%0 Conference Proceedings
%T Cross-domain fashion image retrieval
%A Bojana Gajic
%A Ramon Baldrich
%B CVPR 2018 Workshop on Women in Computer Vision (WiCV 2018, 4th Edition)
%D 2018
%F Bojana Gajic2018
%O CIC; 600.087
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3709), last updated on Thu, 22 Sep 2022 18:40:26 +0200
%X Cross domain image retrieval is a challenging task that implies matching images from one domain to their pairs from another domain. In this paper we focus on fashion image retrieval, which involves matching an image of a fashion item taken by users, to the images of the same item taken in controlled condition, usually by professional photographer. When facing this problem, we have different productsin train and test time, and we use triplet loss to train the network. We stress the importance of proper training of simple architecture, as well as adapting general models to the specific task.
%U http://dx.doi.org/10.1109/CVPRW.2018.00243
%P 19500-19502