neuroexplicit-saar / Discover-then-NameLinks
Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
☆49Updated 11 months ago
Alternatives and similar repositories for Discover-then-Name
Users that are interested in Discover-then-Name are comparing it to the libraries listed below
Sorting:
- [ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled c…☆113Updated last year
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆84Updated last year
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆55Updated last year
- Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆195Updated 3 months ago
- Code for [Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models.☆12Updated 10 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆15Updated last year
- [NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.☆18Updated 4 months ago
- SpuCo is a Python package developed to further research to address spurious correlations.☆24Updated 9 months ago
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆110Updated 2 years ago
- Official repo for ICML25 paper: DCBM: Data-Efficient Visual Concept Bottleneck Models☆22Updated last month
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆20Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆315Updated 3 months ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆93Updated 2 months ago
- Repository for our NeurIPS 2022 paper "Concept Embedding Models", our NeurIPS 2023 paper "Learning to Receive Help", and our ICML 2025 pa…☆69Updated 2 weeks ago
- ☆40Updated last year
- Sparse Linear Concept Embeddings☆115Updated 6 months ago
- Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery via Relevance Patching"☆16Updated last month
- ☆15Updated 5 months ago
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆98Updated last year
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆67Updated 2 years ago
- Existing literature about training-data analysis.☆17Updated 3 years ago
- Concept Bottleneck Models, ICML 2020☆218Updated 2 years ago
- [NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.☆35Updated last week
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆19Updated last year
- Source Code of the ROAD benchmark for feature attribution methods (ICML22)☆23Updated 2 years ago
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).☆26Updated 9 months ago
- LENS Project☆50Updated last year
- Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"☆25Updated 3 weeks ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆49Updated last year
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆17Updated last year