Semi-supervised novelty detection using ensembles with regularized disagreement

被引:0
|
作者
Tifrea, Alexandru [1 ]
Stavarache, Eric [1 ]
Yang, Fanny [1 ]
机构
[1] Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland
来源
UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, VOL 180 | 2022年 / 180卷
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep neural networks often predict samples with high confidence even when they come from unseen classes and should instead be flagged for expert evaluation. Current novelty detection algorithms cannot reliably identify such near OOD points unless they have access to labeled data that is similar to these novel samples. In this paper, we develop a new ensemble-based procedure for semi-supervised novelty detection (SSND) that successfully leverages a mixture of unlabeled ID and novel-class samples to achieve good detection performance. In particular, we show how to achieve disagreement only on OOD data using early stopping regularization. While we prove this fact for a simple data distribution, our extensive experiments suggest that it holds true for more complex scenarios: our approach significantly outperforms state-of-the-art SSND methods on standard image data sets (SVHN/CIFAR-10/CIFAR-100) and medical image data sets with only a negligible increase in computation cost.
引用
收藏
页码:1939 / 1948
页数:10
相关论文
共 50 条
  • [1] Semi-supervised novelty detection
    Blanchard, Gilles
    Lee, Gyemin
    Scott, Clayton
    Journal of Machine Learning Research, 2010, 11 : 2973 - 3009
  • [2] Semi-Supervised Novelty Detection
    Blanchard, Gilles
    Lee, Gyemin
    Scott, Clayton
    JOURNAL OF MACHINE LEARNING RESEARCH, 2010, 11 : 2973 - 3009
  • [3] Semi-Supervised Eigenbasis Novelty Detection
    Thompson, David R.
    Majid, Walid A.
    Reed, Colorado J.
    Wagstaff, Kiri L.
    STATISTICAL ANALYSIS AND DATA MINING, 2013, 6 (03) : 195 - 204
  • [4] Semi-Supervised Learning by Disagreement
    Zhou, Zhi-Hua
    2008 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING, VOLS 1 AND 2, 2008, : 93 - 93
  • [5] Semi-supervised learning by disagreement
    Zhou, Zhi-Hua
    Li, Ming
    KNOWLEDGE AND INFORMATION SYSTEMS, 2010, 24 (03) : 415 - 439
  • [6] Semi-supervised learning by disagreement
    Zhi-Hua Zhou
    Ming Li
    Knowledge and Information Systems, 2010, 24 : 415 - 439
  • [7] CrossRectify: Leveraging disagreement for semi-supervised object detection
    Ma, Chengcheng
    Pan, Xingjia
    Ye, Qixiang
    Tang, Fan
    Dong, Weiming
    Xu, Changsheng
    PATTERN RECOGNITION, 2023, 137
  • [8] Novel Disease Detection Using Ensembles with Regularized Disagreement
    Tifrea, Alexandru
    Stavarache, Eric
    Yang, Fanny
    UNCERTAINTY FOR SAFE UTILIZATION OF MACHINE LEARNING IN MEDICAL IMAGING, AND PERINATAL IMAGING, PLACENTAL AND PRETERM IMAGE ANALYSIS, 2021, 12959 : 133 - 144
  • [9] Semi-Supervised Novelty Detection Using SVM Entire Solution Path
    de Morsier, Frank
    Tuia, Devis
    Borgeaud, Maurice
    Gass, Volker
    Thiran, Jean-Philippe
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (04): : 1939 - 1950
  • [10] Anomaly and Novelty detection for robust semi-supervised learning
    Cappozzo, Andrea
    Greselin, Francesca
    Murphy, Thomas Brendan
    STATISTICS AND COMPUTING, 2020, 30 (05) : 1545 - 1571