Improving image generative models with human interactions
arXiv:1709.10459
Abstract
GANs provide a framework for training generative models which mimic a data distribution. However, in many cases we wish to train these generative models to optimize some auxiliary objective function within the data it generates, such as making more aesthetically pleasing images. In some cases, these objective functions are difficult to evaluate, e.g. they may require human interaction. Here, we develop a system for efficiently improving a GAN to target an objective involving human interaction, specifically generating images that increase rates of positive user interactions. To improve the generative model, we build a model of human behavior in the targeted domain from a relatively small set of interactions, and then use this behavioral model as an auxiliary loss function to improve the generative model. We show that this system is successful at improving positive interaction rates, at least on simulated data, and characterize some of the factors that affect its performance.
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Deep reinforcement learning from human preferences
- Visualizing and Understanding Convolutional Networks
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
- CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
- Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks