题名 | Transformer-based Encoder-Decoder Model for Surface Defect Detection |
作者 | |
发表日期 | 2022-03-04 |
会议名称 | 6th International Conference on Innovation in Artificial Intelligence (ICIAI) |
会议录名称 | ACM International Conference Proceeding Series
![]() |
页码 | 125-130 |
会议日期 | MAR 04-06, 2022 |
会议地点 | ELECTR NETWORK |
摘要 | Recently, deep learning approaches have been gaining popularity in industrial quality control (e.g. surface defect detection), due to their ability for automatically extracting more representative features. In this paper, we propose a two-stage end-to-end approach through a Transformer-based encoder-decoder for surface defect detection. First, we develop a surface defect detection model to train the slicing of input raw images with the same final resolution of the input images and the output images, which better expands the perceptual field. After that, a 1×1 convolution layer is applied to its final layer, thus reducing the number of channels to obtain a single-channel output mask. Then, we combine this single-channel output mask with the output obtained from the last layer of the first stage as the input of the second stage decision layer. Considering different types of sample data, we design two different decision network strategies, namely: plain-up sampling and dynamic-up sampling. Our experimental studies on several publicly available datasets show that the proposed approach is general and effective in detecting defects, and we only need a relatively small number of samples to train the model, which has a good applicability in industrial practice where the sample size is normally limited. |
关键词 | deep learning industrial quality inspection surface anomaly detection transformer |
DOI | 10.1145/3529466.3529471 |
URL | 查看来源 |
收录类别 | CPCI-S |
语种 | 英语English |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods |
WOS记录号 | WOS:001117761800021 |
Scopus入藏号 | 2-s2.0-85131860717 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/13100 |
专题 | 个人在本单位外知识产出 理工科技学院 |
作者单位 | College of Computer Science and Technology,Huaqiao University,Xiamen,China |
推荐引用方式 GB/T 7714 | Lu, Xiaofeng,Fan, Wentao. Transformer-based Encoder-Decoder Model for Surface Defect Detection[C], 2022: 125-130. |
条目包含的文件 | 条目无相关文件。 |
个性服务 |
查看访问统计 |
谷歌学术 |
谷歌学术中相似的文章 |
[Lu, Xiaofeng]的文章 |
[Fan, Wentao]的文章 |
百度学术 |
百度学术中相似的文章 |
[Lu, Xiaofeng]的文章 |
[Fan, Wentao]的文章 |
必应学术 |
必应学术中相似的文章 |
[Lu, Xiaofeng]的文章 |
[Fan, Wentao]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论