A curated list of awesome resources dedicated to One Class Classification and its application to NLP / CV.

Contributing: Please feel free to make pull requests.

• Research Trends and Surveys
• Papers
  • SVM Approaches
  • Deep Learning Approaches
• Datasets

• One-class classification: Concept-learning in the absence of counter-examples (DMJ Tax, 2001)
• One-class classification: taxonomy of study and review of techniques (Shehroz S.Khan, Michael G.Madden, 2014)
• Rethinking Assumptions in Deep Anomaly Detection (Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks, Klaus-Robert Müller, Marius Kloft, 2020)

• Support vector domain description [paper]
  • David M.J. Tax, Robert P.W. Duin
  • Pattern Recognition Letters 20 (1999)

• A bayesian approach to the data description problem [paper]
  • Alireza Ghasemi, Hamid R Rabiee, Mohammad T Manzuri, Mohammad Hossein Rohban
  • AAAI 2012

• Text Classification from Positive and Unlabeled Documents [paper]
  • Hwanjo Yu, ChengXiang Zhai, Jiawei Han
  • CIKM 2003

• Breaking the Closed World Assumption in Text Classification [paper]
  • Geli Fei, Bing Liu
  • NAACL 2016

• Learning Cumulatively to Become More Knowledgeable [paper]
  • Geli Fei, Shuai Wang, Bing Liu
  • KDD 2016

• Towards Open Set Deep Networks [paper]
  • Abhijit Bendale, Terrance Boult
  • CVPR 2016

• DOC: Deep Open Classification of Text Documents [paper]
  • Lei Shu, Hu Xu, Bing Liu
  • EMNLP 2017

• Deep One-Class Classification [paper]
  • Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel Müller, Marius Kloft
  • PMLR 2018

• Out-of-domain Detection based on Generative Adversarial Network [paper]
  • Seonghan Ryu, Sangjun Koo, Hwanjo Yu, Gary Geunbae Lee
  • EMNLP 2018

• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks [paper]
  • Kimin Lee, Kibok Lee, Honglak Lee, Jinwoo Shin
  • NIPS 2018
• Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness [paper]
  • Tianyu Pang, Kun Xu, Yinpeng Dong, Chao Du, Ning Chen, Jun Zhu
  • ICLR 2020

• Inhibited Softmax for Uncertainty Estimation in Neural Networks [paper]
  • Marcin Możejko, Mateusz Susik, Rafał Karczewski
  • ICLR 2019 Conference Withdrawn Submission

• Deep Unknown Intent Detection with Margin Loss [paper]
  • Ting-En Lin, Hua Xu
  • ACL 2019

• KLOOS: KL Divergence-based Out-of-Scope Intent Detection in Human-to-Machine Conversations [paper]
  • Eyup Halit Yilmaz, Cagri Toraman
  • SIGIR 2020

• Out-of-domain Detection for Natural Language Understanding in Dialog Systems [paper]
  • Yinhe Zheng, Guanyi Chen, Minlie Huang
  • TALSP 2020

• Conditional Gaussian Distribution Learning for Open Set Recognition [paper]
  • Xin Sun, Zhenning Yang, Chi Zhang, Guohao Peng, Keck-Voon Ling
  • CVPR 2020

Back to Top

• Intent Classification and Out-of-Scope Prediction Dataset [paper]
  • This dataset dataset covers 150 intent classes over 10 domains, capturing the breadth that a production taskoriented agent must handle. It also includes queries that are out-of-scope i.e., queries that do not fall into any of the system’s supported intents.

Back to Top