deel-ai / oodeel
Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.
☆52Updated this week
Related projects ⓘ
Alternatives and complementary repositories for oodeel
- 👋 Influenciae is a Tensorflow Toolbox for Influence Functions☆56Updated 7 months ago
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layers☆89Updated last month
- Build and train Lipschitz-constrained networks: PyTorch implementation of 1-Lipschitz layers. For TensorFlow/Keras implementation, see ht…☆27Updated last week
- ☆27Updated 7 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
- ☆13Updated last year
- 👋 Xplique is a Neural Networks Explainability Toolbox☆648Updated last month
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆30Updated 7 months ago
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆56Updated last year
- Conformal prediction for uncertainty quantification in image segmentation☆14Updated last month
- 👋 Puncc is a python library for predictive uncertainty quantification using conformal prediction.☆302Updated this week
- LENS Project☆42Updated 9 months ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆118Updated 5 months ago
- A runway dataset and a generator of synthetic aerial images with automatic labeling.☆87Updated 2 months ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆155Updated 10 months ago
- Official PyTorch implementation of improved B-cos models☆42Updated 8 months ago
- Code for Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty☆129Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆30Updated 2 weeks ago
- 👽 Out-of-Distribution Detection with PyTorch☆254Updated 2 weeks ago
- A toolkit for quantitative evaluation of data attribution methods.☆33Updated this week
- Uncertainty-aware representation learning (URL) benchmark☆98Updated 8 months ago
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆203Updated 4 months ago
- Concept Relevance Propagation for Localization Models, accepted at SAIAD workshop at CVPR 2023.☆12Updated 10 months ago
- HCOMP '22 -- Eliciting and Learning with Soft Labels from Every Annotator☆10Updated 2 years ago
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true cla…☆228Updated last year
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation☆108Updated this week
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆143Updated 2 years ago
- NeurIPS 2021 | Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information☆32Updated 2 years ago
- Domain adaptation toolbox compatible with scikit-learn and pytorch☆68Updated this week
- reference implementation for "explanations can be manipulated and geometry is to blame"☆35Updated 2 years ago