open-set

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

awesome open-world outlier-detection anomaly open-set awesome-lists robustness anomaly-detection novelty-detection open-set-recognition out-of-distribution out-of-distribution-detection ood-detection ood-generalization out-of-distribution-generalization open-world-learning ood-robustness distribution-shifts out-of-distribution-robustness

UpdatedNov 5, 2025

zhmiao /OpenLongTailRecognition-OLTR

Star867

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

computer-vision deep-learning open-set long-tail pytorch-implementation cvpr2019 open-long-tail-recognition oltr

UpdatedJul 16, 2022
Python

IDEA-Research /Rex-Omni

Star684

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

object-detection open-set mllm

UpdatedNov 4, 2025
Jupyter Notebook

abhijitbendale /OSDN

Star284

Code and data for the research paper "Towards Open Set Deep Networks" A Bendale, T Boult, CVPR 2016

deep-learning softmax-regression extract-features openmax softmax open-set

UpdatedApr 30, 2018
Python

IDEA-Research /RexSeek

Star172

[ICCV2025] Referring any person or objects given a natural language description. Code base for RexSeek and HumanRef Benchmark

detection multi-modal open-set referring llm vllm

UpdatedOct 15, 2025
Python

ma-xu /Open-Set-Recognition

Star172

Open Set Recognition

pytorch mnist imagenet cifar openmax open-set openset center-loss open-set-recognition oltr openset-classification openset-recognition

UpdatedSep 13, 2021
Python

dlmacedo /entropic-out-of-distribution-detection

Star79

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.

machine-learning deep-learning pytorch ood osr ai-safety open-set anomaly-detection novelty-detection robust-machine-learning open-set-recognition out-of-distribution out-of-distribution-detection ood-detection trustworthy-machine-learning trustworthy-ai

UpdatedSep 22, 2022
Python

Cogito2012 /OpenTAL

Star54

[CVPR 2022 Oral] Towards Open Set Temporal Action Localization

video action open-set open-set-recognition

UpdatedSep 4, 2023
Python

jd730 /EOPSN

Star51

[CVPR 2021] Exemplar-Based Open-Set Panoptic Segmentation Network (EOPSN)

open-set exemplar panoptic-segmentation

UpdatedMay 27, 2022
Python

dlmacedo /distinction-maximization-loss

Star44

A project to improve out-of-distribution detection (open set recognition) and uncertainty estimation by changing a few lines of code in your project! Perform efficient inferences (i.e., do not increase inference time) without repetitive model training, hyperparameter tuning, or collecting additional data.

machine-learning deep-learning pytorch classification ood osr uncertainty-estimation ai-safety open-set anomaly-detection novelty-detection robust-machine-learning open-set-recognition out-of-distribution out-of-distribution-detection ood-detection trustworthy-machine-learning trustworthy-ai

UpdatedSep 22, 2022
Python

openlex3d /openlex3d

Star30

Toolbox for the OpenLex3D benchmark

benchmark semantics clip semantic-segmentation 3d open-set scene-graphs open-vocabulary 3d-understanding scene-understading

UpdatedOct 20, 2025
Python

PRIS-CV /Mutual-to-Separate

Star24

Code release for Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation (TCSVT 2023)

open-set domain-adaptation open-set-recognition open-set-domain-adaptation

UpdatedOct 20, 2023
Python

dlmacedo /robust-deep-learning

Star17

A project to train your model from scratch or fine-tune a pretrained model using the losses provided in this library to improve out-of-distribution detection and uncertainty estimation performances. Calibrate your model to produce enhanced uncertainty estimations. Detect out-of-distribution data using the defined score type and threshold.