Knowledge Commons of Institute of Automation,CAS
MFFNet: Multi-Receptive Field Fusion Net for Microscope Steel Grain Grading | |
Sun JX(孙嘉玺)1,2![]() ![]() ![]() ![]() ![]() | |
2022 | |
会议名称 | ICCIP 2022: 2022 the 8th International Conference on Communication and Information Processin |
会议录名称 | 2022 the 8th International Conference on Communication and Information Processing |
页码 | 49–55 |
会议日期 | 2022年10月3-5日 |
会议地点 | 中国北京 |
摘要 | The grain size is an important steel grading parameter. For metallographic steel images with various grain sizes and complex textures, it is not possible for a human expert to determine the grain size efficiently. Meanwhile, conventional computer vision models are designed based on general images and they are not capable of achieving high performance in metallographic steel grain size recognition. To solve these problems, a method based on multiple receptive field fusion is proposed. A multi-scale convolutional net is used to extract information of microstructures in various scales. In addition, to augment the extracted features, a self-attention module is used to improve the robustness of feature representation with complex metallographic textures. At last, via a multiple feature fusion module, the data capacity is extended by projecting features into multiple hidden spaces. A comprehensive experiment was conducted on the Huawei Cloud Dataset and the classification accuracy was improved by 27% compared with other SOTA models, while our computation cost was only 0.06 GFLOPs |
关键词 | grain size metallographic steel images computer vision multiple receptive field convolutional kernel |
学科门类 | 工学 |
DOI | 10.1145/3571662.3571670 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 三维视觉 |
国重实验室规划方向分类 | 多尺度信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51580 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Xu SB(徐士彪) |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学人工智能学院 3.北京邮电大学人工智能学院 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Sun JX,Zhang JG,Xu SB,et al. MFFNet: Multi-Receptive Field Fusion Net for Microscope Steel Grain Grading[C],2022:49–55. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
3571662.3571670.pdf(1957KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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