MetalGAN: A Cluster-Based Adaptive Training for Few-Shot Adversarial Colorization

Fontanini, Tomaso; Iotti, Eleonora; Prati, Andrea

doi:10.1007/978-3-030-30642-7_25

Cited by 5 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike most colorization algorithms that involve the system's training over large datasets, this paper [49] aims on providing just as good colorization results without the need for huge training datasets. Emphasizing the use of few-shot learning and one-shot learning, the network is then responsible to have a high generalization capacity because of the limited training datasets.…”

Section: Tomasofontaniniet Al [49]mentioning

confidence: 99%

Image Colorization Progress: A Review of Deep Learning Techniques for Automation of Colorization

2021

IJATCSE

View full text Add to dashboard Cite

Image colorization is the process of taking an input gray- scale (black and white) image and then producing an output colorized image that represents the semantic color tones of the input. Since the past few years, the process of automatic image colorization has been of significant interest and a lot of progress has been made in the field by various researchers. Image colorization finds its application in many domains including medical imaging, restoration of historical documents, etc. There have been different approaches to solve this problem using Convolutional Neural Networks as well as Generative Adversarial Networks. These colorization networks are not only based on different architectures but also are tested on varied data sets. This paper aims to cover some of these proposed approaches through different techniques. The results between the generative models and traditional deep neural networks are compared along with presenting the current limitations in those. The paper proposes a summarized view of past and current advances in the field of image colorization contributed by different authors and researchers.

show abstract

Section: Tomasofontaniniet Al [49]mentioning

confidence: 99%

Image Colorization Progress: A Review of Deep Learning Techniques for Automation of Colorization

2021

IJATCSE

View full text Add to dashboard Cite

show abstract

“…On the other hand, unlabeled data has to be clustered into domains, a passage that can be completely automated (in contrast with manual labeling), but using a clustering method, domains does not overlap. A clusterization followed by a meta-learning approach is shown in a preliminary work on colorization [7]. The generator network G is the same as the StarGAN one with the addition of skip-connections (inspired by the classic U-Net), but input labels are removed.…”

Section: Architecture Of the Networkmentioning

confidence: 99%

MetalGAN: Multi-Domain Label-Less Image Synthesis Using cGANs and Meta-Learning

Fontanini¹,

Iotti²,

Donati³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Image synthesis is currently one of the most addressed image processing topic in computer vision and deep learning fields of study. Researchers have tackled this problem focusing their efforts on its several challenging problems, e.g. image quality and size, domain and pose changing, architecture of the networks, and so on. Above all, producing images belonging to different domains by using a single architecture is a very relevant goal for image generation. In fact, a single multi-domain network would allow greater flexibility and robustness in the image synthesis task than other approaches. This paper proposes a novel architecture and a training algorithm, which are able to produce multi-domain outputs using a single network. A small portion of a dataset is intentionally used, and there are no hard-coded labels (or classes). This is achieved by combining a conditional Generative Adversarial Network (cGAN) for image generation and a Meta-Learning algorithm for domain switch, and we called our approach MetalGAN. The approach has proved to be appropriate for solving the multi-domain problem and it is validated on facial attribute transfer, using CelebA dataset.

show abstract