Tiny Det: accurately detecting small objects within 1 GFLOPs

作     者：Shaoyu CHEN Tianheng CHENG Jiemin FANG Qian ZHANG Yuan LI Wenyu LIU Xinggang WANG 

作者机构：School of Electronic Information and Communications Huazhong University of Science and Technology Institute of Artificial Intelligence Huazhong University of Science and Technology Horizon Robotics Inc. Google Inc. 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2023年第66卷第1期

页      面：318-319页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by National Natural Science Foundation of China (Grant Nos. 61876212, 61733007) Zhejiang Laboratory (Grant No. 2019NB0AB02) HUST-Horizon Computer Vision Research Center 

主　　题：Economic and social effects 

摘      要：Dear editor,Object detection plays an important role in computer vision,and has gradually become the technical foundation of many applications. However, the inference procedure of advanced detection models requires massive computational resources,which makes it difficult to apply to resource-constrained mobile or edge devices.