DeepAI AI Chat
Log In Sign Up

Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning

by   Zhiyuan Zeng, et al.

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 features. Traditional cross-entropy loss only focuses on whether a sample is correctly classified, and does not explicitly distinguish the margins between categories. In this paper, we propose a supervised contrastive learning objective to minimize intra-class variance by pulling together in-domain intents belonging to the same class and maximize inter-class variance by pushing apart samples from different classes. Besides, we employ an adversarial augmentation mechanism to obtain pseudo diverse views of a sample in the latent space. Experiments on two public datasets prove the effectiveness of our method capturing discriminative representations for OOD detection.


page 1

page 2

page 3

page 4


Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning

Contrastive self-supervised learning (CSL) leverages unlabeled data to t...

Spatial Contrastive Learning for Few-Shot Classification

Existing few-shot classification methods rely to some degree on the cros...

Deep Unknown Intent Detection with Margin Loss

Identifying the unknown (novel) user intents that have never appeared in...

Real-centric Consistency Learning for Deepfake Detection

Most of previous deepfake detection researches bent their efforts to des...

UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning

Detecting out-of-domain (OOD) intents from user queries is essential for...

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

To learn intrinsic low-dimensional structures from high-dimensional data...

WDiscOOD: Out-of-Distribution Detection via Whitened Linear Discriminative Analysis

Deep neural networks are susceptible to generating overconfident yet err...