Cross-Domain Object Matching with Model Selection

TL;DR

This paper introduces new cross-domain object matching methods that automatically address model selection issues, demonstrated through experiments on image matching, voice conversion, and photo summarization.

Contribution

It proposes alternative CDOM methods that inherently solve the model selection problem, improving upon kernel-based dependency measures.

Findings

Effective in image matching tasks

Successful in unpaired voice conversion

Enhances photo album summarization

Abstract

The goal of cross-domain object matching (CDOM) is to find correspondence between two sets of objects in different domains in an unsupervised way. Photo album summarization is a typical application of CDOM, where photos are automatically aligned into a designed frame expressed in the Cartesian coordinate system. CDOM is usually formulated as finding a mapping from objects in one domain (photos) to objects in the other domain (frame) so that the pairwise dependency is maximized. A state-of-the-art CDOM method employs a kernel-based dependency measure, but it has a drawback that the kernel parameter needs to be determined manually. In this paper, we propose alternative CDOM methods that can naturally address the model selection problem. Through experiments on image matching, unpaired voice conversion, and photo album summarization tasks, the effectiveness of the proposed methods is demonstrated.