Click on Mask: A Labor-efficient Annotation Framework with Level Set for Infrared Small Target Detection
This addresses the resource-heavy annotation bottleneck for researchers in infrared small target detection, though it appears incremental as it builds on existing level set methods.
The paper tackles the labor-intensive manual annotation problem in infrared small target detection by proposing a framework that generates high-quality pseudo masks with just one cursory click, achieving superior performance on NUAA-SIRST and IRSTD-1k datasets.
Infrared Small Target Detection is a challenging task to separate small targets from infrared clutter background. Recently, deep learning paradigms have achieved promising results. However, these data-driven methods need plenty of manual annotation. Due to the small size of infrared targets, manual annotation consumes more resources and restricts the development of this field. This letter proposed a labor-efficient and cursory annotation framework with level set, which obtains a high-quality pseudo mask with only one cursory click. A variational level set formulation with an expectation difference energy functional is designed, in which the zero level contour is intrinsically maintained during the level set evolution. It solves the issue that zero level contour disappearing due to small target size and excessive regularization. Experiments on the NUAA-SIRST and IRSTD-1k datasets reveal that our approach achieves superior performance. Code is available at https://github.com/Li-Haoqing/COM.