mlsanityData to 7 Oct 2026

DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta

arXiv 2207.10271 ↗First posted 21 Jul 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning to generate new images for a novel category based on only a few images, named as few-shot image generation, has attracted increasing research interest. Several state-of-the-art works have yielded impressive results, but the diversity is still limited. In this work, we propose a novel Delta Generative Adversarial Network (DeltaGAN), which consists of a reconstruction subnetwork and a generation subnetwork. The reconstruction subnetwork captures intra-category transformation, i.e., delta, between same-category pairs. The generation subnetwork generates sample-specific delta for an input image, which is combined with this input image to generate a new image within the same category. Besides, an adversarial delta matching loss is designed to link the above two subnetworks together. Extensive experiments on six benchmark datasets demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/bcmi/DeltaGAN-Few-Shot-Image-Generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 67 of its 90 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

67 of 90 references.

References · 67

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  7. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
38 more
  1. 2018Demystifying MMD GANscited by 1,268
  2. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  3. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  4. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  5. 2016Least Squares Generative Adversarial Networkscited by 1,000
  6. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  7. 2018Which Training Methods for GANs do actually Converge?cited by 672
  8. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  9. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  10. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  11. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  12. 2017Toward Multimodal Image-to-Image Translationcited by 295
  13. 2017Data Augmentation Generative Adversarial Networkscited by 278
  14. 2018cGANs with Projection Discriminatorcited by 253
  15. 2017Pose Guided Person Image Generationcited by 251
  16. 2019Fast AutoAugmentcited by 243
  17. 2019Large Scale Adversarial Representation Learningcited by 238
  18. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  19. 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
  20. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  21. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  22. 2018Low-Shot Learning from Imaginary Datacited by 181
  23. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  24. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  25. 2019Progressive Pose Attention Transfer for Person Image Generationcited by 138
  26. 2016Variational Autoencoder for Deep Learning of Images, Labels and Captionscited by 137
  27. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  28. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  29. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  30. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  31. 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
  32. 2017Learning to Compose Domain-Specific Transformations for Data Augmentationcited by 91
  33. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  34. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  35. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
  36. 2020Few-Shot Adaptation of Generative Adversarial Networkscited by 64
  37. 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
  38. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56

50 most cited of 67 All 67 (JSON)

Built on by

Not cited yet.