.png){kind=icon}
返回
Multi-task learning based on geometric invariance discriminative features
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-03617-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-task learning (MTL) aims at tackling multiple tasks through one single network while guarantee all tasks can reach good performance. The main challenge in MTL is how to extract task-specific feature effectively. Existing task-specific feature extraction methods predominantly combine and stack convolutional neural networks (CNNs). However, these methods ignore two points: the geometric variations of the target object have different effects on each task; discriminative features for each task lack a mechanism to ensure they are focused on. In this work, we propose a Deformable-Attention Multi-Task Network (DAMTN) to improve the capability of extracting geometric invariance discriminative features. In particular, deformable convolution is introduced to learn geometric variation rules of the target object for different tasks, and attention mechanism helps task-specific networks focus on discriminative parts. The proposed DAMTN can be trained end-to-end. We empirically analyze the contribution of different components in the proposed method and demonstrate state-of-the-art performance on multiple classification tasks as well as semantic segmentation task and depth estimation task.
Keyword:
Multi-task learning
Attention mechanism
Deformable convolution
Image classification
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏分享收藏Is position important? deep multi-task learning for aspect-based sentiment analysis位置重要吗？面向基于方面的情感分析的深度多任务学习.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THVRSC Advances
RSC AdvancesIF0
PREAI
分享收藏
Usr-mtl: an unsupervised sentence representation learning framework with multi-task learningAPPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏
查看更多内容