stanford-futuredata / sinkhorn-label-allocation
Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.
☆53Updated 3 years ago
Alternatives and similar repositories for sinkhorn-label-allocation:
Users that are interested in sinkhorn-label-allocation are comparing it to the libraries listed below
- Example implementation for the paper: (ICLR Oral) Learning Robust Representations by Projecting Superficial Statistics Out☆27Updated 3 years ago
- Description Code for the paper "Robust Inference via Generative Classifiers for Handling Noisy Labels".☆32Updated 5 years ago
- SwAV for CIFAR-10, adapted from https://github.com/facebookresearch/swav☆28Updated 3 years ago
- We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness o…☆57Updated 3 years ago
- Adjust Decision Boundary for Class Imbalanced Learning☆19Updated 4 years ago
- Code for ICML2020 "Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation"☆90Updated 4 years ago
- [ICML 2021] “ Self-Damaging Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang☆63Updated 3 years ago
- Unsupervised Domain Adaptation through Self-Supervision☆79Updated 3 years ago
- ICML'19: How does Disagreement Help Generalization against Label Corruption?☆21Updated 5 years ago
- Official implementation of paper Gradient Matching for Domain Generalization☆119Updated 3 years ago
- Implementation and datasets for Efficient Domain Generalization via Common-Specific Low-Rank Decomposition (https://arxiv.org/abs/2003.12…☆51Updated 4 years ago
- ☆13Updated 3 years ago
- Gradients as Features for Deep Representation Learning☆43Updated 5 years ago
- Code release for Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML2019)☆81Updated 5 years ago
- Code for our ECCV paper -- "Learning to Balance Specificity and Invariance for In and Out of Domain Generalization"☆55Updated 4 years ago
- Code for the paper "Generalizing to Unseen Domains via Adversarial Data Augmentation", NeurIPS 2018☆121Updated 4 years ago
- Official adversarial mixup resynthesis repository☆35Updated 5 years ago
- MoPro: Webly Supervised Learning☆87Updated 4 years ago
- [NeurIPS 2017] [ICML 2019] Code for complementary-label learning☆47Updated last year
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆55Updated 2 years ago
- Code for the paper "Selecting Relevant Features from a Universal Representation for Few-shot Classification"☆41Updated 3 years ago
- Code release for Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation (ICML 2019)☆63Updated 5 years ago
- ☆46Updated 4 years ago
- ICML'19 How does Disagreement Help Generalization against Label Corruption?☆84Updated 5 years ago
- "Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness" (NeurIPS 2020).☆50Updated 4 years ago
- Code for 'Joint Optimization Framework for Learning with Noisy Labels'☆38Updated 6 years ago
- ☆58Updated 3 years ago
- Feature-Critic Networks for Heterogeneous Domain Generalisation☆52Updated 5 years ago
- ☆40Updated 5 years ago
- Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"☆48Updated 2 years ago