Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Understanding image representations by measuring their equivariance and equivalence
Lenc K., Vedaldi A.  International Journal of Computer Vision 127 (5): 456-476, 2019. Type: Article
Date Reviewed: Jun 17 2019

As the number of artificial intelligence (AI)-based systems that support key aspects of our life, including health and security, increases exponentially, the demand for explainable AI has reached a peak in recent years. In the field of computer vision, image representations are at the heart of most automatic recognition and detection systems. However, their theoretical understanding is still superficial and their development largely empirical. Consequently, our ability to explain image-based decision systems is still limited.

This paper makes a contribution in the area of explainable image representations by investigating, formally and through numerical simulations, their equivariance and equivalence properties. The former refers to the robustness of the output to transformations of the input image. The latter refers to the similarity of representations captured by different models on the same data. While most recent works focus on how to achieve these properties, this paper instead aims at characterizing and quantifying them in a systematic manner, considering both handcrafted and learned representations.

A must-read for anyone working on image representation learning and for practitioners interested in accelerating structured regression classifiers. It is also recommended reading for master’s and PhD students who are approaching the study of convolutional neural networks.

Reviewer:  Mariella Dimiccoli Review #: CR146599 (1909-0348)
Bookmark and Share
  Reviewer Selected
Editor Recommended
Image Representation (I.4.10 )
Would you recommend this review?
Other reviews under "Image Representation": Date
 A discriminatively learned CNN embedding for person reidentification
Zheng Z., Zheng L., Yang Y.  ACM Transactions on Multimedia Computing, Communications, and Applications 14(1): 1-20, 2017. Type: Article
May 4 2018
A new image retrieval model based on monogenic signal representation
Zeng Z., Song L., Zheng Q., Chi Y.  Journal of Visual Communication and Image Representation 33(C): 85-93, 2015. Type: Article
Apr 12 2016
 Center symmetric local binary co-occurrence pattern for texture, face and bio-medical image retrieval
Verma M., Raman B.  Journal of Visual Communication and Image Representation 32(C): 224-236, 2015. Type: Article
Dec 15 2015

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright © 2000-2020 ThinkLoud, Inc.
Terms of Use
| Privacy Policy