# Improving Crowded Object Detection via Copy-Paste

Source: [Improving Crowded Object Detection via Copy-Paste](<https://www.sota2.com/research/paper/68fa6dfc1e209131cea3d2f5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:56.288Z

Authors: Jiangfan Deng, Dewen Fan, Xiaosong Qiu, Feng Zhou

Published: 2022-11-22T09:25:15.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.12110>)

[PDF](<https://arxiv.org/pdf/2211.12110.pdf>)