deel-ai / oodeel
Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.
β56Updated this week
Alternatives and similar repositories for oodeel:
Users that are interested in oodeel are comparing it to the libraries listed below
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ62Updated last year
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ95Updated last month
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β29Updated last month
- β35Updated 2 weeks ago
- π Overcomplete is a Vision-based SAE Toolboxβ51Updated 3 weeks ago
- π Xplique is a Neural Networks Explainability Toolboxβ682Updated 6 months ago
- Conformal prediction for uncertainty quantification in image segmentationβ22Updated 4 months ago
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ34Updated last year
- π Puncc is a python library for predictive uncertainty quantification using conformal prediction.β324Updated 3 months ago
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β62Updated last year
- π Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)β29Updated 2 years ago
- β10Updated 5 months ago
- β13Updated 2 years ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ124Updated 10 months ago
- LENS Projectβ47Updated last year
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertaintyβ139Updated last year
- β11Updated this week
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotligβ¦β148Updated 2 years ago
- π½ Out-of-Distribution Detection with PyTorchβ287Updated 2 weeks ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.β39Updated 5 months ago
- Uncertainty-aware representation learning (URL) benchmarkβ102Updated last month
- Official PyTorch implementation of improved B-cos modelsβ47Updated last year
- A toolkit for quantitative evaluation of data attribution methods.β44Updated last week
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.β222Updated 9 months ago
- Open-source framework for uncertainty and deep learning models in PyTorchβ379Updated this week
- Reliability diagrams visualize whether a classifier model needs calibrationβ149Updated 3 years ago
- π Aligning Human & Machine Vision using explainabilityβ52Updated last year
- A Python toolbox for conformal prediction research on deep learning models, using PyTorch.β367Updated 2 weeks ago
- scikit-activeml: Python library for active learning on top of scikit-learnβ161Updated last week
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"β160Updated last year