Laser & Optoelectronics Progress, Volume. 58, Issue 20, 2010019(2021)
Double-Resolution Attention Network for Person Re-Identification
Fig. 1. Network structure
Fig. 2. Network structure of the channel attention mechanism in this paper
Fig. 3. Features extracted from different resolution feature maps. (a) Original input image; (b)(c) feature maps extracted without downsampling; (d)(e) feature maps extracted after downsampling
Fig. 4. Channeled attention mechanisms focus on different detailed features. (a) Original input image; (b)--(e) heat maps
Fig. 5. Accuracy variation of the algorithm as the epoch increases on different datasets. (a) mAP result analysis; (b) Rank-1 result analysis
|
|
|
|
Get Citation
Copy Citation Text
Jiajie Hu, Chungeng Li, Jubai An, Chao Huang. Double-Resolution Attention Network for Person Re-Identification[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2010019
Category: Image Processing
Received: Dec. 28, 2020
Accepted: Jan. 20, 2021
Published Online: Oct. 13, 2021
The Author Email: Li Chungeng (li_chungeng@dlmu.edu.cn)