Homography augumented momentum constrastive learning for SAR image retrieval

TL;DR

This paper introduces a novel deep learning approach for SAR image retrieval using homography-augmented contrastive learning, enabling large-scale, label-free SAR image search with promising experimental results.

Contribution

The paper proposes a homography-augmented contrastive learning method for SAR image retrieval that does not require labeled data, facilitating large-scale dataset handling.

Findings

Effective retrieval performance on polarimetric SAR datasets

Label-free training method simplifies large-scale dataset processing

Homography augmentation improves contrastive learning for SAR images

Abstract

Deep learning-based image retrieval has been emphasized in computer vision. Representation embedding extracted by deep neural networks (DNNs) not only aims at containing semantic information of the image, but also can manage large-scale image retrieval tasks. In this work, we propose a deep learning-based image retrieval approach using homography transformation augmented contrastive learning to perform large-scale synthetic aperture radar (SAR) image search tasks. Moreover, we propose a training method for the DNNs induced by contrastive learning that does not require any labeling procedure. This may enable tractability of large-scale datasets with relative ease. Finally, we verify the performance of the proposed method by conducting experiments on the polarimetric SAR image datasets.