# Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification

arXiv: https://arxiv.org/abs/2002.03683 · HTML: https://mlsanity.com/paper/2002.03683/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 22 of 22)

- [General Facial Representation Learning in a Visual-Linguistic Manner](https://mlsanity.com/paper/2112.03109/) (2021)
- [SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation](https://mlsanity.com/paper/2308.11509/) (2023)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [Self-Supervised Facial Representation Learning with Facial Region Awareness](https://mlsanity.com/paper/2403.02138/) (2024)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning](https://mlsanity.com/paper/2504.07198/) (2025)
- [Task-adaptive Q-Face](https://mlsanity.com/paper/2405.09059/) (2024)
- [Learning Identity-Preserving Transformations on Data Manifolds](https://mlsanity.com/paper/2106.12096/) (2021)
- [Tasks Structure Regularization in Multi-Task Learning for Improving Facial Attribute Prediction](https://mlsanity.com/paper/2108.04353/) (2021)
- [AAFACE: Attribute-aware Attentional Network for Face Recognition](https://mlsanity.com/paper/2308.07243/) (2023)
- [CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition](https://mlsanity.com/paper/2401.03037/) (2024)
- [Biased Binary Attribute Classifiers Ignore the Majority Classes](https://mlsanity.com/paper/2403.14435/) (2024)
- [FaceCook: Face Generation Based on Linear Scaling Factors](https://mlsanity.com/paper/2109.03492/) (2021)
- [MaskMTL: Attribute prediction in masked facial images with deep multitask learning](https://mlsanity.com/paper/2201.03002/) (2022)
- [TransFA: Transformer-based Representation for Face Attribute Evaluation](https://mlsanity.com/paper/2207.05456/) (2022)
- [ASD: Towards Attribute Spatial Decomposition for Prior-Free Facial Attribute Recognition](https://mlsanity.com/paper/2210.13716/) (2022)
- [PrivacyProber: Assessment and Detection of Soft-Biometric Privacy-Enhancing Techniques](https://mlsanity.com/paper/2211.08864/) (2022)
- [Adaptive Growth: Real-time CNN Layer Expansion](https://mlsanity.com/paper/2309.03049/) (2023)
- [Mask-Guided Multi-Task Network for Face Attribute Recognition](https://mlsanity.com/paper/2601.01408/) (2026)
- [FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition](https://mlsanity.com/paper/2601.01537/) (2026)

## Abstract (arXiv)

Facial Attribute Classification (FAC) has attracted increasing attention in computer vision and pattern recognition. However, state-of-the-art FAC methods perform face detection/alignment and FAC independently. The inherent dependencies between these tasks are not fully exploited. In addition, most methods predict all facial attributes using the same CNN network architecture, which ignores the different learning complexities of facial attributes. To address the above problems, we propose a novel deep multi-task multi-label CNN, termed DMM-CNN, for effective FAC. Specifically, DMM-CNN jointly optimizes two closely-related tasks (i.e., facial landmark detection and FAC) to improve the performance of FAC by taking advantage of multi-task learning. To deal with the diverse learning complexities of facial attributes, we divide the attributes into two groups: objective attributes and subjective attributes. Two different network architectures are respectively designed to extract features for two groups of attributes, and a novel dynamic weighting scheme is proposed to automatically assign the loss weight to each facial attribute during training. Furthermore, an adaptive thresholding strategy is developed to effectively alleviate the problem of class imbalance for multi-label learning. Experimental results on the challenging CelebA and LFWA datasets show the superiority of the proposed DMM-CNN method compared with several state-of-the-art FAC methods.