B-cos / B-cos-v2
Official PyTorch implementation of improved B-cos models
☆47Updated last year
Alternatives and similar repositories for B-cos-v2:
Users that are interested in B-cos-v2 are comparing it to the libraries listed below
- B-cos Networks: Alignment is All we Need for Interpretability☆109Updated last year
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆16Updated last year
- [NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.☆30Updated last month
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆62Updated last year
- ☆39Updated 11 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)☆21Updated 3 weeks ago
- Crowdsourcing metrics and test datasets beyond ImageNet (ICML 2022 workshop)☆38Updated 11 months ago
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"☆24Updated last year
- ☆107Updated last year
- Robustness and adaptation of ImageNet scale models. Pre-Release, stay tuned for updates.☆135Updated last year
- A Benchmark for Failure Detection under Distribution Shifts in Image Classification☆31Updated 6 months ago
- [ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift☆108Updated last year
- LENS Project☆48Updated last year
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection☆52Updated 8 months ago
- FFCV-SSL Fast Forward Computer Vision for Self-Supervised Learning.☆207Updated last year
- Visualizing representations with diffusion based conditional generative model.☆94Updated 2 years ago
- ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition☆37Updated 2 years ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"☆48Updated 9 months ago
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆16Updated 4 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆42Updated 6 months ago
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluation☆35Updated 8 months ago
- Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)☆347Updated 2 weeks ago
- Information Bottlenecks for Attribution☆79Updated 2 years ago
- The official code of Relevance-CAM☆43Updated last year
- 👋 Overcomplete is a Vision-based SAE Toolbox☆53Updated last month
- The official code release for Unsupervised Out-of-distribution Detection with Diffusion Inpainting (ICML 2023)☆26Updated last year
- Natural Language Descriptions of Deep Visual Features, ICLR 2022☆63Updated last year
- PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures (CVPR 2022)☆106Updated 2 years ago
- Code for the NeurIPS 2023 paper "Spatial-frequency channels, shape bias, and adversarial robustness"☆12Updated last year
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty☆139Updated last year