Adversarial Spatial Frequency Domain Critic Learning for Age and Gender Classification

Sangmin Lee, Hak Gu Kim, Ki Hyun Kim, Yong Man RoICIP 2018 · OpenReview

Abstract

This paper proposes a novel deep learning framework for age and gender classification with the adversarial spatial frequency domain critic. In the proposed framework, the encoder-generator synthesizes realistic facial images with real images and corresponding age and gender label. An adversarial critic is devised to make generated images more proper for age and gender classification. In particular, we analyze the characteristic of age and gender attributes in the spatial frequency domain. Based on our investigation, we devise the spatial frequency domain critic network for considering the specific frequency bands which are dominant on age and gender attributes. Our discriminator is designed to simultaneously perform age and gender classification tasks. For this purpose, alternating learning is performed for multi-task classification. Experimental results showed that the proposed method outperformed other state-of-the-art methods in age and gender classifications.
BibTeX
@inproceedings{lee2018adversarial,
  author = {Sangmin Lee and Hak Gu Kim and Ki Hyun Kim and Yong Man Ro},
  title = {{Adversarial Spatial Frequency Domain Critic Learning for Age and Gender Classification}},
  booktitle = {ICIP},
  year = {2018},
  url = {https://openreview.net/forum?id=LgySc8IqQek},
}

Loading related content...

Figure