<ul><li>This paper investigates the robustness of an f-divergence-based class of objective functions, referred to as f-PML, to label noise in supervised classification.</li><li>The study shows that, in the presence of label noise, the f-PML objective functions can be corrected to obtain a neural network that matches the clean dataset.</li><li>An alternative correction approach is proposed to refine the posterior estimation during the test phase for neural networks trained with label noise.</li><li>The paper demonstrates that the f-PML objective functions are robust to symmetric label noise and can achieve competitive performance with refined training strategies.</li></ul>

Robust Classification with Noisy Labels Based on Posterior Maximization

Discover more