MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization
This addresses the challenge of data scarcity in deep learning for image colorization, though it appears incremental as it builds on existing adversarial and meta-learning techniques.
The paper tackles the problem of image colorization with limited data by proposing MetalGAN, which combines adversarial training with meta-learning and dataset clustering to achieve excellent colorization results without large datasets.
In recent years, the majority of works on deep-learning-based image colorization have focused on how to make a good use of the enormous datasets currently available. What about when the data at disposal are scarce? The main objective of this work is to prove that a network can be trained and can provide excellent colorization results even without a large quantity of data. The adopted approach is a mixed one, which uses an adversarial method for the actual colorization, and a meta-learning technique to enhance the generator model. Also, a clusterization a-priori of the training dataset ensures a task-oriented division useful for meta-learning, and at the same time reduces the per-step number of images. This paper describes in detail the method and its main motivations, and a discussion of results and future developments is provided.