CZ4042

This repository contains the Python notebooks for the assignment as well as the project for the NTU CZ4042 Neural Networks and Deep Learning.

Topic: Gender Classification Automatic gender classification has been used in many applications including image analysis on social platforms. The goal of this project is to classify the gender of faces in an image. One can design a convolutional neural network to achieve this goal. Some tasks to consider:

1. Modify some previously published architectures e.g., increase the network depth, reducing their parameters, etc.
2. Consider age and gender recognition simultaneously to take advantage of the gender-specific age characteristics and age-specific gender characteristics inherent to images
3. Consider pre-training using the CelebA dataset http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html

References

1. G. Levi and T. Hassner, “Age and gender classification using convolutional neural networks.” in IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) workshops, 2015
2. Z. Liu and P. Luo and X. Wang, and X. Tang, “Deep learning face attributes in the wild,” in International Conference on Computer Vision (ICCV), 2015

Datasets:

1. Adience Dataset: https://talhassner.github.io/home/projects/Adience/Adiencedata.html#agegender