JonathanCrabbe / CARsLinks
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.
☆14Updated 3 years ago
Alternatives and similar repositories for CARs
Users that are interested in CARs are comparing it to the libraries listed below
Sorting:
- Implementation of Concept-level Debugging of Part-Prototype Networks☆12Updated 2 years ago
- (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation☆42Updated last month
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆36Updated 3 years ago
- ☆47Updated 2 years ago
- Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)☆68Updated 2 years ago
- LISA for ICML 2022☆52Updated 2 years ago
- ☆17Updated last year
- ☆111Updated 2 years ago
- ☆44Updated 2 months ago
- Code for the ICCV 2023 paper "Benchmarking Low-Shot Robustness to Natural Distribution Shifts"☆11Updated last year
- [ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization☆53Updated last year
- Repository for our NeurIPS 2022 paper "Concept Embedding Models", our NeurIPS 2023 paper "Learning to Receive Help", and our ICML 2025 pa…☆71Updated 2 months ago
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆111Updated 2 years ago
- [CVPR 2022] HINT: Hierarchical Neuron Concept Explainer☆20Updated 2 years ago
- [NeurIPS2023] "Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning" by Yihua Zhang*, Yimeng Zhang*,…☆14Updated 2 years ago
- ☆29Updated 2 years ago
- Code and results accompanying our paper titled RLSbench: Domain Adaptation under Relaxed Label Shift☆35Updated 2 years ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28Updated 2 years ago
- Official Code for ICLR2022 Paper: Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap☆28Updated 3 months ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆50Updated last year
- Learning Representations that Support Robust Transfer of Predictors☆20Updated 4 years ago
- Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.☆17Updated last year
- ☆28Updated last year
- [ICML 2022] Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder☆24Updated last year
- This repository is the official implementation of Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regulari…☆21Updated 3 years ago
- [ICLR'22] Self-supervised learning optimally robust representations for domain shift.☆25Updated 3 years ago
- ☆12Updated 3 years ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Updated 2 years ago
- Understanding Rare Spurious Correlations in Neural Network☆12Updated 3 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆73Updated last year