InfoGAN

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets. This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that also maximizes the mutual information between a small subset of the latent variables and the observation. We derive a lower bound to the mutual information objective that can be optimized efficiently, and show that our training procedure can be interpreted as a variation of the Wake-Sleep algorithm. Specifically, InfoGAN successfully disentangles writing styles from digit shapes on the MNIST dataset, pose from lighting of 3D rendered images, and background digits from the central digit on the SVHN dataset. It also discovers visual concepts that include hair styles, presence/absence of eyeglasses, and emotions on the CelebA face dataset. Experiments show that InfoGAN learns interpretable representations that are competitive with representations learned by existing fully supervised methods.


References in zbMATH (referenced in 22 articles )

Showing results 1 to 20 of 22.
Sorted by year (citations)

1 2 next

  1. Rudin, Cynthia; Chen, Chaofan; Chen, Zhi; Huang, Haiyang; Semenova, Lesia; Zhong, Chudi: Interpretable machine learning: fundamental principles and 10 grand challenges (2022)
  2. Akuzawa, Kei; Iwasawa, Yusuke; Matsuo, Yutaka: Information-theoretic regularization for learning global features by sequential VAE (2021)
  3. Benny, Yaniv; Galanti, Tomer; Benaim, Sagie; Wolf, Lior: Evaluation metrics for conditional image generation (2021)
  4. Karn N. Watcharasupat, Junyoung Lee, Alexander Lerch: Latte: Cross-framework Python Package for Evaluation of Latent-Based Generative Models (2021) arXiv
  5. Ke, Liyiming; Choudhury, Sanjiban; Barnes, Matt; Sun, Wen; Lee, Gilwoo; Srinivasa, Siddhartha: Imitation learning as (f)-divergence minimization (2021)
  6. Li, Haoliang; Wan, Renjie; Wang, Shiqi; Kot, Alex C.: Unsupervised domain adaptation in the wild via disentangling representation learning (2021)
  7. Paul, William; Wang, I-Jeng; Alajaji, Fady; Burlina, Philippe: Unsupervised discovery, control, and disentanglement of semantic attributes with applications to anomaly detection (2021)
  8. Qi, Zhongang; Khorram, Saeed; Fuxin, Li: Embedding deep networks into visual explanations (2021)
  9. Abbasnejad, M. Ehsan; Shi, Javen; van den Hengel, Anton; Liu, Lingqiao: GADE: a generative adversarial approach to density estimation and its applications (2020)
  10. Blusseau, Samy; Ponchon, Bastien; Velasco-Forero, Santiago; Angulo, Jesús; Bloch, Isabelle: Approximating morphological operators with part-based representations learned by asymmetric auto-encoders (2020)
  11. Gatti, Filippo; Clouteau, Didier: Towards blending physics-based numerical simulations and seismic databases using generative adversarial network (2020)
  12. Locatello, Francesco; Bauer, Stefan; Lucic, Mario; Raetsch, Gunnar; Gelly, Sylvain; Schölkopf, Bernhard; Bachem, Olivier: A sober look at the unsupervised learning of disentangled representations and their evaluation (2020)
  13. Qi, Guo-Jun: Loss-sensitive generative adversarial networks on Lipschitz densities (2020)
  14. Schmidhuber, Jürgen: Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991) (2020)
  15. Shang, Fei; Zhang, Huaxiang; Sun, Jiande; Nie, Liqiang; Liu, Li: Cross-modal dual subspace learning with adversarial network (2020)
  16. Situ, Haozhen; He, Zhimin; Wang, Yuyi; Li, Lvzhou; Zheng, Shenggen: Quantum generative adversarial network for generating discrete distribution (2020)
  17. Castro, Daniel C.; Tan, Jeremy; Kainz, Bernhard; Konukoglu, Ender; Glocker, Ben: Morpho-MNIST: quantitative assessment and diagnostics for representation learning (2019)
  18. Chen, Pei-Yin; Huang, Jih-Jeng: A hybrid autoencoder network for unsupervised image clustering (2019)
  19. Han, Tian; Xing, Xianglei; Wu, Jiawen; Wu, Ying Nian: Replicating neuroscience observations on ML/MF and AM face patches by deep generative model (2019)
  20. Lorimer, Tom; Kanders, Karlis; Stoop, Ruedi: Natural data structure extracted from neighborhood-similarity graphs (2019)

1 2 next