The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

A curated list of papers & resources linked to open set recognition, out-of-distribution, open set domain adaptation and open world recognition

Benchmarking Generalized Out-of-Distribution Detection

Out-of-distribution detection, robustness, and generalization resources. The repository contains a curated list of papers, tutorials, books, videos, articles and open-source libraries etc

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)

The Official Repository for "Generalized OOD Detection: A Survey"

ADRepository: Real-world anomaly detection datasets, including tabular data (categorical and numerical data), time series data, graph data, image data, and video data.

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (NeurIPS 2020)

Self-Supervised Learning for OOD Detection (NeurIPS 2019)

The Combined Anomalous Object Segmentation (CAOS) Benchmark

[TPAMI 2022] Adversarial Reciprocal Points Learning for Open Set Recognition

Papers for Open Knowledge Discovery

The Ultimate Reference for Out of Distribution Detection with Deep Neural Networks

Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)

Official repository for the paper "Masksembles for Uncertainty Estimation" (CVPR 2021).

[SafeAI'21] Feature Space Singularity for Out-of-Distribution Detection.

Federated Learning with New Knowledge -- explore to incorporate various new knowledge into existing FL systems and evolve these systems to reduce costs, extend their lifespan, and facilitate sustainable development.

A project to add scalable state-of-the-art out-of-distribution detection (open set recognition) support by changing two lines of code! Perform efficient inferences (i.e., do not increase inference time) and detection without classification accuracy drop, hyperparameter tuning, or collecting additional data.