Research map / Image generation / Editing and style transfer
Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
Hao Tang, Philip H. S. Torr, Nicu Sebe
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 |
|---|---|---|---|
| use semantic guidance S_g alone instead of I_a (ablation) | Pix2pix · Dayton a2g ablation | SSIM: 0.4555 -> 0.5223 | Improved |
| add semantic guidance to input image (ablation) | Pix2pix · Dayton a2g ablation | SSIM: 0.4555 -> 0.5374 | Improved |
| add cycled semantic guidance generation (ablation) | Baseline C · Dayton a2g ablation | SSIM: 0.5374 -> 0.5438 | Improved |
| add uncertainty-guided pixel loss (ablation) | Baseline D · Dayton a2g ablation | SSIM: 0.5438 -> 0.5522 | Improved |
| add multi-channel attention selection (ablation) | Baseline E · Dayton a2g ablation | SSIM: 0.5522 -> 0.5989 | Improved |
| add total variation regularization (ablation) | Baseline F · Dayton a2g ablation | SSIM: 0.5989 -> 0.6047 | Improved |
| add multi-scale spatial pooling (ablation) | Baseline G · Dayton a2g ablation | SSIM: 0.6047 -> 0.6167 | Improved |
| add multi-scale spatial pooling (ablation) | Baseline G · Dayton a2g ablation | FID: 74.11 -> 72.23 | Improved |
| add second-stage refinement (coarse-to-fine) (ablation) | Baseline H · Dayton a2g ablation | SSIM: 0.5567 -> 0.6167 | Improved |
| use multi-scale spatial pooling instead of SE layer (ablation) | SelectionGAN · Dayton a2g ablation | SSIM: 0.5912 -> 0.6167 | Improved |
| use N=10 attention channels instead of N=1 (ablation) | SelectionGAN · Dayton a2g ablation | SSIM: 0.5522 -> 0.5986 | Improved |
| increase attention channels from 10 to 32 (ablation) | SelectionGAN · Dayton a2g ablation | SSIM: 0.5986 -> 0.5950 | No clear effect |
Closest papers by meaning
- Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translation (CVPR 2019 · similarity 0.94)
- Edge Guided GANs With Multi-Scale Contrastive Learning for Semantic Image Synthesis (TPAMI 2023 · similarity 0.88)
- Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis (ICLR 2023 · similarity 0.88)
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 2018 · similarity 0.88)
- Saliency-Guided Image Translation (CVPR 2021 · similarity 0.88)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.85)
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.
