GAN-based anomaly detection: A review
X Xia, X Pan, N Li, X He, L Ma, X Zhang, N Ding - Neurocomputing, 2022 - Elsevier
Supervised learning algorithms have shown limited use in the field of anomaly detection due
to the unpredictability and difficulty in acquiring abnormal samples. In recent years …
to the unpredictability and difficulty in acquiring abnormal samples. In recent years …
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 …
dialogue systems. Previous methods commonly restrict the region (in feature space) of In …
Lmc: Large model collaboration with cross-assessment for training-free open-set object recognition
Open-set object recognition aims to identify if an object is from a class that has been
encountered during training or not. To perform open-set object recognition accurately, a key …
encountered during training or not. To perform open-set object recognition accurately, a key …
Modeling discriminative representations for out-of-domain detection with supervised contrastive learning
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-
oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic …
oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic …
A survey on out-of-distribution detection in nlp
Out-of-distribution (OOD) detection is essential for the reliable and safe deployment of
machine learning systems in the real world. Great progress has been made over the past …
machine learning systems in the real world. Great progress has been made over the past …
Revisit overconfidence for ood detection: Reassigned contrastive learning with adaptive class-dependent threshold
Abstract Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential
in a task-oriented dialog system. A key challenge of OOD detection is the overconfidence of …
in a task-oriented dialog system. A key challenge of OOD detection is the overconfidence of …
Generalized intent discovery: Learning from open world dialogue system
Traditional intent classification models are based on a pre-defined intent set and only
recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) …
recognize limited in-domain (IND) intent classes. But users may input out-of-domain (OOD) …
Novel slot detection: A benchmark for discovering unknown slot types in the task-oriented dialogue system
Existing slot filling models can only recognize pre-defined in-domain slot types from a limited
slot set. In the practical application, a reliable dialogue system should know what it does not …
slot set. In the practical application, a reliable dialogue system should know what it does not …
SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank
Deep neural classifiers trained with cross-entropy loss (CE loss) often suffer from poor
calibration, necessitating the task of out-of-distribution (OOD) detection. Traditional …
calibration, necessitating the task of out-of-distribution (OOD) detection. Traditional …
Anomaly prediction of Internet behavior based on generative adversarial networks
XQ Wang, Y An, Q Hu - PeerJ Computer Science, 2024 - peerj.com
With the popularity of Internet applications, a large amount of Internet behavior log data is
generated. Abnormal behaviors of corporate employees may lead to internet security issues …
generated. Abnormal behaviors of corporate employees may lead to internet security issues …