Loading…
Synthetic18K: Learning better representations for person re-ID and attribute recognition from 1.4 million synthetic images
Learning robust representations is critical for the success of person re-identification and attribute recognition systems. However, to achieve this, we must use a large dataset of diverse person images as well as annotations of identity labels and/or a set of different attributes. Apart from the obv...
Saved in:
Published in: | Signal processing. Image communication 2021-09, Vol.97, p.116335, Article 116335 |
---|---|
Main Authors: | , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Learning robust representations is critical for the success of person re-identification and attribute recognition systems. However, to achieve this, we must use a large dataset of diverse person images as well as annotations of identity labels and/or a set of different attributes. Apart from the obvious concerns about privacy issues, the manual annotation process is both time consuming and too costly. In this paper, we instead propose to use synthetic person images for addressing these difficulties. Specifically, we first introduce Synthetic18K, a large-scale dataset of over 1 million computer generated person images of 18K unique identities with relevant attributes. Moreover, we demonstrate that pretraining of simple deep architectures on Synthetic18K for person re-identification and attribute recognition and then fine-tuning on real data leads to significant improvements in prediction performances, giving results better than or comparable to state-of-the-art models.
•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. |
---|---|
ISSN: | 0923-5965 1879-2677 |
DOI: | 10.1016/j.image.2021.116335 |