Li, Xiangtai, Zhang, Jiangning, Yang, Yibo, Cheng, Guangliang 
ORCID: 0000-0001-8686-9513, Yang, Kuiyuan, Tong, Yunhai and Tao, Dacheng
(2024)
Sfnet: Faster and Accurate Semantic Segmentation Via Semantic Flow.
International Journal of Computer Vision, 132 (2).
pp. 466-489.
|
Text
_IJCV_2023__SFNet_ECCV_Extension.pdf - Author Accepted Manuscript Available under License Creative Commons Attribution. Download (5MB) | Preview |
Abstract
<jats:title>Abstract</jats:title><jats:p>In this paper, we focus on exploring effective methods for faster and accurate semantic segmentation. A common practice to improve the performance is to attain high-resolution feature maps with strong semantic representation. Two strategies are widely used: atrous convolutions and feature pyramid fusion, while both are either computationally intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn <jats:italic>Semantic Flow</jats:italic> between feature maps of adjacent levels and broadcast high-level features to high-resolution features effectively and efficiently. Furthermore, integrating our FAM to a standard feature pyramid structure exhibits superior performance over other real-time methods, even on lightweight backbone networks, such as ResNet-18 and DFNet. Then to further speed up the inference procedure, we also present a novel Gated Dual Flow Alignment Module to directly align high-resolution feature maps and low-resolution feature maps where we term the improved version network as SFNet-Lite. Extensive experiments are conducted on several challenging datasets, where results show the effectiveness of both SFNet and SFNet-Lite. In particular, when using Cityscapes test set, the SFNet-Lite series achieve 80.1 mIoU while running at 60 FPS using ResNet-18 backbone and 78.8 mIoU while running at 120 FPS using STDC backbone on RTX-3090. Moreover, we unify four challenging driving datasets (i.e., Cityscapes, Mapillary, IDD, and BDD) into one large dataset, which we named Unified Driving Segmentation (UDS) dataset. It contains diverse domain and style information. We benchmark several representative works on UDS. Both SFNet and SFNet-Lite still achieve the best speed and accuracy trade-off on UDS, which serves as a strong baseline in such a challenging setting. The code and models are publicly available at <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/lxtGH/SFSegNets">https://github.com/lxtGH/SFSegNets</jats:ext-link>.</jats:p>
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Bioengineering |
| Divisions: | Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 04 Oct 2023 08:05 |
| Last Modified: | 17 Mar 2024 18:35 |
| DOI: | 10.1007/s11263-023-01875-x |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3173405 |
Dimensions
Dimensions
