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 Appalaraju | 1 | 2 | 0.37 |
Vineet Chaoji | 2 | 5 | 0.76 |