments on four public datasets and our collected industrial dataset demonstrate that the proposed CARF outperforms state-of-the-art methods, particularly in detecting small-size defects.
{"title":"Cross-Attention Regression Flow for Defect Detection","authors":"Binhui Liu;Tianchu Guo;Bin Luo;Zhen Cui;Jian Yang","doi":"10.1109/TIP.2024.3457236","DOIUrl":"https://doi.org/10.1109/TIP.2024.3457236","url":null,"abstract":"Defect detection from images is a crucial and challenging topic of industry scenarios due to the scarcity and unpredictability of anomalous samples. However, existing defect detection methods exhibit low detection performance when it comes to small-size defects. In this work, we propose a Cross-Attention Regression Flow (CARF) framework to model a compact distribution of normal visual patterns for separating outliers. To retain rich scale information of defects, we build an interactive cross-attention pattern flow module to jointly transform and align distributions of multi-layer features, which is beneficial for detecting small-size defects that may be annihilated in high-level features. To handle the complexity of multi-layer feature distributions, we introduce a layer-conditional autoregression module to improve the fitting capacity of data likelihoods on multi-layer features. By transforming the multi-layer feature distributions into a latent space, we can better characterize normal visual patterns. Extensive experiments on four public datasets and our collected industrial dataset demonstrate that the proposed CARF outperforms state-of-the-art methods, particularly in detecting small-size defects.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5183-5193"},"PeriodicalIF":0.0,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142246501","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 : 2024-09-16DOI: 10.1109/TIP.2024.3451930
Ziheng Chen;Yue Song;Tianyang Xu;Zhiwu Huang;Xiao-Jun Wu;Nicu Sebe
Symmetric Positive Definite (SPD) matrices have received wide attention in machine learning due to their intrinsic capacity to encode underlying structural correlation in data. Many successful Riemannian metrics have been proposed to reflect the non-Euclidean geometry of SPD manifolds. However, most existing metric tensors are fixed, which might lead to sub-optimal performance for SPD matrix learning, especially for deep SPD neural networks. To remedy this limitation, we leverage the commonly encountered pullback techniques and propose Adaptive Log-Euclidean Metrics (ALEMs), which extend the widely used Log-Euclidean Metric (LEM). Compared with the previous Riemannian metrics, our metrics contain learnable parameters, which can better adapt to the complex dynamics of Riemannian neural networks with minor extra computations. We also present a complete theoretical analysis to support our ALEMs, including algebraic and Riemannian properties. The experimental and theoretical results demonstrate the merit of the proposed metrics in improving the performance of SPD neural networks. The efficacy of our metrics is further showcased on a set of recently developed Riemannian building blocks, including Riemannian batch normalization, Riemannian Residual blocks, and Riemannian classifiers.
由于对称正定（SPD）矩阵具有编码数据中潜在结构相关性的内在能力，因此在机器学习领域受到广泛关注。为了反映 SPD 流形的非欧几里得几何特征，人们提出了许多成功的黎曼度量。然而，大多数现有的度量张量都是固定的，这可能会导致 SPD 矩阵学习的性能低于最优，尤其是对于深度 SPD 神经网络而言。为了弥补这一局限，我们利用常见的回拉技术，提出了自适应对数-欧几里得度量（ALEM），扩展了广泛使用的对数-欧几里得度量（LEM）。与之前的黎曼度量相比，我们的度量包含可学习参数，只需少量额外计算即可更好地适应黎曼神经网络的复杂动态。我们还提出了支持我们的 ALEM 的完整理论分析，包括代数和黎曼特性。实验和理论结果证明了所提出的度量在提高 SPD 神经网络性能方面的优势。我们的度量方法在最近开发的一系列黎曼构建模块（包括黎曼批归一化、黎曼残差模块和黎曼分类器）上进一步展示了其功效。
{"title":"Adaptive Log-Euclidean Metrics for SPD Matrix Learning","authors":"Ziheng Chen;Yue Song;Tianyang Xu;Zhiwu Huang;Xiao-Jun Wu;Nicu Sebe","doi":"10.1109/TIP.2024.3451930","DOIUrl":"10.1109/TIP.2024.3451930","url":null,"abstract":"Symmetric Positive Definite (SPD) matrices have received wide attention in machine learning due to their intrinsic capacity to encode underlying structural correlation in data. Many successful Riemannian metrics have been proposed to reflect the non-Euclidean geometry of SPD manifolds. However, most existing metric tensors are fixed, which might lead to sub-optimal performance for SPD matrix learning, especially for deep SPD neural networks. To remedy this limitation, we leverage the commonly encountered pullback techniques and propose Adaptive Log-Euclidean Metrics (ALEMs), which extend the widely used Log-Euclidean Metric (LEM). Compared with the previous Riemannian metrics, our metrics contain learnable parameters, which can better adapt to the complex dynamics of Riemannian neural networks with minor extra computations. We also present a complete theoretical analysis to support our ALEMs, including algebraic and Riemannian properties. The experimental and theoretical results demonstrate the merit of the proposed metrics in improving the performance of SPD neural networks. The efficacy of our metrics is further showcased on a set of recently developed Riemannian building blocks, including Riemannian batch normalization, Riemannian Residual blocks, and Riemannian classifiers.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5194-5205"},"PeriodicalIF":0.0,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236319","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 : 2024-09-13DOI: 10.1109/TIP.2024.3438100
Bin Yang;Yin Mao;Licheng Liu;Leyuan Fang;Xinxin Liu
Deep learning-based hyperspectral image (HSI) change detection (CD) approaches have a strong ability to leverage spectral-spatial-temporal information through automatic feature extraction, and currently dominate in the research field. However, their efficiency and universality are limited by the dependency on labeled data. Although the newly applied untrained networks can avoid the need for labeled data, their feature volatility from the simple difference space easily leads to inaccurate CD results. Inspired by the interesting finding that salient changes appear as bright “stripes” in a new feature space, we propose a novel unsupervised CD method that represents and models changes in stripes for HSIs (named as StripeCD), which integrates optimization modeling into an untrained network. The StripeCD method constructs a new feature space that represents change features in stripes and models them in a novel optimization manner. It consists of three main parts: 1) dual-branch untrained convolutional network, which is utilized to extract deep difference features from bitemporal HSIs and combined with a two-stage channel selection strategy to emphasize the important channels that contribute to CD. 2) multiscale forward-backward segmentation framework, which is proposed for salient change representation. It transforms deep difference features into a new feature space by exploiting the structure information of ground objects and associates salient changes with the stripe-shaped change component. 3) stripe-shaped change extraction model, which characterizes the global sparsity and local discontinuity of salient changes. It explores the intrinsic properties of deep difference features and constructs model-based constraints to better identify changed regions in a controllable manner. The proposed StripeCD method outperformed the state-of-the-art unsupervised CD approaches on three widely used datasets. In addition, the proposed StripeCD method indicates the potential for further investigation of untrained networks in facilitating reliable CD.
基于深度学习的高光谱图像（HSI）变化检测（CD）方法通过自动特征提取，具有很强的光谱-空间-时间信息利用能力，目前在研究领域占据主导地位。然而，由于对标记数据的依赖性，这些方法的效率和普遍性受到了限制。虽然新应用的非训练网络可以避免对标记数据的需求，但其来自简单差分空间的特征波动性容易导致不准确的 CD 结果。受突出变化在新特征空间中表现为明亮 "条纹 "这一有趣发现的启发，我们提出了一种新颖的无监督 CD 方法，该方法以条纹表示恒生指数的变化并对其进行建模（命名为 StripeCD），它将优化建模集成到了未经训练的网络中。StripeCD 方法构建了一个新的特征空间，用于表示条纹的变化特征，并以一种新颖的优化方式对其进行建模。它由三个主要部分组成：1）双分支非训练卷积网络，用于从位时 HSI 中提取深度差异特征，并与两阶段通道选择策略相结合，以强调对 CD 有贡献的重要通道。2) 多尺度前向-后向分割框架，用于突出变化表示。它通过利用地面物体的结构信息，将深层差异特征转化为新的特征空间，并将显著变化与条纹状变化分量关联起来。3）条纹状变化提取模型，该模型表征了显著变化的全局稀疏性和局部不连续性。它探索了深层差异特征的内在属性，并构建了基于模型的约束条件，从而以可控的方式更好地识别变化区域。在三个广泛使用的数据集上，所提出的 StripeCD 方法优于最先进的无监督 CD 方法。此外，所提出的 StripeCD 方法还表明，在促进可靠的 CD 方面，未训练网络具有进一步研究的潜力。
{"title":"Change Representation and Extraction in Stripes: Rethinking Unsupervised Hyperspectral Image Change Detection With an Untrained Network","authors":"Bin Yang;Yin Mao;Licheng Liu;Leyuan Fang;Xinxin Liu","doi":"10.1109/TIP.2024.3438100","DOIUrl":"10.1109/TIP.2024.3438100","url":null,"abstract":"Deep learning-based hyperspectral image (HSI) change detection (CD) approaches have a strong ability to leverage spectral-spatial-temporal information through automatic feature extraction, and currently dominate in the research field. However, their efficiency and universality are limited by the dependency on labeled data. Although the newly applied untrained networks can avoid the need for labeled data, their feature volatility from the simple difference space easily leads to inaccurate CD results. Inspired by the interesting finding that salient changes appear as bright “stripes” in a new feature space, we propose a novel unsupervised CD method that represents and models changes in stripes for HSIs (named as StripeCD), which integrates optimization modeling into an untrained network. The StripeCD method constructs a new feature space that represents change features in stripes and models them in a novel optimization manner. It consists of three main parts: 1) dual-branch untrained convolutional network, which is utilized to extract deep difference features from bitemporal HSIs and combined with a two-stage channel selection strategy to emphasize the important channels that contribute to CD. 2) multiscale forward-backward segmentation framework, which is proposed for salient change representation. It transforms deep difference features into a new feature space by exploiting the structure information of ground objects and associates salient changes with the stripe-shaped change component. 3) stripe-shaped change extraction model, which characterizes the global sparsity and local discontinuity of salient changes. It explores the intrinsic properties of deep difference features and constructs model-based constraints to better identify changed regions in a controllable manner. The proposed StripeCD method outperformed the state-of-the-art unsupervised CD approaches on three widely used datasets. In addition, the proposed StripeCD method indicates the potential for further investigation of untrained networks in facilitating reliable CD.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5098-5113"},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142231614","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}
Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR adaptively decomposes different types of degradations, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively approximate and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalizability of our method. Code is available at https://github.com/mdyao/NDR-Restore .
{"title":"Neural Degradation Representation Learning for All-in-One Image Restoration","authors":"Mingde Yao;Ruikang Xu;Yuanshen Guan;Jie Huang;Zhiwei Xiong","doi":"10.1109/TIP.2024.3456583","DOIUrl":"10.1109/TIP.2024.3456583","url":null,"abstract":"Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch between the model and the degradation will result in a severe performance drop. In this paper, we propose an all-in-one image restoration network that tackles multiple degradations. Due to the heterogeneous nature of different types of degradations, it is difficult to process multiple degradations in a single network. To this end, we propose to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations. The learned NDR adaptively decomposes different types of degradations, similar to a neural dictionary that represents basic degradation components. Subsequently, we develop a degradation query module and a degradation injection module to effectively approximate and utilize the specific degradation based on NDR, enabling the all-in-one restoration ability for multiple degradations. Moreover, we propose a bidirectional optimization strategy to effectively drive NDR to learn the degradation representation by optimizing the degradation and restoration processes alternately. Comprehensive experiments on representative types of degradations (including noise, haze, rain, and downsampling) demonstrate the effectiveness and generalizability of our method. Code is available at \u0000<uri>https://github.com/mdyao/NDR-Restore</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5408-5423"},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142231612","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 : 2024-09-12DOI: 10.1109/TIP.2024.3456000
Xi Yang;Huanling Liu;Nannan Wang;Xinbo Gao
The potential vulnerability of deep neural networks and the complexity of pedestrian images, greatly limits the application of person re-identification techniques in the field of smart security. Current attack methods often focus on generating carefully crafted adversarial samples or only disrupting the metric distances between targets and similar pedestrians. However, both aspects are crucial for evaluating the security of methods adapted for person re-identification tasks. For this reason, we propose an image-level adaptive adversarial ranking method that comprehensively considers two aspects to adapt to changes in pedestrians in the real world and effectively evaluate the robustness of models in adversarial environments. To generate more refined adversarial samples, our image representation enhancement module leverages channel-wise information entropy, assigning varying weights to different channels to produce images with richer information content, along with a generative adversarial network to create adversarial samples. Subsequently, for adaptive perturbation of ranking, the adaptive weight confusion ranking loss is presented to calculate the weights of distances between positive or negative samples and query samples. It endeavors to push positive samples away from query samples and bring negative samples closer, thereby interfering with the ranking of system. Notably, this method requires no additional hyperparameter tuning or extra data training, making it an adaptive attack strategy. Experimental results on large-scale datasets such as Market1501, CUHK03, and DukeMTMC demonstrate the effectiveness of our method in attacking ReID systems.
{"title":"Image-Level Adaptive Adversarial Ranking for Person Re-Identification","authors":"Xi Yang;Huanling Liu;Nannan Wang;Xinbo Gao","doi":"10.1109/TIP.2024.3456000","DOIUrl":"10.1109/TIP.2024.3456000","url":null,"abstract":"The potential vulnerability of deep neural networks and the complexity of pedestrian images, greatly limits the application of person re-identification techniques in the field of smart security. Current attack methods often focus on generating carefully crafted adversarial samples or only disrupting the metric distances between targets and similar pedestrians. However, both aspects are crucial for evaluating the security of methods adapted for person re-identification tasks. For this reason, we propose an image-level adaptive adversarial ranking method that comprehensively considers two aspects to adapt to changes in pedestrians in the real world and effectively evaluate the robustness of models in adversarial environments. To generate more refined adversarial samples, our image representation enhancement module leverages channel-wise information entropy, assigning varying weights to different channels to produce images with richer information content, along with a generative adversarial network to create adversarial samples. Subsequently, for adaptive perturbation of ranking, the adaptive weight confusion ranking loss is presented to calculate the weights of distances between positive or negative samples and query samples. It endeavors to push positive samples away from query samples and bring negative samples closer, thereby interfering with the ranking of system. Notably, this method requires no additional hyperparameter tuning or extra data training, making it an adaptive attack strategy. Experimental results on large-scale datasets such as Market1501, CUHK03, and DukeMTMC demonstrate the effectiveness of our method in attacking ReID systems.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5172-5182"},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174676","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 person re-identification (Re-ID) is challenging due to the lack of ground truth labels. Most existing methods employ iterative clustering to generate pseudo labels for unlabeled training data to guide the learning process. However, how to select samples that are both associated with high-confidence pseudo labels and hard (discriminative) enough remains a critical problem. To address this issue, a disentangled sample guidance learning (DSGL) method is proposed for unsupervised Re-ID. The method consists of disentangled sample mining (DSM) and discriminative feature learning (DFL). DSM disentangles (unlabeled) person images into identity-relevant and identity-irrelevant factors, which are used to construct disentangled positive/negative groups that contain discriminative enough information. DFL incorporates the mined disentangled sample groups into model training by a surrogate disentangled learning loss and a disentangled second-order similarity regularization, to help the model better distinguish the characteristics of different persons. By using the DSGL training strategy, the mAP on Market-1501 and MSMT17 increases by 6.6% and 10.1% when applying the ResNet50 framework, and by 0.6% and 6.9% with the vision transformer (VIT) framework, respectively, validating the effectiveness of the DSGL method. Moreover, DSGL surpasses previous state-of-the-art methods by achieving higher Top-1 accuracy and mAP on the Market-1501, MSMT17, PersonX, and VeRi-776 datasets. The source code for this paper is available at https://github.com/jihaoxuanye/DiseSGL .
{"title":"Disentangled Sample Guidance Learning for Unsupervised Person Re-Identification","authors":"Haoxuanye Ji;Le Wang;Sanping Zhou;Wei Tang;Gang Hua","doi":"10.1109/TIP.2024.3456008","DOIUrl":"10.1109/TIP.2024.3456008","url":null,"abstract":"Unsupervised person re-identification (Re-ID) is challenging due to the lack of ground truth labels. Most existing methods employ iterative clustering to generate pseudo labels for unlabeled training data to guide the learning process. However, how to select samples that are both associated with high-confidence pseudo labels and hard (discriminative) enough remains a critical problem. To address this issue, a disentangled sample guidance learning (DSGL) method is proposed for unsupervised Re-ID. The method consists of disentangled sample mining (DSM) and discriminative feature learning (DFL). DSM disentangles (unlabeled) person images into identity-relevant and identity-irrelevant factors, which are used to construct disentangled positive/negative groups that contain discriminative enough information. DFL incorporates the mined disentangled sample groups into model training by a surrogate disentangled learning loss and a disentangled second-order similarity regularization, to help the model better distinguish the characteristics of different persons. By using the DSGL training strategy, the mAP on Market-1501 and MSMT17 increases by 6.6% and 10.1% when applying the ResNet50 framework, and by 0.6% and 6.9% with the vision transformer (VIT) framework, respectively, validating the effectiveness of the DSGL method. Moreover, DSGL surpasses previous state-of-the-art methods by achieving higher Top-1 accuracy and mAP on the Market-1501, MSMT17, PersonX, and VeRi-776 datasets. The source code for this paper is available at \u0000<uri>https://github.com/jihaoxuanye/DiseSGL</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5144-5158"},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174675","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 : 2024-09-12DOI: 10.1109/TIP.2024.3455989
Somdyuti Paul;Andrey Norkin;Alan C. Bovik
Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection requires a video shot to be pre-encoded with multiple encoding parameters to find the optimal operating points given by the convex hull of the resulting rate-quality curves. However, this pre-encoding step is equivalent to an exhaustive search process over the space of possible encoding parameters, which causes significant overhead in terms of both computation and time expenditure. To reduce this overhead, we propose a deep learning based method of content aware convex hull prediction. We employ a recurrent convolutional network (RCN) to implicitly analyze the spatiotemporal complexity of video shots in order to predict their convex hulls. A two-step transfer learning scheme is adopted to train our proposed RCN-Hull model, which ensures sufficient content diversity to analyze scene complexity, while also making it possible to capture the scene statistics of pristine source videos. Our experimental results reveal that our proposed model yields better approximations of the optimal convex hulls, and offers competitive time savings as compared to existing approaches. On average, the pre-encoding time was reduced by 53.8% by our method, while the average Bjøntegaard delta bitrate (BD-rate) of the predicted convex hulls against ground truth was 0.26%, and the mean absolute deviation of the BD-rate distribution was 0.57%.
{"title":"Convex Hull Prediction for Adaptive Video Streaming by Recurrent Learning","authors":"Somdyuti Paul;Andrey Norkin;Alan C. Bovik","doi":"10.1109/TIP.2024.3455989","DOIUrl":"10.1109/TIP.2024.3455989","url":null,"abstract":"Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection requires a video shot to be pre-encoded with multiple encoding parameters to find the optimal operating points given by the convex hull of the resulting rate-quality curves. However, this pre-encoding step is equivalent to an exhaustive search process over the space of possible encoding parameters, which causes significant overhead in terms of both computation and time expenditure. To reduce this overhead, we propose a deep learning based method of content aware convex hull prediction. We employ a recurrent convolutional network (RCN) to implicitly analyze the spatiotemporal complexity of video shots in order to predict their convex hulls. A two-step transfer learning scheme is adopted to train our proposed RCN-Hull model, which ensures sufficient content diversity to analyze scene complexity, while also making it possible to capture the scene statistics of pristine source videos. Our experimental results reveal that our proposed model yields better approximations of the optimal convex hulls, and offers competitive time savings as compared to existing approaches. On average, the pre-encoding time was reduced by 53.8% by our method, while the average Bjøntegaard delta bitrate (BD-rate) of the predicted convex hulls against ground truth was 0.26%, and the mean absolute deviation of the BD-rate distribution was 0.57%.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5114-5128"},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174679","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}
Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through distinct branch types and output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We have released our source code, pretrained models, and demos to facilitate future studies on https://github.com/cjm-sfw/Uniparser .
{"title":"UniParser: Multi-Human Parsing With Unified Correlation Representation Learning","authors":"Jiaming Chu;Lei Jin;Yinglei Teng;Jianshu Li;Yunchao Wei;Zheng Wang;Junliang Xing;Shuicheng Yan;Jian Zhao","doi":"10.1109/TIP.2024.3456004","DOIUrl":"10.1109/TIP.2024.3456004","url":null,"abstract":"Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through distinct branch types and output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We have released our source code, pretrained models, and demos to facilitate future studies on \u0000<uri>https://github.com/cjm-sfw/Uniparser</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5159-5171"},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174677","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}
In this work, by re-examining the “matching” nature of Anomaly Detection (AD), we propose a novel AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion. Given a test sample, the top-K most similar training images are first selected based on a robust histogram matching process. Secondly, the nearest neighbor of each test patch is retrieved over the similar geometrical locations on those “most similar images”, by using a carefully trained local metric. Finally, the anomaly score of each test image patch is calculated based on the distance to its “nearest neighbor” and the “non-background” probability. The proposed method is termed “Cascade Patch Retrieval” (CPR) in this work. Different from the previous patch-matching-based AD algorithms, CPR selects proper “targets” (reference images and patches) before “shooting” (patch-matching). On the well-acknowledged MVTec AD, BTAD and MVTec-3D AD datasets, the proposed algorithm consistently outperforms all the comparing SOTA methods by remarkable margins, measured by various AD metrics. Furthermore, CPR is extremely efficient. It runs at the speed of 113 FPS with the standard setting while its simplified version only requires less than 1 ms to process an image at the cost of a trivial accuracy drop. The code of CPR is available at https://github.com/flyinghu123/CPR .
在这项工作中，通过重新审视异常检测（AD）的 "匹配 "本质，我们提出了一种新颖的异常检测框架，该框架同时享有新的异常检测准确率记录和显著的高速运行速度。在该框架中，异常检测问题通过级联补丁检索程序来解决，该程序以从粗到细的方式检索每个测试图像补丁的最近邻。给定一个测试样本后，首先根据稳健的直方图匹配过程选出前 K 个最相似的训练图像。其次，通过使用精心训练的局部度量，在这些 "最相似图像 "的相似几何位置上检索每个测试图斑的近邻。最后，根据与 "最近邻居 "的距离和 "非背景 "概率计算出每个测试图像补丁的异常得分。在这项工作中，所提出的方法被称为 "级联补丁检索"（CPR）。与以往基于补丁匹配的 AD 算法不同，CPR 在 "拍摄"（补丁匹配）之前先选择合适的 "目标"（参考图像和补丁）。在广受认可的 MVTec AD、BTAD 和 MVTec-3D AD 数据集上，根据各种 AD 指标衡量，所提出的算法始终优于所有同类 SOTA 方法。此外，CPR 非常高效。在标准设置下，它的运行速度为 113 FPS，而其简化版本处理一幅图像只需不到 1 毫秒，但精度却有微小的下降。CPR 的代码见 https://github.com/flyinghu123/CPR。
{"title":"Target Before Shooting: Accurate Anomaly Detection and Localization Under One Millisecond via Cascade Patch Retrieval","authors":"Hanxi Li;Jianfei Hu;Bo Li;Hao Chen;Yongbin Zheng;Chunhua Shen","doi":"10.1109/TIP.2024.3448263","DOIUrl":"10.1109/TIP.2024.3448263","url":null,"abstract":"In this work, by re-examining the “matching” nature of Anomaly Detection (AD), we propose a novel AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion. Given a test sample, the top-K most similar training images are first selected based on a robust histogram matching process. Secondly, the nearest neighbor of each test patch is retrieved over the similar geometrical locations on those “most similar images”, by using a carefully trained local metric. Finally, the anomaly score of each test image patch is calculated based on the distance to its “nearest neighbor” and the “non-background” probability. The proposed method is termed “Cascade Patch Retrieval” (CPR) in this work. Different from the previous patch-matching-based AD algorithms, CPR selects proper “targets” (reference images and patches) before “shooting” (patch-matching). On the well-acknowledged MVTec AD, BTAD and MVTec-3D AD datasets, the proposed algorithm consistently outperforms all the comparing SOTA methods by remarkable margins, measured by various AD metrics. Furthermore, CPR is extremely efficient. It runs at the speed of 113 FPS with the standard setting while its simplified version only requires less than 1 ms to process an image at the cost of a trivial accuracy drop. The code of CPR is available at \u0000<uri>https://github.com/flyinghu123/CPR</uri>\u0000.","PeriodicalId":94032,"journal":{"name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","volume":"33 ","pages":"5606-5621"},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142170998","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：