Label Evolution Based on Local Contrast Measure for Single-Point Supervised Infrared Small-Target Detection

In recent years, the implementation of infrared small-target detection using convolutional neural networks (CNNs) has garnered widespread attention due to its high performance. Since this issue is often addressed through fully supervised image segmentation networks, the training process requires significant human effort and time to annotate pixel-level mask labels. Consequently, employing single-point supervision as a form of weak supervision for model training has aroused widespread interest in saving annotation costs. However, the class imbalance issue caused by single-point supervision in the early stages of training, along with inaccuracies in pseudo-label updates, and the difficulty in achieving convergence simultaneously, have made it challenging for such methods to attain satisfactory performance. In this article, we introduce a label evolution framework based on local contrast measure (LELCM) to address these issues. Before training, we expand the single-point labels into initial pseudo-labels based on the inherent information of the targets, which mitigates the problem of class imbalance. Furthermore, in the process of updating pseudo-labels, we employ a strategy that utilizes confidence contrast for updates, not only enabling more stable updates of pseudo-labels based on target characteristics but also facilitating adaptive cessation of updates. Our experimental results reveal that our approach not only attains target detection rates (Pd) on par with full supervision models but also achieves 80% of the full supervisory effect in terms of intersection over union (IoU).