Paper Info
Title
Progressive End-to-End Object Detection in Crowded Scenes
Abstract
In this paper, we propose a new query-based detection framework for crowd detection. Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be inferred for a single object, typically in crowded scenes; second, the performance saturates as the depth of the decoding stage increases. Benefiting from the nature of the one-to-one label assignment rule, we propose a progressive predicting method to address the above issues. Specifically, we first select accepted queries prone to generate true positive predictions, then refine the rest noisy queries according to the previously accepted predictions. Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes. Equipped with our approach, Sparse RCNN achieves 92.0% AP, 41.4% MR <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−2</sup> and 83.2% JI on the challenging CrowdHuman [35] dataset, outperforming the box-based method MIP [8] that specifies in handling crowded scenarios. Moreover, the proposed method, robust to crowdedness, can still obtain consistent improvements on moderately and slightly crowded datasets like CityPersons [47] and COCO [26]. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.
Year
DOI
Venue
2022
10.1109/CVPR52688.2022.00093
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Keywords
DocType
Volume
Deep learning architectures and techniques, Recognition: detection,categorization,retrieval, Representation learning, Scene analysis and understanding, Vision applications and systems
Conference
2022
Issue
ISSN
ISBN
1
1063-6919
978-1-6654-6947-0
Citations 
PageRank 
References 
0
0.34
7
Authors
5
Name
Order
Citations
PageRank
Anlin Zheng100.34
Yuang Zhang201.01
Xiangyu Zhang313044437.66
Xiaojuan Qi436224.41
Jian Sun525842956.90