清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

Detecting floating litter in freshwater bodies with semi-supervised deep learning

垃圾箱 环境科学 深水 人工智能 水文学(农业) 地质学 海洋学 计算机科学 生态学 生物 岩土工程
作者
Tianlong Jia,Rinze de Vries,Zoran Kapelan,Tim van Emmerik,Riccardo Taormina
出处
期刊:Water Research [Elsevier BV]
卷期号:266: 122405-122405
标识
DOI:10.1016/j.watres.2024.122405
摘要

Researchers and practitioners have extensively utilized supervised Deep Learning methods to quantify floating litter in rivers and canals. These methods require the availability of large amount of labeled data for training. The labeling work is expensive and laborious, resulting in small open datasets available in the field compared to the comprehensive datasets for computer vision, e.g., ImageNet. Fine-tuning models pre-trained on these larger datasets helps improve litter detection performances and reduces data requirements. Yet, the effectiveness of using features learned from generic datasets is limited in large-scale monitoring, where automated detection must adapt across different locations, environmental conditions, and sensor settings. To address this issue, we propose a two-stage semi-supervised learning method to detect floating litter based on the Swapping Assignments between multiple Views of the same image (SwAV). SwAV is a self-supervised learning approach that learns the underlying feature representation from unlabeled data. In the first stage, we used SwAV to pre-train a ResNet50 backbone architecture on about 100k unlabeled images. In the second stage, we added new layers to the pre-trained ResNet50 to create a Faster R-CNN architecture, and fine-tuned it with a limited number of labeled images (≈1.8k images with 2.6k annotated litter items). We developed and validated our semi-supervised floating litter detection methodology for images collected in canals and waterways of Delft (the Netherlands) and Jakarta (Indonesia). We tested for out-of-domain generalization performances in a zero-shot fashion using additional data from Ho Chi Minh City (Vietnam), Amsterdam and Groningen (the Netherlands). We benchmarked our results against the same Faster R-CNN architecture trained via supervised learning alone by fine-tuning ImageNet pre-trained weights. The findings indicate that the semi-supervised learning method matches or surpasses the supervised learning benchmark when tested on new images from the same training locations. We measured better performances when little data (≈200 images with about 300 annotated litter items) is available for fine-tuning and with respect to reducing false positive predictions. More importantly, the proposed approach demonstrates clear superiority for generalization on the unseen locations, with improvements in average precision of up to 12.7%. We attribute this superior performance to the more effective high-level feature extraction from SwAV pre-training from relevant unlabeled images. Our findings highlight a promising direction to leverage semi-supervised learning for developing foundational models, which have revolutionized artificial intelligence applications in most fields. By scaling our proposed approach with more data and compute, we can make significant strides in monitoring to address the global challenge of litter pollution in water bodies.
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
XIA完成签到 ,获得积分10
8秒前
喜悦的香之完成签到 ,获得积分10
13秒前
嘻嘻哈哈啊完成签到 ,获得积分10
15秒前
科研佟完成签到 ,获得积分10
29秒前
Skywalk满天星完成签到,获得积分10
30秒前
心想事成完成签到 ,获得积分10
31秒前
Lny发布了新的文献求助10
45秒前
通科研完成签到 ,获得积分10
52秒前
在水一方应助飞翔的企鹅采纳,获得10
1分钟前
creep2020完成签到,获得积分10
1分钟前
小二郎应助科研通管家采纳,获得10
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
少年完成签到,获得积分10
1分钟前
liuzhigang完成签到 ,获得积分10
1分钟前
2分钟前
2分钟前
榆木小鸟完成签到 ,获得积分10
2分钟前
雪流星完成签到 ,获得积分10
2分钟前
科研通AI2S应助科研通管家采纳,获得10
3分钟前
3分钟前
蒙面侠完成签到 ,获得积分10
3分钟前
CC发布了新的文献求助10
3分钟前
哈哈哈完成签到 ,获得积分10
3分钟前
王世卉完成签到,获得积分10
3分钟前
ccyy完成签到 ,获得积分10
3分钟前
3120221053完成签到,获得积分10
3分钟前
是玥玥啊完成签到 ,获得积分10
3分钟前
小新小新完成签到 ,获得积分10
4分钟前
Qvby3完成签到 ,获得积分10
4分钟前
英姑应助ceeray23采纳,获得20
4分钟前
imica完成签到 ,获得积分10
4分钟前
bkagyin应助ceeray23采纳,获得20
4分钟前
Ralph完成签到,获得积分10
4分钟前
科研搬运工完成签到,获得积分0
4分钟前
binbinbin发布了新的文献求助20
5分钟前
binbinbin完成签到,获得积分20
5分钟前
cy完成签到,获得积分10
5分钟前
满意的伊完成签到,获得积分10
6分钟前
6分钟前
John完成签到 ,获得积分10
6分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3990568
求助须知:如何正确求助?哪些是违规求助? 3532220
关于积分的说明 11256532
捐赠科研通 3271057
什么是DOI,文献DOI怎么找? 1805207
邀请新用户注册赠送积分活动 882302
科研通“疑难数据库(出版商)”最低求助积分说明 809234