Object Counting Using a Refinement Network

作     者：Lehan Sun Junjie Ma Liping Jing Lehan Sun;Junjie Ma;Liping Jing

作者机构：School of ScienceBeijing Jiaotong UniversityBeijing 100044China Department of Computer Science and Technologyand Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China School of Computer and Information TechnologyBeijing Jiaotong UniversityBeijing 100044China 

出 版 物：《Tsinghua Science and Technology》 (清华大学学报（自然科学版（英文版）)

年 卷 期：2022年第27卷第5期

页      面：869-879页

核心收录：

学科分类：02[经济学] 0202[经济学-应用经济学] 020208[经济学-统计学] 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] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：object counting Refinement Network(RefNet) scale variation uneven distribution 

摘      要：To address the scale variance and uneven distribution of objects in scenarios of object-counting tasks,an algorithm called Refinement Network(RefNet) is exploited.The proposed top-down scheme sequentially aggregates multiscale features,which are laterally connected with low-level information.Trained by a multiresolution density regression loss,a set of intermediate-density maps are estimated on each scale in a multiscale feature pyramid,and the detailed information of the density map is gradually added through coarse-to-fine granular refinement progress to predict the final density map.We evaluate our RefNet on three crowd-counting benchmark datasets,namely,ShanghaiTech,UCFC0,and UCSD,and our method achieves competitive performances on the mean absolute error and root mean squared error compared to the state-of-the-art approaches.We further extend our RefNet to cell counting,illustrating its effectiveness on relative counting tasks.