论文标题
GPU-NET：具有更多样化功能的轻质U-NET
GPU-Net: Lightweight U-Net with more diverse features
论文作者
论文摘要
图像分割是医学图像字段中的一项重要任务，已经提出了许多基于卷积的神经网络（CNN）方法，其中U-NET及其变体显示出有希望的性能。在本文中，我们提出了基于U-NET的GP模块和GPU-NET，通过引入幽灵模块和极端的空间金字塔池（ASPP），它可以学习更多多样化的功能（ASPP）。我们的方法可实现更好的性能，较少的参数少了4倍以上，而较少的拖鞋则提供了2倍，这为将来的研究提供了新的潜在方向。我们的插件模块也可以应用于现有的分割方法，以进一步提高其性能。
Image segmentation is an important task in the medical image field and many convolutional neural networks (CNNs) based methods have been proposed, among which U-Net and its variants show promising performance. In this paper, we propose GP-module and GPU-Net based on U-Net, which can learn more diverse features by introducing Ghost module and atrous spatial pyramid pooling (ASPP). Our method achieves better performance with more than 4 times fewer parameters and 2 times fewer FLOPs, which provides a new potential direction for future research. Our plug-and-play module can also be applied to existing segmentation methods to further improve their performance.
