FineTag: Multi-label Retrieval of Attributes at Fine-grained Level in Images

06/19/2018

∙

by   Roshanak Zakizadeh, et al.

∙

0

∙

share

In image retrieval, the features extracted from an item are used to look for similar lookalike of the items (e.g. finding a match for a bag in a retail catalogue). Identifying all the attributes of a single instance of an item in an image (e.g. the shape of the bag) could facilitate the task of image retrieval. In this work, we introduce a simple end-to-end architecture for retrieving the attributes at a fine-grained level in an image.