Learning fashion compatibility across apparel categories for outfit recommendation
This work addresses outfit recommendation for fashion consumers, presenting an incremental improvement by integrating color features and structured priors into existing neural network frameworks.
The paper tackles the problem of recommending complementary apparel items to complete an outfit based on a user's interest in a specific item, using a siamese network with color histogram features and a MAP training formulation to learn a fashion compatibility metric.
This paper addresses the problem of generating recommendations for completing the outfit given that a user is interested in a particular apparel item. The proposed method is based on a siamese network used for feature extraction followed by a fully-connected network used for learning a fashion compatibility metric. The embeddings generated by the siamese network are augmented with color histogram features motivated by the important role that color plays in determining fashion compatibility. The training of the network is formulated as a maximum a posteriori (MAP) problem where Laplacian distributions are assumed for the filters of the siamese network to promote sparsity and matrix-variate normal distributions are assumed for the weights of the metric network to efficiently exploit correlations between the input units of each fully-connected layer.