Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

Understand

Prior works have found it beneficial to combine provably noise-robust loss functions e.g., mean absolute error (MAE) with standard categorical loss function e.g.

• cross entropy (CE) to improve their learnability.
• Here, we propose to use Jensen-Shannon divergence as a noise-robust loss function and show that it interestingly interpolate between CE and MAE with a controllable mixing parameter.
• Furthermore, we make a crucial observation that CE exhibit lower consistency around noisy data points.