DTCC:Multi-level dilated convolution with transformer for weakly-supervised crowd counting

查看全文 作　　者：Zhuangzhuang [1]Miao;Yong [1]Zhang;Yuan [2]Peng;Haocheng [1]Peng;Baocai [1]Yin 机构地区：[1]Beijing Key Laboratory of Multimedia and Intelligent Software Technology,Beijing Institute of Artificial Intelligence,Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;[2]Taiji Computer Corporation Ltd.,China 出　　处：《Computational Visual Media》索引2023年第9卷第4期,共15页 基　　金：This research project was partially supported by the National Natural Science Foundation of China(Grant Nos.62072015,U19B2039,U1811463);the National Key R&D Program of China(Grant No.2018YFB1600903). 摘　　要：Crowd counting provides an important foundation for public security and urban management.Due to the existence of small targets and large density variations in crowd images,crowd counting is a challenging task.Mainstream methods usually apply convolution neural networks(CNNs)to regress a density map,which requires annotations of individual persons and counts.Weakly-supervised methods can avoid detailed labeling and only require counts as annotations of images,but existing methods fail to achieve satisfactory performance because a global perspective field and multi-level information are usually ignored.We propose a weakly-supervised method,DTCC,which effectively combines multi-level dilated convolution and transformer methods to realize end-to-end crowd counting.Its main components include a recursive swin transformer and a multi-level dilated convolution regression head.The recursive swin transformer combines a pyramid visual transformer with a fine-tuned recursive pyramid structure to capture deep multi-level crowd features,including global features.The multi-level dilated convolution regression head includes multi-level dilated convolution and a linear regression head for the feature extraction module.This module can capture both low-and high-level features simultaneously to enhance the receptive field.In addition,two regression head fusion mechanisms realize dynamic and mean fusion counting.Experiments on four well-known benchmark crowd counting datasets(UCF_CC_50,ShanghaiTech,UCF_QNRF,and JHU-Crowd++)show that DTCC achieves results superior to other weakly-supervised methods and comparable to fully-supervised methods. 关 键 词：crowd counting TRANSFORMER dilated convolution global perspective field PYRAMID