Apr 14, 2023 · In this paper, we propose a novel Hybrid Contrastive Learning (HybridCL) framework to model both intra-class and inter-class constraints in OOD detection.
Oct 7, 2022 · In this paper, we propose to model both inter-class and intra-class constraints in NCD based on the symmetric Kullback-Leibler divergence (sKLD).
Out-of-Domain (OOD) detection aims to identify whether a query falls outside the predefined intent set, which is crucial to maintaining high reliability and ...
To this end, in this paper, we pro- pose to model both inter-class and intra-class constraints in NCD based on the symmetric Kullback-Leibler diver- gence (sKLD) ...
In this paper, we propose a novel model to generate high-quality pseudo OOD samples that are akin to IN-Domain (IND) input utterances, and thereby improves the ...
May 29, 2021 · In this paper, we propose a supervised contrastive learning objective to minimize intra-class variance by pulling together in-domain intents ...
Missing: Constraints | Show results with:Constraints
Jan 28, 2022 · We show that intra-class mixup forces the network to learn representations with low angular spread in the latent space. This improves the separability of OoD ...
Missing: Modeling | Show results with:Modeling
Recognizing visual unseen classes, i.e. for which no training data is available, is known as Zero Shot Learn- ing (ZSL). Some of the best performing methods ...
An inter-class sKLD constraint is proposed to effectively exploit the disjoint relationship between labelled and unlabelled classes, enforcing the ...
Missing: Domain | Show results with:Domain
Sep 8, 2024 · ... Modeling intra-class and inter-class constraints for out-of-domain detection. In: Proceedings of DASFAA (2023). Google Scholar. [50]. Zhang, S ...