State-of-the-art models for semantic segmentation are based on adaptations of
convolutional networks that had originally been designed for image
classification. However, dense prediction and image classification are
structurally different. In this work, we develop a new convolutional network
module that is specifically designed for dense prediction. The presented module
uses dilated convolutions to systematically aggregate multi-scale contextual
information without losing resolution. The architecture is based on the fact
that dilated convolutions support exponential expansion of the receptive field
without loss of resolution or coverage. We show that the presented context
module increases the accuracy of state-of-the-art semantic segmentation
systems. In addition, we examine the adaptation of image classification
networks to dense prediction and show that simplifying the adapted network can
increase accuracy.

本文提出了一种特别为密集预测设计的新的卷积网络模块，该模块利用扩张卷积系统地汇集多尺度上下文信息，而不会丢失分辨率，并证明了该模块可以提高现有最先进的语义分割系统的精度。同时，作者还探究了将图像分类网络适应于密集预测的可能性，并提出了简化适应后的网络结构有助于提高精度。