Representation Learning by Learning to Count

Noroozi, Mehdi; Pirsiavash, Hamed; Favaro, Paolo (2017). Representation Learning by Learning to Count. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE

Text Noroozi_Representation_Learning_by_ICCV_2017_paper.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (1MB)

We introduce a novel method for representation learning that uses an artificial supervision signal based on count- ing 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 trans- formation 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 pro- posed task produces representations that perform on par or exceed the state of the art in transfer learning benchmarks.

Interest & Impact

Downloads

1 since deposited on 20 Apr 2018
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item