摘要
Object detection, the important task in computer vision, is widely used in face recognition and unmanned drive. Based on VGG161, a fast and simple backbone comparing to deeper network, this paper proposes a new block, named Modify Feature Map (MFM) Block, to improve feature maps, leading from two facts: different channel in the feature map represents different feature in an image; every position in a feature map belong to the object or background. We establish MFM Net to predict location and classification. Some experiments on Pascal VOC 2007 and MS COCO show that MFM Net can achieve high performance with real-time speed.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | 2019 International Conference on Image and Video Processing, and Artificial Intelligence |
| 编辑 | Ruidan Su |
| 出版商 | SPIE |
| ISBN（电子版） | 9781510634091 |
| DOI | |
| 出版状态 | 已出版 - 2019 |
| 活动 | 2019 2nd International Conference on Image and Video Processing, and Artificial Intelligence, IVPAI 2019 - Shanghai, 中国 期限: 23 8月 2019 → 25 8月 2019 |
出版系列
| 姓名 | Proceedings of SPIE - The International Society for Optical Engineering |
|---|---|
| 卷 | 11321 |
| ISSN（印刷版） | 0277-786X |
| ISSN（电子版） | 1996-756X |
会议
| 会议 | 2019 2nd International Conference on Image and Video Processing, and Artificial Intelligence, IVPAI 2019 |
|---|---|
| 国家/地区 | 中国 |
| 市 | Shanghai |
| 时期 | 23/08/19 → 25/08/19 |
指纹
探究 'MFM Net: Modify feature map for object detection' 的科研主题。它们共同构成独一无二的指纹。引用此
Qin, J., Jin, W., Qiu, S., & Li, L. (2019). MFM Net: Modify feature map for object detection. 在 R. Su (编辑), 2019 International Conference on Image and Video Processing, and Artificial Intelligence 文章 113211J (Proceedings of SPIE - The International Society for Optical Engineering; 卷 11321). SPIE. https://doi.org/10.1117/12.2548140