CRAFT: Complementary recommendation by adversarial feature transform

We propose a framework that harnesses visual cues in an unsupervised manner to learn the co-occurrence distribution of items in real-world images for complementary recommendation. Our model learns a non-linear transformation between the two manifolds of source and target item categories (e.g., tops and bottoms in outfits). Given a large dataset of images containing instances of co-occurring items, we train a generative transformer network directly on the feature representation by casting it as an adversarial optimization problem. Such a conditional generative model can produce multiple novel samples of complementary items (in the feature space) for a given query item. We demonstrate our framework for the task of recommending complementary top apparel for a given bottom clothing item. The recommendations made by our system are diverse, and are favored by human experts over the baseline approaches.