Dense Dual-Path Network for Real-time Semantic Segmentation

TL;DR

This paper introduces DDPNet, a lightweight dense dual-path network designed for real-time semantic segmentation that balances high accuracy with fast inference on resource-limited devices.

Contribution

The paper presents a novel Dense Dual-Path Network architecture with dense connectivity and dual-path modules for efficient multi-scale feature aggregation in real-time segmentation.

Findings

Achieves 75.3% mIoU on Cityscapes with 52.6 FPS

Uses fewer parameters than comparable methods

Balances accuracy and speed effectively

Abstract

Semantic segmentation has achieved remarkable results with high computational cost and a large number of parameters. However, real-world applications require efficient inference speed on embedded devices. Most previous works address the challenge by reducing depth, width and layer capacity of network, which leads to poor performance. In this paper, we introduce a novel Dense Dual-Path Network (DDPNet) for real-time semantic segmentation under resource constraints. We design a light-weight and powerful backbone with dense connectivity to facilitate feature reuse throughout the whole network and the proposed Dual-Path module (DPM) to sufficiently aggregate multi-scale contexts. Meanwhile, a simple and effective framework is built with a skip architecture utilizing the high-resolution feature maps to refine the segmentation output and an upsampling module leveraging context information from the feature maps to refine the heatmaps. The proposed DDPNet shows an obvious advantage in balancing accuracy and speed. Specifically, on Cityscapes test dataset, DDPNet achieves 75.3% mIoU with 52.6 FPS for an input of 1024 X 2048 resolution on a single GTX 1080Ti card. Compared with other state-of-the-art methods, DDPNet achieves a significant better accuracy with a comparable speed and fewer parameters.