neuroexplicit-saar / Discover-then-Name
Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.
☆29Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for Discover-then-Name
- A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept dat…☆79Updated 7 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023☆72Updated 6 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆15Updated 7 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆12Updated 10 months ago
- A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.☆78Updated 2 years ago
- An automatic and efficient tool to describe functionalities of individual neurons in DNNs☆38Updated last year
- Concept Bottleneck Models, ICML 2020☆180Updated last year
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆100Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆45Updated 4 months ago
- CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification☆83Updated 5 months ago
- Official PyTorch implementation of improved B-cos models☆42Updated 8 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆118Updated 5 months ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆56Updated last year
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆19Updated 10 months ago
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"☆24Updated last year
- SpuCo is a Python package developed to further research to address spurious correlations.☆21Updated last month
- ☆105Updated last year
- Invertible Concept-based Explanation (ICE)☆18Updated 3 years ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆336Updated 3 months ago
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆116Updated last year
- LENS Project☆42Updated 8 months ago
- B-cos Networks: Alignment is All we Need for Interpretability☆105Updated last year
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆29Updated 3 months ago
- ☆39Updated 2 years ago
- Pytorch SimCLR on CIFAR10 (92.85% test accuracy)☆56Updated 4 years ago
- Layer-Wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆100Updated last week
- [NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threa…☆38Updated 10 months ago
- ☆36Updated 6 months ago
- reference implementation for "explanations can be manipulated and geometry is to blame"☆35Updated 2 years ago
- [ICLR 2023 spotlight] MEDFAIR: Benchmarking Fairness for Medical Imaging☆59Updated last year