Matching Targets Across Domains with RADON, the Re-Identification Across Domain Network

TL;DR

RADON is a new neural network model designed to accurately match images of objects taken from different viewpoints or sensors, excelling especially in low- and no-shot learning scenarios for cross-view vehicle and person identification.

Contribution

It introduces a modified Siamese network architecture tailored for challenging cross-domain and low-data matching tasks, advancing re-identification capabilities.

Findings

Strong performance on cross-view vehicle matching

Effective in cross-domain person identification

Operates well in low- and no-shot learning environments

Abstract

We present a novel convolutional neural network that learns to match images of an object taken from different viewpoints or by different optical sensors. Our Re-Identification Across Domain Network (RADON) scores pairs of input images from different domains on similarity. Our approach extends previous work on Siamese networks and modifies them to more challenging use cases, including low- and no-shot learning, in which few images of a specific target are available for training. RADON shows strong performance on cross-view vehicle matching and cross-domain person identification in a no-shot learning environment.