serre-lab / LensLinks
LENS Project
β50Updated last year
Alternatives and similar repositories for Lens
Users that are interested in Lens are comparing it to the libraries listed below
Sorting:
- π Aligning Human & Machine Vision using explainabilityβ52Updated 2 years ago
- π Overcomplete is a Vision-based SAE Toolboxβ85Updated 2 months ago
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β67Updated 2 years ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ131Updated last year
- Python package for extracting representations from state-of-the-art computer vision modelsβ171Updated last month
- β25Updated last year
- [NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.β35Updated 4 months ago
- Official PyTorch implementation of improved B-cos modelsβ51Updated last week
- A framework for evaluating models on their alignment to brain and behavioral measurements (100+ benchmarks)β155Updated this week
- Instructions and examples to deploy some PyTorch code on slurm using a Singularity Containerβ33Updated 2 years ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).β308Updated 2 months ago
- Code for the NeurIPS 2023 paper "Spatial-frequency channels, shape bias, and adversarial robustness"β11Updated last year
- Dataset and code for the CLEVR-XAI dataset.β32Updated 2 years ago
- β15Updated 5 months ago
- β31Updated 2 years ago
- Temporal Neural Networksβ19Updated 2 months ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ39Updated last year
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformersβ41Updated 7 months ago
- Mechanistic understanding and validation of large AI models with SemanticLensβ35Updated last week
- Natural Language Descriptions of Deep Visual Features, ICLR 2022β65Updated 2 years ago
- Code for the paper "Post-hoc Concept Bottleneck Models". Spotlight @ ICLR 2023β84Updated last year
- β32Updated this week
- [ICLR 23 spotlight] An automatic and efficient tool to describe functionalities of individual neurons in DNNsβ55Updated last year
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.β233Updated 2 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.β48Updated 11 months ago
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNetβ32Updated 2 years ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"β53Updated last year
- Uncertainty-aware representation learning (URL) benchmarkβ105Updated 6 months ago
- Repository for our NeurIPS 2022 paper "Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off" and our NeurIPS 2023 paperβ¦β69Updated last month
- Code from the paper "Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Scorβ¦β16Updated 3 years ago