mertyg / debug-mistakes-cce
Meaningfully debugging model mistakes with conceptual counterfactual explanations. ICML 2022
☆75Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for debug-mistakes-cce
- ☆103Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆45Updated 4 months ago
- CVPR 2022, Robust Contrastive Learning against Noisy Views☆83Updated 2 years ago
- This is the code of paper ``Contrastive Coding for Active Learning under Class Distribution Mismatch'' with python.☆28Updated last year
- ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition☆34Updated last year
- Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paper…☆52Updated this week
- Official implementation for "Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition" (I…☆40Updated last year
- MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts (ICLR 2022)☆108Updated 2 years ago
- Implementation of Beyond Neural Scaling beating power laws for deep models and prototype-based models☆32Updated 3 months ago
- Implementation of Concept-level Debugging of Part-Prototype Networks☆11Updated last year
- Official code for ICML 2022: Mitigating Neural Network Overconfidence with Logit Normalization☆143Updated 2 years ago
- MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space☆88Updated 3 years ago
- ☆41Updated 2 weeks ago
- PyTorch implementation of the paper "Discovering and Explaining the Representation Bottleneck of DNNs" (ICLR 2022)☆37Updated 3 weeks ago
- Code for paper: “What Data Benefits My Classifier?” Enhancing Model Performance and Interpretability through Influence-Based Data Selecti…☆22Updated 6 months ago
- Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)☆54Updated last year
- Official Implementation of Robust Training under Label Noise by Over-parameterization☆62Updated 2 years ago
- Code for "Interpretable image classification with differentiable prototypes assignment", ECCV 2022☆21Updated 2 years ago
- LISA for ICML 2022☆47Updated last year
- ☆25Updated 8 months ago
- A regularized self-labeling approach to improve the generalization and robustness of fine-tuned models☆27Updated 2 years ago
- ☆151Updated 2 years ago
- Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"☆35Updated 2 years ago
- ☆33Updated 7 months ago
- This repository holds code and other relevant files for the NeurIPS 2022 tutorial: Foundational Robustness of Foundation Models.☆70Updated last year
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆72Updated 6 months ago
- Code for the ICLR 2022 paper "Attention-based interpretability with Concept Transformers"☆39Updated last year
- Discover and Cure: Concept-aware Mitigation of Spurious Correlation (ICML 2023)☆40Updated 7 months ago
- [ICLR 2023, ICLR DG oral] PAIR, the optimizer and model selection criteria for OOD Generalization☆50Updated 7 months ago
- Code for Active Learning at The ImageNet Scale. This repository implements many popular active learning algorithms and allows training wi…☆52Updated 2 years ago