A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification

Jong-Chyi Su, Zezhou Cheng, Subhransu Maji; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 12966-12975

Abstract


We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes. Our benchmark consists of two fine-grained classification datasets obtained by sampling classes from the Aves and Fungi taxonomy. We find that recently proposed SSL methods provide significant benefits, and can effectively use out-of-class data to improve performance when deep networks are trained from scratch. Yet their performance pales in comparison to a transfer learning baseline, an alternative approach for learning from a few examples. Furthermore, in the transfer setting, while existing SSL methods provide improvements, the presence of out-of-class is often detrimental. In this setting, standard fine-tuning followed by distillation-based self-training is the most robust. Our work suggests that semi-supervised learning with experts on realistic datasets may require different strategies than those currently prevalent in the literature.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2021_CVPR, author = {Su, Jong-Chyi and Cheng, Zezhou and Maji, Subhransu}, title = {A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {12966-12975} }