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
  • [21] Evolutionary Classifier Ensembles for Semi-supervised Learning
    Zhang, Qingjiu
    Sun, Shiliang
    2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [22] Semi-supervised Regularized Coplanar Discriminant Analysis
    Sanodiya, Rakesh Kumar
    Thalakottur, Michelle Davies
    Mathew, Jimson
    Khushi, Matloob
    NEURAL INFORMATION PROCESSING, ICONIP 2019, PT V, 2019, 1143 : 198 - 205
  • [23] Adaptive Regularized Semi-Supervised Clustering Ensemble
    Luo, Rui
    Yu, Zhiwen
    Cao, Wenming
    Liu, Cheng
    Wong, Hau-San
    Chen, C. L. Philip
    IEEE ACCESS, 2020, 8 : 17926 - 17934
  • [24] Extreme Learning Machine based Novelty Detection for Incremental Semi-Supervised Learning
    Al-Behadili, Husam
    Grumpe, Arne
    Dopp, Christian
    Woehler, Christian
    2015 THIRD INTERNATIONAL CONFERENCE ON IMAGE INFORMATION PROCESSING (ICIIP), 2015, : 230 - 235
  • [25] Semi-supervised learning using constrained laplacian regularized least squares
    Sousa, Celso A. R.
    2024 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN 2024, 2024,
  • [26] FAST SEMI-SUPERVISED IMAGE SEGMENTATION BY NOVELTY SELECTION
    Paiva, Antonio R. C.
    Tasdizen, Tolga
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 1054 - 1057
  • [27] Manifold regularized semi-supervised Gaussian mixture model
    Gan, Haitao
    Sang, Nong
    Huang, Rui
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2015, 32 (04) : 566 - 575
  • [28] Fisher-regularized supervised and semi-supervised extreme learning machine
    Ma, Jun
    Wen, Yakun
    Yang, Liming
    KNOWLEDGE AND INFORMATION SYSTEMS, 2020, 62 (10) : 3995 - 4027
  • [29] Fisher-regularized supervised and semi-supervised extreme learning machine
    Jun Ma
    Yakun Wen
    Liming Yang
    Knowledge and Information Systems, 2020, 62 : 3995 - 4027
  • [30] Wavelet-Regularized Graph Semi-Supervised Learning
    Ekambaram, Venkatesan N.
    Fanti, Giulia
    Ayazifar, Babak
    Ramchandran, Kannan
    2013 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2013, : 423 - 426