jfc43 / self-training-ensembles
Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.
☆14Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for self-training-ensembles
- [NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?☆59Updated 2 years ago
- Visual Representation Learning Benchmark for Self-Supervised Models☆35Updated 7 months ago
- Evaluation of semi-supervised learning on challenging datasets☆35Updated 2 years ago
- Pytorch Code for "A Broad Study on the Transferability of Visual Representations with Contrastive Learning" (ICCV 2021)☆36Updated 2 years ago
- Latent Discriminant deterministic Uncertainty [ECCV2022]☆39Updated 2 years ago
- ☆21Updated last year
- The official code for the NeurIPS 2021 paper Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels (https://arxiv.org…☆21Updated 2 years ago
- The official PyTorch Implementation of the Paper "Adversarial Visual Robustness by Causal Intervention"☆18Updated 3 years ago
- Robustness via Cross-Domain Ensembles, ICCV 2021 [Oral]☆38Updated 3 years ago
- Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization☆83Updated 2 years ago
- Code Release for Learning to Adapt to Evolving Domains☆30Updated 3 years ago
- [ICLR 2021] Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization☆40Updated 3 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- ☆12Updated 2 years ago
- This is a public repository for:☆38Updated 3 years ago
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆53Updated 2 years ago
- [ECCV2022] The PyTorch implementation of paper "Equivariance and Invariance Inductive Bias for Learning from Insufficient Data"☆18Updated 2 years ago
- Code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning", Ren et al., NeurIPS'20☆25Updated 3 years ago
- HIVE: Evaluating the Human Interpretability of Visual Explanations (ECCV 2022)☆19Updated last year
- Test-Time Adaptation via Conjugate Pseudo-Labels☆38Updated last year
- PyTorch implementation of Weighted Batch-Normalization layers☆37Updated 4 years ago
- [ICML'21] Estimate the accuracy of the classifier in various environments through self-supervision☆27Updated 3 years ago
- ☆84Updated 2 years ago
- ICLR 2022 (Spolight): Continual Learning With Filter Atom Swapping☆14Updated last year
- This code accompanies the paper "Parameter-free Online Test-time Adaptation".☆66Updated 2 years ago
- [NeurIPS 2020, Spotlight] Improved Schemes for Episodic Memory-based Lifelong Learning☆18Updated 3 years ago
- Robust Optimal Transport code☆40Updated 2 years ago
- Code and results accompanying our paper titled Leveraging Unlabeled Data to Predict Out-of-Distribution Performance at ICLR 2022☆10Updated last year
- The Official Implementation of the ICCV-2021 Paper: Semantically Coherent Out-of-Distribution Detection.☆69Updated 2 years ago
- ☆44Updated 3 years ago