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

09/17/2019
by   Tomaso Fontanini, et al.
1

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.

READ FULL TEXT

page 1

page 5

page 8

page 9

research
05/22/2020

A Concise Review of Recent Few-shot Meta-learning Methods

Few-shot meta-learning has been recently reviving with expectations to m...
research
04/17/2020

A Comprehensive Overview and Survey of Recent Advances in Meta-Learning

This article reviews meta-learning which seeks rapid and accurate model ...
research
04/27/2021

Adaptive Adversarial Training for Meta Reinforcement Learning

Meta Reinforcement Learning (MRL) enables an agent to learn from a limit...
research
06/09/2022

Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning

Brain networks characterize complex connectivities among brain regions a...
research
01/02/2020

DAWSON: A Domain Adaptive Few Shot Generation Framework

Training a Generative Adversarial Networks (GAN) for a new domain from s...
research
12/01/2021

A Few-Shot Meta-Learning based Siamese Neural Network using Entropy Features for Ransomware Classification

Ransomware defense solutions that can quickly detect and classify differ...
research
01/04/2021

Single-shot fringe projection profilometry based on Deep Learning and Computer Graphics

Multiple works have applied deep learning to fringe projection profilome...

Please sign up or login with your details

Forgot password? Click here to reset