
A simple and effective method, named Learning to Bootstrap (L2B), enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning.


coremsg

learning-to-bootstrap-robust-models-for-combating-label-noise


Learning to Bootstrap Robust Models for Combating Label Noise


title_rewrite


A novel Two-Stream Sample Distillation (TSSD) framework is designed to train a robust network under the supervision of noisy labels by jointly considering the sample structure in feature space and the human prior in loss space.


robust-noisy-label-learning-via-two-stream-sample-distillation


Robust Noisy Label Learning via Two-Stream Sample Distillation



A novel Potential Energy-based Mixture Model (PEMM) that can effectively handle noisy labels by preserving the intrinsic data structure and achieving a co-stable state among class centers.


potential-energy-based-mixture-model-for-robust-learning-from-noisy-labels


Potential Energy-based Mixture Model for Robust Learning from Noisy Labels
