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
  • [31] Semi-supervised evolutionary ensembles for Web video categorization
    Mahmood, Amjad
    Li, Tianrui
    Yang, Yan
    Wang, Hongjun
    Afzal, Mehtab
    KNOWLEDGE-BASED SYSTEMS, 2015, 76 : 53 - 66
  • [32] Regularized Multi-Class Semi-Supervised Boosting
    Saffari, Amir
    Leistner, Christian
    Bischof, Horst
    CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4, 2009, : 967 - 974
  • [33] Hypergraph regularized semi-supervised support vector machine
    Sun, Yuting
    Ding, Shifei
    Guo, Lili
    Zhang, Zichen
    INFORMATION SCIENCES, 2022, 591 : 400 - 421
  • [34] Regularized correntropy criterion based semi-supervised ELM
    Yang, Jie
    Cao, Jiuwen
    Wang, Tianlei
    Xue, Anke
    Chen, Badong
    NEURAL NETWORKS, 2020, 122 : 117 - 129
  • [35] Graph-based Semi-supervised Support Vector Data Description for Novelty Detection
    Phuong Duong
    Van Nguyen
    Mi Dinh
    Trung Le
    Dat Tran
    Ma, Wanli
    2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,
  • [36] Disagreement based semi-supervised learning approaches with belief functions
    He, Hongshun
    Han, Deqiang
    Dezert, Jean
    KNOWLEDGE-BASED SYSTEMS, 2020, 193 (193)
  • [37] LEVERAGING INTER-ANNOTATOR DISAGREEMENT FOR SEMI-SUPERVISED SEGMENTATION
    Sauer, Alexander
    Dmitrieva, Mariia
    Han, Hongqing
    Rittscher, Jens
    2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, 2023,
  • [38] Semi-Supervised Community Detection Using Structure and Size
    Bakshi, Arjun
    Parthasarathy, Srinivasan
    Srinivasan, Kaman
    2018 IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM), 2018, : 869 - 874
  • [39] Semi-supervised community detection using label propagation
    Liu, Dong
    Bai, Hong-Yu
    Li, Hui-Jia
    Wang, Wen-Jun
    INTERNATIONAL JOURNAL OF MODERN PHYSICS B, 2014, 28 (29):
  • [40] Review Spam Detection Using Semi-supervised Technique
    Narayan, Rohit
    Rout, Jitendra Kumar
    Jena, Sanjay Kumar
    PROGRESS IN INTELLIGENT COMPUTING TECHNIQUES: THEORY, PRACTICE, AND APPLICATIONS, VOL 2, 2018, 719 : 281 - 286