A 3D Shrinking-and-Expanding Module with Channel Attention for Efficient Deep Learning-Based Super-Resolution
A 3D Shrinking-and-Expanding Module with Channel Attention for Efficient Deep Learning-Based Super-Resolution
复制标题
DOI：
10.1007/978-981-15-5852-8_11
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Yinhao Li;Yutaro Iwamoto;Yenwei Chen
中科院分区：
文献类型：
--
作者：
Yinhao Li;Yutaro Iwamoto;Yenwei Chen
与传统的二维处理相比，医学体积数据的三维（3D）超分辨率（SR）被证实可以提供更好的视觉结果。然后，考虑到实际应用，我们提出了一种新的3D sr卷积神经网络。此外，为了减少模型参数并达到高精度，我们在映射前缩小输入特征维度，然后使用点向卷积扩展，从而重新制定了标准卷积层。因此，我们利用信道关注来优化网络以获得最佳性能。虽然所提出的架构可以嵌入到任何3D模型中，但它与最先进的模型3D残差密集网络（RDN）结合使用时性能更好。此外，我们证明了我们提出的方法在精度方面优于最先进的方法，只有大约1/8个参数和标准模型3D RDN的3/5倍。因此，我们的网络非常适合实际情况，如训练样本小，处理时间短，嵌入芯片。
The 3-dimensional (3D) super-resolution (SR) for medical volumetric data is confirmed to provide better visual results compared to conventional 2-dimensional processing. Then, considering practical applications, we propose a novel convolutional neural network for a 3D SR. Moreover, to reduce model parameters and achieve high precision, we reformulating the standard convolution layer by shrinking the input feature dimension before mapping and expanding back afterward using pointwise convolution. Thus, we utilize channel attention to optimize the network for optimum performance. Although the proposed architecture can be embedded into any 3D model, it performs better while combined with the state-of-the-art model, the 3D residual dense network (RDN). Furthermore, we demonstrate that our proposed method outperforms the state-of-the-art methods in terms of accuracy with only approximately 1/8 parameters and 3/5 times of the standard model, 3D RDN. Consequently, our network is quite suitable in practical situations, such as small training samples, short processing time, and being embedded into chips.