Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition

Autor:	Zeng, Haitian, Ai, Haizhou, Zhuang, Zijie, Chen, Long
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Learning to predict multiple attributes of a pedestrian is a multi-task learning problem. To share feature representation between two individual task networks, conventional methods like Cross-Stitch and Sluice network learn a linear combination of features or feature subspaces. However, linear combination rules out the complex interdependency between channels. Moreover, spatial information exchanging is less-considered. In this paper, we propose a novel Co-Attentive Sharing (CAS) module which extracts discriminative channels and spatial regions for more effective feature sharing in multi-task learning. The module consists of three branches, which leverage different channels for between-task feature fusing, attention generation and task-specific feature enhancing, respectively. Experiments on two pedestrian attribute recognition datasets show that our module outperforms the conventional sharing units and achieves superior results compared to the state-of-the-art approaches using many metrics. Comment: 2020 IEEE International Conference on Multimedia & Expo
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.03164 Zobrazit plný text záznamu View this record from Arxiv