Reproduce “SMPISD-MTPNet: Scene Semantic Prior-Assisted Infrared Ship Detection Using Multi-Task Perception Networks” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Chen Hu, Xiaogang Dong, Yian Huang Lele Wang, Liang Xu, Tian Pu, Zhenming Peng

SMPISD-MTPNet addresses infrared satellite ship detection by combining ship appearance with local scene cues. Its Scene Semantic Extractor adds multi-scale contrast and background-variation information, while scene-segmentation supervision and a learned gradient module provide additional training signals. On IRSDSS, it reports 44.5% AP@50:95 for all targets, versus KCPNet’s 43.9%; this comparison is limited to one dataset.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.