Exchangeable deep neural networks for set-to-set matching and learning

TL;DR

This paper introduces a novel deep neural network architecture designed specifically for heterogeneous set-to-set matching, addressing the challenges of feature extraction and exchangeability preservation, with applications in fashion recommendation and group re-identification.

Contribution

The paper proposes a new deep learning architecture and training framework tailored for set-to-set matching that maintains exchangeability and improves performance over existing methods.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of exchangeability in heterogeneous set matching.

Validated on industrial applications like fashion recommendation and re-identification.

Abstract

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.