gohsyi / PeerLoss
Learning with Noisy Labels by adopting a peer prediction loss function.
☆36Updated 4 years ago
Related projects: ⓘ
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR2021)☆34Updated 3 years ago
- ICML'19: How does Disagreement Help Generalization against Label Corruption?☆21Updated 5 years ago
- MoPro: Webly Supervised Learning☆87Updated 3 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆82Updated 5 years ago
- NeurIPS'18: Masking: A New Perspective of Noisy Supervision☆54Updated 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
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR2021)☆36Updated 3 years ago
- [NeurIPS 2017] [ICML 2019] Code for complementary-label learning☆44Updated 7 months ago
- Chainer Implementation of TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning☆56Updated 4 years ago
- Code for ICLR 2019 Paper, "MAX-MIG: AN INFORMATION THEORETIC APPROACH FOR JOINT LEARNING FROM CROWDS"☆25Updated last year
- Example implementation for the paper: (ICLR Oral) Learning Robust Representations by Projecting Superficial Statistics Out☆27Updated 3 years ago
- Meta Label Correction for Noisy Label Learning☆79Updated last year
- Code release for Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning (NeurIPS 2019)☆24Updated 2 years ago
- Code for 'Joint Optimization Framework for Learning with Noisy Labels'☆38Updated 6 years ago
- [ICML 2021] “ Self-Damaging Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang☆63Updated 2 years ago
- Code release for Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML2019)☆80Updated 5 years ago
- Description Code for the paper "Robust Inference via Generative Classifiers for Handling Noisy Labels".☆33Updated 5 years ago
- Code for our paper "Auxiliary Task Reweighting for Minimum-data Learning" (NeurIPS 2020)☆17Updated 3 years ago
- Feature-Critic Networks for Heterogeneous Domain Generalisation☆50Updated 5 years ago
- Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21☆9Updated 3 weeks ago
- infinite mixture prototypes for few-shot learning☆49Updated last year
- PyTorch implementation of the paper "SuperLoss: A Generic Loss for Robust Curriculum Learning" in NIPS 2020.☆30Updated 3 years ago
- Self-supervised Label Augmentation via Input Transformations (ICML 2020)☆103Updated 3 years ago
- NeurIPS 2019 : Learning to Propagate for Graph Meta-Learning☆36Updated 4 years ago
- "Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness" (NeurIPS 2020).☆50Updated 3 years ago
- Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"☆117Updated last year
- pytorch maml with Multi-GPUs, fast and simplest implementation☆13Updated 3 years ago
- Implementation "Adapting Auxiliary Losses Using Gradient Similarity" article☆32Updated 5 years ago
- Meta-Learning based Noise-Tolerant Training☆122Updated 4 years ago
- Codes for UODTN; Open domain recognition; CVPR19☆44Updated 3 years ago