Toward a Taxonomy and Computational Models of Abnormalities in Images

@article{Saleh2016TowardAT,
  title={Toward a Taxonomy and Computational Models of Abnormalities in Images},
  author={B. Saleh and A. Elgammal and J. Feldman and Ali Farhadi},
  journal={ArXiv},
  year={2016},
  volume={abs/1512.01325}
}
  • B. Saleh, A. Elgammal, +1 author Ali Farhadi
  • Published 2016
  • Computer Science, Mathematics
  • ArXiv
  • The human visual system can spot an abnormal image, and reason about what makes it strange. [...] Key Method We design human subject experiments to discover a coarse taxonomy of the reasons for abnormality. Our experiments reveal three major categories of abnormality: object-centric, scene-centric, and contextual. Based on this taxonomy, we propose a comprehensive computational model that can predict all different types of abnormality in images and outperform prior arts in abnormality recognition.Expand Abstract
    9 Citations

    Figures, Tables, and Topics from this paper.

    Landmark detection with surprise saliency using convolutional neural networks
    • F. Tang, D. Lyons, Daniel D. Leeds
    • Computer Science
    • 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
    • 2016
    Sample-efficient image segmentation through recurrence
    • 8
    What’s Wrong with That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution
    • 8
    • PDF
    Context-based abnormal object detection using the fully-connected conditional random fields
    • 5
    Automatic Understanding of Image and Video Advertisements
    • 56
    • PDF
    How Convolutional Neural Networks Remember Art
    • Eva Cetinic, T. Lipic, S. Grgic
    • Computer Science
    • 2018 25th International Conference on Systems, Signals and Image Processing (IWSSIP)
    • 2018
    • 1
    • PDF
    Multi-view manifold learning with locality alignment
    • 34

    References

    SHOWING 1-10 OF 46 REFERENCES
    Object-Centric Anomaly Detection by Attribute-Based Reasoning
    • 49
    • PDF
    SUN database: Large-scale scene recognition from abbey to zoo
    • 2,004
    • PDF
    Recognition-by-components: a theory of human image understanding.
    • 5,418
    • PDF
    The Role of Context for Object Detection and Semantic Segmentation in the Wild
    • 642
    • PDF
    Abnormal Object Detection by Canonical Scene-Based Contextual Model
    • 11
    • Highly Influential
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 41,211
    • PDF
    Blocks That Shout: Distinctive Parts for Scene Classification
    • 395
    • PDF
    Learning Deep Features for Scene Recognition using Places Database
    • 2,214
    • PDF
    Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
    • 11,919
    • PDF