julilien / LabelRelaxation
Supplementary material and code for "From Label Smoothing to Label Relaxation" as published at AAAI 2021.
☆14Updated last year
Related projects ⓘ
Alternatives and complementary repositories for LabelRelaxation
- ☆21Updated last year
- PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018☆125Updated 5 years ago
- Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxi…☆67Updated 3 years ago
- Official Implementation of Unweighted Data Subsampling via Influence Function - AAAI 2020☆65Updated 3 years ago
- ICLR 2021, "Learning with feature-dependent label noise: a progressive approach"☆42Updated 2 years ago
- [ICLR 2021] Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization☆40Updated 3 years ago
- ☆30Updated 3 years ago
- Learning with Instance-Dependent Label Noise: A Sample Sieve Approach (ICLR2021)☆34Updated 3 years ago
- Official implementation of Auxiliary Learning by Implicit Differentiation [ICLR 2021]☆84Updated 3 months 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
- A new code framework that uses pytorch to implement meta-learning, and takes Meta-Weight-Net as an example.☆56Updated 3 years ago
- [ICLR 2022] "Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity" by Shiwei Liu,…☆27Updated 2 years ago
- [ICML2020] "Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training" by Xuxi Chen, Wuyang Chen, Tianlong Chen, Ye Yuan, Chen Gon…☆67Updated 2 years ago
- Official Pytorch Implementation for CVPR'20 paper: Deep Semantic Clustering by Partition Confidence Maximisation☆56Updated 4 years ago
- AAAI 2021: Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise☆35Updated 3 years ago
- ICML'20: SIGUA: Forgetting May Make Learning with Noisy Labels More Robust☆13Updated 3 years ago
- We propose a theoretically motivated method, Adversarial Training with informative Outlier Mining (ATOM), which improves the robustness o…☆56Updated 2 years ago
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated last year
- ☆31Updated 3 years ago
- Code for the article "Confidence Scores Make Instance-dependent Label-noise Learning Possible", ICML'21☆9Updated 3 months ago
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆53Updated 2 years ago
- Gradients as Features for Deep Representation Learning☆42Updated 4 years ago
- Codebase for "Online Continual Learning with Maximally Interfered Retrieval"☆99Updated last year
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆49Updated 3 years ago
- ☆27Updated 3 years ago
- NeurIPS 2020, "A Topological Filter for Learning with Label Noise".☆29Updated 2 years ago
- The official code for the publication: "The Close Relationship Between Contrastive Learning and Meta-Learning".☆20Updated 2 years ago
- infinite mixture prototypes for few-shot learning☆50Updated 2 years ago
- code for paper Decoupling "when to update" from "how to update" [https://arxiv.org/abs/1706.02613]☆21Updated 7 years ago
- Pytorch implementation of risk estimators for unbiased and non-negative positive-unlabeled learning☆87Updated 3 months ago