Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Frontiers of Information Technology & Electronic Engineering >> 2020, Volume 21, Issue 12 doi: 10.1631/FITEE.1900697

SPSSNet: a real-time network for image semantic segmentation

Affiliation(s): School of Computer Science and Engineering, Nanjing University of Science & Technology, Nanjing 210094, China; AInnovation, Beijing 100080, China; less

Received:2019-12-14 Accepted: 2020-12-10 Available online:2020-12-10

Next Previous


Although deep neural networks (DNNs) have achieved great success in semantic segmentation tasks, it is still challenging for real-time applications. A large number of feature channels, parameters, and floating-point operations make the network sluggish and computationally heavy, which is not desirable for real-time tasks such as robotics and autonomous driving. Most approaches, however, usually sacrifice spatial resolution to achieve inference speed in real time, resulting in poor performance. In this paper, we propose a light-weight semantic segmentation network (SPSSN), which can efficiently reuse the paramount features from early layers at multiple stages, at different spatial resolutions. SPSSN takes input of full resolution 2048×1024 pixels, uses only 1.42×10 parameters, yields 69.4% mIoU accuracy without pre-training, and obtains an inference speed of 59 frames/s on the Cityscapes dataset. SPSSN can run directly on mobile devices in real time, due to its light-weight architecture. To demonstrate the effectiveness of the proposed network, we compare our results with those of state-of-the-art networks.

Related Research