Infrared small target detection has long faced significant challenges due to the extremely small size of targets, low contrast, and the scarcity of annotated data. To tackle these issues, we propose a wavelet-recalibrated semi-supervised network (WRSSNet) that integrates synthetic data augmentation, feature reconstruction, and semi-supervised learning, aiming to fully exploit the potential of unlabeled infrared images under limited supervision. We construct a dataset containing 843 visible-light small target images and employ an improved CycleGAN model to convert them into high-quality pseudo-infrared images, effectively expanding the scale of training data for infrared small target detection. In addition, we design a lightweight wavelet-enhanced channel recalibration and fusion (WECRF) module, which integrates wavelet decomposition with both channel and spatial attention mechanisms. This module enables adaptive reweighting and efficient fusion of multi-scale features, highlighting high-frequency details and weak target responses. Extensive experiments on two public infrared small target datasets, NUAA-SIRST and IRSTD-1K, demonstrate that WRSSNet achieves superior detection accuracy and lower false alarm rates compared to several state-of-the-art methods, while maintaining low computational complexity.

Infrared small target detection remains a challenging task due to the inherent limitations of complex backgrounds and the absence of distinct target features. To address these challenges, we propose a Dual-Focus Residual Tensor Enhancement Network (DRTENet) which integrates edge enhancement and noise suppression. We propose a residual tensor weighting module (RTWM) that computes the local structure tensors to yield edge-saliency maps and integrates a residual learning strategy to preserve target contours and suppress background clutters. Based on the RTWM, we construct a Gaussian pyramid encoder to excavate multi-scale edge features and smooth point noise. Furthermore, we propose a dual-focus optimization module that designs a two-branch structure to enhance small targets powered by local semantic content, while simultaneously reducing background noise through global contextual information. Extensive experiments on several public infrared datasets demonstrate the effectiveness of DRTENet, achieving state-of-the-art detection performance. The source code is publicly available at: https://github.com/MJW66/DRTENet.