Research map / Image generation / Text-to-image diffusion
Large-Scale Tag-Based Font Retrieval With Generative Feature Learning
Tianlang Chen, Zhaowen Wang, Ning Xu, Hailin Jin, Jiebo Luo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add generative feature learning (GAN) module (ablation) | Ours-Basic · MyFonts-test (single tag, 300 tags) | mAP: 26.29 -> 26.99 | Improved |
| add generative feature learning (GAN) module (ablation) | Ours-Basic · MyFonts-test (multi tag) | mAP: 14.93 -> 15.37 | Improved |
| add attentive feature selection (ablation) | Ours-Basic · MyFonts-test (single tag, 300 tags) | mAP: 26.29 -> 27.75 | Improved |
| add attentive feature selection (ablation) | Ours-Basic · MyFonts-test (single tag, full) | mAP: 16.77 -> 17.76 | Improved |
| add attentive feature selection (ablation) | Ours-Basic · MyFonts-test (multi tag) | mAP: 14.93 -> 15.78 | Improved |
| add both GAN and attention modules (ablation) | Ours-Basic · MyFonts-test (single tag, 300 tags) | mAP: 26.29 -> 28.08 | Improved |
| add both GAN and attention modules (ablation) | Ours-Basic · MyFonts-test (single tag, full) | NDCG: 42.63 -> 43.95 | Improved |
| add retrieval model on top of recognition model (ablation) | Ours w/ GAN+Att · MyFonts-test (multi tag) | mAP: 16.06 -> 16.74 | Improved |
| add retrieval model on top of recognition model (ablation) | Ours w/ GAN+Att · MyFonts-test (multi tag) | NDCG: 36.72 -> 37.57 | Improved |
| add retrieval model on top of recognition model (ablation) | Ours w/ GAN+Att · MyFonts-test (single tag, 300 tags) | mAP: 28.08 -> 28.08 | No clear effect |
| use recognition model with multi-label cross-entropy instead of joint-embedding retrieval | RelationNet · MyFonts-test (single tag, 300 tags) | mAP: 15.33 -> 26.29 | Improved |
| add full model modules to basic recognition model | Ours-Basic · AMT-test | accuracy: 44.49 -> 47.50 | Improved |
Closest papers by meaning
- Font-Agent: Enhancing Font Understanding with Large Language Models (CVPR 2025 · similarity 0.88)
- A Multi-Implicit Neural Representation for Fonts (NeurIPS 2021 · similarity 0.85)
- Look Closer To Supervise Better: One-Shot Font Generation via Component-Based Discriminator (CVPR 2022 · similarity 0.85)
- FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning (AAAI 2024 · similarity 0.85)
- Few-Shot Font Generation With Weakly Supervised Localized Representations (TPAMI 2022 · similarity 0.85)
- Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models (CVPR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
