# Multi-task Learning of Cascaded CNN for Facial Attribute Classification

arXiv: https://arxiv.org/abs/1805.01290 · HTML: https://mlsanity.com/paper/1805.01290/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2018.

## Built on by (most cited first, 12 of 12)

- [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)
- [Label2Label: A Language Modeling Framework for Multi-Attribute Learning](https://mlsanity.com/paper/2207.08677/) (2022)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Distributionally Generative Augmentation for Fair Facial Attribute Classification](https://mlsanity.com/paper/2403.06606/) (2024)
- [Task-adaptive Q-Face](https://mlsanity.com/paper/2405.09059/) (2024)
- [Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models](https://mlsanity.com/paper/2405.15687/) (2024)
- [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)
- [CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems](https://mlsanity.com/paper/2407.13922/) (2024)
- [FaceCook: Face Generation Based on Linear Scaling Factors](https://mlsanity.com/paper/2109.03492/) (2021)

## Abstract (arXiv)

Recently, facial attribute classification (FAC) has attracted significant attention in the computer vision community. Great progress has been made along with the availability of challenging FAC datasets. However, conventional FAC methods usually firstly pre-process the input images (i.e., perform face detection and alignment) and then predict facial attributes. These methods ignore the inherent dependencies among these tasks (i.e., face detection, facial landmark localization and FAC). Moreover, some methods using convolutional neural network are trained based on the fixed loss weights without considering the differences between facial attributes. In order to address the above problems, we propose a novel multi-task learning of cas- caded convolutional neural network method, termed MCFA, for predicting multiple facial attributes simultaneously. Specifically, the proposed method takes advantage of three cascaded sub-networks (i.e., S_Net, M_Net and L_Net corresponding to the neural networks under different scales) to jointly train multiple tasks in a coarse-to-fine manner, which can achieve end-to-end optimization. Furthermore, the proposed method automatically assigns the loss weight to each facial attribute based on a novel dynamic weighting scheme, thus making the proposed method concentrate on predicting the more difficult facial attributes. Experimental results show that the proposed method outperforms several state-of-the-art FAC methods on the challenging CelebA and LFWA datasets.