One Model Is Enough: Toward Multiclass Weakly Supervised Remote Sensing Image Semantic Segmentation

计算机科学 人工智能 分割 过度拟合 像素 图像分割 公制(单位) 模式识别(心理学) 计算机视觉 遥感 人工神经网络 地理 运营管理 经济
作者
Zhenshi Li,Xueliang Zhang,Pengfeng Xiao
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-13 被引量:14
标识
DOI:10.1109/tgrs.2023.3290242
摘要

Semantic segmentation of remote sensing images is effective for large-scale land cover mapping, which heavily relies on a large amount of training data with laborious pixel-level labeling. Weakly supervised semantic segmentation (WSSS) based on image-level labels has attracted intensive attention due to its easy availability. However, existing image-level WSSS methods for remote sensing images mainly focus on binary segmentation, which are difficult to apply to multiclass scenarios. This study proposes a comprehensive framework for image-level multiclass WSSS of remote sensing images, consisting of appropriate image-level label generation, high-quality pixel-level pseudo mask generation, and segmentation network iterative training. Specifically, a training sample filtering method, as well as a dataset cooccurrence evaluation metric, is proposed to demonstrate proper image-level training samples. Leveraging multiclass class activation maps, an uncertainty-driven pixel-level weighted mask is proposed to relieve the overfitting of labeling noise in pseudo masks when training the segmentation network. Extensive experiments demonstrate that the proposed framework can achieve high-quality multiclass WSSS performance with image-level labels, which can attain 94.23% and 90.77% of the IoUs from pixel-level labels for the ISPRS Potsdam and Vaihingen datasets, respectively. Beyond that, for the DeepGlobe dataset with more complex landscapes, the WSSS framework can achieve an accuracy close to 99% of the fully supervised case. Additionally, we further demonstrate that compared to adopting multiple binary WSSS models, directly training a multiclass WSSS model can achieve better results, which can provide new thoughts to achieve WSSS of remote sensing images for multiclass application scenarios. Our code is public at https://github.com/NJU-LHRS/OME.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
刚刚
隐形曼青应助魏开铭采纳,获得10
刚刚
烟花应助干净的涵山采纳,获得10
1秒前
羽生发布了新的文献求助10
1秒前
dudu完成签到,获得积分10
1秒前
1秒前
2秒前
2秒前
jiaru完成签到,获得积分10
2秒前
2秒前
英姑应助陌路孤星采纳,获得10
2秒前
俏皮念寒完成签到,获得积分10
3秒前
Aliothae发布了新的文献求助10
4秒前
傲娇完成签到,获得积分10
4秒前
量子星尘发布了新的文献求助10
4秒前
机智乐蕊完成签到,获得积分10
4秒前
Yeyuntian发布了新的文献求助10
5秒前
小二郎应助dudu采纳,获得10
6秒前
li发布了新的文献求助10
6秒前
6秒前
一介书生完成签到,获得积分10
6秒前
6秒前
俏皮念寒发布了新的文献求助10
6秒前
7秒前
hoshizora765完成签到 ,获得积分10
7秒前
完美世界应助zz采纳,获得10
7秒前
细心的飞荷完成签到,获得积分20
8秒前
善学以致用应助Aliothae采纳,获得10
8秒前
9秒前
10秒前
CodeCraft应助羽生采纳,获得10
10秒前
饱满以松发布了新的文献求助10
10秒前
11秒前
Yeyuntian完成签到,获得积分10
11秒前
12秒前
加电时间发布了新的文献求助10
12秒前
13秒前
KComboN发布了新的文献求助10
13秒前
ZZ发布了新的文献求助10
13秒前
FashionBoy应助清脆乌采纳,获得10
14秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3974882
求助须知:如何正确求助?哪些是违规求助? 3519431
关于积分的说明 11198315
捐赠科研通 3255698
什么是DOI,文献DOI怎么找? 1797904
邀请新用户注册赠送积分活动 877237
科研通“疑难数据库(出版商)”最低求助积分说明 806219