Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
This work addresses fine-grained recognition in noisy, semi-supervised settings for computer vision applications, but appears incremental as it combines existing methods.
The authors tackled the Simi-Supervised Recognition Challenge-FGVC7, a fine-grained bird recognition competition with noisy data and limited labeled examples, by combining pseudo-tag data mining with generic and fine-grained image recognition models, achieving third place in the competition.
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.