serre-lab / HoramaLinks
β11Updated last month
Alternatives and similar repositories for Horama
Users that are interested in Horama are comparing it to the libraries listed below
Sorting:
- π Overcomplete is a Vision-based SAE Toolboxβ57Updated 2 months ago
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β64Updated last year
- LENS Projectβ48Updated last year
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β14Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.β44Updated 7 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ32Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ34Updated last year
- New implementations of old orthogonal layers unlock large scale training.β17Updated last week
- A toolkit for quantitative evaluation of data attribution methods.β47Updated last month
- β13Updated 3 weeks ago
- Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).β24Updated 4 months ago
- CoSy: Evaluating Textual Explanationsβ16Updated 4 months ago
- β39Updated last year
- What do we learn from inverting CLIP models?β54Updated last year
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?β40Updated 2 years ago
- β12Updated 2 years ago
- Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"β14Updated 3 weeks ago
- The code for the Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness paperβ21Updated 6 months ago
- Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"β48Updated 10 months ago
- FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)β16Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).β250Updated this week
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ63Updated last year
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networksβ12Updated last month
- Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"β24Updated last year
- SpuCo is a Python package developed to further research to address spurious correlations.β24Updated 4 months ago
- Official PyTorch implementation of improved B-cos modelsβ48Updated last year
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)β30Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformersβ41Updated 3 months ago
- β97Updated last month
- [NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.β30Updated this week