G-Head: Gating Head for Multi-task Learning in One-stage Object Detection

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	G-Head: Gating Head for Multi-task Learning in One-stage Object Detection
	He, Jiang1,2 ; Qingyi, Gu1
	2022-03
会议名称	2022 IEEE International Conference on Multimedia & Expo (ICME)
会议日期	2022-7
会议地点	Taiwan
摘要	Object detection is commonly formulated as a multi-task learning problem in deep learning methods. Due to the divergence between classification and regression tasks, modern one-stage detectors typically utilize two parallel branches as the detection head, which might be sub-optimal. In this paper, we propose a new Gating Head (G-Head) to enhance the interaction between different tasks and promote the multi-task learning process. By introducing Multi-Scale Aggregation (MSA), Multi-Aspect Learning (MAL), and Gating Selector (GS), our method can signifificantly boost the performance of existing one-stage frameworks with fewer parameters and computational costs. To validate the effificiency, effectiveness, and generalization of our G-Head, extensive experiments are conducted on the challenging MS COCO dataset. Without bells and whistles, we achieve a new state-of-the-art 48.7 AP under single-model and single-scale test.
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48641
专题	中科院工业视觉智能装备工程实验室_精密感知与控制中国科学院自动化研究所
通讯作者	Qingyi, Gu
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences
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	He, Jiang,Qingyi, Gu. G-Head: Gating Head for Multi-task Learning in One-stage Object Detection[C],2022.

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
GHead.pdf（485KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载