Sanet: Spatial Attention Network with Global Average Contrast Learning for Infrared Small Target Detection

Infrared small target detection has always been a challenging theme, due to small target size, unconspicuous contour and texture, even low vision contrast to background. Because of these causes, some popular object detection methods, such as Faster-RCNN and YOLOV, could often lose effectiveness. Aiming to promote the comprehensive performance of detection, this paper proposes a Spatial Attention Network (SANet) with global average contrast learning specially for infrared small target. Different from the other detection strategies by pixel-level segmentation, our scheme extends traditional contrast methods to target detection framework of deep learning, so as to achieve robust performance. In feature extraction, a group of cross stage partial networks (CSPNet) is designed to capture the local semantic information, and a cluster of spatial attention modules with global average contrast (SAG) is devised to obtain global spatial semantics. Moreover, a series of selective kernel convolution (SKConv) is adopted to effectively fuse semantic and spatial features. For robust feature representation, an Spatial Pyramid Pooling (SPP) scheme is utilized in our detection model. The experiments on two public datasets show that our detection model could often obviously outperform current state-of-the-art ones. The source code is available at https://github.com/UESTC-nnLab/SANet.