Matching Targets Across Domains with RADON, the Re-Identification Across Domain Network
This work addresses the challenge of object re-identification across domains for applications like surveillance or autonomous systems, but it is incremental as it builds on existing Siamese network approaches.
The paper tackles the problem of matching images of objects across different viewpoints or sensors with limited training data, introducing RADON, a convolutional neural network that achieves strong performance in cross-view vehicle matching and cross-domain person identification under no-shot learning conditions.
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.