shrebox / B-cosificationLinks
[NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.
β30Updated this week
Alternatives and similar repositories for B-cosification
Users that are interested in B-cosification are comparing it to the libraries listed below
Sorting:
- Official PyTorch implementation of improved B-cos modelsβ48Updated last year
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β64Updated last year
- B-cos Networks: Alignment is All we Need for Interpretabilityβ109Updated last year
- Official PyTorch Implementation of "Rosetta Neurons: Mining the Common Units in a Model Zoo"β30Updated last year
- β72Updated 7 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β21Updated last month
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).β24Updated 4 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β16Updated last year
- Uncertainty-aware representation learning (URL) benchmarkβ105Updated 2 months ago
- Official code for "Good Teachers Explain: Explanation-enhanced Knowledge Distillation", ECCV 2024β19Updated 7 months ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023β77Updated last year
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"β48Updated 10 months ago
- Sparse Linear Concept Embeddingsβ98Updated 2 months ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β65Updated last year
- Code and instructions accompanying ICCV'23 paper Protoype-based Dataset Comparisonβ18Updated last year
- Temperature Schedules for self-supervised contrastive methods on long-tail data (ICLR'23)β17Updated 2 years ago
- Re-implementation of the StylEx paper, training a GAN to explain a classifier in StyleSpace, paper by Lang et al. (2021).β37Updated last year
- Visualizing representations with diffusion based conditional generative model.β95Updated 2 years ago
- Code release for "Improved baselines for vision-language pre-training"β60Updated last year
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretabβ¦β17Updated 5 months ago
- π Overcomplete is a Vision-based SAE Toolboxβ57Updated 2 months ago
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNsβ50Updated last year
- Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detectionβ54Updated 9 months ago
- [ICLR 2025] Official code repository for "TULIP: Token-length Upgraded CLIP"β26Updated 3 months ago
- [ICLR 2025] Video Action Differencingβ38Updated 2 months ago
- β16Updated last year
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based modelsβ25Updated last year
- ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognitionβ37Updated 2 years ago
- Learning Bottleneck Concepts in Image Classification (CVPR 2023)β39Updated last year
- Code for the NeurIPS 2023 paper "Spatial-frequency channels, shape bias, and adversarial robustness"β12Updated last year