DRNet: Dual-stage refinement network with boundary inference for RGB-D semantic segmentation of indoor scenes

计算机科学 人工智能 分割 模式识别(心理学) 尺度空间分割 图像分割 基于分割的对象分类 增采样 卷积神经网络 推论 计算机视觉 图像(数学)
作者
Enquan Yang,Wujie Zhou,Xiaohong Qian,Jingsheng Lei,Lu Yu
出处
期刊:Engineering Applications of Artificial Intelligence [Elsevier]
卷期号:125: 106729-106729 被引量:21
标识
DOI:10.1016/j.engappai.2023.106729
摘要

Semantic segmentation is a dense pixel prediction task, and its accuracy depends on the extraction of long-range contextual knowledge and refinement of segmentation boundaries. Most segmentation methods are based on feature extraction using a convolutional neural network, and layer-by-layer sampling and fusion are applied to solve inherent problems such as chaotic boundaries and scattered objects. Owing to the limited receptive field and loss of details during downsampling, the segmentation results may be unsatisfactory. To address existing shortcomings, we propose a dual-stage refinement network (DRNet) for semantic segmentation. In the first stage, we adopt an efficient spatiotemporal representation learning framework called UniFormer. We also use a novel boundary extractor and initial segmentation map generator to obtain rough segmentation results. In the second stage, we use the rough segmentation map and extracted boundary information in a graph reasoning module that restores the class boundary features while completing global modeling and local information inference. Benefiting from the acquisition of long-range dependencies between image pixels, contextual information promotes the distinction of pixel categories. In addition, edge information can increase the interclass distinguishability and refine the segmentation boundaries. Results from extensive experiments demonstrate that the proposed DRNet outperforms state-of-the-art semantic segmentation methods. The codes and results are available at: https://github.com/EnquanYang2022/DRNet.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
好了没了完成签到,获得积分10
1秒前
2秒前
zhuhaishan完成签到,获得积分10
4秒前
qqa完成签到,获得积分10
5秒前
河南老友发布了新的文献求助10
6秒前
脑洞疼应助林夏采纳,获得10
9秒前
树池应助林夏采纳,获得10
9秒前
小鱼儿发布了新的文献求助10
11秒前
贝贝完成签到 ,获得积分10
11秒前
11秒前
xv完成签到,获得积分10
15秒前
guo发布了新的文献求助10
17秒前
17秒前
朱冰蓝完成签到 ,获得积分10
18秒前
NIHAO完成签到 ,获得积分10
19秒前
hyw010724完成签到,获得积分20
21秒前
千纸鹤完成签到,获得积分10
22秒前
仁爱听露完成签到 ,获得积分10
23秒前
KKKZ完成签到,获得积分10
24秒前
小鱼儿完成签到,获得积分10
24秒前
hyw010724发布了新的文献求助10
24秒前
26秒前
CipherSage应助guo采纳,获得10
28秒前
小二郎应助瑾玉采纳,获得10
29秒前
Christine完成签到 ,获得积分20
31秒前
领导范儿应助zly采纳,获得10
31秒前
是微微完成签到,获得积分10
31秒前
Akim应助hyw010724采纳,获得10
33秒前
Orange应助从容的白竹采纳,获得10
34秒前
37秒前
sun完成签到,获得积分10
37秒前
37秒前
38秒前
cctv18应助嘻嘻采纳,获得10
38秒前
热心的思天完成签到,获得积分10
39秒前
40秒前
安静幻枫应助Hongni采纳,获得20
41秒前
珍珠发布了新的文献求助10
43秒前
穆紫应助热心的思天采纳,获得10
44秒前
Logan发布了新的文献求助10
44秒前
高分求助中
Sustainability in Tides Chemistry 1500
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 799
Livre et militantisme : La Cité éditeur 1958-1967 500
Retention of title in secured transactions law from a creditor's perspective: A comparative analysis of selected (non-)functional approaches 500
"Sixth plenary session of the Eighth Central Committee of the Communist Party of China" 400
Introduction to Modern Controls, with illustrations in MATLAB and Python 310
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3057308
求助须知:如何正确求助?哪些是违规求助? 2713802
关于积分的说明 7437402
捐赠科研通 2358921
什么是DOI,文献DOI怎么找? 1249607
科研通“疑难数据库(出版商)”最低求助积分说明 607190
版权声明 596314