MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification
Lists
Only you see this
Abstract
Although person re-identification (ReID) has achieved significant improvement recently by enforcing part alignment, it is still a challenging task when it comes to distinguishing visually similar identities or identifying the occluded person. In these scenarios, magnifying details in each part features and selectively fusing them together may provide a feasible solution. In this work, we propose MagnifierNet, a triple-branch network which accurately mines details from whole to parts. Firstly, the holistic salient features are encoded by a global branch. Secondly, to enhance detailed representation for each semantic region, the "Semantic Adversarial Branch" is designed to learn from dynamically generated semantic-occluded samples during training. Meanwhile, we introduce "Semantic Fusion Branch" to filter out irrelevant noises by selectively fusing semantic region information sequentially. To further improve feature diversity, we introduce a novel loss function "Semantic Diversity Loss" to remove redundant overlaps across learned semantic representations. State-of-the-art performance has been achieved on three benchmarks by large margins. Specifically, the mAP score is improved by 6% and 5% on the most challenging CUHK03-L and CUHK03-D benchmarks.
BibTeX
@inproceedings{lan2020magnifiernet,
author = {Yushi Lan and Yuan Liu and Maoqing Tian and Xinchi Zhou and Xuesen Zhang and Shuai Yi and Hongsheng Li},
title = {{MagnifierNet: Towards Semantic Regularization and Fusion for Person Re-identification}},
booktitle = {BMVC},
year = {2020},
url = {https://openreview.net/forum?id=6x2SIR93bod},
}| Mask-Guided Region Attention Network for Person Re-Identification | Lecture Notes in Computer Science · 2020 |
| Attention driven person re-identification | arXiv · 2018 |
| A Mask Based Deep Ranking Neural Network for Person Retrieval | arXiv · 2018 |
| Multi-Scale Body-Part Mask Guided Attention for Person Re-Identification | Workshops @ CVPR · 2019 |
| Integrating Coarse Granularity Part-level Features with Supervised Global-level Features for Person Re-identification | arXiv · 2020 |
| Improving person re-identification by attention and multi-attributes | Journal of Image and Graphics · 2020 |