Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification

Guo-qing, Zhang; Yu, Ge; Dong, Zhicheng; Wang, Hao; Zheng, Yuhui; Chen, Shengyong

doi:10.1109/tip.2021.3120054

Cited by 73 publications

(34 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average CMC rates are summarised as the evaluation results. Besides, the proposed method is compared to several metric learning‐based methods, including RDC, ITML, LMNN, KISSME, MVSLDDL, XQDA, MLAPG, NFST, MCK‐CCA, KEPLER, JLDM, SCML and several deep learning‐based methods, including Improved Deep, SCIR, TCP, IPMLLSL, HRNet [36], SpindleNet, HydraPlus‐Net [37], OSNet [28]. The final evaluation results are displayed in Table 1.…”

Section: Resultsmentioning

confidence: 99%

Distribution probability‐based self‐adaption metric learning for person re‐identification

Ren

Huang

2022

IET Computer Vision

View full text Add to dashboard Cite

Person re-identification addresses the problem of pedestrian image matching in a nonoverlapped surveillance network. Traditional metric learning methods try to learn a fixed pedestrian images matching metric model. However, existing metric learning-based methods have the problem of overfitting the training data. In order to solve this problem, a sample-specific metric learning-based method is proposed. In the perspective of probability distribution, the over-fitting problem is attributed to the problem that the generalisation ability of projection features is weak. Firstly, the proposed method learns a metric subspace, which projects the raw feature to a discriminative subspace. Then, a projection feature selection method is established based on the probability distribution of positive image pairs. According to the proposed method, the probability that the test samples following the training data distribution is closely related to the adaptability. The proposed projection feature selection method selects different projection features for each individual's similarity distance measure. Finally, extensive experiments on four published datasets verify the effectiveness of the proposed metric learning method. It performs favourably against the comparison methods, especially on the rank-1 rate.

show abstract

Section: Resultsmentioning

confidence: 99%

Distribution probability‐based self‐adaption metric learning for person re‐identification

Ren

Huang

2022

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Unlike other SR-based methods, FFSR combines Re-ID loss and foreground attention loss during training and suppresses irrelevant background while restoring pedestrian image resolution. Some other SR models are also widely used in cross-resolution person Re-ID, such as Meta-SR [ 17 ] and VDSR [ 40 ].…”

Section: Related Workmentioning

confidence: 99%

SR-DSFF and FENet-ReID: A Two-Stage Approach for Cross Resolution Person Re-Identification

Zhu

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In real-life scenarios, the accuracy of person re-identification (Re-ID) is subject to the limitation of camera hardware conditions and the change of image resolution caused by factors such as camera focusing errors. People call this problem cross-resolution person Re-ID. In this paper, we improve the recognition accuracy of cross-resolution person Re-ID by enhancing the image enhancement network and feature extraction network. Specifically, we treat cross-resolution person Re-ID as a two-stage task: the first stage is the image enhancement stage, and we propose a Super-Resolution Dual-Stream Feature Fusion sub-network, named SR-DSFF, which contains SR module and DSFF module. The SR-DSFF utilizes the SR module recovers the resolution of the low-resolution (LR) images and then obtains the feature maps of the LR images and super-resolution (SR) images, respectively, through the dual-stream feature fusion with learned weights extracts and fuses feature maps from LR and SR images in the DSFF module. At the end of SR-DSFF, we set a transposed convolution to visualize the feature maps into images. The second stage is the feature acquisition stage. We design a global-local feature extraction network guided by human pose estimation, named FENet-ReID. The FENet-ReID obtains the final features through multistage feature extraction and multiscale feature fusion for the Re-ID task. The two stages complement each other, making the final pedestrian feature representation has the advantage of accurate identification compared with other methods. Experimental results show that our method improves significantly compared with some state-of-the-art methods.

show abstract

“…To address the practical challenge of CRReID, two main categories of methods have been developed: 1) metric learning or dictionary learning based approaches [24]- [26]; and 2) super-resolution (SR) based approaches [3]- [7], [27], [28]. For instance, to overcome the resolution mismatch, Jing et al [24] developed a semi-coupled low-rank dictionary learning method to associate the mapping between the HR and LR images.…”

Section: B Cross-resolution Person Re-id (Crreid)mentioning

confidence: 99%

“…To address the CRReID problem, state-of-the-art (SOTA) methods would employ either methods [3]- [7] with superresolution (SR) modules or methods [8] that learn resolutioninvariant features The former first recovers the missing details of LR queries before performing the re-ID. The basic assumption is that by using the prior knowledge learned from the training data, the missing details of LR images can be recovered or at least be estimated in a way that will benefit the cross-resolution comparison.…”

Section: Introductionmentioning

confidence: 99%

Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification

Lin¹,

Liu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The cross-resolution person re-identification (CR-ReID) problem aims to match low-resolution (LR) query identity images against high resolution (HR) gallery images. It is a challenging and practical problem since the query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras. To address this problem, state-of-the-art (SOTA) solutions either learn the resolutioninvariant representation or adopt super-resolution (SR) module to recover the missing information from the LR query. This paper explores an alternative SR-free paradigm to directly compare HR and LR images via a dynamic metric, which is adaptive to the resolution of a query image. We realize this idea by learning resolution-adaptive representations for crossresolution comparison. Specifically, we propose two resolutionadaptive mechanisms. The first one disentangles the resolutionspecific information into different sub-vectors in the penultimate layer of the deep neural networks, and thus creates a varyinglength representation. To better extract resolution-dependent information, we further propose to learn resolution-adaptive masks for intermediate residual feature blocks. A novel progressive learning strategy is proposed to train those masks properly. These two mechanisms are combined to boost the performance of CRReID. Experimental results show that the proposed method is superior to existing approaches and achieves SOTA performance on multiple CRReID benchmarks.

show abstract

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification

Cited by 73 publications

References 64 publications

Distribution probability‐based self‐adaption metric learning for person re‐identification

Distribution probability‐based self‐adaption metric learning for person re‐identification

SR-DSFF and FENet-ReID: A Two-Stage Approach for Cross Resolution Person Re-Identification

Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification

Contact Info

Product

Resources

About