For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for classification networks, but applicable to the problem domains better suited to similarity learning. The visualization shows how similarity networks that are fine-tuned learn to focus on different features. We also generalize our approach to embedding networks that use different pooling strategies and provide a simple mechanism to support image similarity searches on objects or sub-regions in the query image.
@article{arxiv.1901.00536,
title = {Visualizing Deep Similarity Networks},
author = {Abby Stylianou and Richard Souvenir and Robert Pless},
journal= {arXiv preprint arXiv:1901.00536},
year = {2019}
}