Object-Centric Anomaly Detection by Attribute-Based Reasoning

  title={Object-Centric Anomaly Detection by Attribute-Based Reasoning},
  author={B. Saleh and A. Farhadi and A. Elgammal},
  journal={2013 IEEE Conference on Computer Vision and Pattern Recognition},
  • B. Saleh, A. Farhadi, A. Elgammal
  • Published 2013
  • Computer Science
  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • When describing images, humans tend not to talk about the obvious, but rather mention what they find interesting. We argue that abnormalities and deviations from typicalities are among the most important components that form what is worth mentioning. In this paper we introduce the abnormality detection as a recognition problem and show how to model typicalities and, consequently, meaningful deviations from prototypical properties of categories. Our model can recognize abnormalities and report… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions
    • 212
    • Open Access
    Decorrelating Semantic Visual Attributes by Resisting the Urge to Share
    • 125
    • Open Access
    Understanding and Predicting Image Memorability at a Large Scale
    • 164
    • Open Access
    Learning Deep Features for One-Class Classification
    • 83
    • Highly Influenced
    • Open Access
    MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
    • 38
    • Open Access
    End-to-End Localization and Ranking for Relative Attributes
    • 55
    • Open Access
    Category Specific Dictionary Learning for Attribute Specific Feature Selection
    • 47
    • Open Access
    OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations
    • 64
    • Open Access
    Multi-attribute Queries: To Merge or Not to Merge?
    • 42
    • Open Access


    Publications referenced by this paper.
    Object Detection with Discriminatively Trained Part Based Models
    • 8,290
    • Open Access
    The Pascal Visual Object Classes (VOC) Challenge
    • 8,114
    • Open Access
    Anomaly detection: A survey
    • 6,547
    • Open Access
    Learning to detect unseen object classes by between-class attribute transfer
    • 1,612
    • Open Access
    Describing objects by their attributes
    • 1,580
    • Open Access
    Learning Patterns of Activity Using Real-Time Tracking
    • 3,558
    • Open Access
    Family resemblances: Studies in the internal structure of categories
    • 4,771
    • Open Access
    Relative attributes
    • 813
    • Open Access
    Learning to predict where humans look
    • 1,657
    • Open Access
    Attribute and simile classifiers for face verification
    • 1,348
    • Open Access