帕斯卡(单位)
计算机科学
目标检测
探测器
骨干网
对象(语法)
特征(语言学)
骨料(复合)
特征提取
人工智能
模式识别(心理学)
计算机网络
复合材料
材料科学
程序设计语言
哲学
电信
语言学
作者
Qiankun Tang,Jie Li,Zhiping Shi,Yu Hu
标识
DOI:10.1109/icassp40776.2020.9054101
摘要
The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level features by the proposed Detail-Preserving Module. To effectively aggregate bottom and top-down features, we introduce an efficient Feature-Preserving and Refinement Module. A lightweight prediction head is employed to further reduce the entire network complexity. Experimental results show that our LightDet achieves 75.5% mAP on PASCAL VOC 2007 at the speed of 250 FPS and 24.0% mAP on MS COCO dataset.
科研通智能强力驱动
Strongly Powered by AbleSci AI