English

Visualizing Deep Similarity Networks

Computer Vision and Pattern Recognition 2019-01-04 v1 Machine Learning

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T07:01:48.425Z