.png){kind=icon}
返回
Mask-guided multi-task network for face attribute recognition
.png){kind=icon}
PRE
AI
DOI：10.1007/s13042-025-02900-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Face Attribute Recognition (FAR) plays a crucial role in applications such as person re-identification, face retrieval, and face editing. Conventional multi-task attribute recognition methods often process the entire feature map for feature extraction and attribute classification, which can produce redundant features due to reliance on global regions. To address these challenges, we propose a novel approach emphasizing the selection of specific feature regions for efficient feature learning. We introduce the Mask-Guided Multi-Task Network (MGMTN), which integrates Adaptive Mask Learning (AML) and Group-Global Feature Fusion (G2FF) to address the aforementioned limitations. Leveraging a pre-trained keypoint annotation model and a fully convolutional network, AML accurately localizes critical facial parts (e.g., eye and mouth groups) and generates group masks that delineate meaningful feature regions, thereby mitigating negative transfer from global region usage. Furthermore, G2FF combines group and global features to enhance FAR learning, enabling more precise attribute identification. Extensive experiments on two challenging facial attribute recognition datasets demonstrate the effectiveness of MGMTN in improving FAR performance.
Keyword:
Multi-task network
Face attribute recognition
Negative transfer
Fully convolutional network
Feature fusion
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
分享收藏
BLAN: Bi-directional ladder attentive network for facial attribute predictionBLAN: 用于面部属性预测的双向梯形注意网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability属性引导的人行检索：连接行人重识别与内部属性变异性
PREAI
分享收藏Learning an attention-aware parallel sharing network for facial attribute recognition学习一种用于面部属性识别的关注度感知并行共享网络
PREAI
分享收藏Prior-Guided Multi-scale Fusion Transformer for Face Attribute RecognitionSong, S., Huang, H., Wang, J., Zheng, A., He, R., 2022. 基于先验引导的多尺度融合Transformer用于人脸属性识别，载于：模式识别与计算机视觉：第5届中国会议，PRCV 2022，中国深圳，2022年11月4-7日，会议录，第I部分，Springer。第645-659页。
PREAI
分享收藏
查看更多内容