# Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks Source: [Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:39:29.972Z Authors: Seungjoo Yoo, Hyojin Bahng, Sunghyo Chung, Junsoo Lee, Jaehyuk Chang, Jaegul Choo Published: 2019-06-09T07:26:54.000Z ## 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. We also propose a novel threshold triplet loss that enables unsupervised training of memory networks without the need of class labels. Experiments show that our model has superior quality in both few-shot and one-shot colorization tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Grayscale Image Colorization on VCIP 2020 (test)](): Grayscale Image Colorization; VCIP 2020 (test); PSNR: 28.56. ## Original sources and implementation [Original paper]() [PDF]()