Infrared small target detection (ISTD) is widely used in civilian and military applications. However, ISTD encounters several challenges, including the tendency for small and dim targets to be obscured by complex backgrounds. To address this issue, we propose the Dynamic Attention Transformer Network (DATransNet), which aims to extract and preserve detailed information vital for small targets. DATransNet employs the Dynamic Attention Transformer (DATrans), simulating central difference convolutions (CDC) to extract gradient features. Furthermore, we propose a global feature extraction module (GFEM) that offers a comprehensive perspective to prevent the network from focusing solely on details while neglecting the global information. We compare the network with state-of-the-art (SOTA) approaches and demonstrate that our method performs effectively. Our source code is available at https://github.com/greekinRoma/DATransNet.

Infrared ship detection (IRSD) is crucial for numerous applications but faces challenges, such as small targets and complex backgrounds, resulting in misdetections and false alarms. In order to address these challenges, we propose the scene semantic prior-assisted infrared ship detection using multitask perception network (SMPISD-MTPNet). This network employs multitask perception: one task is to predict targets, and the other focuses on scene perception to suppress false alarms caused by background interference. To highlight dim and small targets, we use the scene semantic extractor (SSE) to guide the network using features extracted based on expert knowledge and the gradient-based module to enhance the edge and point features. We apply data augmentation to the networks and employ a training trick called soft fine-tuning to improve the network’s generalization and suppress the distortion caused by the augmentation process. Due to the unavailability of datasets with appropriate scene labels for scene perception, we have developed a new dataset called the infrared ship dataset with scene segmentation (IRSDSS). In addition, we have enhanced an existing dataset by adding scene masks and created the enhanced infrared ship detection dataset (EISDD). Our evaluations using both IRSDSS and EISDD demonstrate that SMPISD-MTPNet exceeds contemporary state-of-the-art (SOTA) methods in accuracy. The source code and dataset for this research can be available at:https://github.com/greekinRoma/SMPISD-MTPNet.

Random features (Rahimi & Recht, 2007), based on Monte Carlo (MC) method, is one of the most popular approximation techniques to accelerate kernel methods. We show for a class of kernels, including Gaussian kernels, quasi-Monte Carlo (QMC) methods can be used in place of MC to improve the approximation error from $O_P(1/\sqrt{M})$ to $O(1/M)$ (up to logarithmic factors), for estimating both the kernel function itself and the associated integral operator, where $M$ is the number of features being used. Furthermore, we demonstrate the advantage of QMC features in the case of kernel ridge regression, where theoretically, fewer random features suffice to guarantee the same convergence rate of the excess risk. In practice, the QMC kernel approximation approach is easily implementable and shows superior performance, as supported by the empirical evidence provided in the paper.

Deep learning (DL) networks have achieved remarkable performance in infrared small target detection (ISTD). However, these structures exhibit a deficiency in interpretability and are widely regarded as black boxes, as they disregard domain knowledge in ISTD. To alleviate this issue, this work proposes an interpretable deep network for detecting infrared dim targets, dubbed RPCANet. Specifically, our approach formulates the ISTD task as sparse target extraction, low-rank background estimation, and image reconstruction in a relaxed Robust Principle Component Analysis (RPCA) model. By unfolding the iterative optimization updating steps into a deep-learning framework, time-consuming and complex matrix calculations are replaced by theory-guided neural networks. RPCANet detects targets with clear interpretability and preserves the intrinsic image feature, instead of directly transforming the detection task into a matrix decomposition problem. Extensive experiments substantiate the effectiveness of our deep unfolding framework and demonstrate its trustworthy results, surpassing baseline methods in both qualitative and quantitative evaluations. Our source code is available at https://github.com/fengyiwu98/RPCANet.