deel-ai / Craft
π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)
β56Updated last year
Related projects β
Alternatives and complementary repositories for Craft
- LENS Projectβ42Updated 8 months ago
- Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paperβ¦β52Updated this week
- Uncertainty-aware representation learning (URL) benchmarkβ98Updated 8 months ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"β44Updated 4 months ago
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)β101Updated 2 years ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β20Updated 9 months ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β62Updated last year
- B-cos Networks: Alignment is All we Need for Interpretabilityβ105Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ30Updated 7 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"β44Updated 5 months ago
- This repository contains the code for our paper "Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguoβ¦β37Updated last year
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detectionβ49Updated 2 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ29Updated last year
- A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept datβ¦β79Updated 7 months ago
- β13Updated last year
- Visualizing representations with diffusion based conditional generative model.β84Updated last year
- The official PyTorch implementation - Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from tβ¦β76Updated 2 years ago
- β36Updated 6 months ago
- β61Updated last month
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Conceptsβ¦β53Updated last year
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"β24Updated last year
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023β72Updated 6 months ago
- β105Updated last year
- Re-implementation of the StylEx paper, training a GAN to explain a classifier in StyleSpace, paper by Lang et al. (2021).β36Updated 11 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 6 months ago
- β41Updated last week
- β17Updated 2 months ago
- Official code for "Are Vision Language Models Texture or Shape Biased and Can We Steer Them?".β12Updated 8 months ago