Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks

被引:11
|
作者
Jezequel, Loic [1 ,2 ]
Vu, Ngoc-Son [1 ]
Beaudet, Jean [2 ]
Histace, Aymeric [1 ]
机构
[1] CY Cergy Paris Univ, ENSEA, CNRS, ETIS UMR 8051, F-95000 Paris, France
[2] Idemia Ident & Secur, F-95520 Osny, France
关键词
Task analysis; Anomaly detection; Training; Feature extraction; Self-supervised learning; Faces; Neural networks; fine grained classification; self-supervised learning; multi-task learning; one-class learning;
D O I
10.1109/TIP.2022.3231532
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Anomaly detection is important in many real-life applications. Recently, self-supervised learning has greatly helped deep anomaly detection by recognizing several geometric transformations. However these methods lack finer features, usually highly depend on the anomaly type, and do not perform well on fine-grained problems. To address these issues, we first introduce in this work three novel and efficient discriminative and generative tasks which have complementary strength: (i) a piece-wise jigsaw puzzle task focuses on structure cues; (ii) a tint rotation recognition is used within each piece, taking into account the colorimetry information; (iii) and a partial re-colorization task considers the image texture. In order to make the re-colorization task more object-oriented than background-oriented, we propose to include the contextual color information of the image border via an attention mechanism. We then present a new out-of-distribution detection function and highlight its better stability compared to existing methods. Along with it, we also experiment different score fusion functions. Finally, we evaluate our method on an extensive protocol composed of various anomaly types, from object anomalies, style anomalies with fine-grained classification to local anomalies with face anti-spoofing datasets. Our model significantly outperforms state-of-the-art with up to 36% relative error improvement on object anomalies and 40% on face anti-spoofing problems.
引用
收藏
页码:807 / 821
页数:15
相关论文
共 50 条
  • [41] CADet: Fully Self-Supervised Anomaly Detection With Contrastive Learning
    Guille-Escuret, Charles
    Rodriguez, Pau
    Vazquez, David
    Mitliagkas, Ioannis
    Monteiro, Joao
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [42] Deep anomaly detection with self-supervised learning and adversarial training
    Zhang, Xianchao
    Mu, Jie
    Zhang, Xiaotong
    Liu, Han
    Zong, Linlin
    Li, Yuangang
    PATTERN RECOGNITION, 2022, 121
  • [43] Self-Supervised Feature Extraction for Video Surveillance Anomaly Detection
    de Paula, Davi D.
    Salvadeo, Denis H. P.
    Silva, Lucas B.
    Uemerson, P., Jr.
    2023 36TH CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES, SIBGRAPI 2023, 2023, : 115 - 120
  • [44] Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization
    Schluter, Hannah M.
    Tan, Jeremy
    Hou, Benjamin
    Kainz, Bernhard
    COMPUTER VISION, ECCV 2022, PT XXXI, 2022, 13691 : 474 - 489
  • [45] Pavement anomaly detection based on transformer and self-supervised learning
    Lin, Zijie
    Wang, Hui
    Li, Shenglin
    AUTOMATION IN CONSTRUCTION, 2022, 143
  • [46] Self-Supervised Learning for Anomaly Detection With Dynamic Local Augmentation
    Yoa, Seungdong
    Lee, Seungjun
    Kim, Chiyoon
    Kim, Hyunwoo J.
    IEEE ACCESS, 2021, 9 : 147201 - 147211
  • [47] Understanding the limitations of self-supervised learning for tabular anomaly detection
    Mai, Kimberly T.
    Davies, Toby
    Griffin, Lewis D.
    PATTERN ANALYSIS AND APPLICATIONS, 2024, 27 (02)
  • [48] SELF-SUPERVISED SAR ANOMALY DETECTION GUIDED WITH RX DETECTOR
    Muzeau, M.
    Ren, C.
    Angelliaume, S.
    Datcu, M.
    Ovarlez, J. -P.
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 1918 - 1921
  • [49] Self-Supervised Random Forest on Transformed Distribution for Anomaly Detection
    Liu, Jiabin
    Wang, Huadong
    Hang, Hanyuan
    Ma, Shumin
    Shen, Xin
    Shi, Yong
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 36 (02) : 2675 - 2689
  • [50] Self-Supervised Image Anomaly Detection and Localization with Synthetic Anomalies
    Tsai, Min-Chun
    Wang, Sheng-De
    2023 10TH INTERNATIONAL CONFERENCE ON INTERNET OF THINGS: SYSTEMS, MANAGEMENT AND SECURITY, IOTSMS, 2023, : 90 - 95