Bo Han's Projects
NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
ICML'19: How does Disagreement Help Generalization against Label Corruption?
ICML'19: Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
ICML'20: Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
An update-to-date list for papers related with label-noise representation learning is here.
NeurIPS'18: Masking: A New Perspective of Noisy Supervision
Related papers for robust machine learning
IJCAI'19: Towards Robust ResNet: A Small Step but a Giant Leap
ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
NeurIPS'19: Are Anchor Points Really Indispensable in Label-Noise Learning?
ICML'20: Variational Imitation Learning with Diverse-quality Demonstrations