JonathanCrabbe / CARs
This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human concepts. For more details, please read our NeurIPS 2022 paper: 'Concept Activation Regions: a Generalized Framework for Concept-Based Explanations.
☆11Updated 2 years ago
Alternatives and similar repositories for CARs:
Users that are interested in CARs are comparing it to the libraries listed below
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated last year
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆23Updated 3 years ago
- ☆44Updated 2 years ago
- ☆26Updated 11 months ago
- ☆30Updated 3 years ago
- Repository for the NeurIPS 2023 paper "Beyond Confidence: Reliable Models Should Also Consider Atypicality"☆12Updated 9 months ago
- Code for the ICCV 2023 paper "Benchmarking Low-Shot Robustness to Natural Distribution Shifts"☆11Updated last year
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- ☆12Updated last year
- LISA for ICML 2022☆47Updated last year
- ☆15Updated 7 months ago
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆34Updated last year
- Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.☆14Updated 8 months ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆65Updated last year
- [NeurIPS'22] Official Repository for Characterizing Datapoints via Second-Split Forgetting☆14Updated last year
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated 2 years ago
- ☆21Updated 2 years ago
- Learning Representations that Support Robust Transfer of Predictors☆20Updated 3 years ago
- ☆25Updated 2 years ago
- SpuCo is a Python package developed to further research to address spurious correlations.☆24Updated 3 weeks ago
- Discover and Cure: Concept-aware Mitigation of Spurious Correlation (ICML 2023)☆40Updated 10 months ago
- ☆24Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆30Updated last year
- The code for our NeurIPS 2021 paper "Kernelized Heterogeneous Risk Minimization".☆12Updated 3 years ago
- ☆25Updated last year
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated last year
- Quantile risk minimization☆24Updated 6 months ago
- Post-processing for fair classification☆13Updated 3 weeks ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆50Updated 3 years ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆47Updated 7 months ago