(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation
☆44Nov 17, 2025Updated 3 months ago
Alternatives and similar repositories for DISC
Users that are interested in DISC are comparing it to the libraries listed below
Sorting:
- Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning (ICML 2023)☆19Dec 15, 2023Updated 2 years ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆90May 20, 2024Updated last year
- This is an implementation of the paper "Are We Done with Object-Centric Learning?"☆12Sep 11, 2025Updated 5 months ago
- The official implementation of the paper **Learning Concise and Descriptive Attributes for Visual Recognition**☆49Dec 14, 2023Updated 2 years ago
- DISSECT: Disentangled Simultaneous Explanations via Concept Traversals☆12Feb 5, 2024Updated 2 years ago
- Official codebase for the NeurIPS 2023 paper: Towards Last-layer Retraining for Group Robustness with Fewer Annotations. https://arxiv.or…☆12May 15, 2024Updated last year
- ☆12Oct 2, 2023Updated 2 years ago
- ☆13Mar 5, 2023Updated 3 years ago
- Official Implementation of Avoiding spurious correlations via logit correction☆17May 6, 2023Updated 2 years ago
- One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks (ICLR 2023 Spotlight)☆14Sep 28, 2025Updated 5 months ago
- Meaningfully debugging model mistakes with conceptual counterfactual explanations. ICML 2022☆75Jul 15, 2022Updated 3 years ago
- SpuCo is a Python package developed to further research to address spurious correlations.☆25Jan 16, 2025Updated last year
- [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled c…☆132Mar 31, 2024Updated last year
- ☆12Oct 23, 2022Updated 3 years ago
- Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)☆21Oct 16, 2025Updated 4 months ago
- Code for Environment Inference for Invariant Learning (ICML 2021 Paper)☆51Jun 10, 2021Updated 4 years ago
- Bias-to-Text: Debiasing Unknown Visual Biases through Language Interpretation☆32May 21, 2023Updated 2 years ago
- Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023☆29Jun 27, 2023Updated 2 years ago
- Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.☆17Jun 2, 2024Updated last year
- This is the official implementation of the Concept Discovery Models paper.☆15Aug 27, 2023Updated 2 years ago
- Implementation of Concept-level Debugging of Part-Prototype Networks☆12May 9, 2023Updated 2 years ago
- Reinforced Causal Explainer for Graph Neural Networks, TPAMI2022☆41Jun 13, 2022Updated 3 years ago
- This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human con…☆16Oct 7, 2022Updated 3 years ago
- Code and instructions accompanying ICCV'23 paper Protoype-based Dataset Comparison☆18Dec 15, 2023Updated 2 years ago
- Implementation for MICCAI DART paper: 'Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification'☆18Jun 22, 2022Updated 3 years ago
- Code for the ICLR 2022 paper "Attention-based interpretability with Concept Transformers"☆42Sep 17, 2025Updated 5 months ago
- ☆32Aug 7, 2025Updated 6 months ago
- ☆18Mar 9, 2023Updated 2 years ago
- MEGC2022☆21Jun 29, 2022Updated 3 years ago
- ☆22Feb 27, 2023Updated 3 years ago
- ☆132Apr 11, 2024Updated last year
- ☆17Jul 25, 2021Updated 4 years ago
- Official code for "Probabilistic Concept Bottleneck Models (ICML 2023)"☆19Aug 14, 2023Updated 2 years ago
- ☆19Jun 15, 2020Updated 5 years ago
- Distilling Model Failures as Directions in Latent Space☆47Feb 8, 2023Updated 3 years ago
- Official code of "Discover the Unknown Biased Attribute of an Image Classifier" (ICCV 2021)☆21Oct 11, 2021Updated 4 years ago
- PMR: Prototypical Modal Rebalance for Multimodal Learning☆46Mar 10, 2023Updated 2 years ago
- (ICLR 2022) Discovering Invariant Rationales for Graph Neural Networks☆131Jul 15, 2023Updated 2 years ago
- [ICML 2023] Official repository of paper: Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repe…☆25Aug 2, 2025Updated 7 months ago