DNS: A multi-scale deconvolution semantic segmentation network for joint detection and segmentation

¹ School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China
² School of Electronic Engineering and Computer Science, Queen Mary, University of London, London, E1 4NS, UK
³ School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China
⁴ School of Computer Science, Chengdu University of Information Technology, Chengdu, 610103, China
⁵ School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China

^* Corresponding author: ledong@uestc.edu.cn

Abstract

Real-time semantic segmentation has become crucial in many applications such as medical image analysis and autonomous driving. In this paper, we introduce a single semantic segmentation network, called DNS, for joint object detection and segmentation task. We take advantage of multi-scale deconvolution mechanism to perform real time computations. To this goal, down-scale and up-scale streams are utilized to combine the multi-scale features for the final detection and segmentation task. By using the proposed DNS, not only the tradeoff between accuracy and cost but also the balance of detection and segmentation performance are settled. Experimental results for PASCAL VOC datasets show competitive performance for joint object detection and segmentation task.