Oct 2026
RECE Loss: A Reward-Enhanced Cross Entropy Loss Function for Learning with Noisy Labels
Robust loss functions to support adaptation to noisy labels are developed by improving the cross-entropy loss function, which is effective with clean data but lacks robustness with noisy labels.
Thi Thu Huong Nguyen, Duy Tung Nguyen, T. Nguyen et al.
· Neural computing & applicati... · 0 citations