Newbeeer / Max-MIG
Code for ICLR 2019 Paper, "MAX-MIG: AN INFORMATION THEORETIC APPROACH FOR JOINT LEARNING FROM CROWDS"
☆25Updated last year
Alternatives and similar repositories for Max-MIG:
Users that are interested in Max-MIG are comparing it to the libraries listed below
- Gradients as Features for Deep Representation Learning☆43Updated 5 years ago
- Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in fu…☆53Updated 3 years ago
- ☆14Updated 5 years ago
- ☆50Updated 2 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 3 years ago
- ☆64Updated 4 years ago
- Regularized Learning under label shifts☆18Updated 5 years ago
- Code for the paper: On Symmetric Losses for Learning from Corrupted Labels☆19Updated 5 years ago
- Official code for "In Search of Robust Measures of Generalization" (NeurIPS 2020)☆28Updated 4 years ago
- Tensorflow implementation of "Meta Dropout: Learning to Perturb Latent Features for Generalization" (ICLR 2020)☆27Updated 4 years ago
- Example implementation for the paper: (ICLR Oral) Learning Robust Representations by Projecting Superficial Statistics Out☆27Updated 3 years ago
- Tensorflow implementation of Invariant Rationalization☆49Updated 2 years ago
- Meta Label Correction for Noisy Label Learning☆85Updated 2 years ago
- Description Code for the paper "Robust Inference via Generative Classifiers for Handling Noisy Labels".☆32Updated 5 years ago
- ☆62Updated 3 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆84Updated 5 years ago
- code for paper Decoupling "when to update" from "how to update" [https://arxiv.org/abs/1706.02613]☆21Updated 7 years ago
- Official Implementation of Unweighted Data Subsampling via Influence Function - AAAI 2020☆65Updated 3 years ago
- Official adversarial mixup resynthesis repository☆35Updated 5 years ago
- Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICML 2020☆22Updated 4 years ago
- ☆30Updated 3 years ago
- ☆34Updated 4 years ago
- ☆27Updated 4 years ago
- ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust☆15Updated 4 years ago
- ☆37Updated 3 years ago
- Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)☆100Updated 3 years ago
- Tensorflow implementation of "Learning to Balance: Bayesian Meta-learning for Imbalanced and Out-of-distribution Tasks" (ICLR 2020 oral)☆100Updated 4 years ago
- Computing various measures and generalization bounds on convolutional and fully connected networks☆35Updated 6 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆71Updated 10 months ago
- Simple data balancing baselines for worst-group-accuracy benchmarks.☆42Updated last year