XNet v2改进生物医学图像分割，提升低频高频信息融合效果。
XNet v2: Fewer Limitations, Better Results and Greater Universality
- 基于小波变换实现图像级互补融合，增强多尺度特征提取。
- 在半监督与全监督场景下均达到顶尖性能，优于原版XNet。
- 特别擅长原模型失效的弱高频信息图像，适用性更广。
XNet提出一种基于小波变换的X型统一架构，用于全监督和半监督生物医学图像分割。然而，现有XNet在缺乏高频信息的图像中性能下降，原始图像利用不充分，特征融合不足。为此，本文提出XNet v2，一种低频与高频互补模型。XNet v2采用小波变换进行图像级互补融合，将融合结果与原始图像输入三个子网络以构建一致性损失；同时引入特征级融合模块，强化低频与高频信息传递。XNet v2在半监督分割中达到当前最优，全监督表现也具竞争力。更重要的是，其在原XNet失效的场景中表现卓越。在三个2D和两个3D数据集上的大量实验验证了其有效性。代码已开源：https://github.com/Yanfeng-Zhou/XNetv2。
原文摘要 · Abstract (English)
XNet introduces a wavelet-based X-shaped unified architecture for fully- and semi-supervised biomedical segmentation. So far, however, XNet still faces the limitations, including performance degradation when images lack high-frequency (HF) information, underutilization of raw images and insufficient fusion. To address these issues, we propose XNet v2, a low- and high-frequency complementary model. XNet v2 performs wavelet-based image-level complementary fusion, using fusion results along with raw images inputs three different sub-networks to construct consistency loss. Furthermore, we introduce a feature-level fusion module to enhance the transfer of low-frequency (LF) information and HF information. XNet v2 achieves state-of-the-art in semi-supervised segmentation while maintaining competitve results in fully-supervised learning. More importantly, XNet v2 excels in scenarios where XNet fails. Compared to XNet, XNet v2 exhibits fewer limitations, better results and greater universality. Extensive experiments on three 2D and two 3D datasets demonstrate the effectiveness of XNet v2. Code is available at https://github.com/Yanfeng-Zhou/XNetv2 .
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。