Improving Crowded Object Detection via Copy-Paste
DOI:
https://doi.org/10.1609/aaai.v37i1.25124Keywords:
CV: Scene Analysis & Understanding, CV: Object Detection & CategorizationAbstract
Crowdedness caused by overlapping among similar objects is a ubiquitous challenge in the field of 2D visual object detection. In this paper, we first underline two main effects of the crowdedness issue: 1) IoU-confidence correlation disturbances (ICD) and 2) confused de-duplication (CDD). Then we explore a pathway of cracking these nuts from the perspective of data augmentation. Primarily, a particular copy- paste scheme is proposed towards making crowded scenes. Based on this operation, we first design a "consensus learning" method to further resist the ICD problem and then find out the pasting process naturally reveals a pseudo "depth" of object in the scene, which can be potentially used for alleviating CDD dilemma. Both methods are derived from magical using of the copy-pasting without extra cost for hand-labeling. Experiments show that our approach can easily improve the state-of-the-art detector in typical crowded detection task by more than 2% without any bells and whistles. Moreover, this work can outperform existing data augmentation strategies in crowded scenario.Downloads
Published
2023-06-26
How to Cite
Deng, J., Fan, D., Qiu, X., & Zhou, F. (2023). Improving Crowded Object Detection via Copy-Paste. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 497-505. https://doi.org/10.1609/aaai.v37i1.25124
Issue
Section
AAAI Technical Track on Computer Vision I