Open Set Learning
88 papers with code • 0 benchmarks • 6 datasets
Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. Open set learning (OSL) is a more challenging and realistic setting, where there exist test samples from the classes that are unseen during training. Open set recognition (OSR) is the sub-task of detecting test samples which do not come from the training.
Benchmarks
These leaderboards are used to track progress in Open Set Learning
Libraries
Use these libraries to find Open Set Learning models and implementations
MIMII
NINCO
ImageNet-1k vs NINCO
UCCS
Most implemented papers
Towards Open Set Deep Networks
We present a methodology to adapt deep networks for open set recognition, by introducing a new model layer, OpenMax, which estimates the probability of an input being from an unknown class.
Learning a Neural-network-based Representation for Open Set Recognition
shrtCKT/opennet
•
•
Open set recognition problems exist in many domains.
Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
MrtnMndt/OCDVAE_ContinualLearning
•
•
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge.
Generalized Out-of-Distribution Detection: A Survey
In this survey, we first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i. e., AD, ND, OSR, OOD detection, and OD.
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature.
Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
layumi/A_reID
•
•
Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.
Large-Scale Long-Tailed Recognition in an Open World
zhmiao/OpenLongTailRecognition-OLTR
•
•
CVPR 2019
We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes.
Adversarial Motorial Prototype Framework for Open Set Recognition
Xiaziheng89/Adversarial-Motorial-Prototype-Framework-for-Open-Set-Recognition
•
•
Second, this paper proposes the adversarial motorial prototype framework (AMPF) based on the MPF.
Evidential Deep Learning for Open Set Action Recognition
Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions.
Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
sgvaze/osr_closed_set_all_you_need
•
•
ICLR 2022
In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes.
