KempnerInstitute / overcompleteLinks
π Overcomplete is a Vision-based SAE Toolbox
β57Updated 2 months ago
Alternatives and similar repositories for overcomplete
Users that are interested in overcomplete are comparing it to the libraries listed below
Sorting:
- LENS Projectβ48Updated last year
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β64Updated last year
- β11Updated last month
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ34Updated last year
- A toolkit for quantitative evaluation of data attribution methods.β47Updated last month
- π Aligning Human & Machine Vision using explainabilityβ52Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ32Updated last year
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ63Updated last year
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β30Updated 3 months ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β14Updated last year
- New implementations of old orthogonal layers unlock large scale training.β17Updated last week
- β39Updated last year
- Codebase for Mechanistic Mode Connectivityβ14Updated last year
- CoSy: Evaluating Textual Explanationsβ16Updated 4 months ago
- β13Updated 3 weeks ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformersβ41Updated 3 months ago
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ96Updated 2 months ago
- Large-scale uncertainty benchmark in deep learning.β60Updated 3 weeks ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.β44Updated 7 months ago
- Conformal prediction for uncertainty quantification in image segmentationβ23Updated 5 months ago
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based modelsβ25Updated last year
- Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)β16Updated 2 years ago
- β13Updated 2 years ago
- Attribution-based Parameter Decompositionβ23Updated this week
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?β40Updated 2 years ago
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β65Updated last year
- β45Updated 2 years ago
- β37Updated last week
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ129Updated 11 months ago
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNsβ50Updated last year