neuroexplicit-saar / Discover-then-Name
Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
☆38Updated 5 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
- A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept dat…☆93Updated last year
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆75Updated 10 months ago
- ☆17Updated 11 months ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆62Updated last year
- ☆10Updated 3 months ago
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆91Updated 10 months ago
- An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆48Updated last year
- LENS Project☆47Updated last year
- SpuCo is a Python package developed to further research to address spurious correlations.☆24Updated 2 months ago
- CoSy: Evaluating Textual Explanations☆16Updated 2 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆14Updated last year
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆19Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆48Updated 8 months ago
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆107Updated last year
- Official repo for arxiv paper: Aligning Visual and Semantic Interpretability through Visually Grounded Concept Bottleneck Models☆19Updated 3 months ago
- ☆12Updated 2 years ago
- ☆107Updated last year
- ☆10Updated last year
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆16Updated 11 months ago
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"☆24Updated last year
- What do we learn from inverting CLIP models?☆53Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆216Updated 3 weeks ago
- A collection of model transferability estimation methods.☆26Updated 5 months ago
- ☆10Updated 4 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆30Updated last year
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆14Updated 10 months ago
- Code for CVPR 2023 Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization☆13Updated 2 years ago
- Official PyTorch implementation of improved B-cos models☆47Updated last year
- [NeurIPS '24] Frustratingly easy Test-Time Adaptation of VLMs!!☆41Updated last week
- 👋 Overcomplete is a Vision-based SAE Toolbox☆43Updated last week