Knowledge Commons of Institute of Automation,CAS
COG: COnsistent data auGmentation for object perception | |
Zewen He1,2; Rui Wu3; Dingqian Zhang3 | |
2021-02 | |
会议名称 | ACCV: Asian Conference on Computer Vision |
会议日期 | 2020-11 |
会议地点 | 日本京都(在线) |
摘要 | Recently, data augmentation techniques for training conv-nets emerge one after another, especially focusing on image classification. They’re always applied to object detection without further careful design. In this paper we propose COG, a general domain migration scheme for augmentation. Specifically, based on a particular augmentation, we first analyze its inherent inconsistency, and then adopt an adaptive strategy to rectify ground-truths of the augmented input images. Next, deep detection networks are trained on the rectified data to achieve better performance. Our extensive experiments show that our method COG’s performance is superior to its competitor on detection and instance segmentation tasks. In addition, the results manifest the robustness of COG when faced with hyper-parameter variations, etc. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/45000 |
专题 | 多模态人工智能系统全国重点实验室_人工智能与机器学习(杨雪冰)-技术团队 |
通讯作者 | Zewen He |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of Computer and Control Engineering, University of Chinese Academy of Science, Beijing, China 3.Horizon Robotics, Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zewen He,Rui Wu,Dingqian Zhang. COG: COnsistent data auGmentation for object perception[C],2021. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
He_COG_COnsistent_da(1961KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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