Progressive End-to-End Object Detection in Crowded Scenes

Code

• github.com/megvii-model/iter-e2edet
  OfficialIn paperpytorch★ 96
• github.com/zyayoung/Iter-Deformable-DETR
  pytorch★ 32

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^-2 and 83.2\% JI on the challenging CrowdHuman shao2018crowdhuman dataset, outperforming the box-based method MIP chu2020detection 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 zhang2017citypersons and COCO lin2014microsoft. Code will be made publicly available at https://github.com/megvii-model/Iter-E2EDET.

Tasks

Benchmark Results

Reproductions