.png){kind=icon}
返回
Fine-Grained Face Annotation Using Deep Multi-Task CNN
.png){kind=icon}
OA
AI
DOI：10.3390/s18082666.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present a multi-task learning-based convolutional neural network (MTL-CNN) able to estimate multiple tags describing face images simultaneously. In total, the model is able to estimate up to 74 different face attributes belonging to three distinct recognition tasks: age group, gender and visual attributes (such as hair color, face shape and the presence of makeup). The proposed model shares all the CNN's parameters among tasks and deals with task-specific estimation through the introduction of two components: (i) a gating mechanism to control activations' sharing and to adaptively route them across different face attributes; (ii) a module to post-process the predictions in order to take into account the correlation among face attributes. The model is trained by fusing multiple databases for increasing the number of face attributes that can be estimated and using a center loss for disentangling representations among face attributes in the embedding space. Extensive experiments validate the effectiveness of the proposed approach.
Keyword:
face analysis
convolutional neural networks
multi-task learning
gender recognition
age group recognition
face attributes' estimation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
Quality of life and audiologic performance through the ability to phone of cochlear implant users
PREAI
分享收藏Cerebral Temperature Changes in the Monkey (Macaca mulatta) after 2500 RADS Ionizing Radiation.png)
IF0
PREAI
分享收藏Properties of the double well potential and relaxation processes in a model glassPhysChemComm
PhysChemCommIF0
PREAI
分享收藏Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks从没有面部标志的单个图像对真实年龄和表观年龄的深刻期望
PREAI
分享收藏
查看更多内容