Clustering-Based Representation Learning through Output Translation and Its Application to Remote-Sensing Images

Li, Qinglin; Li, Bin; Garibaldi, Jonathan M.; Qiu, Guoping

Abstract

In supervised deep learning, learning good representations for remote-sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obtain huge amounts of labeled data. Recently, self-supervised learning shows its outstanding capability to learn representations of images, especially the methods of instance discrimination. Comparing methods of instance discrimination, clustering-based methods not only view the transformations of the same image as “positive” samples but also similar images. In this paper, we propose a new clustering-based method for representation learning. We first introduce a quantity to measure representations’ discriminativeness and from which we show that even distribution requires the most discriminative representations. This provides a theoretical insight into why evenly distributing the images works well. We notice that only the even distributions that preserve representations’ neighborhood relations are desirable. Therefore, we develop an algorithm that translates the outputs of a neural network to achieve the goal of evenly distributing the samples while preserving outputs’ neighborhood relations. Extensive experiments have demonstrated that our method can learn representations that are as good as or better than the state of the art approaches, and that our method performs computationally efficiently and robustly on various RSI datasets.

Citation

Li, Q., Li, B., Garibaldi, J. M., & Qiu, G. (2022). Clustering-Based Representation Learning through Output Translation and Its Application to Remote-Sensing Images. Remote Sensing, 14(14), Article 3361. https://doi.org/10.3390/rs14143361

• Journal Article Type: Article
• Acceptance Date: Jul 8, 2022
• Online Publication Date: Jul 12, 2022
• Publication Date: Jul 12, 2022
• Deposit Date: Mar 17, 2025
• Publicly Available Date: Mar 17, 2025
• Journal: Remote Sensing
• Electronic ISSN: 2072-4292
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 14
• Issue: 14
• Article Number: 3361
• DOI: https://doi.org/10.3390/rs14143361
• Public URL: https://nottingham-repository.worktribe.com/output/8955733
• Publisher URL: https://www.mdpi.com/2072-4292/14/14/3361