MPANet: Multi-Patch Attention For Infrared Small Target object Detection
This work addresses infrared small target detection for applications in fields like surveillance and remote sensing, representing an incremental improvement over existing CNN-based methods.
The paper tackles the problem of infrared small target detection (ISTD) by proposing MPANet, a multi-patch attention network that addresses limitations in CNNs, such as noise interference and inability to encode long-distance dependencies, resulting in superior performance on the SIRST dataset compared to state-of-the-art methods.
Infrared small target detection (ISTD) has attracted widespread attention and been applied in various fields. Due to the small size of infrared targets and the noise interference from complex backgrounds, the performance of ISTD using convolutional neural networks (CNNs) is restricted. Moreover, the constriant that long-distance dependent features can not be encoded by the vanilla CNNs also impairs the robustness of capturing targets' shapes and locations in complex scenarios. To this end, a multi-patch attention network (MPANet) based on the axial-attention encoder and the multi-scale patch branch (MSPB) structure is proposed. Specially, an axial-attention-improved encoder architecture is designed to highlight the effective features of small targets and suppress background noises. Furthermore, the developed MSPB structure fuses the coarse-grained and fine-grained features from different semantic scales. Extensive experiments on the SIRST dataset show the superiority performance and effectiveness of the proposed MPANet compared to the state-of-the-art methods.