MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization

Abstract

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.

References in corpus (13)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Generative Adversarial Text to Image Synthesis
• A Simple Neural Attentive Meta-Learner
• Particular object retrieval with integral max-pooling of CNN activations
• On First-Order Meta-Learning Algorithms
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Learning to reinforcement learn
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• Learned Optimizers that Scale and Generalize
• Learning to Optimize Neural Nets
• One-Shot Generalization in Deep Generative Models