Authors:
Ryo Matsui
;
Takayoshi Yamashita
and
Hironobu Fujiyoshi
Affiliation:
Chubu University, Kasugai, Aichi and Japan
Keyword(s):
Deep Convolutional Neural Network, Multi-task Learning, Channel-wise Convolution, Facial Landmark Detection, Facial Attribute Estimation.
Abstract:
Multi-task learning is a machine learning approach in which multiple tasks are solved simultaneously. This approach can improve learning efficiency and prediction accuracy for the task-specific models. Furthermore, it has been used successfully across various applications such as natural language processing and computer vision. Multi-task learning consists of shared layers and task-specific layers. The shared layers extract common low-level features for all tasks, the task-specific layers diverge from the shared layers and extract specific high-level features for each task. Hence, conventional multi-task learning architecture cannot extract the low-level task-specific feature. In this work, we propose Separation Multi-task Networks, a novel multi-task learning architecture that extracts shared features and task-specific features in various layers. Our proposed method extracts low- to high-level task-specific features by feeding task-specific layers in parallel to each shared layer. M
oreover, we employ channel-wise convolution when concatenating feature maps of shared layers and task-specific layers. This convolution allows concatenation even if layers have a different number of channels of feature maps. In experiments on CelebA dataset, our proposed method outperformed conventional methods at facial landmark detection and facial attribute estimation.
(More)