English

Semi-Supervised Recognition under a Noisy and Fine-grained Dataset

Computer Vision and Pattern Recognition 2020-06-19 v1

Abstract

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.

Keywords

Cite

@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}
}

Comments

5 pages, 3 figures, 3 tables

R2 v1 2026-06-23T16:26:36.142Z