Synthetic18K: Learning better representations for person re-ID and attribute recognition from 1.4 million synthetic images

作者：

Highlights：

• Our work learns robust representations for person re-id and attribute recognition.

• We introduce Synthetic18K dataset for person re-id and attribute recognition.

• Synthetic18K provides a strong alternative to the widely used ImageNet pre-training.

• Our pre-trained models give highly competitive results against the state-of-the-art.

摘要

•Our work learns robust representations for person re-id and attribute recognition.•We introduce Synthetic18K dataset for person re-id and attribute recognition.•Synthetic18K provides a strong alternative to the widely used ImageNet pre-training.•Our pre-trained models give highly competitive results against the state-of-the-art.

论文关键词：Person re-identification,Attribute recognition,Synthetic data

论文评审过程：Received 18 May 2020, Revised 27 February 2021, Accepted 19 May 2021, Available online 26 May 2021, Version of Record 29 May 2021.

论文官网地址：https://doi.org/10.1016/j.image.2021.116335