SegNetr：重新思考U型网络中的局部-全局交互与跳跃连接
SegNetr: Rethinking the local-global interactions and skip connections in U-shaped networks
AI总结：
针对现有U型医学图像分割网络自注意力模块复杂度高、编码器解码器特征融合忽略空间关联的问题，提出轻量网络SegNetr，含线性复杂度的局部-全局交互模块和信息保留跳跃连接，在参数量和计算量大幅降低的同时达到最优性能，且组件可迁移。
摘要：
近年来，U型网络凭借其结构简单、易于调优的特点，在医学图像分割领域占据主导地位。然而，现有U型分割网络存在两个问题：1）大多聚焦于设计复杂的自注意力模块，以弥补卷积操作缺乏长距离依赖的不足，这增加了网络的整体参数量与计算复杂度；2）仅简单融合编码器与解码器的特征，忽略了二者空间位置之间的关联。本文针对上述问题进行重新思考，构建了一个名为SegNetr的轻量级医学图像分割网络。具体而言，我们提出了一种新颖的SegNetr模块，它能在任意阶段动态进行局部-全局交互，且仅具有线性复杂度。同时，我们设计了一种通用的信息保留跳跃连接（IRSC），用于保留编码器特征的空间位置信息，实现与解码器特征的精准融合。我们在四个主流医学图像分割数据集上验证了SegNetr的有效性，其参数量和GFLOPs比原始U-Net分别减少59%和76%，同时取得了与当前最优方法相当的分割性能。值得注意的是，本文提出的组件可应用于其他U型网络，以提升其分割性能。
英文摘要：
Recently, U-shaped networks have dominated the field of medical image segmentation due to their simple and easily tuned structure. However, existing U-shaped segmentation networks: 1) mostly focus on designing complex self-attention modules to compensate for the lack of long-term dependence based on convolution operation, which increases the overall number of parameters and computational complexity of the network; 2) simply fuse the features of encoder and decoder, ignoring the connection between their spatial locations. In this paper, we rethink the above problem and build a lightweight medical image segmentation network, called SegNetr. Specifically, we introduce a novel SegNetr block that can perform local-global interactions dynamically at any stage and with only linear complexity. At the same time, we design a general information retention skip connection (IRSC) to preserve the spatial location information of encoder features and achieve accurate fusion with the decoder features. We validate the effectiveness of SegNetr on four mainstream medical image segmentation datasets, with 59\% and 76\% fewer parameters and GFLOPs than vanilla U-Net, while achieving segmentation performance comparable to state-of-the-art methods. Notably, the components proposed in this paper can be applied to other U-shaped networks to improve their segmentation performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
