🤖 AI Summary
Infrared small target detection suffers from poor separability between targets and complex backgrounds; existing deep learning methods over-rely on edge and shape cues while neglecting directional structural details encoded in high-frequency components. To address this, we propose a novel framework that explicitly models high-frequency directional features as structured priors embeddable into neural networks. Specifically, we introduce two lightweight, parameter-free modules: the High-Frequency Directional Injection (HFDI) module and the Multi-Scale Direction-Aware (MSDA) module, which jointly enhance directional sensitivity and structural detail representation. Our method integrates dilated convolutions, direction-sensitive attention, feature aggregation, and calibration-based fusion—breaking away from conventional edge- or shape-driven paradigms. Extensive experiments on multiple public benchmarks demonstrate state-of-the-art performance, with significant improvements in detection accuracy and robustness. The source code is publicly available.
📝 Abstract
Infrared small target detection faces the problem that it is difficult to effectively separate the background and the target. Existing deep learning-based methods focus on edge and shape features, but ignore the richer structural differences and detailed information embedded in high-frequency components from different directions, thereby failing to fully exploit the value of high-frequency directional features in target perception. To address this limitation, we propose a multi-scale direction-aware network (MSDA-Net), which is the first attempt to integrate the high-frequency directional features of infrared small targets as domain prior knowledge into neural networks. Specifically, to fully mine the high-frequency directional features, on the one hand, a high-frequency direction injection (HFDI) module without trainable parameters is constructed to inject the high-frequency directional information of the original image into the network. On the other hand, a multi-scale direction-aware (MSDA) module is constructed, which promotes the full extraction of local relations at different scales and the full perception of key features in different directions. In addition, considering the characteristics of infrared small targets, we construct a feature aggregation (FA) structure to address target disappearance in high-level feature maps, and a feature calibration fusion (FCF) module to alleviate feature bias during cross-layer feature fusion. Extensive experimental results show that our MSDA-Net achieves state-of-the-art (SOTA) results on multiple public datasets. The code can be available at https://github.com/YuChuang1205/MSDA-Net