Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation

TL;DR

This paper introduces a Boundary Corrected Multi-scale Fusion Network that balances high accuracy and real-time speed in semantic segmentation by using a novel fusion module and boundary correction loss.

Contribution

It proposes a new multi-scale fusion network with boundary correction loss to improve real-time semantic segmentation accuracy.

Findings

Achieves state-of-the-art accuracy-speed trade-off

Effective boundary error correction in low-resolution features

Outperforms existing methods in real-time segmentation tasks

Abstract

Image semantic segmentation aims at the pixel-level classification of images, which has requirements for both accuracy and speed in practical application. Existing semantic segmentation methods mainly rely on the high-resolution input to achieve high accuracy and do not meet the requirements of inference time. Although some methods focus on high-speed scene parsing with lightweight architectures, they can not fully mine semantic features under low computation with relatively low performance. To realize the real-time and high-precision segmentation, we propose a new method named Boundary Corrected Multi-scale Fusion Network, which uses the designed Low-resolution Multi-scale Fusion Module to extract semantic information. Moreover, to deal with boundary errors caused by low-resolution feature map fusion, we further design an additional Boundary Corrected Loss to constrain overly smooth features. Extensive experiments show that our method achieves a state-of-the-art balance of accuracy and speed for the real-time semantic segmentation.