Mancs: A Multi-Task Attentional Network with Curriculum Sampling for Person Re-Identification
Abstract
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation. Technically, we contribute a novel fully attentional block which is deeply supervised and can be plugged into any CNN, and a novel curriculum sampling method which is effective for training ranking losses. The learning tasks are integrated into a unified framework and jointly optimized. Experiments have been carried out on Market1501, CUHK03 and DukeMTMC. All the results show that Mancs can significantly outperform the previous state-of-the-arts. In addition, the effectiveness of the newly proposed ideas has been confirmed by extensive ablation studies.
Cite
Text
Wang et al. "Mancs: A Multi-Task Attentional Network with Curriculum Sampling for Person Re-Identification." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01225-0_23Markdown
[Wang et al. "Mancs: A Multi-Task Attentional Network with Curriculum Sampling for Person Re-Identification." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/wang2018eccv-mancs/) doi:10.1007/978-3-030-01225-0_23BibTeX
@inproceedings{wang2018eccv-mancs,
title = {{Mancs: A Multi-Task Attentional Network with Curriculum Sampling for Person Re-Identification}},
author = {Wang, Cheng and Zhang, Qian and Huang, Chang and Liu, Wenyu and Wang, Xinggang},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01225-0_23},
url = {https://mlanthology.org/eccv/2018/wang2018eccv-mancs/}
}