deel-ai / oodeelLinks
Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.
β60Updated 2 weeks ago
Alternatives and similar repositories for oodeel
Users that are interested in oodeel are comparing it to the libraries listed below
Sorting:
- π Influenciae is a Tensorflow Toolbox for Influence Functionsβ64Updated last year
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layersβ100Updated 6 months ago
- β37Updated 3 weeks ago
- New implementations of old orthogonal layers unlock large scale training.β21Updated 3 weeks ago
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see htβ¦β34Updated last month
- π Xplique is a Neural Networks Explainability Toolboxβ702Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metricsβ39Updated last year
- π CODS - Conformal Object Detection and Segmentationβ17Updated last week
- π½ Out-of-Distribution Detection with PyTorchβ316Updated this week
- Open-source framework for uncertainty and deep learning models in PyTorchβ433Updated this week
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.β233Updated 2 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximizationβ133Updated last year
- πͺ Interpreto is an interpretability toolbox for LLMsβ35Updated this week
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertaintyβ144Updated 2 years ago
- π Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)β30Updated 3 years ago
- The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a β¦β366Updated last year
- β13Updated 2 years ago
- π Overcomplete is a Vision-based SAE Toolboxβ90Updated 2 months ago
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true claβ¦β248Updated 2 years ago
- A toolkit for quantitative evaluation of data attribution methods.β53Updated 2 months ago
- [CVPRW 2024] Conformal prediction for uncertainty quantification in image segmentationβ25Updated 10 months ago
- Reliability diagrams visualize whether a classifier model needs calibrationβ158Updated 3 years ago
- Official PyTorch implementation of improved B-cos modelsβ52Updated 2 weeks ago
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanationsβ625Updated 2 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.β15Updated last year
- Papers and code of Explainable AI esp. w.r.t. Image classificiationβ218Updated 3 years ago
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β67Updated 2 years ago
- Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"β188Updated last year
- π Puncc is a python library for predictive uncertainty quantification using conformal prediction.β348Updated 4 months ago
- β15Updated 5 months ago