GPONet: A two-stream gated progressive optimization network for salient object detection

计算机科学 人工智能 突出 GSM演进的增强数据速率 模式识别(心理学) 特征(语言学) 像素 骨干网 计算机视觉 过程(计算) 计算机网络 哲学 语言学 操作系统
作者
Yugen Yi,Ningyi Zhang,Wei Zhou,Yanjiao Shi,Gengsheng Xie,Jianzhong Wang
出处
期刊:Pattern Recognition [Elsevier BV]
卷期号:150: 110330-110330 被引量:9
标识
DOI:10.1016/j.patcog.2024.110330
摘要

The salient object detection task is to locate and detect salient regions in images, which is widely applied in various fields. In this paper, we propose a gated progressive optimization network (GPONet) for salient object detection. Firstly, to extract salient regions more accurately, we design a multi-level feature fusion module with a gating mechanism named gate fusion network (GFN). GFN focuses on the semantic information of high-level features as well as the detailed information of low-level features, enabling purposeful delivery of high-level features to low-level features. The gate fusion unit (GFU) is also able to maintain valid information and suppress redundant information in the fusion process. Secondly, while some existing methods have shown that the additional edge supervision can facilitate salient object detection, edge pixels are often much less common than non-edge pixels, leading to the challenge of class imbalance. To overcome this issue, we introduce detail labels that provide additional internal details as a supplementary supervisory signal. Combining these labels with proposed Detail Perception Loss enables our network to learn edge information of salient objects more effectively. To complement each other and guide information exchange between the two branches, we propose a cross guide module (CGM) to control the information flow transfer between them. Finally, we develop a simple and efficient attention fusion strategy to merge the prediction maps of the two branches to generate the final salient prediction map. Extensive experimental results validate that our method reaches optimal or comparable performance on several mainstream datasets. The code of GPONet is available from https://github.com/antonie-z/GPONet
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
Lucas应助自由的凛采纳,获得10
刚刚
徐徐发布了新的文献求助10
刚刚
3秒前
Binbin发布了新的文献求助10
4秒前
科目三应助Li采纳,获得10
5秒前
6秒前
9秒前
summer 3575发布了新的文献求助10
9秒前
刘潮汕发布了新的文献求助10
11秒前
HIMINNN发布了新的文献求助10
11秒前
科研通AI5应助科研通管家采纳,获得10
12秒前
12秒前
12秒前
大模型应助科研通管家采纳,获得10
12秒前
Hello应助科研通管家采纳,获得10
12秒前
Advance.Cheng完成签到,获得积分10
12秒前
清爽乐菱应助科研通管家采纳,获得30
12秒前
汉堡包应助科研通管家采纳,获得10
12秒前
reirei应助科研通管家采纳,获得20
12秒前
CodeCraft应助科研通管家采纳,获得10
13秒前
13秒前
13秒前
likes完成签到,获得积分10
14秒前
科研通AI5应助黄憨憨采纳,获得10
14秒前
星辰大海应助Binbin采纳,获得10
16秒前
dreamy4869完成签到,获得积分10
16秒前
16秒前
汉堡包应助轻轻采纳,获得10
17秒前
勤奋高丽发布了新的文献求助10
17秒前
hhw发布了新的文献求助10
17秒前
19秒前
可爱的函函应助dreamy4869采纳,获得10
19秒前
HSA发布了新的文献求助10
20秒前
然大宝发布了新的文献求助10
21秒前
你好可爱完成签到,获得积分10
21秒前
111关注了科研通微信公众号
22秒前
CodeCraft应助勤奋高丽采纳,获得10
23秒前
loong发布了新的文献求助10
24秒前
orixero应助刘潮汕采纳,获得10
25秒前
烂漫平蓝关注了科研通微信公众号
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
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
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 3976253
求助须知:如何正确求助?哪些是违规求助? 3520405
关于积分的说明 11203301
捐赠科研通 3257028
什么是DOI,文献DOI怎么找? 1798589
邀请新用户注册赠送积分活动 877755
科研通“疑难数据库(出版商)”最低求助积分说明 806521