KempnerInstitute / overcompleteLinks
π Overcomplete is a Vision-based SAE Toolbox
β63Updated 3 months ago
Alternatives and similar repositories for overcomplete
Users that are interested in overcomplete are comparing it to the libraries listed below
Sorting:
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β65Updated last year
- LENS Projectβ48Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ35Updated last year
- β11Updated last month
- π Aligning Human & Machine Vision using explainabilityβ52Updated last year
- A toolkit for quantitative evaluation of data attribution methods.β48Updated last week
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ63Updated last year
- New implementations of old orthogonal layers unlock large scale training.β17Updated this week
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β31Updated last week
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformersβ41Updated 4 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ32Updated last year
- Conformal prediction for uncertainty quantification in image segmentationβ23Updated 6 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.β45Updated 7 months ago
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based modelsβ25Updated last year
- π Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)β30Updated 2 years ago
- CoSy: Evaluating Textual Explanationsβ16Updated 5 months ago
- Official PyTorch implementation of improved B-cos modelsβ50Updated last year
- β13Updated last month
- β13Updated 2 years ago
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ96Updated 3 months ago
- β45Updated 2 years ago
- β37Updated 3 weeks ago
- Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.β58Updated this week
- β39Updated last year
- Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AIβ55Updated 2 years ago
- Code for the ICLR 2022 paper. Salient Imagenet: How to discover spurious features in deep learning?β40Updated 2 years ago
- Repository for PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits, accepted at CVPR 2024 XAI4CV Worksβ¦β15Updated last year
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ129Updated last year
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β65Updated last year
- β107Updated last year