On the Effect of Data Imbalance for Multi-Label Pedestrian Attribute Recognition

Tsai-Pei Wang, Kai Chen Shu, Chia Hao Chang, Yi Fu Chen

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

Pedestrian attribute recognition has many applications in surveillance and attribute based query, tracking, and person re-identification. The recent trend in deep-learning based pedestrian attribute recognition is to use a shared CNN backbone for feature extraction and multiple subsequent branches for the individual branches. While this allows the end-to-end learning to simultaneously recognize multiple attributes, the data imbalance problem of most attributes becomes a challenge that has not been studied sufficiently for this application. This paper presents studies on how the cost adjustment method affects several common evaluation metrics. We also propose a two-stage training procedure, where an additional fine-tuning stage on the classifier layers only with class-balanced data is shown to improve recognition performances.

原文English
主出版物標題Proceedings - 2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018
發行者Institute of Electrical and Electronics Engineers Inc.
頁面74-77
頁數4
ISBN(電子)9781728112299
DOIs
出版狀態Published - 24 12月 2018
事件2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018 - Taichung, Taiwan
持續時間: 30 11月 20182 12月 2018

出版系列

名字Proceedings - 2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018

Conference

Conference2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018
國家/地區Taiwan
城市Taichung
期間30/11/182/12/18

指紋

深入研究「On the Effect of Data Imbalance for Multi-Label Pedestrian Attribute Recognition」主題。共同形成了獨特的指紋。

引用此