Generative Cooperative Net for Image Generation and Data Augmentation
This work addresses image generation and data augmentation for computer vision applications, but it appears incremental as it builds on concepts similar to generative adversarial networks.
The paper tackles the problem of generating images with desired features from abstract concepts by proposing the Generative Cooperative Net (GCN), which achieves promising results in experiments on hand-written digit and facial expression generation. It also demonstrates the model's effectiveness as a data-augmentation tool for recognition tasks, outperforming existing methods.
How to build a good model for image generation given an abstract concept is a fundamental problem in computer vision. In this paper, we explore a generative model for the task of generating unseen images with desired features. We propose the Generative Cooperative Net (GCN) for image generation. The idea is similar to generative adversarial networks except that the generators and discriminators are trained to work accordingly. Our experiments on hand-written digit generation and facial expression generation show that GCN's two cooperative counterparts (the generator and the classifier) can work together nicely and achieve promising results. We also discovered a usage of such generative model as an data-augmentation tool. Our experiment of applying this method on a recognition task shows that it is very effective comparing to other existing methods. It is easy to set up and could help generate a very large synthesized dataset.