Learning a Complete Image Indexing Pipeline

12/12/2017
by   Himalaya Jain, et al.
0

To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance computation mechanism to rapidly scan these lists. While supervised deep learning has recently enabled improvements to the latter, the former continues to be based on unsupervised clustering in the literature. In this work, we propose a first system that learns both components within a unifying neural framework of structured binary encoding.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset