andrijazz / ash
Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection
☆49Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for ash
- This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguo…☆38Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆45Updated 4 months ago
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆53Updated last year
- Code for the ICCV 2023 paper "Benchmarking Low-Shot Robustness to Natural Distribution Shifts"☆11Updated 10 months ago
- Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation☆43Updated last year
- Create generated datasets and train robust classifiers☆35Updated last year
- ImageNetV2 Pytorch Dataset☆37Updated last year
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆29Updated 3 months ago
- ☆41Updated last year
- ☆30Updated 9 months ago
- ☆25Updated 8 months ago
- Official Code Release for "Diagnosing and Rectifying Vision Models using Language" (ICLR 2023)☆32Updated last year
- Augmenting with Language-guided Image Augmentation (ALIA)☆63Updated last year
- Code release for "Semi-supervised learning made simple with self-supervised clustering"☆54Updated last year
- ☆34Updated 2 years ago
- ☆29Updated last year
- LISA for ICML 2022☆47Updated last year
- Github code for the paper Maximum Class Separation as Inductive Bias in One Matrix. Arxiv link: https://arxiv.org/abs/2206.08704☆27Updated last year
- Code for a research paper "Part-Based Models Improve Adversarial Robustness" (ICLR 2023)☆22Updated last year
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆20Updated 9 months ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated last year
- Switch EMA: A Free Lunch for Better Flatness and Sharpness☆24Updated 9 months ago
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"☆24Updated last year
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated last year
- source code for NeurIPS'23 paper "Dream the Impossible: Outlier Imagination with Diffusion Models"☆62Updated 3 weeks ago
- Code for ECCV 2022 paper "DICE: Leveraging Sparsification for Out-of-Distribution Detection"☆39Updated 2 years ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆44Updated 5 months ago
- ☆15Updated 5 months ago
- LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections (NeurIPS 2023)☆25Updated 10 months ago
- Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]☆35Updated 2 months ago