# Large-scale Tag-based Font Retrieval with Generative Feature Learning

arXiv: https://arxiv.org/abs/1909.02072 · HTML: https://mlsanity.com/paper/1909.02072/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2019.

## Built on by (most cited first, 22 of 22)

- [De-rendering Stylized Texts](https://mlsanity.com/paper/2110.01890/) (2021)
- [Impressions2Font: Generating Fonts by Specifying Impressions](https://mlsanity.com/paper/2103.10036/) (2021)
- [FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications](https://mlsanity.com/paper/2403.06453/) (2024)
- [Shared Latent Space of Font Shapes and Their Noisy Impressions](https://mlsanity.com/paper/2103.12347/) (2021)
- [Which Parts Determine the Impression of the Font?](https://mlsanity.com/paper/2103.14216/) (2021)
- [Font Generation with Missing Impression Labels](https://mlsanity.com/paper/2203.10348/) (2022)
- [AdaptiFont: Increasing Individuals' Reading Speed with a Generative Font Model and Bayesian Optimization](https://mlsanity.com/paper/2104.10741/) (2021)
- [Ambigram Generation by A Diffusion Model](https://mlsanity.com/paper/2306.12049/) (2023)
- [GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models](https://mlsanity.com/paper/2408.07259/) (2024)
- [Font Shape-to-Impression Translation](https://mlsanity.com/paper/2203.05808/) (2022)
- [Font Style Interpolation with Diffusion Models](https://mlsanity.com/paper/2402.14311/) (2024)
- [Impression-CLIP: Contrastive Shape-Impression Embedding for Fonts](https://mlsanity.com/paper/2402.16350/) (2024)
- [VecGlypher: Unified Vector Glyph Generation with Language Models](https://mlsanity.com/paper/2602.21461/) (2026)
- [AmbiGen: Generating Ambigrams from Pre-trained Diffusion Model](https://mlsanity.com/paper/2312.02967/) (2023)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [TrueType Transformer: Character and Font Style Recognition in Outline Format](https://mlsanity.com/paper/2203.05338/) (2022)
- [Contextual Font Recommendations based on User Intent](https://mlsanity.com/paper/2306.08188/) (2023)
- [Embedding Font Impression Word Tags Based on Co-occurrence](https://mlsanity.com/paper/2508.18825/) (2025)
- [Font Representation Learning via Paired-glyph Matching](https://mlsanity.com/paper/2211.10967/) (2022)
- [Total Disentanglement of Font Images into Style and Character Class Features](https://mlsanity.com/paper/2403.12784/) (2024)
- [FontUse: A Data-Centric Approach to Style- and Use-Case-Conditioned In-Image Typography](https://mlsanity.com/paper/2603.06038/) (2026)
- [Hierarchical Co-Embedding of Font Shapes and Impression Tags](https://mlsanity.com/paper/2604.04158/) (2026)

## Abstract (arXiv)

Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag relations. We propose a novel generative feature learning algorithm that leverages the unique characteristics of fonts. The key idea is that font images are synthetic and can therefore be controlled by the learning algorithm. We design an integrated rendering and learning process so that the visual feature from one image can be used to reconstruct another image with different text. The resulting feature captures important font design details while is robust to nuisance factors such as text. We propose a novel attention mechanism to re-weight the visual feature for joint visual-text modeling. We combine the feature and the attention mechanism in a novel recognition-retrieval model. Experimental results show that our method significantly outperforms the state-of-the-art for the important problem of large-scale tag-based font retrieval.