28 April 2026 in IEEE Transactions on Geoscience and Remote Sensing
Infrared small target detection remains challenging due to weak target responses, cluttered backgrounds, and large variations in target appearance. In this paper, we propose FLINet, a fuzzy-logic-guided network that introduces a fuzzy set perspective for uncertainty-aware feature fusion in infrared small target detection. FLINet follows a U-shaped encoder-decoder architecture and incorporates two key modules: a Global-Local Fuzzy computation module (GLF) and a Difference-Aware Feature fusion module (DAF). GLF performs dual-branch fuzzy reasoning at both local-window and global-image levels to model feature uncertainty during cross-level fusion. Specifically, the local branch enhances contrast-sensitive target cues via adaptive membership-based amplification, while the global branch suppresses clutter-dominant responses through global statistical normalization, jointly improving target-background separation and morphology preservation. DAF further strengthens cross-level integration by exploiting inter-level discrepancy maps to guide a self-attention-based fusion, prioritizing complementary fine-grained details from shallow layers and semantic cues from deep layers to reduce small-target information loss. Extensive experiments on three benchmark datasets (NUDT-SIRST, NUAA-SIRST, and IRSTD-1K) demonstrate that FLINet consistently achieves superior performance across multiple evaluation metrics. Our code is available at: https://github.com/PZYang/FLINet.
1 January 2026 in IEEE Transactions on Circuits and Systems for Video Technology