deel-ai / oodeel
Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.
☆55Updated last week
Alternatives and similar repositories for oodeel:
Users that are interested in oodeel are comparing it to the libraries listed below
- 👋 Influenciae is a Tensorflow Toolbox for Influence Functions☆58Updated 10 months ago
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layers☆91Updated last week
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see ht…☆27Updated this week
- Conformal prediction for uncertainty quantification in image segmentation☆20Updated 2 months ago
- ☆27Updated 10 months ago
- 👋 Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)☆27Updated 2 years ago
- 👋 Xplique is a Neural Networks Explainability Toolbox☆664Updated 4 months ago
- ☆13Updated 2 years ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆61Updated last year
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆33Updated 10 months ago
- LENS Project☆46Updated 11 months ago
- 👋 Puncc is a python library for predictive uncertainty quantification using conformal prediction.☆312Updated last month
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆144Updated 2 years ago
- Open-source framework for uncertainty and deep learning models in PyTorch☆349Updated this week
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆123Updated 8 months ago
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty☆134Updated last year
- 👽 Out-of-Distribution Detection with PyTorch☆276Updated last week
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆209Updated 7 months ago
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation☆116Updated this week
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆160Updated last year
- ☆15Updated 8 months ago
- Reliability diagrams visualize whether a classifier model needs calibration☆145Updated 3 years ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆35Updated 3 months ago
- A toolkit for quantitative evaluation of data attribution methods.☆39Updated this week
- Official PyTorch implementation of improved B-cos models☆45Updated 11 months ago
- The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a …☆353Updated 6 months ago
- Code for "On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty".☆111Updated 2 years ago
- Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. Paper presented at MICCAI 2023 conference.☆19Updated last year
- ☆99Updated 3 years ago