mlsanityData to 14 Oct 2026

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

arXiv 2105.14289 ↗First posted 29 May 2021cs.CLcited by 42

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 29 May 2021.

Builds on

23 of 34 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2020Supervised Contrastive Learningcited by 2,829
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  11. 2015Towards Open Set Deep Networkscited by 538
  12. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
11 more
  1. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  2. 2018Additive Margin Softmax for Face Verificationcited by 278
  3. 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 276
  4. 2017DOC: Deep Open Classification of Text Documentscited by 109
  5. 2018From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbotscited by 85
  6. 2019Deep Unknown Intent Detection with Margin Losscited by 66
  7. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  8. 2020Generating Fluent Adversarial Examples for Natural Languagescited by 49
  9. 2016Adversarial Diversity and Hard Positive Generationcited by 35
  10. 2018Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Ratescited by 17
  11. 2017Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systemscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 15; 2023: 16; 2024: 6; 2025: 3; 2026: 2.

42 papers.

Sort:

By area:

  1. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  2. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 93
  3. 2022Rank-N-Contrast: Learning Continuous Representations for Regressioncited by 76
  4. 2022Contrastive Positive Sample Propagation along the Audio-Visual Event Linecited by 50
  5. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  6. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29
  7. 2022Graph Enhanced Contrastive Learning for Radiology Findings Summarizationcited by 24
  8. 2024Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detectioncited by 14
  9. 2022Estimating Soft Labels for Out-of-Domain Intent Detectioncited by 11
  10. 2022Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Textcited by 11
  11. 2025CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Losscited by 11
  12. 2022Generalized Intent Discovery: Learning from Open World Dialogue Systemcited by 10
30 more
  1. 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognitioncited by 10
  2. 2022Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discoverycited by 9
  3. 2022Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemblecited by 9
  4. 2022Distribution Calibration for Out-of-Domain Detection with Bayesian Approximationcited by 7
  5. 2023Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contextscited by 6
  6. 2022UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learningcited by 5
  7. 2023Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discoverycited by 5
  8. 2023Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognitioncited by 5
  9. 2023Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistantscited by 4
  10. 2023MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognitioncited by 4
  11. 2023SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rankcited by 3
  12. 2023APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detectioncited by 3
  13. 2022The Open-World Lottery Ticket Hypothesis for OOD Intent Classificationcited by 2
  14. 2022Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learningcited by 2
  15. 2023Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learningcited by 2
  16. 2023Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLPcited by 2
  17. 2023DualTalker: A Cross-Modal Dual Learning Approach for Speech-Driven 3D Facial Animationcited by 2
  18. 2024From Zero to Hero: Cold-Start Anomaly Detectioncited by 2
  19. 2022Exploring the Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Out-of-Scope Detection Taskscited by 1
  20. 2022Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Modelscited by 1
  21. 2023Open World Classification with Adaptive Negative Samplescited by 1
  22. 2023Open Set Relation Extraction via Unknown-Aware Trainingcited by 1
  23. 2024Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanismcited by 1
  24. 2024One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learningcited by 0
  25. 2024Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discoverycited by 0
  26. 2024eDOC: Explainable Decoding Out-of-domain Cell Types with Evidential Learningcited by 0
  27. 2025OpenCML: End-to-End Framework of Open-world Machine Learning to Learn Unknown Classes Incrementallycited by 0
  28. 2025Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solutioncited by 0
  29. 2026How to Achieve Prototypical Birth and Death for OOD Detection?cited by 0
  30. 2026A Multi-cluster Boundary Learning Method for Out-of-Scope Intent Detection via MiniLM Embeddingcited by 0