shrebox / B-cosification
[NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.
β30Updated last month
Alternatives and similar repositories for B-cosification:
Users that are interested in B-cosification are comparing it to the libraries listed below
- B-cos Networks: Alignment is All we Need for Interpretabilityβ109Updated last year
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β62Updated last year
- Official PyTorch implementation of improved B-cos modelsβ47Updated last year
- Visualizing representations with diffusion based conditional generative model.β94Updated last year
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β21Updated 2 weeks ago
- β65Updated 6 months ago
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).β23Updated 3 months ago
- Official PyTorch Implementation of "Rosetta Neurons: Mining the Common Units in a Model Zoo"β30Updated last year
- Official code for "Good Teachers Explain: Explanation-enhanced Knowledge Distillation", ECCV 2024β18Updated 5 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β16Updated last year
- β39Updated 11 months ago
- Code and instructions accompanying ICCV'23 paper Protoype-based Dataset Comparisonβ18Updated last year
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detectionβ52Updated 7 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023β77Updated 11 months ago
- Official PyTorch code for "Out-of-distribution detection with denoising diffusion models"β49Updated 10 months ago
- Sparse Linear Concept Embeddingsβ91Updated 3 weeks ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"β48Updated 9 months ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β63Updated last year
- Re-implementation of the StylEx paper, training a GAN to explain a classifier in StyleSpace, paper by Lang et al. (2021).β36Updated last year
- Code for the paper "Hyperbolic Image-Text Representations", Desai et al, ICML 2023β159Updated last year
- Code for Continuously Changing Corruptions (CCC) benchmark + evaluationβ35Updated 8 months ago
- Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)β11Updated 8 months ago
- Uncertainty-aware representation learning (URL) benchmarkβ102Updated last month
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretabβ¦β16Updated 4 months ago
- Create generated datasets and train robust classifiersβ35Updated last year
- Official Code for the ACCV 2022 paper Diffusion Models for Counterfactual Explanationsβ25Updated last month
- The official code release for Unsupervised Out-of-distribution Detection with Diffusion Inpainting (ICML 2023)β26Updated last year
- Fast Diffusion-Based Counterfactuals for Shortcut Removal and Generation (ECCV 2024 ORAL)β13Updated 7 months ago
- ImageNetV2 Pytorch Datasetβ41Updated 2 years ago
- Augmenting with Language-guided Image Augmentation (ALIA)β76Updated last year