提出动态注意力网络，提升红外小目标检测精度
DATransNet: Dynamic Attention Transformer Network for Infrared Small Target Detection
- 用动态注意力机制模拟梯度提取，增强小目标特征
- 引入全局特征模块，避免忽略背景上下文信息
- 在复杂背景下显著提升小目标识别效果，适合军事与安防应用
红外小目标检测（ISTD）广泛应用于民用和军事领域。然而，由于小目标尺寸小、亮度低，易被复杂背景遮蔽，检测难度大。为此，我们提出动态注意力变换网络（DATransNet），旨在提取并保留对小目标至关重要的细节信息。DATransNet采用动态注意力变换器（DATrans），通过模拟中心差分卷积（CDC）来提取梯度特征。此外，我们设计了全局特征提取模块（GFEM），从整体视角提供信息，防止网络过度聚焦局部细节而忽略全局上下文。与当前最优方法对比，实验表明该方法具有优异性能。代码已开源：https://github.com/greekinRoma/DATransNet。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。