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 metalearning, 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.
MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization / Fontanini, Tomaso; Iotti, Eleonora; Prati, Andrea. - (2019), pp. 280-291. (Intervento presentato al convegno International Conference on Image Analysis and Processing tenutosi a Trento, Italy nel 9-13 September 2019).
MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization
Tomaso FontaniniMethodology
;Eleonora IottiSoftware
;Andrea PratiSupervision
2019-01-01
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 metalearning, 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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.