Semantic image segmentation plays a pivotal role in many vision applications
including autonomous driving and medical image analysis. Most of the former
approaches move towards enhancing the performance in terms of accuracy with a
little awareness of computational efficiency. In this paper, we introduce
LiteSeg, a lightweight architecture for semantic image segmentation. In this
work, we explore a new deeper version of Atrous Spatial Pyramid Pooling module
(ASPP) and apply short and long residual connections, and depthwise separable
convolution, resulting in a faster and efficient model. LiteSeg architecture is
introduced and tested with multiple backbone networks as Darknet19, MobileNet,
and ShuffleNet to provide multiple trade-offs between accuracy and
computational cost. The proposed model LiteSeg, with MobileNetV2 as a backbone
network, achieves an accuracy of 67.81% mean intersection over union at 161
frames per second with $640 \times 360$ resolution on the Cityscapes dataset.

本文介绍了一种适用于语义图像分割的轻型体系结构 LiteSeg , 该体系结构采用了深度可分离卷积技术和新型 Atrous Spatial Pyramid Pooling 模块，同时提高了计算效率和精度。使用 MobileNetV2 作为骨干网络时，LiteSeg 在 Cityscapes 数据集上以 $640 	imes 360$ 分辨率，每秒处理 161 帧的速度，实现了 67.81% 的平均交集联合值。