# Mask-Guided Multi-Task Network for Face Attribute Recognition

arXiv: https://arxiv.org/abs/2601.01408 · HTML: https://mlsanity.com/paper/2601.01408/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 63 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classification](https://mlsanity.com/paper/1611.05377/) (2016)
- [Dynamic Curriculum Learning for Imbalanced Data Classification](https://mlsanity.com/paper/1901.06783/) (2019)
- [Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control](https://mlsanity.com/paper/2405.12970/) (2024)
- [Masked Face Recognition Dataset and Application](https://mlsanity.com/paper/2003.09093/) (2020)
- [Equalized Focal Loss for Dense Long-Tailed Object Detection](https://mlsanity.com/paper/2201.02593/) (2022)
- [Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach](https://mlsanity.com/paper/1706.00906/) (2017)
- [Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions](https://mlsanity.com/paper/2112.05561/) (2021)
- [Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent](https://mlsanity.com/paper/2501.01230/) (2025)
- [Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval](https://mlsanity.com/paper/2403.16005/) (2024)
- [MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes](https://mlsanity.com/paper/1603.07027/) (2016)
- [PANDA: Pose Aligned Networks for Deep Attribute Modeling](https://mlsanity.com/paper/1311.5591/) (2013)
- [Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification](https://mlsanity.com/paper/2002.03683/) (2020)
- [Improving Facial Attribute Prediction using Semantic Segmentation](https://mlsanity.com/paper/1704.08740/) (2017)
- [Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System](https://mlsanity.com/paper/2302.05031/) (2023)
- [A Deep Cascade Network for Unaligned Face Attribute Classification](https://mlsanity.com/paper/1709.03851/) (2017)
- [Improving Facial Attribute Recognition by Group and Graph Learning](https://mlsanity.com/paper/2105.13825/) (2021)
- [Stable Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2302.00179/) (2023)
- [Neural Architecture Searching for Facial Attributes-based Depression Recognition](https://mlsanity.com/paper/2201.09799/) (2022)
- [Differentiable Model Scaling using Differentiable Topk](https://mlsanity.com/paper/2405.07194/) (2024)
- [Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields](https://mlsanity.com/paper/2406.14052/) (2024)
- [Local-Global Methods for Generalised Solar Irradiance Forecasting](https://mlsanity.com/paper/2303.06010/) (2023)

## Abstract (arXiv)

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.