mlsanityData to 7 Oct 2026

Double InfoGAN for Contrastive Analysis

arXiv 2401.17776 ↗First posted 31 Jan 2024cs.CV cs.AI stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

Contrastive Analysis (CA) deals with the discovery of what is common and what is distinctive of a target domain compared to a background one. This is of great interest in many applications, such as medical imaging. Current state-of-the-art (SOTA) methods are latent variable models based on VAE (CA-VAEs). However, they all either ignore important constraints or they don't enforce fundamental assumptions. This may lead to sub-optimal solutions where distinctive factors are mistaken for common ones (or viceversa). Furthermore, the generated images have a rather poor quality, typical of VAEs, decreasing their interpretability and usefulness. Here, we propose Double InfoGAN, the first GAN based method for CA that leverages the high-quality synthesis of GAN and the separation power of InfoGAN. Experimental results on four visual datasets, from simple synthetic examples to complex medical images, show that the proposed method outperforms SOTA CA-VAEs in terms of latent separation and image quality. Datasets and code are available online.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 36 of its 72 references that are in the map. First posted on arXiv 31 Jan 2024.

Builds on

36 of 72 references.

References · 36

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  10. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  11. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  12. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
24 more
  1. 2018Disentangling by Factorisingcited by 614
  2. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  3. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  4. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 308
  5. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  6. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 278
  7. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  8. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  9. 2020Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Studycited by 146
  10. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  11. 2019Weakly Supervised Disentanglement with Guaranteescited by 82
  12. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  13. 2022Unbiased Supervised Contrastive Learningcited by 40
  14. 2020Capturing Label Characteristics in VAEscited by 30
  15. 2017Angle-Based Joint and Individual Variation Explainedcited by 29
  16. 2018Style and Content Disentanglement in Generative Adversarial Networkscited by 29
  17. 2019Contrastive Variational Autoencoder Enhances Salient Featurescited by 28
  18. 2019Domain Intersection and Domain Differencecited by 17
  19. 2018Unsupervised learning with contrastive latent variable modelscited by 15
  20. 2020NestedVAE: Isolating Common Factors via Weak Supervisioncited by 13
  21. 2022Moment Matching Deep Contrastive Latent Variable Modelscited by 13
  22. 2022A deep residual learning implementation of Metamorphosiscited by 6
  23. 2016Common and Distinct Components in Data Fusioncited by 4
  24. 2021Capturing patterns of variation unique to a specific datasetcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 4.

7 papers.

  1. 2024Separating common from salient patterns with Contrastive Representation Learningcited by 6
  2. 2025Learning Common and Salient Generative Factors Between Two Image Datasetscited by 3
  3. 2024Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion modelscited by 1
  4. 2026Diff-CA: Separating Common and Salient Factors with Diffusion Modelscited by 1
  5. 2026Margin-Consistent Deep Subtyping of Invasive Lung Adenocarcinoma via Perturbation Fidelity in Whole-Slide Image Analysiscited by 0
  6. 2026Counterfactual Contrastive Analysiscited by 0
  7. 2026SAGE: Salient Factor Discovery and Generation with Visual Foundation Representationscited by 0