yaodongyu / ProjNorm
Predicting Out-of-Distribution Error with the Projection Norm
☆17Updated 2 years ago
Related projects: ⓘ
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 2 years ago
- LISA for ICML 2022☆47Updated last year
- ☆21Updated 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
- ☆11Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- Code for CVPR2021 paper: MOOD: Multi-level Out-of-distribution Detection☆38Updated last year
- Code relative to "Adversarial robustness against multiple and single $l_p$-threat models via quick fine-tuning of robust classifiers"☆15Updated last year
- On the Importance of Gradients for Detecting Distributional Shifts in the Wild☆52Updated 2 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆34Updated last year
- Invariant-feature Subspace Recovery (ISR)☆22Updated last year
- ☆31Updated 7 months ago
- ☆27Updated 3 years ago
- Code Release for Learning to Adapt to Evolving Domains☆30Updated 3 years ago
- Codebase for the paper titled "Continual learning with local module selection"☆26Updated 2 years ago
- ☆17Updated 2 years ago
- ☆16Updated 2 years ago
- PyTorch implementation of "Online Hyperparameter Optimization for Class-Incremental Learning" (AAAI 2023 Oral)☆17Updated last year
- Code for Model Agnostic Sample Reweighting for Out-of-Distribution Learning☆40Updated last year
- Code for "BayesAdapter: Being Bayesian, Inexpensively and Robustly, via Bayeisan Fine-tuning"☆30Updated last month
- ☆47Updated last year
- [ICLR 2021] Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization☆40Updated 3 years ago
- NeurIPS 2021, Code for Measuring Generalization with Optimal Transport☆28Updated 2 years ago
- Training vision models with full-batch gradient descent and regularization☆37Updated last year
- ☆24Updated last year
- ☆18Updated 2 years ago
- Do input gradients highlight discriminative features? [NeurIPS 2021] (https://arxiv.org/abs/2102.12781)☆13Updated last year
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated last year
- ☆57Updated last year
- [NeurIPS'22] Official Repository for Characterizing Datapoints via Second-Split Forgetting☆14Updated last year