Attribute disentanglement with gradient reversal for interactive fashion retrieval

Interactive fashion search is gaining more and more interest thanks to the rapid diffusion of online retailers. It allows users to browse fashion items and perform attribute manipulations, modifying parts or details of given garments. To successfully model and analyze garments at such a fine-grained level, it is necessary to obtain attribute-wise representations, separating information relative to different characteristics. In this work we propose an attribute disentanglement method based on attribute classifiers and the usage of gradient reversal layers. This combination allows us to learn attribute-specific features, removing unwanted details from each representation. We test the effectiveness of our learned features in a fashion attribute manipulation task, obtaining state of the art results. Furthermore, to favor training stability we present a novel loss balancing approach, preventing reversed losses to diverge during the optimization process.