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.
@article{arxiv.1906.00330,
title = {Incremental Few-Shot Learning for Pedestrian Attribute Recognition},
author = {Liuyu Xiang and Xiaoming Jin and Guiguang Ding and Jungong Han and Leida Li},
journal= {arXiv preprint arXiv:1906.00330},
year = {2019}
}