IEEE transactions on image processing : a publication of the IEEE Signal Processing Society最新文献

Blind Video Quality Prediction by Uncovering Human Video Perceptual Representation. 通过揭示人类视频感知表征进行盲视频质量预测

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3445738

Liang Liao, Kangmin Xu, Haoning Wu, Chaofeng Chen, Wenxiu Sun, Qiong Yan, C-C Jay Kuo, Weisi Lin

{"title":"Blind Video Quality Prediction by Uncovering Human Video Perceptual Representation.","authors":"Liang Liao, Kangmin Xu, Haoning Wu, Chaofeng Chen, Wenxiu Sun, Qiong Yan, C-C Jay Kuo, Weisi Lin","doi":"10.1109/TIP.2024.3445738","DOIUrl":"https://doi.org/10.1109/TIP.2024.3445738","url":null,"abstract":"Blind video quality assessment (VQA) has become an increasingly demanding problem in automatically assessing the quality of ever-growing in-the-wild videos. Although efforts have been made to measure temporal distortions, the core to distinguish between VQA and image quality assessment (IQA), the lack of modeling of how the human visual system (HVS) relates to the temporal quality of videos hinders the precise mapping of predicted temporal scores to the human perception. Inspired by the recent discovery of the temporal straightness law of natural videos in the HVS, this paper intends to model the complex temporal distortions of in-the-wild videos in a simple and uniform representation by describing the geometric properties of videos in the visual perceptual domain. A novel videolet, with perceptual representation embedding of a few consecutive frames, is designed as the basic quality measurement unit to quantify temporal distortions by measuring the angular and linear displacements from the straightness law. By combining the predicted score on each videolet, a perceptually temporal quality evaluator (PTQE) is formed to measure the temporal quality of the entire video. Experimental results demonstrate that the perceptual representation in the HVS is an efficient way of predicting subjective temporal quality. Moreover, when combined with spatial quality metrics, PTQE achieves top performance over popular in-the-wild video datasets. More importantly, PTQE requires no additional information beyond the video being assessed, making it applicable to any dataset without parameter tuning. Additionally, the generalizability of PTQE is evaluated on video frame interpolation tasks, demonstrating its potential to benefit temporal-related enhancement 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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142132","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}

引用次数: 0

UVaT: Uncertainty Incorporated View-aware Transformer for Robust Multi-view Classification. UVaT：用于稳健多视角分类的不确定性纳入视角感知变换器。

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451931

Yapeng Li, Yong Luo, Bo Du

{"title":"UVaT: Uncertainty Incorporated View-aware Transformer for Robust Multi-view Classification.","authors":"Yapeng Li, Yong Luo, Bo Du","doi":"10.1109/TIP.2024.3451931","DOIUrl":"https://doi.org/10.1109/TIP.2024.3451931","url":null,"abstract":"Existing multi-view classification algorithms usually assume that all examples have observations on all views, and the data in different views are clean. However, in real-world applications, we are often provided with data that have missing representations or contain noise on some views (i.e., missing or noise views). This may lead to significant performance degeneration, and thus many algorithms are proposed to address the incomplete view or noisy view issues. However, most of existing algorithms deal with the two issues separately, and hence may fail when both missing and noisy views exist. They are also usually not flexible in that the view or feature significance cannot be adaptively identified. Besides, the view missing patterns may vary in the training and test phases, and such difference is often ignored. To remedy these drawbacks, we propose a novel multi-view classification framework that is simultaneously robust to both incomplete and noisy views. This is achieved by integrating early fusion and late fusion in a single framework. Specifically, in our early fusion module, we propose a view-aware transformer to mask the missing views and adaptively explore the relationships between views and target tasks to deal with missing views. Considering that view missing patterns may change from the training to the test phase, we also design single-view classification and category-consistency constraints to reduce the dependence of our model on view-missing patterns. In our late fusion module, we quantify the view uncertainty in an ensemble way to estimate the noise level of that view. Then the uncertainty and prediction logits of different views are integrated to make our model robust to noisy views. The framework is trained in an end-to-end manner. Experimental results on diverse datasets demonstrate the robustness and effectiveness of our model for both incomplete and noisy views. Codes are available at https://github.com/li-yapeng/UVaT.","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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142174","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}

引用次数: 0

M2GCNet: Multi-Modal Graph Convolution Network for Precise Brain Tumor Segmentation Across Multiple MRI Sequences M2GCNet：多模态图卷积网络用于在多个磁共振成像序列中精确划分脑肿瘤。

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451936

Tongxue Zhou

{"title":"M2GCNet: Multi-Modal Graph Convolution Network for Precise Brain Tumor Segmentation Across Multiple MRI Sequences","authors":"Tongxue Zhou","doi":"10.1109/TIP.2024.3451936","DOIUrl":"10.1109/TIP.2024.3451936","url":null,"abstract":"Accurate segmentation of brain tumors across multiple MRI sequences is essential for diagnosis, treatment planning, and clinical decision-making. In this paper, I propose a cutting-edge framework, named multi-modal graph convolution network (M2GCNet), to explore the relationships across different MR modalities, and address the challenge of brain tumor segmentation. The core of M2GCNet is the multi-modal graph convolution module (M2GCM), a pivotal component that represents MR modalities as graphs, with nodes corresponding to image pixels and edges capturing latent relationships between pixels. This graph-based representation enables the effective utilization of both local and global contextual information. Notably, M2GCM comprises two important modules: the spatial-wise graph convolution module (SGCM), adept at capturing extensive spatial dependencies among distinct regions within an image, and the channel-wise graph convolution module (CGCM), dedicated to modelling intricate contextual dependencies among different channels within the image. Additionally, acknowledging the intrinsic correlation present among different MR modalities, a multi-modal correlation loss function is introduced. This novel loss function aims to capture specific nonlinear relationships between correlated modality pairs, enhancing the model’s ability to achieve accurate segmentation results. The experimental evaluation on two brain tumor datasets demonstrates the superiority of the proposed M2GCNet over other state-of-the-art segmentation methods. Furthermore, the proposed method paves the way for improved tumor diagnosis, multi-modal information fusion, and a deeper understanding of brain tumor pathology.","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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142168","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}

引用次数: 0

Privacy-Preserving Autoencoder for Collaborative Object Detection 用于协作对象检测的隐私保护自动编码器

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451938

Bardia Azizian;Ivan V. Bajić

{"title":"Privacy-Preserving Autoencoder for Collaborative Object Detection","authors":"Bardia Azizian;Ivan V. Bajić","doi":"10.1109/TIP.2024.3451938","DOIUrl":"10.1109/TIP.2024.3451938","url":null,"abstract":"Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural Network (DNN) model runs on the edge, and the rest is executed on the cloud. In such applications, the machine vision model does not need the exact visual content to perform its task. Taking advantage of this potential, private information could be removed from the data insofar as it does not significantly impair the accuracy of the machine vision system. In this paper, we present an autoencoder-style network integrated within an object detection pipeline, which generates a latent representation of the input image that preserves task-relevant information while removing private information. Our approach employs an adversarial training strategy that not only removes private information from the bottleneck of the autoencoder but also promotes improved compression efficiency for feature channels coded by conventional codecs like VVC-Intra. We assess the proposed system using a realistic evaluation framework for privacy, directly measuring face and license plate recognition accuracy. Experimental results show that our proposed method is able to reduce the bitrate significantly at the same object detection accuracy compared to coding the input images directly, while keeping the face and license plate recognition accuracy on the images recovered from the bottleneck features low, implying strong privacy protection. Our code is available at \u0000<uri>https://github.com/bardia-az/ppa-code</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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142169","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}

引用次数: 0

Style Consistency Unsupervised Domain Adaptation Medical Image Segmentation 风格一致的无监督领域适应医学图像分割。

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451934

Lang Chen;Yun Bian;Jianbin Zeng;Qingquan Meng;Weifang Zhu;Fei Shi;Chengwei Shao;Xinjian Chen;Dehui Xiang

{"title":"Style Consistency Unsupervised Domain Adaptation Medical Image Segmentation","authors":"Lang Chen;Yun Bian;Jianbin Zeng;Qingquan Meng;Weifang Zhu;Fei Shi;Chengwei Shao;Xinjian Chen;Dehui Xiang","doi":"10.1109/TIP.2024.3451934","DOIUrl":"10.1109/TIP.2024.3451934","url":null,"abstract":"Unsupervised domain adaptation medical image segmentation is aimed to segment unlabeled target domain images with labeled source domain images. However, different medical imaging modalities lead to large domain shift between their images, in which well-trained models from one imaging modality often fail to segment images from anothor imaging modality. In this paper, to mitigate domain shift between source domain and target domain, a style consistency unsupervised domain adaptation image segmentation method is proposed. First, a local phase-enhanced style fusion method is designed to mitigate domain shift and produce locally enhanced organs of interest. Second, a phase consistency discriminator is constructed to distinguish the phase consistency of domain-invariant features between source domain and target domain, so as to enhance the disentanglement of the domain-invariant and style encoders and removal of domain-specific features from the domain-invariant encoder. Third, a style consistency estimation method is proposed to obtain inconsistency maps from intermediate synthesized target domain images with different styles to measure the difficult regions, mitigate domain shift between synthesized target domain images and real target domain images, and improve the integrity of interested organs. Fourth, style consistency entropy is defined for target domain images to further improve the integrity of the interested organ by the concentration on the inconsistent regions. Comprehensive experiments have been performed with an in-house dataset and a publicly available dataset. The experimental results have demonstrated the superiority of our framework over state-of-the-art 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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142173","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}

引用次数: 0

Reference-Based Multi-Stage Progressive Restoration for Multi-Degraded Images 基于参考的多级渐进式修复多降级图像。

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451939

Yi Zhang;Qixue Yang;Damon M. Chandler;Xuanqin Mou

{"title":"Reference-Based Multi-Stage Progressive Restoration for Multi-Degraded Images","authors":"Yi Zhang;Qixue Yang;Damon M. Chandler;Xuanqin Mou","doi":"10.1109/TIP.2024.3451939","DOIUrl":"10.1109/TIP.2024.3451939","url":null,"abstract":"Image restoration (IR) via deep learning has been vigorously studied in recent years. However, due to the ill-posed nature of the problem, it is challenging to recover the high-quality image details from a single distorted input especially when images are corrupted by multiple distortions. In this paper, we propose a multi-stage IR approach for progressive restoration of multi-degraded images via transferring similar edges/textures from the reference image. Our method, called a Reference-based Image Restoration Transformer (Ref-IRT), operates via three main stages. In the first stage, a cascaded U-Transformer network is employed to perform the preliminary recovery of the image. The proposed network consists of two U-Transformer architectures connected by feature fusion of the encoders and decoders, and the residual image is estimated by each U-Transformer in an easy-to-hard and coarse-to-fine fashion to gradually recover the high-quality image. The second and third stages perform texture transfer from a reference image to the preliminarily-recovered target image to further enhance the restoration performance. To this end, a quality-degradation-restoration method is proposed for more accurate content/texture matching between the reference and target images, and a texture transfer/reconstruction network is employed to map the transferred features to the high-quality image. Experimental results tested on three benchmark datasets demonstrate the effectiveness of our model as compared with other state-of-the-art multi-degraded IR methods. Our code and dataset are available at \u0000<uri>https://vinelab.jp/refmdir/</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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142170","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}

引用次数: 0

Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection 为弱监督视频异常检测学习提示增强型上下文特征

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451935

Yujiang Pu;Xiaoyu Wu;Lulu Yang;Shengjin Wang

{"title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","authors":"Yujiang Pu;Xiaoyu Wu;Lulu Yang;Shengjin Wang","doi":"10.1109/TIP.2024.3451935","DOIUrl":"10.1109/TIP.2024.3451935","url":null,"abstract":"Weakly supervised video anomaly detection aims to locate abnormal activities in untrimmed videos without the need for frame-level supervision. Prior work has utilized graph convolution networks or self-attention mechanisms alongside multiple instance learning (MIL)-based classification loss to model temporal relations and learn discriminative features. However, these approaches are limited in two aspects: 1) Multi-branch parallel architectures, while capturing multi-scale temporal dependencies, inevitably lead to increased parameter and computational costs. 2) The binarized MIL constraint only ensures the interclass separability while neglecting the fine-grained discriminability within anomalous classes. To this end, we introduce a novel WS-VAD framework that focuses on efficient temporal modeling and anomaly innerclass discriminability. We first construct a Temporal Context Aggregation (TCA) module that simultaneously captures local-global dependencies by reusing an attention matrix along with adaptive context fusion. In addition, we propose a Prompt-Enhanced Learning (PEL) module that incorporates semantic priors using knowledge-based prompts to boost the discrimination of visual features while ensuring separability across anomaly subclasses. The proposed components have been validated through extensive experiments, which demonstrate superior performance on three challenging datasets, UCF-Crime, XD-Violence and ShanghaiTech, with fewer parameters and reduced computational effort. Notably, our method can significantly improve the detection accuracy for certain anomaly subclasses and reduced the false alarm rate. Our code is available at: \u0000<uri>https://github.com/yujiangpu20/PEL4VAD</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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142167","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}

引用次数: 0

Structural Relation Modeling of 3D Point Clouds 三维点云的结构关系建模

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451940

Yu Zheng;Jiwen Lu;Yueqi Duan;Jie Zhou

{"title":"Structural Relation Modeling of 3D Point Clouds","authors":"Yu Zheng;Jiwen Lu;Yueqi Duan;Jie Zhou","doi":"10.1109/TIP.2024.3451940","DOIUrl":"10.1109/TIP.2024.3451940","url":null,"abstract":"In this paper, we propose an effective plug-and-play module called structural relation network (SRN) to model structural dependencies in 3D point clouds for feature representation. Existing network architectures such as PointNet++ and RS-CNN capture local structures individually and ignore the inner interactions between different sub-clouds. Motivated by the fact that structural relation modeling plays critical roles for humans to understand 3D objects, our SRN exploits local information by modeling structural relations in 3D spaces. For a given sub-cloud of point sets, SRN firstly extracts its geometrical and locational relations with the other sub-clouds and maps them into the embedding space, then aggregates both relational features with the other sub-clouds. As the variation of semantics embedded in different sub-clouds is ignored by SRN, we further extend SRN to enable dynamic message passing between different sub-clouds. We propose a graph-based structural relation network (GSRN) where sub-clouds and their pairwise relations are modeled as nodes and edges respectively, so that the node features are updated by the messages along the edges. Since the node features might not be well preserved when acquiring the global representation, we propose a Combined Entropy Readout (CER) function to adaptively aggregate them into the holistic representation, so that GSRN simultaneously models the local-local and local-global region-wise interaction. The proposed SRN and GSRN modules are simple, interpretable, and do not require any additional supervision signals, which can be easily equipped with the existing networks. Experimental results on the benchmark datasets (ScanObjectNN, ModelNet40, ShapeNet Part, S3DIS, ScanNet and SUN-RGBD) indicate promising boosts on the tasks of 3D point cloud classification, segmentation and object detection.","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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142172","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}

引用次数: 0

Contrastive Open-set Active Learning based Sample Selection for Image Classification. 基于对比开放集主动学习的图像分类样本选择。

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451928

Zizheng Yan, Delian Ruan, Yushuang Wu, Junshi Huang, Zhenhua Chai, Xiaoguang Han, Shuguang Cui, Guanbin Li

{"title":"Contrastive Open-set Active Learning based Sample Selection for Image Classification.","authors":"Zizheng Yan, Delian Ruan, Yushuang Wu, Junshi Huang, Zhenhua Chai, Xiaoguang Han, Shuguang Cui, Guanbin Li","doi":"10.1109/TIP.2024.3451928","DOIUrl":"https://doi.org/10.1109/TIP.2024.3451928","url":null,"abstract":"In this paper, we address a complex but practical scenario in Active Learning (AL) known as open-set AL, where the unlabeled data consists of both in-distribution (ID) and out-of-distribution (OOD) samples. Standard AL methods will fail in this scenario as OOD samples are highly likely to be regarded as uncertain samples, leading to their selection and wasting of the budget. Existing methods focus on selecting the highly likely ID samples, which tend to be easy and less informative. To this end, we introduce two criteria, namely contrastive confidence and historical divergence, which measure the possibility of being ID and the hardness of a sample, respectively. By balancing the two proposed criteria, highly informative ID samples can be selected as much as possible. Furthermore, unlike previous methods that require additional neural networks to detect the OOD samples, we propose a contrastive clustering framework that endows the classifier with the ability to identify the OOD samples and further enhances the network's representation learning. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on several benchmark 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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142133","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}

引用次数: 0

Balanced Destruction-Reconstruction Dynamics for Memory-Replay Class Incremental Learning 记忆重放类增量学习的平衡破坏-重建动力学

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society Pub Date : 2024-09-05 DOI: 10.1109/TIP.2024.3451932

Yuhang Zhou;Jiangchao Yao;Feng Hong;Ya Zhang;Yanfeng Wang

{"title":"Balanced Destruction-Reconstruction Dynamics for Memory-Replay Class Incremental Learning","authors":"Yuhang Zhou;Jiangchao Yao;Feng Hong;Ya Zhang;Yanfeng Wang","doi":"10.1109/TIP.2024.3451932","DOIUrl":"10.1109/TIP.2024.3451932","url":null,"abstract":"Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e., catastrophic forgetting, the mainstream paradigm is memory-replay CIL, which consolidates old knowledge by replaying a small number of old classes of samples saved in the memory. Despite effectiveness, the inherent destruction-reconstruction dynamics in memory-replay CIL are an intrinsic limitation: if the old knowledge is severely destructed, it will be quite hard to reconstruct the lossless counterpart. Our theoretical analysis shows that the destruction of old knowledge can be effectively alleviated by balancing the contribution of samples from the current phase and those saved in the memory. Motivated by this theoretical finding, we propose a novel Balanced Destruction-Reconstruction module (BDR) for memory-replay CIL, which can achieve better knowledge reconstruction by reducing the degree of maximal destruction of old knowledge. Specifically, to achieve a better balance between old knowledge and new classes, the proposed BDR module takes into account two factors: the variance in training status across different classes and the quantity imbalance of samples from the current phase and memory. By dynamically manipulating the gradient during training based on these factors, BDR can effectively alleviate knowledge destruction and improve knowledge reconstruction. Extensive experiments on a range of CIL benchmarks have shown that as a lightweight plug-and-play module, BDR can significantly improve the performance of existing state-of-the-art methods with good generalization. Our code is publicly available here.","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":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142142131","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}

引用次数: 0