Object-Centric Anomaly Detection by Attribute-Based Reasoning

@article{Saleh2013ObjectCentricAD,
  title={Object-Centric Anomaly Detection by Attribute-Based Reasoning},
  author={Babak Saleh and Ali Farhadi and A. Elgammal},
  journal={2013 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2013},
  pages={787-794}
}
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… 

Figures and Tables from this paper

Detecting Strange Objects via Visual Attributes
TLDR
This work investigates what is the main characteristics of an object category in terms of its visual attributes and shows how to improve object detectors by making assumptions on typicality of the objects.
Toward a Taxonomy and Computational Models of Abnormalities in Images
TLDR
A comprehensive computational model is proposed that can predict all different types of abnormality in images and outperform prior arts in abnormality recognition.
Wow! that looks strange: computational models for detection and reasoning about abnormalities in images
TLDR
This work proposes a new dataset of abnormal images, extracting a list of reasons of atypicality, enumerating distinct modes or types of abnormal image types, and deriving computational models motivated by human-level reasoning.
Decorrelating Semantic Visual Attributes by Resisting the Urge to Share
TLDR
It is shown that accounting for structure in the visual attribute space is key to learning attribute models that preserve semantics, yielding improved generalizability that helps in the recognition and discovery of unseen object categories.
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
TLDR
A novel computational model of automatic landmark detection from a single image without any pre-defined landmark database is proposed, which leverages state-of-the-art algorithms based on convolutional neural networks to recognize scenes and objects.
MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
TLDR
This work introduces the MVTec Anomaly Detection (MVTec AD) dataset containing 5354 high-resolution color images of different object and texture categories, and conducts a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pre-trained convolved neural networks.
Spatiotemporal deep networks for detecting abnormality in videos
TLDR
The gradient-based approach is utilized to generate adversarial samples for an abnormality detection system and the defense mechanism to detect the abnormality in the presence of such adversarial attacks is built.
Localizing and Visualizing Relative Attributes
TLDR
This chapter presents a weakly supervised approach that discovers the spatial extent of relative attributes, given only pairs of ordered images, and develops a novel formulation that combines a detector with local smoothness to discover a set of coherent visual chains across the image collection.
CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows
TLDR
A real-time model based on a conditional normalizing flow frame- work adopted for anomaly detection with localization that is faster and smaller by a factor of 10× than prior state-of-the-art with the same input setting and outperforms previous methods.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
Attribute-centric recognition for cross-category generalization
TLDR
This work introduces a new dataset that provides annotation for sharing models of appearance and correlation across categories and uses it to learn part and category detectors that serve as the visual basis for an integrated model of objects.
Abnormal Object Detection by Canonical Scene-Based Contextual Model
TLDR
A novel generative model is proposed that detects abnormal objects by meeting four proposed criteria of success, and this model generates normal as well as abnormal objects, each following their respective tendencies.
Learning to detect unseen object classes by between-class attribute transfer
TLDR
The experiments show that by using an attribute layer it is indeed possible to build a learning object detection system that does not require any training images of the target classes, and assembled a new large-scale dataset, “Animals with Attributes”, of over 30,000 animal images that match the 50 classes in Osherson's classic table of how strongly humans associate 85 semantic attributes with animal classes.
Describing objects by their attributes
TLDR
This paper proposes to shift the goal of recognition from naming to describing, and introduces a novel feature selection method for learning attributes that generalize well across categories.
Recognizing human actions by attributes
TLDR
This paper argues that attributes enable the construction of more descriptive models for human action recognition and proposes a unified framework wherein manually specified attributes are selected in a discriminative fashion and coherently integrated with data-driven attributes to make the attribute set more descriptive.
Relative attributes
TLDR
This work proposes a generative model over the joint space of attribute ranking outputs, and proposes a novel form of zero-shot learning in which the supervisor relates the unseen object category to previously seen objects via attributes (for example, ‘bears are furrier than giraffes’).
Beyond Novelty Detection: Incongruent Events, When General and Specific Classifiers Disagree
TLDR
A formal framework for the representation and processing of incongruent events is defined, starting from the notion of label hierarchy, and it is shown how partial order on labels can be deduced from such hierarchies.
Object Detection with Discriminatively Trained Part Based Models
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in
The Pascal Visual Object Classes (VOC) Challenge
TLDR
The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.
Detecting Irregularities in Images and in Video
  • Oren Boiman, M. Irani
  • Computer Science
    Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
TLDR
This work addresses the problem of detecting irregularities in visual data, e.g., detecting suspicious behaviors in video sequences, or identifying salient patterns in images, using a probabilistic graphical model.
...
1
2
3
4
...