Research map / Image generation / Autoregressive and latent generation
Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation
Chenchen Xu, Min Zhou, Tiezheng Ge, Yuning Jiang, 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 |
|---|---|---|---|
| Replace CGL-GAN discriminator with pixel-level discriminator on shallow features and drop Gaussian blur | CGL-GAN (PDA-GAN) · CGL-Dataset | R_com (lower better): 35.77 -> 33.55 | Improved |
| Replace CGL-GAN discriminator with pixel-level discriminator on shallow features and drop Gaussian blur | CGL-GAN (PDA-GAN) · CGL-Dataset | R_shm and R_sub (lower better): R_shm 15.47 -> 12.77; R_sub 0.805 -> 0.688 | Improved |
| Replace CGL-GAN discriminator with pixel-level discriminator and drop Gaussian blur | CGL-GAN (PDA-GAN) · CGL-Dataset | R_ove (lower better): 0.0233 -> 0.0290 | Hurt |
| Replace CGL-GAN discriminator with pixel-level discriminator and drop Gaussian blur | CGL-GAN (PDA-GAN) · CGL-Dataset | R_ali (lower better): 0.0098 -> 0.0105 | Hurt |
| Pixel-level discriminator instead of global discriminator (DA) (ablation) | PDA-GAN · CGL-Dataset | R_com, R_shm, R_sub, R_ove: best DA R_com 34.07 vs PDA 33.55; R_ove 0.0350 vs 0.0290 | Improved |
| Global discriminator with large loss weight (ablation) | DA global discriminator · CGL-Dataset | layout generation success: DA-6.0 and DA-1.0 fail (R_ove ~9); DA-0.01 R_ove 4.7764 | Hurt |
| PatchGAN-style patch-level discriminator instead of pixel-level output (ablation) | PDA-GAN discriminator · CGL-Dataset | R_com, R_shm, R_sub: e.g. 88*60 patch: R_com 32.65 (better) but R_shm 13.35 and R_sub 0.735 vs pixel 12.77 and 0.688 | Hurt |
| Attach PD to deep (fourth residual block) features instead of shallow first-block features (ablation) | PDA-GAN · CGL-Dataset | R_com, R_shm, R_sub: R_com 34.22 vs 33.55; R_shm 13.97 vs 12.77; R_sub 0.770 vs 0.688 | Hurt |
| Attach PD to fused multi-level features instead of shallow first-block features (ablation) | PDA-GAN · CGL-Dataset | R_com, R_shm, R_sub: R_com 35.36 vs 33.55; R_sub 0.817 vs 0.688 | Hurt |
| Add one-target label smoothing (0 to 0.2 on non-inpainted pixels) (ablation) | PDA-GAN · CGL-Dataset | R_shm, R_sub, R_ove, R_und: R_shm 14.04 -> 12.77; R_sub 0.718 -> 0.688; R_ove 0.0346 -> 0.0290 | Improved |
| One-source label smoothing (only 1 to 0.8) instead of one-target (ablation) | PDA-GAN · CGL-Dataset | R_com and R_ali: R_com 32.20 vs 33.55 (better); R_ali 0.0085 vs 0.0105 (better) but R_shm 15.23 vs 12.77 and R_ove 0.0431 vs 0.0290 worse | Mixed |
Closest papers by meaning
- GAN-Based Domain Adaptation for Image-Aware Layout Generation in Advertising Poster Design (TPAMI 2025 · similarity 0.96)
- PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout (CVPR 2023 · similarity 0.87)
- Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis (TPAMI 2021 · similarity 0.85)
- Logo Synthesis and Manipulation With Clustered Generative Adversarial Networks (CVPR 2018 · similarity 0.85)
- PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation (CVPR 2025 · similarity 0.83)
- Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive (ICLR 2024 · similarity 0.83)
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.
