Learning High-Resolution representations is essential for semantic segmentation. Convolutional neural network (CNN)architectures with downstream and upstream propagation flow are popular for segmentation in medical diagnosis. However, due to performing spatial downsampling and upsampling in multiple stages, information loss is inexorable. On the contrary, connecting layers densely on high spatial resolution is computationally expensive. In this work, we devise a Loose Dense Connection Strategy to connect neurons in subsequent layers with reduced parameters. On top of that, using a m-way Tree structure for feature propagation we propose Receptive Field Chain Network (RFC-Net) that learns high resolution global features on a compressed computational space. Our experiments demonstrates that RFC-Net achieves state-of-the-art performance on Kvasir and CVC-ClinicDB benchmarks for Polyp segmentation.

翻译：学习高分辨率表示对语义分割至关重要。采用下游和上游传播流的卷积神经网络架构在医学诊断分割中较为常见。然而，由于在多阶段中进行空间下采样和上采样，信息损失不可避免。相反，在高空间分辨率上密集连接层则计算成本高昂。本文提出了一种松散密集连接策略，以减少后续层中神经元的参数连接。在此基础上，利用m路树结构进行特征传播，提出了感受野链网络（RFC-Net），使其能够在压缩的计算空间中学习高分辨率全局特征。实验表明，RFC-Net在Kvasir和CVC-ClinicDB数据集上的息肉分割任务中达到了最先进的性能。