MSAFFNet: A Multiscale Label-Supervised Attention Feature Fusion Network for Infrared Small Target Detection

The detection of small infrared targets with low signal-to-noise ratios (SNRs) and contrasts in noisy and cluttered backgrounds is challenging and therefore a domain of active research. Traditional methods result in a large number of false alarms and missed detections. In the case of convolutional neural network (CNN)-based methods, it may not be possible to identify deep small targets or the details of the target’s edge contours may not be appropriately considered. Therefore, this article proposes MSAFFNet to perform infrared small target detection (IRSTD) based on an encoder–decoder framework. In the encoder stage, small target features are extracted using a resnet-20 backbone network, and the global contextual features of small targets are extracted using an atrous spatial pyramid pooling module (ASPPM). In the decoding stage, a dual-attention module (DAM) is used to selectively enhance the spatial details of the target at the shallow level and representative features of the semantic information at the deep level. Multiscale feature maps are then concatenated to achieve superior feature fusion. Additionally, multiscale labels are constructed to focus on the details of the target contour and internal features based on edge information and an internal feature aggregation module (EIFAM). Experiments conducted on the nanjing university of aeronautics and astronautics-single-frame infrared small target (NUAA-SIRST), national university of defense technology- SIRST (NUDT-SIRST), and xidian university-SIRST (XDU-SIRST) datasets revealed that the proposed approach outperforms the representative methods and achieves an improved detection performance.