Saved in:
Bibliographic Details
Main Authors: Gao, Gong, Wang, Zekai, Zhao, Jian, Xie, Ziqi, Liu, Xianhui, Zhao, Weidong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01408
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912861051158528
author Gao, Gong
Wang, Zekai
Zhao, Jian
Xie, Ziqi
Liu, Xianhui
Zhao, Weidong
author_facet Gao, Gong
Wang, Zekai
Zhao, Jian
Xie, Ziqi
Liu, Xianhui
Zhao, Weidong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01408
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Mask-Guided Multi-Task Network for Face Attribute Recognition
Gao, Gong
Wang, Zekai
Zhao, Jian
Xie, Ziqi
Liu, Xianhui
Zhao, Weidong
Computer Vision and Pattern Recognition
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.
title Mask-Guided Multi-Task Network for Face Attribute Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.01408