Knowledge Commons of Institute of Automation,CAS
Adaptive Coarse-to-Fine Interactor for Multi-Scale Object Detection | |
Li Zekun1,2; Liu Yufan1,2; Li Bing1,2,4; Hu Weiming1,2,3; Zhou Xue5 | |
2021 | |
会议名称 | International Joint Conference on Neural Networks |
会议日期 | 2021.07 |
会议地点 | 线上 |
摘要 | Scale variation is one of the key challenges of object detection. Multi-level feature fusion is presented to alleviate the problems, e.g., Feature Pyramid Network (FPN) and its extended methods. However, the input features fed into these methods and the interaction among features from different levels are insufficient and rigid. To fully exploit the features of multi-scale objects and enhance the feature interaction, we propose a novel and effective framework called Adaptive Coarse-to-Fine Interactor (ACFI). Specifically, ACFI consists of three cascaded components: Multi-Resolution Fusion (MRF), Fine-Grained Interaction (FGI), and Edge-aware Enhancement (EAE). MRF adaptively extracts multi-level features from multi-resolution images and multi-stage features, and then these features are fed into FGI to have a fine-grained interaction utilizing bottom-up guidance. After that, EAE further refines the features obtained by FGI, and enhances the detailed edge information and suppresses the redundant noise. After the coarse-to-fine process, we can obtain powerful multi-scale representations of various objects. Each component can be embedded into any backbones, separately. Experimental results show the superiority of our method and verify the effectiveness of each proposed module. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48855 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Li Bing |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.PeopleAI Inc 5.School of Automation Engineering University of Electronic Science and Technology of China. |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li Zekun,Liu Yufan,Li Bing,et al. Adaptive Coarse-to-Fine Interactor for Multi-Scale Object Detection[C],2021. |
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 | ||
ACFI.pdf(5908KB) | 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