mlsanityData to 7 Oct 2026

ReMix: Towards Image-to-Image Translation with Limited Data

arXiv 2103.16835 ↗First posted 31 Mar 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Image-to-image (I2I) translation methods based on generative adversarial networks (GANs) typically suffer from overfitting when limited training data is available. In this work, we propose a data augmentation method (ReMix) to tackle this issue. We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples. The generator learns to translate the in-between samples rather than memorizing the training set, and thereby forces the discriminator to generalize. The proposed approach effectively reduces the ambiguity of generation and renders content-preserving results. The ReMix method can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ReMix method achieve significant improvements.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 38 of its 45 references that are in the map. First posted on arXiv 31 Mar 2021.

Builds on

38 of 45 references.

References · 38

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  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. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  9. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  10. 2017Improved Training of Wasserstein GANscited by 2,223
  11. 2014Conditional Generative Adversarial Netscited by 2,152
  12. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
26 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  2. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  5. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  6. 2016Least Squares Generative Adversarial Networkscited by 1,000
  7. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  8. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  9. 2018Which Training Methods for GANs do actually Converge?cited by 672
  10. 2017Wasserstein GANcited by 635
  11. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  12. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  13. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  14. 2017Dilated Residual Networkscited by 293
  15. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  16. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  17. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  18. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  19. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  20. 2016Unsupervised Cross-Domain Image Generationcited by 125
  21. 2017Dataset Augmentation in Feature Spacecited by 124
  22. 2020Image Augmentations for GAN Trainingcited by 78
  23. 2020COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encodercited by 39
  24. 2020On Data Augmentation for GAN Trainingcited by 25
  25. 2019On Adversarial Mixup Resynthesiscited by 2
  26. 2015HDIdx: High-Dimensional Indexing for Efficient Approximate Nearest Neighbor Searchcited by 1

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 2; 2024: 1.

9 papers.

  1. 2022Region-aware Knowledge Distillation for Efficient Image-to-Image Translationcited by 10
  2. 2022DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Datacited by 7
  3. 2021ManiFest: Manifold Deformation for Few-shot Image Translationcited by 6
  4. 2022Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Datacited by 6
  5. 2023UGC: Unified GAN Compression for Efficient Image-to-Image Translationcited by 3
  6. 2022ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Datacited by 2
  7. 2024Prompt Augmentation for Self-supervised Text-guided Image Manipulationcited by 2
  8. 2021Leveraging Local Domains for Image-to-Image Translationcited by 1
  9. 2023Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Reviewcited by 0