Alternatives and similar repositories for cosy

Users that are interested in cosy are comparing it to the libraries listed below

• rachtibat / LRP-eXplains-Transformers
  Layer-wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]
  ☆211Updated 5 months ago
• neuroexplicit-saar / Discover-then-Name
  Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
  ☆52Updated last year
• annahedstroem / MetaQuantus
  MetaQuantus is an XAI performance tool to identify reliable evaluation metrics
  ☆39Updated last year
• maxdreyer / Reveal2Revise
  Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.
  ☆20Updated last year
• maxdreyer / L-CRP
  Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.
  ☆15Updated last year
• rachtibat / zennit-crp
  An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization
  ☆139Updated last year
• chr5tphr / zennit
  Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.
  ☆238Updated 4 months ago
• serre-lab / Horama
  ☆16Updated 7 months ago
• ahmedmagdiosman / clevr-xai
  Dataset and code for the CLEVR-XAI dataset.
  ☆33Updated 2 years ago
• maxdreyer / PURE
  Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Works…
  ☆19Updated last year
• tleemann / road_evaluation
  Source Code of the ROAD benchmark for feature attribution methods (ICML22)
  ☆24Updated 2 years ago
• maxdreyer / pcx
  Prototypical Concept-based Explanations, accepted at SAIAD workshop at CVPR 2024.
  ☆15Updated 5 months ago
• jim-berend / semanticlens
  Mechanistic understanding and validation of large AI models with SemanticLens
  ☆47Updated last week
• deel-ai / influenciae
  👋 Influenciae is a Tensorflow Toolbox for Influence Functions
  ☆64Updated last year
• KempnerInstitute / overcomplete
  👋 Overcomplete is a Vision-based SAE Toolbox
  ☆106Updated last week
• mertyg / post-hoc-cbm
  Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023
  ☆89Updated last year
• understandable-machine-intelligence-lab / Quantus
  Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
  ☆634Updated 4 months ago
• serre-lab / Lens
  LENS Project
  ☆51Updated last year
• kaifishr / PyTorchRelevancePropagation
  A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.
  ☆100Updated 3 years ago
• Trustworthy-ML-Lab / CLIP-dissect
  [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNs
  ☆58Updated 2 years ago
• AI4LIFE-GROUP / OpenXAI
  OpenXAI : Towards a Transparent Evaluation of Model Explanations
  ☆252Updated last year
• Prisma-Multimodal / ViT-Prisma
  ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
  ☆325Updated 4 months ago
• dilyabareeva / quanda
  A toolkit for quantitative evaluation of data attribution methods.
  ☆54Updated 5 months ago
• SquareResearchCenter-AI / BEExAI
  Benchmark to Evaluate EXplainable AI
  ☆20Updated 9 months ago
• jjcherian / conformal-safety
  ☆32Updated last year
• yewsiang / ConceptBottleneck
  Concept Bottleneck Models, ICML 2020
  ☆233Updated 2 years ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆285Updated last year
• pankessel / adv_explanation_ref
  reference implementation for "explanations can be manipulated and geometry is to blame"
  ☆37Updated 3 years ago
• yangjenny / adversarial_learning_bias_mitigation
  ☆12Updated last year
• dgcnz / FACT
  Code for [Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models.
  ☆12Updated last year