What's Mine is Yours: Pretrained CNNs for Limited Training Sonar ATR
This addresses the challenge of applying CNNs to sonar ATR for military and commercial seafaring, but it is incremental as it adapts existing transfer learning methods to a specific domain.
The paper tackles the problem of limited training data for automatic target recognition (ATR) in sonar imagery by using transfer learning with pretrained CNNs, achieving impressive results, though not state-of-the-art, on a synthetic aperture sonar dataset.
Finding mines in Sonar imagery is a significant problem with a great deal of relevance for seafaring military and commercial endeavors. Unfortunately, the lack of enormous Sonar image data sets has prevented automatic target recognition (ATR) algorithms from some of the same advances seen in other computer vision fields. Namely, the boom in convolutional neural nets (CNNs) which have been able to achieve incredible results - even surpassing human actors - has not been an easily feasible route for many practitioners of Sonar ATR. We demonstrate the power of one avenue to incorporating CNNs into Sonar ATR: transfer learning. We first show how well a straightforward, flexible CNN feature-extraction strategy can be used to obtain impressive if not state-of-the-art results. Secondly, we propose a way to utilize the powerful transfer learning approach towards multiple instance target detection and identification within a provided synthetic aperture Sonar data set.