- ArcFace Loss
- Triplet Loss
- ResNet-50
- Replace
_C.DATA.ROOT
and_C.OUTPUT
inconfigs/default.py
with your owndata path
andoutput path
, respectively. - Run
train.sh
If you use our code in your research or wish to refer to the baseline results, please use the following BibTeX entry.
@InProceedings{CVPR2019IANet
author = {Hou, Ruibing and Ma, Bingpeng and Chang, Hong and Gu, Xinqian and Shan, Shiguang and Chen, Xilin},
title = {Interaction-And-Aggregation Network for Person Re-Identification},
booktitle = {CVPR},
year = {2019}
}