Representation Learning by Learning to Count
Loading...
Links to Files
Author/Creator
Author/Creator ORCID
Date
2017-12-25
Type of Work
Department
Program
Citation of Original Publication
Mehdi Noroozi , et.al, Representation Learning by Learning to Count, 2017 IEEE International Conference on Computer Vision (ICCV), DOI: 10.1109/ICCV.2017.628
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
© 2017 IEEE
© 2017 IEEE
Abstract
We introduce a novel method for representation learning that uses an artificial supervision signal based on counting visual primitives. This supervision signal is obtained from an equivariance relation, which does not require any manual annotation. We relate transformations of images to transformations of the representations. More specifically, we look for the representation that satisfies such relation rather than the transformations that match a given representation. In this paper, we use two image transformations in the context of counting: scaling and tiling. The first transformation exploits the fact that the number of visual primitives should be invariant to scale. The second transformation allows us to equate the total number of visual primitives in each tile to that in the whole image. These two transformations are combined in one constraint and used to train a neural network with a contrastive loss. The proposed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.