Difference Decomposition Networks for Infrared Small Target Detection

Chen Hu; Mingyu Zhou; Shuai Yuan; Zhenming Peng; Tian Pu; Xiyin Li

Paper

Difference Decomposition Networks for Infrared Small Target Detection

Abstract

Infrared small target detection (ISTD) faces two major challenges: a lack of discernible target texture and severe background clutter, which results in the background obscuring the target. To enhance targets and suppress backgrounds, we propose the Basis Decomposition Module (BDM) as an extensible and lightweight module based on basis decomposition, which decomposes a complex feature into several basis features and enhances certain information while eliminating redundancy. Extending BDM leads to a series of modules, including the Spatial Difference Decomposition Module (SD

M), Spatial Difference Decomposition Downsampling Module (SD

M), and Temporal Difference Decomposition Module (TD

M). Based on these modules, we develop the Spatial Difference Decomposition Network (SD

Net) for single-frame ISTD (SISTD) and the Spatiotemporal Difference Decomposition Network (STD

Net) for multi-frame ISTD (MISTD). SD

Net integrates SD

M and SD

M within an adapted U-shaped architecture. We employ TD

M to introduce motion information, which transforms SD

Net into STD

Net. Extensive experiments on SISTD and MISTD datasets demonstrate state-of-the-art (SOTA) performance. On the SISTD task, SD

Net performs well compared to most established networks. On the MISTD datasets, STD

Net achieves a mIoU of 87.68\%, outperforming SD

Net, which achieves a mIoU of 64.97\%. Our codes are available: https://github.com/greekinRoma/IRSTD_HC_Platform.