Image similarity involves fetching similar looking images given a reference image. Our solution called SimNet, is a deep siamese network which is trained on pairs of positive and negative images using a novel online pair mining strategy inspired by Curriculum learning. We also created a multi-scale CNN, where the final image embedding is a joint representation of top as well as lower layer embedding's. We go on to show that this multi-scale siamese network is better at capturing fine grained image similarities than traditional CNN's.
@article{arxiv.1709.08761,
title = {Image similarity using Deep CNN and Curriculum Learning},
author = {Srikar Appalaraju and Vineet Chaoji},
journal= {arXiv preprint arXiv:1709.08761},
year = {2018}
}