Well-Classified Examples Are Underestimated in Classification with Deep Neural Networks


  • Guangxiang Zhao Peking University
  • Wenkai Yang Peking University
  • Xuancheng Ren Peking University
  • Lei Li Peking University
  • Yunfang Wu Peking University
  • Xu Sun Peking University




Machine Learning (ML), Computer Vision (CV)


The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundary. For instance, when training with cross-entropy loss, examples with higher likelihoods (i.e., well-classified examples) contribute smaller gradients in back-propagation. However, we theoretically show that this common practice hinders representation learning, energy optimization, and margin growth. To counteract this deficiency, we propose to reward well-classified examples with additive bonuses to revive their contribution to the learning process. This counterexample theoretically addresses these three issues. We empirically support this claim by directly verifying the theoretical results or significant performance improvement with our counterexample on diverse tasks, including image classification, graph classification, and machine translation. Furthermore, this paper shows that we can deal with complex scenarios, such as imbalanced classification, OOD detection, and applications under adversarial attacks because our idea can solve these three issues. Code is available at https://github.com/lancopku/well-classified-examples-are-underestimated.




How to Cite

Zhao, G., Yang, W., Ren, X., Li, L., Wu, Y., & Sun, X. (2022). Well-Classified Examples Are Underestimated in Classification with Deep Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 9180-9189. https://doi.org/10.1609/aaai.v36i8.20904



AAAI Technical Track on Machine Learning III