lkopf / cosy
CoSy: Evaluating Textual Explanations
☆14Updated last month
Alternatives and similar repositories for cosy:
Users that are interested in cosy are comparing it to the libraries listed below
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆33Updated 10 months ago
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆19Updated last year
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆123Updated 8 months ago
- A toolkit for quantitative evaluation of data attribution methods.☆39Updated this week
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆209Updated 7 months ago
- Layer-Wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆125Updated last week
- Dataset and code for the CLEVR-XAI dataset.☆31Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆35Updated 3 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆13Updated last year
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…☆12Updated 8 months ago
- Prototypical Concept-based Explanations, accepted at SAIAD workshop at CVPR 2024.☆11Updated this week
- Source Code of the ROAD benchmark for feature attribution methods (ICML22)☆20Updated last year
- A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.☆86Updated 2 years ago
- code release for the paper "On Completeness-aware Concept-Based Explanations in Deep Neural Networks"☆53Updated 2 years ago
- reference implementation for "explanations can be manipulated and geometry is to blame"☆36Updated 2 years ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆73Updated 9 months ago
- ☆11Updated last year
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆105Updated last year
- implements some LRP rules to get explanations for Resnets and Densenet-121, including batchnorm-Conv canonization and tensorbiased layers…☆24Updated 11 months ago
- ☆120Updated 2 years ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆61Updated last year
- CoRelAy is a tool to compose small-scale (single-machine) analysis pipelines.☆27Updated 2 years ago
- A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept dat…☆88Updated 10 months ago
- Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curv…☆15Updated 2 years ago
- An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆43Updated last year
- [ICLR 2023 spotlight] MEDFAIR: Benchmarking Fairness for Medical Imaging☆60Updated last year
- A benchmark for distribution shift in tabular data☆50Updated 8 months ago
- h-Shap provides an exact, fast, hierarchical implementation of Shapley coefficients for image explanations☆16Updated last year
- Concept Bottleneck Models, ICML 2020☆188Updated last year