Incremental Few-Shot Learning for Pedestrian Attribute Recognition
Abstract
Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a fixed set of attributes. They are unable to handle the incremental few-shot learning scenario, i.e. adapting a well-trained model to newly added attributes with scarce data, which commonly exists in the real world. In this work, we present a meta learning based method to address this issue. The core of our framework is a meta architecture capable of disentangling multiple attribute information and generalizing rapidly to new coming attributes. By conducting extensive experiments on the benchmark dataset PETA and RAP under the incremental few-shot setting, we show that our method is able to perform the task with competitive performances and low resource requirements.
Cite
Text
Xiang et al. "Incremental Few-Shot Learning for Pedestrian Attribute Recognition." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/543Markdown
[Xiang et al. "Incremental Few-Shot Learning for Pedestrian Attribute Recognition." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/xiang2019ijcai-incremental/) doi:10.24963/IJCAI.2019/543BibTeX
@inproceedings{xiang2019ijcai-incremental,
title = {{Incremental Few-Shot Learning for Pedestrian Attribute Recognition}},
author = {Xiang, Liuyu and Jin, Xiaoming and Ding, Guiguang and Han, Jungong and Li, Leida},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2019},
pages = {3912-3918},
doi = {10.24963/IJCAI.2019/543},
url = {https://mlanthology.org/ijcai/2019/xiang2019ijcai-incremental/}
}