標題: ON THE EFFECT OF DATA IMBALANCE FOR MULTI-LABEL PEDESTRIAN ATTRIBUTE RECOGNITION
作者: Wang, Tsaipei
Shu, Kai-Chen
Chang, Chia-Hao
Chen, Yi-Fu
資訊工程學系
Department of Computer Science
關鍵字: Human attribute recognition;pedestrian attribute recognition;multi-label classification;data imbalance;classification evaluation metrics
公開日期: 1-Jan-2018
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.
URI: http://dx.doi.org/10.1109/TAAI.2018.00025
http://hdl.handle.net/11536/151039
ISSN: 2376-6816
DOI: 10.1109/TAAI.2018.00025
期刊: 2018 CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE (TAAI)
起始頁: 74
結束頁: 77
Appears in Collections:Conferences Paper