lkopf / cosyLinks
[NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.
☆18Updated 3 months ago
Alternatives and similar repositories for cosy
Users that are interested in cosy are comparing it to the libraries listed below
Sorting:
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆39Updated last year
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆20Updated last year
- Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆192Updated 3 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆49Updated 11 months ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆233Updated 2 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆133Updated last year
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆15Updated last year
- Dataset and code for the CLEVR-XAI dataset.☆32Updated 2 years ago
- Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery via Relevance Patching"☆15Updated last month
- Source Code of the ROAD benchmark for feature attribution methods (ICML22)☆23Updated 2 years ago
- Prototypical Concept-based Explanations, accepted at SAIAD workshop at CVPR 2024.☆15Updated 3 months ago
- ☆15Updated 5 months ago
- A toolkit for quantitative evaluation of data attribution methods.☆53Updated 2 months ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆90Updated 2 months ago
- A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.☆96Updated 2 years ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆19Updated last year
- LENS Project☆50Updated last year
- Mechanistic understanding and validation of large AI models with SemanticLens☆37Updated 3 weeks ago
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations☆625Updated 2 months ago
- Papers and code of Explainable AI esp. w.r.t. Image classificiation☆218Updated 3 years ago
- 👋 Influenciae is a Tensorflow Toolbox for Influence Functions☆64Updated last year
- Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curv…☆16Updated 3 years ago
- Existing literature about training-data analysis.☆17Updated 3 years ago
- OpenXAI : Towards a Transparent Evaluation of Model Explanations☆248Updated last year
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆84Updated last year
- ☆32Updated 10 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆309Updated 2 months ago
- CoRelAy is a tool to compose small-scale (single-machine) analysis pipelines.☆28Updated 2 months ago
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆55Updated last year
- Concept Bottleneck Models, ICML 2020☆215Updated 2 years ago