CSRNet : Cascaded Selective Resolution Network for real-time semantic segmentation
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 118537 |
Journal / Publication | Expert Systems with Applications |
Volume | 211 |
Online published | 17 Aug 2022 |
Publication status | Published - Jan 2023 |
Link(s)
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 well-known road scene datasets demonstrate that the proposed CSRNet outperforms the main-stream efficient semantic segmentation approaches by accuracy and can be performed at a fast inference speed.
Research Area(s)
- Attention mechanism, Deep neural networks, Real-time inference, Semantic segmentation
Citation Format(s)
CSRNet: Cascaded Selective Resolution Network for real-time semantic segmentation. / Xiong, Jingjing; Po, Lai-Man; Yu, Wing-Yin et al.
In: Expert Systems with Applications, Vol. 211, 118537, 01.2023.
In: Expert Systems with Applications, Vol. 211, 118537, 01.2023.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review