CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation

TL;DR

CSRNet is a real-time semantic segmentation network that enhances feature aggregation and context embedding through a cascaded architecture, achieving better accuracy while maintaining efficiency for practical applications.

Contribution

The paper introduces CSRNet, a novel three-stage network with SPFM and SRM modules that improve multi-resolution feature fusion and context understanding in real-time segmentation.

Findings

Improves segmentation accuracy on benchmark datasets.

Enlarges receptive fields efficiently with SPFM.

Effectively fuses multi-resolution features with SRM.

Abstract

Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc. Existing real-time segmentation approaches often utilize feature fusion to improve segmentation accuracy. However, they fail to fully consider the feature information at different resolutions and the receptive fields of the networks are relatively limited, thereby compromising the performance. To tackle this problem, we propose a light Cascaded Selective Resolution Network (CSRNet) to improve the performance of real-time segmentation through multiple context information embedding and enhanced feature aggregation. The proposed network builds a three-stage segmentation system, which integrates feature information from low resolution to high resolution and achieves feature refinement progressively. CSRNet contains two critical modules: the Shorted Pyramid Fusion Module (SPFM) and the Selective Resolution Module (SRM). The SPFM is a computationally efficient module to incorporate the global context information and significantly enlarge the receptive field at each stage. The SRM is designed to fuse multi-resolution feature maps with various receptive fields, which assigns soft channel attentions across the feature maps and helps to remedy the problem caused by multi-scale objects. Comprehensive experiments on two well-known datasets demonstrate that the proposed CSRNet effectively improves the performance for real-time segmentation.