Exchangeable deep neural networks for set-to-set matching and learning
It addresses a practical problem for applications like fashion recommendation and group identification, but appears incremental as it builds on existing attention to set-to-set matching.
The paper tackles the heterogeneous set-to-set matching problem by proposing a novel deep learning architecture and efficient training framework, showing significant improvements over state-of-the-art methods in fashion set recommendation and group re-identification experiments.
Matching two different sets of items, called heterogeneous set-to-set matching problem, has recently received attention as a promising problem. The difficulties are to extract features to match a correct pair of different sets and also preserve two types of exchangeability required for set-to-set matching: the pair of sets, as well as the items in each set, should be exchangeable. In this study, we propose a novel deep learning architecture to address the abovementioned difficulties and also an efficient training framework for set-to-set matching. We evaluate the methods through experiments based on two industrial applications: fashion set recommendation and group re-identification. In these experiments, we show that the proposed method provides significant improvements and results compared with the state-of-the-art methods, thereby validating our architecture for the heterogeneous set matching problem.