Abstract
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.
Abstract (translated)
面部属性识别（FAR）在人员再识别、人脸检索和人脸编辑等应用中扮演着重要角色。传统的多任务属性识别方法通常在整个特征图上进行特征提取和属性分类，这可能会由于依赖全局区域而导致冗余特征的产生。为了解决这些问题，我们提出了一种新的方法，强调选择特定的特征区域以实现高效的特征学习。为此，我们引入了Mask-Guided Multi-Task Network（MGMTN），该网络结合了自适应掩码学习（Adaptive Mask Learning, AML）和组全局特征融合（Group-Global Feature Fusion, G2FF），旨在解决上述限制。 AML利用预训练的关键点标注模型和全卷积网络，能够精确定位关键面部部分（如眼睛和嘴巴等区域），并生成分组掩码以界定有意义的特征区域，从而减轻使用全局区域所带来的负面转移效应。此外，G2FF结合了组内和全局特征，增强FAR的学习能力，使得属性识别更加精确。 在两个具有挑战性的面部属性识别数据集上的广泛实验表明，MGMTN能够有效提升FAR性能。
URL
https://arxiv.org/abs/2601.01408
