Hierarchical Multi-Task Network For Race, Gender and Facial Attractiveness Recognition

Lu Xu, Heng Fan, Jinhai XiangICIP 2019 · OpenReview

Abstract

Deep learning has powered many face related tasks and shown state-of-the-art performance. However, existing deep models are often trained separately for different problems, which results in heavy computational burden. To address this problem, we propose a novel multi-task network with fully convolutional architecture-Hierarchical Multi-task Network (HMT-Net), that simultaneously recognizes a person's gender, race and facial attractiveness from a given portrait image. Aiming to improve the robustness to outliers in facial beauty prediction task, a novel loss is introduced into HMTNet. Compared to existing deep approaches, the proposed HMTNet achieves state-of-the-art performance on several datasets, and it can learn more discriminative feature representation through joint training and feature aggregation. Extensive experiments evidence the effectiveness of HMTNet.
BibTeX
@inproceedings{xu2019hierarchical,
  author = {Lu Xu and Heng Fan and Jinhai Xiang},
  title = {{Hierarchical Multi-Task Network For Race, Gender and Facial Attractiveness Recognition}},
  booktitle = {ICIP},
  year = {2019},
  url = {https://openreview.net/forum?id=kUtM9eAQoj},
}

Loading related content...

Figure