Paper Info
Title
Image similarity using Deep CNN and Curriculum Learning.
Abstract
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 embeddingu0027s. We go on to show that this multi-scale siamese network is better at capturing fine grained image similarities than traditional CNNu0027s.
Year
Venue
Field
2017
arXiv: Computer Vision and Pattern Recognition
Computer vision,Embedding,Computer science,Reference image,Curriculum,Artificial intelligence,Machine learning
DocType
Volume
Citations 
Journal
abs/1709.08761
2
PageRank 
References 
Authors
0.37
21
2
Name
Order
Citations
PageRank
Srikar Appalaraju120.37
Vineet Chaoji250.76