arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08849cs.CV
收藏

ECCV 2020 VIPriors目标检测挑战赛第二名解决方案

2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge

Jilian Technology Group(吉涟科技集团)

Yinzheng Gu, Yihan Pan, Shizhe Chen

摘要:

在本报告中,我们描述了我们在2020年3月至7月举行的ECCV 2020 VIPriors目标检测挑战赛的方法。我们表明,通过使用最先进的数据增强策略,模型设计和后处理集成方法,有可能克服数据短缺的困难,并获得有竞争力的结果。值得注意的是,我们的整体检测系统在COCO 2017验证集上仅使用10K训练图像就实现了36.6 $\%$ AP,而没有任何预训练或迁移学习权重,使我们在挑战中排名第二。

英文摘要:

In this report, we descibe our approach to the ECCV 2020 VIPriors Object Detection Challenge which took place from March to July in 2020. We show that by using state-of-the-art data augmentation strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. Notably, our overall detection system achieves 36.6$\%$ AP on the COCO 2017 validation set using only 10K training images without any pre-training or transfer learning weights ranking us 2nd place in the challenge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑