Distribution-Aware Infrared Small Target Detection Based on Multiscale Convolutional Decoder and Hypergraph Attention

Infrared Small Target Detection has advanced substantially with the rapid progress of deep learning, yet prevailing approaches—predominantly based on local convolution or attention-driven feature enhancement—remain inadequate for modeling high-order correlations among multi-scale features, thereby leading to persistent false alarms and missed detections under complex backgrounds and low Signal-to Noise Ratio (SNR) conditions. To overcome these limitations, we present an Infrared Small Target Detection network that couples a Multi-Scale Convolutional Decoder (MSCD) with a Hypergraph Attention (HA) mechanism and introduces a Distribution-aware Pixelwise Wasserstein Loss (DPWL) to jointly enforce scale, positional, and distributional consistency. Concretely, MSCD aggregates cross-layer representations through multi–receptive-field convolutional structures to preserve fine-grained target details and amplify saliency; HA employs learnable soft hyperedges to capture high-order dependencies across channel and spatial dimensions, suppressing background interference via global contextual reasoning; and DPWL injects a distribution-consistency constraint into the optimization process to enhance convergence robustness and localization accuracy in SNR condition scenarios. Extensive experiments on four datasets (IRSTD-1k, NUDT-SIRST, DenseSIRST, and NUAA-SIRST) demonstrate consistent gains over state-of-the-art methods across all metrics, namelyIoU, Pd, andFa. Specifically, the proposed model attains an impressive average performance of 75.89% inIoU, 96.70% inPd, and 8.67×10−6inFaacross these evaluation benchmarks. Finally, a comprehensive ablation study corroborates the effectiveness and complementary roles of the three core components.