# Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1712.04407 · HTML: https://mlsanity.com/paper/1712.04407/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2017.

## Built on by (most cited first, 20 of 20)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Ensembling Off-the-shelf Models for GAN Training](https://mlsanity.com/paper/2112.09130/) (2021)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines -- From Medical to Remote Sensing](https://mlsanity.com/paper/2110.01442/) (2021)
- [Partition-Guided GANs](https://mlsanity.com/paper/2104.00816/) (2021)
- [LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer](https://mlsanity.com/paper/2312.09935/) (2023)
- [Design What You Desire: Icon Generation from Orthogonal Application and Theme Labels](https://mlsanity.com/paper/2208.00439/) (2022)
- [Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing](https://mlsanity.com/paper/2408.12099/) (2024)
- [Multi-Label Logo Recognition and Retrieval based on Weighted Fusion of Neural Features](https://mlsanity.com/paper/2205.05419/) (2022)
- [Temporal Pair Consistency for Variance-Reduced Flow Matching](https://mlsanity.com/paper/2602.04908/) (2026)
- [Unsupervised Image Generation with Infinite Generative Adversarial Networks](https://mlsanity.com/paper/2108.07975/) (2021)
- [Famous Companies Use More Letters in Logo:A Large-Scale Analysis of Text Area in Logo](https://mlsanity.com/paper/2104.00327/) (2021)
- [Logo Generation Using Regional Features: A Faster R-CNN Approach to Generative Adversarial Networks](https://mlsanity.com/paper/2109.12628/) (2021)
- [Interspecies Collaboration in the Design of Visual Identity: A Case Study](https://mlsanity.com/paper/2201.10393/) (2022)
- [Rooms with Text: A Dataset for Overlaying Text Detection](https://mlsanity.com/paper/2211.11350/) (2022)
- [DualVAE: Controlling Colours of Generated and Real Images](https://mlsanity.com/paper/2305.18769/) (2023)
- [Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network](https://mlsanity.com/paper/2407.04334/) (2024)
- [GRAPHIC--Guidelines for Reviewing Algorithmic Practices in Human-centred Design and Interaction for Creativity](https://mlsanity.com/paper/2511.17443/) (2025)

## Abstract (arXiv)

Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset -- LLD -- of 600k+ logos crawled from the world wide web. Training Generative Adversarial Networks (GANs) for logo synthesis on such multi-modal data is not straightforward and results in mode collapse for some state-of-the-art methods. We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training. We are able to generate a high diversity of plausible logos and we demonstrate latent space exploration techniques to ease the logo design task in an interactive manner. Moreover, we validate the proposed clustered GAN training on CIFAR 10, achieving state-of-the-art Inception scores when using synthetic labels obtained via clustering the features of an ImageNet classifier. GANs can cope with multi-modal data by means of synthetic labels achieved through clustering, and our results show the creative potential of such techniques for logo synthesis and manipulation. Our dataset and models will be made publicly available at https://data.vision.ee.ethz.ch/cvl/lld/.