Recent advances in open set recognition: A survey

C Geng, S Huang, S Chen - IEEE transactions on pattern …, 2020 - ieeexplore.ieee.org
In real-world recognition/classification tasks, limited by various objective factors, it is usually
difficult to collect training samples to exhaust all classes when training a recognizer or …

Zero-day attack detection: a systematic literature review

R Ahmad, I Alsmadi, W Alhamdani… - Artificial Intelligence …, 2023 - Springer
With the continuous increase in cyberattacks over the past few decades, the quest to
develop a comprehensive, robust, and effective intrusion detection system (IDS) in the …

Classification-reconstruction learning for open-set recognition

R Yoshihashi, W Shao, R Kawakami… - Proceedings of the …, 2019 - openaccess.thecvf.com
Open-set classification is a problem of handling'unknown'classes that are not contained in
the training dataset, whereas traditional classifiers assume that only known classes appear …

Zero-shot out-of-distribution detection based on the pre-trained model clip

S Esmaeilpour, B Liu, E Robertson, L Shu - Proceedings of the AAAI …, 2022 - ojs.aaai.org
In an out-of-distribution (OOD) detection problem, samples of known classes (also called in-
distribution classes) are used to train a special classifier. In testing, the classifier can (1) …

Integrative few-shot learning for classification and segmentation

D Kang, M Cho - Proceedings of the IEEE/CVF Conference …, 2022 - openaccess.thecvf.com
We introduce the integrative task of few-shot classification and segmentation (FS-CS) that
aims to both classify and segment target objects in a query image when the target classes …

Doc: Deep open classification of text documents

L Shu, H Xu, B Liu - arXiv preprint arXiv:1709.08716, 2017 - arxiv.org
Traditional supervised learning makes the closed-world assumption that the classes
appeared in the test data must have appeared in training. This also applies to text learning …

KNN-contrastive learning for out-of-domain intent classification

Y Zhou, P Liu, X Qiu - Proceedings of the 60th Annual Meeting of …, 2022 - aclanthology.org
Abstract The Out-of-Domain (OOD) intent classification is a basic and challenging task for
dialogue systems. Previous methods commonly restrict the region (in feature space) of In …

Open-world machine learning: applications, challenges, and opportunities

J Parmar, S Chouhan, V Raychoudhury… - ACM Computing …, 2023 - dl.acm.org
Traditional machine learning, mainly supervised learning, follows the assumptions of closed-
world learning, ie, for each testing class, a training class is available. However, such …

Deep open intent classification with adaptive decision boundary

H Zhang, H Xu, TE Lin - Proceedings of the AAAI Conference on …, 2021 - ojs.aaai.org
Open intent classification is a challenging task in dialogue systems. On the one hand, it
should ensure the quality of known intent identification. On the other hand, it needs to detect …

Deep unknown intent detection with margin loss

TE Lin, H Xu - arXiv preprint arXiv:1906.00434, 2019 - arxiv.org
Identifying the unknown (novel) user intents that have never appeared in the training set is a
challenging task in the dialogue system. In this paper, we present a two-stage method for …