Pyramid cross attention network for pixel-wise surface defect detection

计算机科学 棱锥(几何) 人工智能 过程(计算) 编码器 噪音(视频) 像素 交叉口(航空) GSM演进的增强数据速率 面子(社会学概念) 特征(语言学) 分割 计算机视觉 模式识别(心理学) 图像(数学) 工程类 数学 操作系统 哲学 语言学 社会学 航空航天工程 社会科学 几何学
作者
Zihan Cheng,Haotian Sun,Yuzhu Cao,Weiwei Cao,Jingkun Wang,Gang Yuan,Jian Zheng
出处
期刊:NDT & E international [Elsevier BV]
卷期号:143: 103053-103053 被引量:2
标识
DOI:10.1016/j.ndteint.2024.103053
摘要

Surface defect detection plays a crucial role in improving the overall quality of industrial production processes and ensuring that the resulting products meet the required quality standards. However, detecting these defects can be challenging due to various issues, including low image contrast, significant background noise, variable defect scales, and blurred boundaries. Although several segmentation networks have been developed to address these challenges, they still face difficulties in preserving fine-grained details during the encoding process and maintaining global features during the decoding process. Moreover, the simple skip connection that combines global and local information for feature fusion fails to consider their discrepancies and varying levels of significance. To overcome these limitations, this paper proposes a Pyramid Cross Attention Network (PCANet) for pixel-level surface defect detection. The encoder extracts multiresolution features, and the pyramid adaptive selection module (PASM) is introduced to supplement lost information and adaptively select information based on its importance. Furthermore, the cross attention fusion module (CAFM) is designed to address the incompatibility between the features extracted by the encoder and decoder in the raw skip connection, while strengthening defect areas and suppressing irrelevant noise using cross attention mechanisms. Finally, extensive experimental results demonstrate that the proposed PCANet outperforms other state-of-the-art methods in terms of mean Intersection over Union (mIoU). Specifically, it achieves an mIoU of 84.57 % in NEU-Seg and 79.37 % in MT_defect, respectively.
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
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
Daphne完成签到,获得积分10
刚刚
刚刚
研友_VZG7GZ的应助被谢ber采纳,获得10
刚刚
FashionBoy的应助被HudsonWei采纳,获得10
刚刚
香蕉觅云的应助被HudsonWei采纳,获得10
1秒前
脑洞疼的应助被HudsonWei采纳,获得10
1秒前
ke完成签到,获得积分10
1秒前
NexusExplorer的应助被HudsonWei采纳,获得10
1秒前
行呀完成签到,获得积分10
1秒前
赘婿的应助被HudsonWei采纳,获得10
1秒前
Lucky0704发布了新的文献求助50
1秒前
Jasper的应助被HudsonWei采纳,获得10
2秒前
2秒前
gdh发布了新的文献求助10
2秒前
JamesPei的应助被SciKid524采纳,获得10
2秒前
molihuakai的应助被HudsonWei采纳,获得10
2秒前
不安的小刺猬完成签到,获得积分10
2秒前
2秒前
lr完成签到,获得积分10
3秒前
bkagyin的应助被Heyley采纳,获得10
3秒前
3秒前
luo完成签到,获得积分10
3秒前
4秒前
别让我讨厌你给别让我讨厌你的求助进行了留言
4秒前
gem关闭了gem的文献求助
4秒前
初初初啊发布了新的文献求助10
4秒前
4秒前
5秒前
NexusExplorer的应助被yx采纳,获得10
5秒前
5秒前
CipherSage的应助被专注的囧采纳,获得10
5秒前
5秒前
5秒前
5秒前
搜集达人的应助被缥缈一曲采纳,获得10
5秒前
卡西莫多完成签到,获得积分10
6秒前
angelalxj完成签到,获得积分10
6秒前
友好的天奇完成签到,获得积分10
6秒前
6秒前
凶狠的八宝粥完成签到,获得积分10
6秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Markov Decision Processes and Reinforcement Learning 700
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8170142
求助须知:如何正确求助?哪些是违规求助? 9563136
关于积分的说明 21768635
捐赠科研通 7761603
什么是DOI,文献DOI怎么找? 3430600
关于科研通互助平台的介绍 2554420
邀请新用户注册赠送积分活动 2475330