mlsanityData to 7 Oct 2026

OSSGAN: Open-Set Semi-Supervised Image Generation

arXiv 2204.14249 ↗First posted 29 Apr 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce a challenging training scheme of conditional GANs, called open-set semi-supervised image generation, where the training dataset consists of two parts: (i) labeled data and (ii) unlabeled data with samples belonging to one of the labeled data classes, namely, a closed-set, and samples not belonging to any of the labeled data classes, namely, an open-set. Unlike the existing semi-supervised image generation task, where unlabeled data only contain closed-set samples, our task is more general and lowers the data collection cost in practice by allowing open-set samples to appear. Thanks to entropy regularization, the classifier that is trained on labeled data is able to quantify sample-wise importance to the training of cGAN as confidence, allowing us to use all samples in unlabeled data. We design OSSGAN, which provides decision clues to the discriminator on the basis of whether an unlabeled image belongs to one or none of the classes of interest, smoothly integrating labeled and unlabeled data during training. The results of experiments on Tiny ImageNet and ImageNet show notable improvements over supervised BigGAN and semi-supervised methods. Our code is available at https://github.com/raven38/OSSGAN.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 23 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

20 of 23 references.

References · 20

  1. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2014Conditional Generative Adversarial Netscited by 2,152
  5. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2018Self-Attention Generative Adversarial Networkscited by 809
  8. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  9. 2018Assessing Generative Models via Precision and Recallcited by 401
  10. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  11. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  12. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
8 more
  1. 2018Self-Supervised GANs via Auxiliary Rotation Losscited by 94
  2. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 85
  3. 2020Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learningcited by 82
  4. 2020Improved Techniques for Training Single-Image GANscited by 77
  5. 2017Triple Generative Adversarial Netscited by 59
  6. 2019High-Fidelity Image Generation With Fewer Labelscited by 51
  7. 2017Structured Generative Adversarial Networkscited by 4
  8. 2017Semi-supervised Conditional GANscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  2. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2
  3. 2023Soft Curriculum for Learning Conditional GANs with Noisy-Labeled and Uncurated Unlabeled Datacited by 0
  4. 2024Learning from Concealed Labelscited by 0