Newbeeer / Max-MIG
Code for ICLR 2019 Paper, "MAX-MIG: AN INFORMATION THEORETIC APPROACH FOR JOINT LEARNING FROM CROWDS"
☆25Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Max-MIG
- 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
- ☆48Updated last year
- Gradients as Features for Deep Representation Learning☆42Updated 4 years ago
- code for paper Decoupling "when to update" from "how to update" [https://arxiv.org/abs/1706.02613]☆21Updated 6 years ago
- ☆21Updated last year
- Tensorflow implementation of "Learning to Balance: Bayesian Meta-learning for Imbalanced and Out-of-distribution Tasks" (ICLR 2020 oral)☆98Updated 3 years ago
- Example implementation for the paper: (ICLR Oral) Learning Robust Representations by Projecting Superficial Statistics Out☆27Updated 3 years ago
- ☆65Updated 4 years ago
- Regularized Learning under label shifts☆18Updated 5 years ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆49Updated 3 years ago
- Description Code for the paper "Robust Inference via Generative Classifiers for Handling Noisy Labels".☆33Updated 5 years ago
- ☆14Updated 5 years ago
- Code for the paper: On Symmetric Losses for Learning from Corrupted Labels☆18Updated 5 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆66Updated 5 months ago
- ☆30Updated 3 years ago
- Official Implementation of Unweighted Data Subsampling via Influence Function - AAAI 2020☆65Updated 3 years ago
- ICML'19: How does Disagreement Help Generalization against Label Corruption?☆21Updated 5 years ago
- Meta Label Correction for Noisy Label Learning☆81Updated 2 years ago
- MoPro: Webly Supervised Learning☆86Updated 3 years ago
- Q. Yao, H. Yang, B. Han, G. Niu, J. Kwok. Searching to Exploit Memorization Effect in Learning from Noisy Labels. ICML 2020☆21Updated 4 years ago
- PyTorch implementation for the paper Classification from Positive, Unlabeled and Biased Negative Data.☆19Updated 11 months ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆83Updated 5 years ago
- Code for paper "Dimensionality-Driven Learning with Noisy Labels" - ICML 2018☆58Updated 4 months ago
- A supplementary code for Editable Neural Networks, an ICLR 2020 submission.☆46Updated 4 years ago
- Tensorflow implementation of Invariant Rationalization☆48Updated last year
- Domain Adaptation as a Problem of Inference on Graphical Models☆29Updated 3 years ago
- ☆27Updated 4 years ago
- Official adversarial mixup resynthesis repository☆35Updated 4 years ago
- An Empirical Study of Invariant Risk Minimization☆28Updated 4 years ago