Self-supervised Learning for Sonar Image Classification
This work addresses the challenge of limited labeled data for sonar image classification in underwater robotics, though it is incremental as it applies existing self-supervised methods to a new domain.
The paper tackled the problem of sonar image classification by applying self-supervised learning methods (RotNet, Denoising Autoencoders, and Jigsaw) to learn representations without human labels, achieving classification performance comparable to supervised pre-training in few-shot transfer learning setups.
Self-supervised learning has proved to be a powerful approach to learn image representations without the need of large labeled datasets. For underwater robotics, it is of great interest to design computer vision algorithms to improve perception capabilities such as sonar image classification. Due to the confidential nature of sonar imaging and the difficulty to interpret sonar images, it is challenging to create public large labeled sonar datasets to train supervised learning algorithms. In this work, we investigate the potential of three self-supervised learning methods (RotNet, Denoising Autoencoders, and Jigsaw) to learn high-quality sonar image representation without the need of human labels. We present pre-training and transfer learning results on real-life sonar image datasets. Our results indicate that self-supervised pre-training yields classification performance comparable to supervised pre-training in a few-shot transfer learning setup across all three methods. Code and self-supervised pre-trained models are be available at https://github.com/agrija9/ssl-sonar-images