Research map / Image generation / Editing and style transfer
GAN-Based Domain Adaptation for Image-Aware Layout Generation in Advertising Poster Design
Chenchen Xu, Min Zhou, Tiezheng Ge, Weiwei Xu
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 the pixel-level discriminator (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 15.13 -> 12.77 | Improved |
| apply Gaussian blur to input images (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_com: 33.55 -> 36.71 | Hurt |
| apply Gaussian blur to input images (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 12.77 -> 20.14 | Hurt |
| replace global discriminator with pixel-level discriminator (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 13.78 -> 12.77 | Improved |
| replace PatchGAN 88*60 with pixel-level discriminator (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 13.35 -> 12.77 | Improved |
| attach PD to shallow instead of deep features (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 13.97 -> 12.77 | Improved |
| attach PD to shallow instead of fused features (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 14.54 -> 12.77 | Improved |
| add one-target label smoothing (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 14.04 -> 12.77 | Improved |
| use one-target instead of one-source label smoothing (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 15.23 -> 12.77 | Improved |
| use 7x7 kernel instead of 3x3 in PD (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_com: R_com 31.69 vs 33.55; R_shm 14.73 vs 12.77 | Mixed |
| vary PD depth (2, 3, 6, 9 layers) (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_shm: 13.48, 12.77, 15.25, 13.80 | No clear effect |
| replace DETR with deformable DETR (ablation) | PDA-GAN · CGL-Dataset ablation (Data I) | R_ove: R_ove 0.1085 vs 0.0290; R_com 32.48 vs 33.55 | Mixed |
Closest papers by meaning
- Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation (CVPR 2023 · similarity 0.96)
- PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout (CVPR 2023 · similarity 0.91)
- PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation (CVPR 2025 · similarity 0.87)
- POSTA: A Go-to Framework for Customized Artistic Poster Generation (CVPR 2025 · similarity 0.86)
- GlyphDraw2: Automatic Generation of Complex Glyph Posters with Diffusion Models and Large Language Models (AAAI 2025 · similarity 0.85)
- AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models (CVPR 2025 · similarity 0.84)
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.
