Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

All except the real data are augmented with synthetic targets using the method from [15] 3, examples of these are provided in Figure 1. 4) Experiment 2.1: Data shortage: for this experiment MC-pix2pix was trained on the available real training set (flat and non-complex). The MC-pix2pix-generated data were used to train the A TR, which then was tested on another flat and non-complex dataset. Table II (top) shows that MC-pix2pix provides significant improvements in MAP, compared to just real data and other baselines, and the best F1. 5) Experiment 2.2: Lack of complexity: in this case MC-pix2pix was pre-trained with slightly more complex ripply seabeds, emulating previous exposure to the complex data. It then generated more of the complex seabeds, that were used to train the A TR alongside the flat and non-complex real data. When testing this A TR on complex real terrains (results presented at the bottom of Table II), both F1-score and mAP drastically improve with the MC-pix2pix data bootstrapping, compared to just real data training and baselines. This confirms that MC-pix2pix could be deployed as a highly efficient bootstrapping technique for improving A TR performance in cases of low real data availability or low real data diversity, that are common in the real life applications.