The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low- and high-level convolutional features, resulting in not only blurred feature maps, but also over- and under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.

建立在全卷积网络之上的 U-Net 架构已被证明在生物医学图像分割中是有效的。然而，U-Net 应用跳过连接来合并语义不同的低级和高级卷积特征，不仅导致模糊的特征图，而且导致过度和欠分割的目标区域。为了解决这些限制，我们提出了一种简单而有效的端到端深度编码解码器全卷积网络架构，称为 Sharp U-Net，用于二进制和多类生物医学图像分割。Sharp U-Net 的关键原理是，在合并编码器和解码器特征之前，使用编码器特征图与锐化内核滤波器的深度卷积，而不是应用简单的跳过连接，从而产生与编码器图相同大小的锐化中间特征图。使用这个锐化过滤器层，我们不仅能够融合语义上不太相似的特征，而且能够在训练的早期阶段平滑整个网络层的伪影。我们在六个数据集上的大量实验表明，所提出的 Sharp U-Net 模型在二元和多类分割任务中始终优于或匹配最近最先进的基线，同时不添加额外的可学习参数。此外，Sharp U-Net 的性能优于可学习参数数量超过三倍的基线。还要在训练的早期阶段消除整个网络层中的伪影。我们在六个数据集上的大量实验表明，所提出的 Sharp U-Net 模型在二元和多类分割任务中始终优于或匹配最近最先进的基线，同时不添加额外的可学习参数。此外，Sharp U-Net 的性能优于可学习参数数量超过三倍的基线。还要在训练的早期阶段消除整个网络层中的伪影。我们在六个数据集上的大量实验表明，所提出的 Sharp U-Net 模型在二元和多类分割任务中始终优于或匹配最近最先进的基线，同时不添加额外的可学习参数。此外，Sharp U-Net 的性能优于可学习参数数量超过三倍的基线。