Seeing Like a Human: Asynchronous Learning With Dynamic Progressive Refinement for Person Re-Identification

Zhang, Quan; Lai, Jianhuang; Feng, Zhanxiang; Xie, Xiaohua

doi:10.1109/tip.2021.3128330

Cited by 31 publications

(6 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The progressive refinement network has been explored in many supervised tasks, such as supervised image matting [64], person re-identification [65], and temporal action detection [66], motivated by the thought of progressive learning [67], [68]. For example, PBRNet [66] is equipped with three cascaded detection modules for progressive localizing action boundaries more and more precisely.…”

Section: B Progressive Refinementmentioning

confidence: 99%

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

Huang¹,

Xu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, anomaly detection and localization in multimedia data have received significant attention among the machine learning community. In real-world applications such as medical diagnosis and industrial defect detection, anomalies only present in a fraction of the images. To extend the reconstructionbased anomaly detection architecture to the localized anomalies, we propose a self-supervised learning approach through random masking and then restoring, named Self-Supervised Masking (SSM) for unsupervised anomaly detection and localization. SSM not only enhances the training of the inpainting network but also leads to great improvement in the efficiency of mask prediction at inference. Through random masking, each image is augmented into a diverse set of training triplets, thus enabling the autoencoder to learn to reconstruct with masks of various sizes and shapes during training. To improve the efficiency and effectiveness of anomaly detection and localization at inference, we propose a novel progressive mask refinement approach that progressively uncovers the normal regions and finally locates the anomalous regions. The proposed SSM method outperforms several state-of-the-arts for both anomaly detection and anomaly localization, achieving 98.3% AUC on Retinal-OCT and 93.9% AUC on MVTec AD, respectively.

show abstract

Section: B Progressive Refinementmentioning

confidence: 99%

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

Huang¹,

Xu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Thus, enriching the input features is necessary for overcoming the defects of the widely used single-scale spatial patch (SP) [30,[32][33][34][35][37][38][39][40] and reducing the learning difficulty. This motivates us to propose a novel shallow feature by taking inspiration from the human visual perception mechanism that processes local and global information in different functional areas of the brain [49,50].…”

Section: Shallow Feature Extractionmentioning

confidence: 99%

“…Due to the existence of diversified characteristics in real changed regions, the singlescale image patch feature, as shown in Figure 3a, which is commonly utilized as the basic processing unit in deep learning-based CD approaches, fails to precisely and flexibly describe diverse characteristics of changed regions and differentiate pseudochanges. Motivated by seeking a new processing unit that can overcome the disadvantages of the single-scale patch, the ESP feature is constructed to better correlate with the human perception mechanism [49,50]. As shown in Figure 3b, the generation of the ESP feature is accomplished by carrying out the following steps.…”

Section: Esp Generationmentioning

confidence: 99%

Hybrid Variability Aware Network (HVANet): A Self-Supervised Deep Framework for Label-Free SAR Image Change Detection

Wang

Liu

2022

Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) image change detection (CD) aims to automatically recognize changes over the same geographic region by comparing prechange and postchange SAR images. However, the detection performance is usually subject to several restrictions and problems, including the absence of labeled SAR samples, inherent multiplicative speckle noise, and class imbalance. More importantly, for bitemporal SAR images, changed regions tend to present highly variable sizes, irregular shapes, and different textures, typically referred to as hybrid variabilities, further bringing great difficulties to CD. In this paper, we argue that these internal hybrid variabilities can also be used for learning stronger feature representation, and we propose a hybrid variability aware network (HVANet) for completely unsupervised label-free SAR image CD by taking inspiration from recent developments in deep self-supervised learning. First, since different changed regions may exhibit hybrid variabilities, it is necessary to enrich distinguishable information within the input features. To this end, in shallow feature extraction, we generalize the traditional spatial patch (SP) feature to allow for each pixel in bitemporal images to be represented at diverse scales and resolutions, called extended SP (ESP). Second, with the carefully customized ESP features, HVANet performs local spatial structure information extraction and multiscale–multiresolution (MS-MR) information encoding simultaneously through a local spatial stream and a scale-resolution stream, respectively. Intrinsically, HVANet projects the ESP features into a new high-level feature space, where the change identification becomes easier. Third, to train the framework effectively, a self-supervision layer is attached to the top of the HVANet to enable the two-stream feature learning and recognition of changed pixels in the corresponding feature space, in a self-supervised manner. Experimental results on three low/medium-resolution SAR datasets demonstrate the effectiveness and superiority of the proposed framework in unsupervised SAR CD tasks.

show abstract

“…The red box and the red bidirectional arrow indicates to learn the interaction using self-attention and the cross-attention, respectively. development of deep learning, deep feature learning methods [2], [11]- [14] have significantly improved the performance of the person ReID task. However, most of them usually adopt the Convolutional Neural Networks (CNNs) as a backbone to extract deep features, where the long-range dependencies are neglected.…”

Section: Introductionmentioning

confidence: 99%

Completed Part Transformer for Person Re-Identification

Zhang

Liu

et al. 2024

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Recently, part information of pedestrian images has been demonstrated to be effective for person re-identification (ReID), but the part interaction is ignored when using Transformer to learn long-range dependencies. In this paper, we propose a novel transformer network named Completed Part Transformer (CPT) for person ReID, where we design the part transformer layer to learn the completed part interaction. The part transformer layer includes the intra-part layer and the part-global layer, where they consider long-range dependencies from the aspects of the intra-part interaction and the partglobal interaction, simultaneously. Furthermore, in order to overcome the limitation of fixed number of the patch tokens in the transformer layer, we propose the Adaptive Refined Tokens (ART) module to focus on learning the interaction between the informative patch tokens in the pedestrian image, which improves the discrimination of the pedestrian representation. Extensive experimental results on four person ReID datasets, i.e., MSMT17, Market1501, DukeMTMC-reID and CUHK03, demonstrate that the proposed method achieves a new stateof-the-art performance, e.g., it achieves 68.0% mAP and 84.6% Rank-1 accuracy on MSMT17.

show abstract

Seeing Like a Human: Asynchronous Learning With Dynamic Progressive Refinement for Person Re-Identification

Cited by 31 publications

References 69 publications

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

Self-Supervised Masking for Unsupervised Anomaly Detection and Localization

Hybrid Variability Aware Network (HVANet): A Self-Supervised Deep Framework for Label-Free SAR Image Change Detection

Completed Part Transformer for Person Re-Identification

Contact Info

Product

Resources

About