# Coloring With Limited Data: Few-Shot Colorization via Memory-Augmented Networks

arXiv: https://arxiv.org/abs/1906.11888 · HTML: https://mlsanity.com/paper/1906.11888/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jun 2019.

## Built on by (most cited first, 30 of 32)

- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Cross Modal Retrieval with Querybank Normalisation](https://mlsanity.com/paper/2112.12777/) (2021)
- [Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation](https://mlsanity.com/paper/2307.09906/) (2023)
- [Video-based Person Re-identification with Spatial and Temporal Memory Networks](https://mlsanity.com/paper/2108.09039/) (2021)
- [MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation](https://mlsanity.com/paper/2307.14336/) (2023)
- [Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning](https://mlsanity.com/paper/2110.04562/) (2021)
- [Deep Edge-Aware Interactive Colorization against Color-Bleeding Effects](https://mlsanity.com/paper/2107.01619/) (2021)
- [Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization](https://mlsanity.com/paper/2112.01335/) (2021)
- [HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition](https://mlsanity.com/paper/2301.03330/) (2023)
- [Few-Shot Learning by Integrating Spatial and Frequency Representation](https://mlsanity.com/paper/2105.05348/) (2021)
- [Wavelet Transform-assisted Adaptive Generative Modeling for Colorization](https://mlsanity.com/paper/2107.04261/) (2021)
- [Pik-Fix: Restoring and Colorizing Old Photos](https://mlsanity.com/paper/2205.01902/) (2022)
- [Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies](https://mlsanity.com/paper/2108.06515/) (2021)
- [Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation](https://mlsanity.com/paper/2308.03348/) (2023)
- [Remember What You have drawn: Semantic Image Manipulation with Memory](https://mlsanity.com/paper/2107.12579/) (2021)
- [ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networks](https://mlsanity.com/paper/2204.02824/) (2022)
- [Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization](https://mlsanity.com/paper/2210.14270/) (2022)
- [MFIM: Megapixel Facial Identity Manipulation](https://mlsanity.com/paper/2308.01536/) (2023)
- [MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translation](https://mlsanity.com/paper/2108.05693/) (2021)
- [Separating Content and Style for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2110.14404/) (2021)
- [Analysis of Different Losses for Deep Learning Image Colorization](https://mlsanity.com/paper/2204.02980/) (2022)
- [Cross-Camera Deep Colorization](https://mlsanity.com/paper/2209.01211/) (2022)
- [Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer](https://mlsanity.com/paper/2212.03434/) (2022)
- [CNN with large memory layers](https://mlsanity.com/paper/2101.11685/) (2021)
- [Towards Photorealistic Colorization by Imagination](https://mlsanity.com/paper/2108.09195/) (2021)
- [ROMNet: Renovate the Old Memories](https://mlsanity.com/paper/2202.02606/) (2022)
- [MOST-Net: A Memory Oriented Style Transfer Network for Face Sketch Synthesis](https://mlsanity.com/paper/2202.03596/) (2022)
- [Styleverse: Towards Identity Stylization across Heterogeneous Domains](https://mlsanity.com/paper/2203.00861/) (2022)
- [Influence of Color Spaces for Deep Learning Image Colorization](https://mlsanity.com/paper/2204.02850/) (2022)
- [Human vs Objective Evaluation of Colourisation Performance](https://mlsanity.com/paper/2204.05200/) (2022)

## Abstract (arXiv)

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.