Simi-Supervised Recognition Challenge-FGVC7 is a challenging fine-grained recognition competition. One of the difficulties of this competition is how to use unlabeled data. We adopted pseudo-tag data mining to increase the amount of training data. The other one is how to identify similar birds with a very small difference, especially those have a relatively tiny main-body in examples. We combined generic image recognition and fine-grained image recognition method to solve the problem. All generic image recognition models were training using PaddleClas . Using the combination of two different ways of deep recognition models, we finally won the third place in the competition.
@article{arxiv.2006.10702,
title = {Semi-Supervised Recognition under a Noisy and Fine-grained Dataset},
author = {Cheng Cui and Zhi Ye and Yangxi Li and Xinjian Li and Min Yang and Kai Wei and Bing Dai and Yanmei Zhao and Zhongji Liu and Rong Pang},
journal= {arXiv preprint arXiv:2006.10702},
year = {2020}
}