TY - GEN
T1 - RaftNet
T2 - 2nd International Conference on Computer Science and Artificial Intelligence, CSAI 2018
AU - Zhang, Wuhao
AU - Ma, Lizhuang
AU - Ge, Yanhao
N1 - Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/12/8
Y1 - 2018/12/8
N2 - Pedestrian attribute recognition, a multi-task problem, is a popular task in computer vision. Generally, deep learning end-to-end networks to predict attributes are the basic method to solve this problem. To fully use deep neural network, this paper proposes a novel network structure called Raft Block. Raft Block is designed not only to extract task-specific features, but also to share the features of different tasks. Using the Raft Block, we build an end-to-end network Raftnet for pedestrian attribute recognition. We implement experiments on three public datasets, the results prove that the design idea of Raft Block is valid and effective. Specifically, we achieve state-of-art results as 85.64% and 82.79% mean accuracy on Market-1501 and DukeMTMC datasets, and competitive result as 72.53% mAP on PA-100K dataset.
AB - Pedestrian attribute recognition, a multi-task problem, is a popular task in computer vision. Generally, deep learning end-to-end networks to predict attributes are the basic method to solve this problem. To fully use deep neural network, this paper proposes a novel network structure called Raft Block. Raft Block is designed not only to extract task-specific features, but also to share the features of different tasks. Using the Raft Block, we build an end-to-end network Raftnet for pedestrian attribute recognition. We implement experiments on three public datasets, the results prove that the design idea of Raft Block is valid and effective. Specifically, we achieve state-of-art results as 85.64% and 82.79% mean accuracy on Market-1501 and DukeMTMC datasets, and competitive result as 72.53% mAP on PA-100K dataset.
KW - Attribute Recognition
KW - Computer Vision
KW - Multi-task Learning
UR - https://www.scopus.com/pages/publications/85062778762
U2 - 10.1145/3297156.3297260
DO - 10.1145/3297156.3297260
M3 - 会议稿件
AN - SCOPUS:85062778762
T3 - ACM International Conference Proceeding Series
SP - 286
EP - 290
BT - Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence, CSAI 2018 - 2018 the 10th International Conference on Information and Multimedia Technology, ICIMT 2018
PB - Association for Computing Machinery
Y2 - 8 December 2018 through 10 December 2018
ER -