bhanML
Bo Han is an Assistant Professor at HKBU CSD and a BAIHO Visiting Scientist at RIKEN AIP. He is heading Trustworthy Machine Learning and Reasoning Group.
HKBU / RIKENHong Kong / Japan
Pinned Repositories
bhanML.github.io
Co-teaching
NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
coteaching_plus
ICML'19: How does Disagreement Help Generalization against Label Corruption?
FasTer
ICML'19: Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
label-noise-papers
An update-to-date list for papers related with label-noise representation learning is here.
Masking
NeurIPS'18: Masking: A New Perspective of Noisy Supervision
Robust-ResNet
IJCAI'19: Towards Robust ResNet: A Small Step but a Giant Leap
SIGUA
ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
.github
wsl-workshop.github.io
Weakly supervised learning workshops
bhanML's Repositories
bhanML/Co-teaching
NeurIPS'18: Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
bhanML/label-noise-papers
An update-to-date list for papers related with label-noise representation learning is here.
bhanML/Masking
NeurIPS'18: Masking: A New Perspective of Noisy Supervision
bhanML/coteaching_plus
ICML'19: How does Disagreement Help Generalization against Label Corruption?
bhanML/SIGUA
ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
bhanML/bhanML.github.io
bhanML/Robust-ResNet
IJCAI'19: Towards Robust ResNet: A Small Step but a Giant Leap
bhanML/FasTer
ICML'19: Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
bhanML/Friendly-Adversarial-Training
ICML'20: Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
bhanML/Papers-of-Robust-ML
Related papers for robust machine learning
bhanML/T-Revision
NeurIPS'19: Are Anchor Points Really Indispensable in Label-Noise Learning?
bhanML/vild_code
ICML'20: Variational Imitation Learning with Diverse-quality Demonstrations