ILNet: Low-Level Matters for Salient Infrared Small Target Detection

Haoqing Li, Jinfu Yang, Runshi Wang, Yifei Xu

Abstract: Infrared small target detection is a technique for finding small targets from infrared clutter background. Previous deep-learning-based approaches have achieved promising results. However, the lack of high-level semantic information leads to a degradation of small infrared target features in the deeper layers of the neural network, resulting in suboptimal representation capabilities. To address this issue, we propose an infrared low-level network (ILNet) that conceptualizes infrared small targets as salient regions characterized by limited semantic information. In contrast to other state-of-the-art methods, ILNet emphasizes low-level information more significantly, rather than treating it uniformly with high-level information. A lightweight feature fusion module, named the interactive polarized orthogonal fusion module (IPOF), is proposed, which integrates more important low-level features from the shallow layers into the deep layers. A dynamic 1-D aggregation layers are inserted into the IPOF, to dynamically adjust the aggregation of low-dimensional information according to the number of input channels. In addition, the idea of ensemble learning is used to design a representative block to dynamically allocate weights for shallow and deep layers. Experimental results on the challenging NUAA-SIRST (78.22% nIoU and 1.33 × 10$^{-6}$ Fa) and IRSTD-1k (68.91% nIoU and 3.23 × 10$^{-6}$Fa) datasets demonstrate that the proposed ILNet can get better performances than other state-of-the-art methods. Moreover, ILNet can obtain a greater improvement with the increase of data volume.

External IDs:dblp:journals/taes/LiYWX25