DSCSNet: A Dynamic Sparse Compression Sensing Network for Closely-Spaced Infrared Small Target Unmixing
This work addresses the challenge of accurately recovering individual infrared small targets in complex scenarios, which is critical for applications like surveillance and remote sensing, though it appears incremental by combining model-driven and data-driven approaches.
The paper tackles the ill-posed problem of unmixing closely-spaced infrared small targets from mixed spots by proposing DSCSNet, a deep-unfolded network that integrates ADMM with learnable parameters and a self-attention mechanism, achieving improved unmixing accuracy and generalization, as demonstrated by outperforming state-of-the-art methods on the CSIST-100K dataset in metrics like CSO-mAP and sub-pixel localization error.
Due to the limitations of optical lens focal length and detector resolution, distant clustered infrared small targets often appear as mixed spots. The Close Small Object Unmixing (CSOU) task aims to recover the number, sub-pixel positions, and radiant intensities of individual targets from these spots, which is a highly ill-posed inverse problem. Existing methods struggle to balance the rigorous sparsity guarantees of model-driven approaches and the dynamic scene adaptability of data-driven methods. To address this dilemma, this paper proposes a Dynamic Sparse Compressed Sensing Network (DSCSNet), a deep-unfolded network that couples the Alternating Direction Method of Multipliers (ADMM) with learnable parameters. Specifically, we embed a strict $\ell_1$-norm sparsity constraint into the auxiliary variable update step of ADMM to replace the traditional $\ell_2$-norm smoothness-promoting terms, which effectively preserves the discrete energy peaks of small targets. We also integrate a self-attention-based dynamic thresholding mechanism into the reconstruction stage, which adaptively adjusts the sparsification intensity using the sparsity-enhanced information from the iterative process. These modules are jointly optimized end-to-end across the three iterative steps of ADMM. Retaining the physical logic of compressed sensing, DSCSNet achieves robust sparsity induction and scene adaptability, thus enhancing the unmixing accuracy and generalization in complex infrared scenarios. Extensive experiments on the synthetic infrared dataset CSIST-100K demonstrate that DSCSNet outperforms state-of-the-art methods in key metrics such as CSO-mAP and sub-pixel localization error.