mlsanityData to 14 Oct 2026

FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition

arXiv 2601.01537 ↗First posted 4 Jan 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

To enhance the generalization performance of Multi-Task Networks (MTN) in Face Attribute Recognition (FAR), it is crucial to share relevant information across multiple related prediction tasks effectively. Traditional MTN methods create shared low-level modules and distinct high-level modules, causing an exponential increase in model parameters with the addition of tasks. This approach also limits feature interaction at the high level, hindering the exploration of semantic relations among attributes, thereby affecting generalization negatively. In response, this study introduces FAR-AMTN, a novel Attention Multi-Task Network for FAR. It incorporates a Weight-Shared Group-Specific Attention (WSGSA) module with shared parameters to minimize complexity while improving group feature representation. Furthermore, a Cross-Group Feature Fusion (CGFF) module is utilized to foster interactions between attribute groups, enhancing feature learning. A Dynamic Weighting Strategy (DWS) is also introduced for synchronized task convergence. Experiments on the CelebA and LFWA datasets demonstrate that the proposed FAR-AMTN demonstrates superior accuracy with significantly fewer parameters compared to existing models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 51 references that are in the map. First posted on arXiv 4 Jan 2026.

Builds on

24 of 51 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2017Non-local Neural Networkscited by 2,293
  4. 2015Spatial Transformer Networkscited by 1,429
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  6. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  7. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  8. 2021Deep Long-Tailed Learning: A Surveycited by 417
  9. 2021General Facial Representation Learning in a Visual-Linguistic Mannercited by 195
  10. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  11. 2016Fully-adaptive Feature Sharing in Multi-Task Networks with Applications in Person Attribute Classificationcited by 93
  12. 2019Dynamic Curriculum Learning for Imbalanced Data Classificationcited by 93
12 more
  1. 2021Influence-Balanced Loss for Imbalanced Visual Classificationcited by 91
  2. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  3. 2020SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learningcited by 50
  4. 2023TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Expertscited by 45
  5. 2016MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributescited by 34
  6. 2020Deep Multi-task Multi-label CNN for Effective Facial Attribute Classificationcited by 22
  7. 2017Improving Facial Attribute Prediction using Semantic Segmentationcited by 16
  8. 2020Hierarchical Feature Embedding for Attribute Recognitioncited by 16
  9. 2019Slim-CNN: A Light-Weight CNN for Face Attribute Predictioncited by 11
  10. 2017A Deep Cascade Network for Unaligned Face Attribute Classificationcited by 8
  11. 2021Improving Facial Attribute Recognition by Group and Graph Learningcited by 7
  12. 2018Deep Sketch-Photo Face Recognition Assisted by Facial Attributescited by 4

Built on by

Not cited yet.