Journal article 206 views 72 downloads
Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification
Yuanbo Wu,
Lingqiao Liu 
,
Yang Wang ,
Zheng Zhang ,
Farid Boussaid,
Mohammed Bennamoun ,
Xianghua Xie
,
Yang Wang ,
Zheng Zhang ,
Farid Boussaid,
Mohammed Bennamoun ,
Xianghua Xie
IEEE Transactions on Image Processing, Volume: 32, Pages: 4800 - 4811
Swansea University Authors:
Yuanbo Wu, Xianghua Xie
-
PDF | Accepted Manuscript
Download (761.29KB)
DOI (Published version): 10.1109/tip.2023.3305817
Abstract
Cross-resolution person re-identification (CRReID) is a challenging and practical problem that involves matching low-resolution (LR) query identity images against high-resolution (HR) gallery images. Query images often suffer from resolution degradation due to the different capturing conditions from...
| Published in: | IEEE Transactions on Image Processing |
|---|---|
| ISSN: | 1057-7149 1941-0042 |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2023
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa64124 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
Cross-resolution person re-identification (CRReID) is a challenging and practical problem that involves matching low-resolution (LR) query identity images against high-resolution (HR) gallery images. Query images often suffer from resolution degradation due to the different capturing conditions from real-world cameras. State-of-the-art solutions for CRReID either learn a resolution-invariant representation or adopt a super-resolution (SR) module to recover the missing information from the LR query. In this paper, we propose an alternative SR-free paradigm to directly compare HR and LR images via a dynamic metric that is adaptive to the resolution of a query image. We realize this idea by learning resolution-adaptive representations for cross-resolution comparison. We propose two resolution-adaptive mechanisms to achieve this. The first mechanism encodes the resolution specifics into different subvectors in the penultimate layer of the deep neural network, creating a varying-length 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 outperforms existing approaches and achieves state-of-the-art performance. |
|---|---|
| Keywords: |
Image resolution, Feature extraction ,Measurement,Training, Superresolution, Cameras, Adaptation models |
| College: |
Faculty of Science and Engineering |
| Start Page: |
4800 |
| End Page: |
4811 |