论文标题
UIU-net：U-NET中的U-NET用于红外小物体检测
UIU-Net: U-Net in U-Net for Infrared Small Object Detection
论文作者
论文摘要
目前，基于学习的红外对象检测方法严重依赖分类骨干网络。随着网络深度的增加，这往往会导致微小的对象丢失，并具有区分性限制。此外，红外图像中的小物体经常出现明亮和黑暗，对获得精确的物体对比度信息提出了严重的要求。因此，我们在本文中提出了一个简单有效的``u-net''框架，简称UIU-net，并在红外图像中检测小对象。顾名思义，UIU-NET将一个小的U-NET嵌入了较大的U-NET主链中，从而使对象的多级和多尺度表示。此外，可以从头开始训练UIU-NET，并且学习的功能可以有效地增强全球和本地对比信息。更具体地说，UIU-NET模型分为两个模块：分辨率维护深度监督（RM-DS）模块和交互式跨性别（IC-A）模块。 RM-DS将残留U块集成到深度监督网络中，以在学习全球上下文信息的同时生成深层的多尺度分辨率维护特征。此外，IC-A还编码低级细节和高级语义功能之间的本地上下文信息。在两个红外单帧图像数据集（即SIRST和合成数据集）上进行的广泛实验显示了所提出的UIU-NET的有效性和优势，与几种先进的红外小型对象检测方法相比。提出的UIU-NET还为视频序列红外小对象数据集（例如ATR接地/空气视频序列数据集）产生强大的概括性能。这项工作的代码可在\ url {https://github.com/danfenghong/ieee_tip_uiu-net}中公开获得。
Learning-based infrared small object detection methods currently rely heavily on the classification backbone network. This tends to result in tiny object loss and feature distinguishability limitations as the network depth increases. Furthermore, small objects in infrared images are frequently emerged bright and dark, posing severe demands for obtaining precise object contrast information. For this reason, we in this paper propose a simple and effective ``U-Net in U-Net'' framework, UIU-Net for short, and detect small objects in infrared images. As the name suggests, UIU-Net embeds a tiny U-Net into a larger U-Net backbone, enabling the multi-level and multi-scale representation learning of objects. Moreover, UIU-Net can be trained from scratch, and the learned features can enhance global and local contrast information effectively. More specifically, the UIU-Net model is divided into two modules: the resolution-maintenance deep supervision (RM-DS) module and the interactive-cross attention (IC-A) module. RM-DS integrates Residual U-blocks into a deep supervision network to generate deep multi-scale resolution-maintenance features while learning global context information. Further, IC-A encodes the local context information between the low-level details and high-level semantic features. Extensive experiments conducted on two infrared single-frame image datasets, i.e., SIRST and Synthetic datasets, show the effectiveness and superiority of the proposed UIU-Net in comparison with several state-of-the-art infrared small object detection methods. The proposed UIU-Net also produces powerful generalization performance for video sequence infrared small object datasets, e.g., ATR ground/air video sequence dataset. The codes of this work are available openly at \url{https://github.com/danfenghong/IEEE_TIP_UIU-Net}.
