$ε$ -Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Neural Information Processing Systems (NeurIPS), 2025

4 August 2025

Papers citing "$ε$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise"

3 / 3 papers shown

Title
Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labels Jeremiah Birrell Reza Ebrahimi NoLa 80 0 0 08 Aug 2025
Box-Constrained Softmax Function and Its Application for Post-Hoc Calibration Kyohei Atarashi S. Oyama Hiromi Arai H. Kashima 173 0 0 12 Jun 2025
Combating noisy labels by agreement: A joint training method with co-regularizationComputer Vision and Pattern Recognition (CVPR), 2020 Jianguo Huang Lei Feng Xiangyu Chen Bo An NoLa 719 596 0 05 Mar 2020