BPR-Net: Balancing Precision and Recall for Infrared Small Target Detection

Most current infrared small target detection methods attempt to fuse local and global information by using single-scale inputs and creating a multiscale feature pyramid during network feeding forward. Further to this, our research finds that using high-resolution inputs can improve recall, while low-resolution inputs improve precision. Nevertheless, solely focusing on global or local information can result in missing targets and false alarms. To address these issues, we propose the BPR-Net to balance precision and recall via a novel multiscale attention mechanism, which combines semantic and shallow features of multiscale inputs (MS). We first scale the input image into multiple images with varying resolutions and feed them into the network. In the encoder, the scale fusion module (SFM) fuses features from corresponding images of different resolutions. In the decoder, a channel fusion module (CFM) fuses useful information from multiple channels. Furthermore, a wavelet transform cross-layer skip layer (WTL) is employed to enhance the interaction between decoder layers for more effective multiscale feature fusion. Experimental results demonstrate that our approach achieves a balance between recall and precision and yields state-of-the-art performance on challenging benchmarks including Sirst, miss detection versus false alarm (MDvsFA), and small infrared aerial target detection (SIATD). Notably, our approach achieves an F1 score of 0.9409 on the challenging benchmark SIATD, surpassing the state-of-the-art method by 16.7%.