mlsanityData to 14 Oct 2026

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

arXiv 1906.11888 ↗First posted 9 Jun 2019cs.CVcited by 32

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 13; 2023: 5; 2024: 1.

32 papers.

Sort:

  1. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  2. 2021Cross Modal Retrieval with Querybank Normalisationcited by 72
  3. 2023Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generationcited by 61
  4. 2021Video-based Person Re-identification with Spatial and Temporal Memory Networkscited by 35
  5. 2023MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimationcited by 24
  6. 2021Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learningcited by 22
  7. 2021Deep Edge-Aware Interactive Colorization against Color-Bleeding Effectscited by 12
  8. 2021Semantic-Sparse Colorization Network for Deep Exemplar-based Colorizationcited by 12
  9. 2023HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognitioncited by 12
  10. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  11. 2021Wavelet Transform-assisted Adaptive Generative Modeling for Colorizationcited by 8
  12. 2022Pik-Fix: Restoring and Colorizing Old Photoscited by 8
20 more
  1. 2021Focusing on Persons: Colorizing Old Images Learning from Modern Historical Moviescited by 6
  2. 2023Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translationcited by 6
  3. 2021Remember What You have drawn: Semantic Image Manipulation with Memorycited by 3
  4. 2022ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networkscited by 3
  5. 2022Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritizationcited by 3
  6. 2023MFIM: Megapixel Facial Identity Manipulationcited by 3
  7. 2021MISS GAN: A Multi-IlluStrator Style Generative Adversarial Network for image to illustration translationcited by 2
  8. 2021Separating Content and Style for Unsupervised Image-to-Image Translationcited by 1
  9. 2022Analysis of Different Losses for Deep Learning Image Colorizationcited by 1
  10. 2022Cross-Camera Deep Colorizationcited by 1
  11. 2022Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformercited by 1
  12. 2021CNN with large memory layerscited by 0
  13. 2021Towards Photorealistic Colorization by Imaginationcited by 0
  14. 2022ROMNet: Renovate the Old Memoriescited by 0
  15. 2022MOST-Net: A Memory Oriented Style Transfer Network for Face Sketch Synthesiscited by 0
  16. 2022Styleverse: Towards Identity Stylization across Heterogeneous Domainscited by 0
  17. 2022Influence of Color Spaces for Deep Learning Image Colorizationcited by 0
  18. 2022Human vs Objective Evaluation of Colourisation Performancecited by 0
  19. 2022iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformercited by 0
  20. 2024Computer-aided Colorization State-of-the-science: A Surveycited by 0