Mask-guided multi-task network for face attribute recognition

2026-01-04

International Journal of Machine Learning and Cybernetics

AI Summary

This work proposes a mask-guided multitask network for facial attribute recognition to address the limitations of conventional approaches that rely on global features, which often introduce redundant information and suffer from negative transfer. By leveraging an adaptive masking mechanism, the method precisely localizes critical facial regions through group masks generated by integrating a pretrained landmark model with a fully convolutional network. This enables effective fusion of localized group features and global contextual information. Extensive experiments on two widely used facial attribute datasets demonstrate significant performance improvements, validating the approach’s effectiveness and robustness. The core contribution lies in mitigating negative transfer across tasks while enhancing the discriminative power of learned features.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Algorithmic accountability and transparency on the web

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.

Problem

• Face Attribute Recognition
• Multi-Task Learning
• Feature Redundancy
• Global Region Dependency

Innovation

• Mask-Guided Multi-Task Network
• Adaptive Mask Learning
• Group-Global Feature Fusion
• Face Attribute Recognition
• Feature Localization