Coloring with Limited Data: Few-Shot Colorization via Memory Augmented Networks
Abstract
Despite recent advancements in deep learning-based automatic colorization, they are still limited when it comes to few-shot learning. Existing models require a significant amount of training data. To tackle this issue, we present a novel memory-augmented colorization model MemoPainter that can produce high-quality colorization with limited data. In particular, our model is able to capture rare instances and successfully colorize them. Also, we propose a novel threshold triplet loss that enables unsupervised training of memory networks without the need for class labels. Experiments show that our model has superior quality in both few-shot and one-shot colorization tasks.
Cite
Text
Yoo et al. "Coloring with Limited Data: Few-Shot Colorization via Memory Augmented Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01154Markdown
[Yoo et al. "Coloring with Limited Data: Few-Shot Colorization via Memory Augmented Networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/yoo2019cvpr-coloring/) doi:10.1109/CVPR.2019.01154BibTeX
@inproceedings{yoo2019cvpr-coloring,
title = {{Coloring with Limited Data: Few-Shot Colorization via Memory Augmented Networks}},
author = {Yoo, Seungjoo and Bahng, Hyojin and Chung, Sunghyo and Lee, Junsoo and Chang, Jaehyuk and Choo, Jaegul},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.01154},
url = {https://mlanthology.org/cvpr/2019/yoo2019cvpr-coloring/}
}