outlier-exposure
Outlier detector
Anomaly detection framework utilizing out-of-distribution data to improve deep learning model performance.
Deep Anomaly Detection with Outlier Exposure (ICLR 2019)
548 stars
19 watching
108 forks
Language: Python
last commit: about 3 years ago
Linked from 1 awesome list
anomalyanomaly-detectioncalibrationdeep-learningml-safetyout-of-distribution-detectionpytorch
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 yzhao062/suod | A Python framework for accelerating large-scale unsupervised outlier detection in heterogeneous datasets | 380 |
 datamllab/pyodds | An end-to-end outlier detection system that integrates machine learning algorithms with database support | 252 |
| hendrycks/robustness | Evaluates and benchmarks the robustness of deep learning models to various corruptions and perturbations in computer vision tasks. | 1,022 |
 pygod-team/pygod | Detects anomalies in graph data using various algorithms | 1,336 |
 eaglelab-zju/dgld | An open-source library for training and evaluating graph anomaly detection models | 64 |
| datamllab/tods | An automated system for detecting outliers in time-series data using machine learning algorithms and human expertise. | 1,459 |
 kdd-opensource/deepadots | A benchmarking pipeline for evaluating anomaly detection methods on time series data using deep learning algorithms | 566 |
 orobix/visual-feature-attribution-using-wasserstein-gans-pytorch | A PyTorch implementation of a feature attribution technique using Wasserstein Generative Adversarial Networks for anomaly detection in medical images. | 93 |
 shiyuliang/odin-pytorch | An implementation of a method for detecting out-of-distribution examples in neural networks | 200 |
 arundo/adtk | A toolkit for rule-based and unsupervised anomaly detection in time series data | 1,098 |
 chanyn/hkrm | Develops a deep learning model for large-scale object detection that leverages hybrid knowledge and routing mechanisms. | 104 |
 rentruewang/koila | A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution | 1,821 |
 seldonio/alibi-detect | A Python library for detecting outliers, adversarial examples, and data drift in various types of data | 2,247 |
 meiqihu/acda | Detects anomalies in hyperspectral images using an autoencoder-based approach | 44 |
 eth-sri/bayes-framework-leakage | Develops and evaluates a framework for detecting attacks on federated learning systems | 11 |