Intelligent Maritime Radar Target Detection With Partial Annotation via Progressive Learning

Most deep learning-based maritime radar target detectors are trained in a full-supervised fashion, and accurate annotations are required in the training stage. However, we may not label rightly some unforeseen targets for their unknown positions relative to the radar when the radar collects the target echoes for the detector training. The mislabeled targets in the training set would confuse the detector parameter optimization, decreasing significantly its performance. In this article, we deal with the problem of detection with partial annotation, where partial targets are mislabeled as the sea clutter. We propose a progressive learning (PL) framework, which guides correct supervised training of the detector by identifying the mislabeled target samples and relabeling them using the pseudo label. First, we pretrain the detector using the training set to separate the features of the clutters and the mislabeled targets based on objective echo differences between them. Then, we identify the mislabeled target samples in the high-dimensional feature space by way of anomaly detection and clean them from the training set. Next, the detector is retrained utilizing the rest of the training set to obtain explicit decision boundary with intraclass compactness and interclass divergence through the sample-wise metric learning paradigm. Finally, we present a pseudo-label assignment strategy to relabel the anomaly samples and optimize the detector parameters combined with the relabeled samples and the cleaned training set. Experimental results on the public maritime radar database show the effectiveness of the proposed PL framework.