deel-ai / Craft
π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)
β55Updated last year
Related projects β
Alternatives and complementary repositories for Craft
- LENS Projectβ42Updated 8 months ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β62Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"β43Updated 3 months ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)β100Updated 2 years ago
- Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paperβ¦β52Updated this week
- β61Updated 3 weeks ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ30Updated 6 months ago
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detectionβ48Updated 2 months ago
- B-cos Networks: Alignment is All we Need for Interpretabilityβ105Updated 11 months ago
- The official PyTorch implementation of the Iterated Integrated Attributions (IIA) method.β9Updated 9 months ago
- Re-implementation of the StylEx paper, training a GAN to explain a classifier in StyleSpace, paper by Lang et al. (2021).β35Updated 11 months ago
- Official PyTorch implementation of improved B-cos modelsβ42Updated 8 months ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"β43Updated 5 months ago
- Uncertainty-aware representation learning (URL) benchmarkβ98Updated 8 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023β71Updated 5 months ago
- Sparse Linear Concept Embeddingsβ66Updated 3 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β20Updated 8 months ago
- β40Updated 8 months ago
- Patching open-vocabulary models by interpolating weightsβ90Updated last year
- β30Updated 9 months ago
- β34Updated 2 years ago
- β35Updated 6 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ29Updated last year
- Official PyTorch Implementation of "Rosetta Neurons: Mining the Common Units in a Model Zoo"β27Updated last year
- β105Updated last year
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ118Updated 4 months ago
- What do we learn from inverting CLIP models?β45Updated 8 months ago
- Crowdsourcing metrics and test datasets beyond ImageNet (ICML 2022 workshop)β37Updated 5 months ago
- β177Updated last year
- Visualizing representations with diffusion based conditional generative model.β83Updated last year