mlsanityData to 7 Oct 2026

Adaptive Feature Interpolation for Low-Shot Image Generation

arXiv 2112.02450 ↗First posted 4 Dec 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Training of generative models especially Generative Adversarial Networks can easily diverge in low-data setting. To mitigate this issue, we propose a novel implicit data augmentation approach which facilitates stable training and synthesize high-quality samples without need of label information. Specifically, we view the discriminator as a metric embedding of the real data manifold, which offers proper distances between real data points. We then utilize information in the feature space to develop a fully unsupervised and data-driven augmentation method. Experiments on few-shot generation tasks show the proposed method significantly improve results from strong baselines with hundreds of training samples.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 4 Dec 2021.

Builds on

27 of 42 references.

References · 27

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  2. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  4. 2018Demystifying MMD GANscited by 1,268
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  6. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  7. 2018Assessing Generative Models via Precision and Recallcited by 401
  8. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  9. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  10. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  11. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  12. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
15 more
  1. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  2. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 127
  3. 2017Dataset Augmentation in Feature Spacecited by 124
  4. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  5. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  6. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 105
  7. 2017The Riemannian Geometry of Deep Generative Modelscited by 81
  8. 2021Learning in High Dimension Always Amounts to Extrapolationcited by 62
  9. 2020F2GAN: Fusing-and-Filling GAN for Few-shot Image Generationcited by 29
  10. 2020Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learningcited by 27
  11. 2020Automated Relational Meta-learningcited by 25
  12. 2020DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Deltacited by 22
  13. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  14. 2021Manifold Matching via Deep Metric Learning for Generative Modelingcited by 3
  15. 2021Rethinking Multidimensional Discriminator Output for Generative Adversarial Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 2.

6 papers.

  1. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
  2. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  3. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  4. 2025Phi-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Datacited by 4
  5. 2023A survey of manifold learning and its applications for multimediacited by 1
  6. 2024Noisy Data Visualization using Functional Data Analysiscited by 0