Semi Few-Shot Attribute Translation
This addresses the data scarcity issue in supervised methods for image-to-image translation, enabling applications in domains with limited labeled data, though it appears incremental by combining existing techniques.
The paper tackles the problem of image-to-image translation for attribute transfer with limited labeled data by proposing a GAN-based meta-training approach, achieving results using just a few samples for new target classes in hair color synthesis tasks.
Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and require an abundant amount of labeled data to produce good results, therefore limiting their applicability. In the same vein, recent advances in meta-learning have led to successful implementations with limited available data, allowing so-called few-shot learning. In this paper, we address this limitation of supervised methods, by proposing a novel approach based on GANs. These are trained in a meta-training manner, which allows them to perform image-to-image translations using just a few labeled samples from a new target class. This work empirically demonstrates the potential of training a GAN for few shot image-to-image translation on hair color attribute synthesis tasks, opening the door to further research on generative transfer learning.