mlsanityData to 7 Oct 2026

Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels

arXiv 2208.00439 ↗First posted 31 Jul 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) have been trained to be professional artists able to create stunning artworks such as face generation and image style transfer. In this paper, we focus on a realistic business scenario: automated generation of customizable icons given desired mobile applications and theme styles. We first introduce a theme-application icon dataset, termed AppIcon, where each icon has two orthogonal theme and app labels. By investigating a strong baseline StyleGAN2, we observe mode collapse caused by the entanglement of the orthogonal labels. To solve this challenge, we propose IconGAN composed of a conditional generator and dual discriminators with orthogonal augmentations, and a contrastive feature disentanglement strategy is further designed to regularize the feature space of the two discriminators. Compared with other approaches, IconGAN indicates a superior advantage on the AppIcon benchmark. Further analysis also justifies the effectiveness of disentangling app and theme representations. Our project will be released at: https://github.com/architect-road/IconGAN.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 31 Jul 2022.

Builds on

32 of 47 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  11. 2014Conditional Generative Adversarial Netscited by 2,152
  12. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
20 more
  1. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  3. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  4. 2018Self-Attention Generative Adversarial Networkscited by 809
  5. 2018Which Training Methods for GANs do actually Converge?cited by 672
  6. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  7. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  8. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  9. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  10. 2019Controllable Text-to-Image Generationcited by 187
  11. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  12. 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
  13. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  14. 2021Image-to-image Translation via Hierarchical Style Disentanglementcited by 63
  15. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
  16. 2019Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classificationcited by 22
  17. 2017Logo Synthesis and Manipulation with Clustered Generative Adversarial Networkscited by 20
  18. 2021ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approachcited by 20
  19. 2018LoGAN: Generating Logos with a Generative Adversarial Neural Network Conditioned on colorcited by 6
  20. 2019LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 73
  2. 2023Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regressioncited by 7
  3. 2026Steering Generative Models for Accessibility: EasyRead Image Generationcited by 0