Research map / Image generation / GANs
Discriminative Region Proposal Adversarial Network for High-Quality Image-to-Image Translation
Chao Wang, Wenjie Niu, Yufeng Jiang, Haiyong Zheng, Zhibin Yu, Zhaorui Gu, Bing Zheng
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 fake-mask region proposal and reviser (ablation) | DRPAN · Image de-raining | PSNR: 25.51 -> 25.87 | Improved |
| use discriminative region size 16 instead of 128 (ablation) | DRPAN · Image de-raining | PSNR: 25.87 -> 26.20 | Improved |
| use region size 16 instead of 32 (ablation) | DRPAN · Image de-raining | SSIM: 0.8788 -> 0.8712 | Hurt |
| use DRPAN instead of PAN | DRPAN · Image de-raining | PSNR: 23.35 -> 25.51 | Improved |
| add fake-mask (ablation) | DRPAN · Cityscapes real to labels | Class IOU: 0.39 -> 0.43 | Improved |
| add fake-mask (ablation) | DRPAN · Cityscapes real to labels | per-pixel accuracy: 0.86 -> 0.88 | Improved |
| add fake-mask (ablation) | DRPAN · Cityscapes labels to photo FCN-8s | per-pixel accuracy: 0.72 -> 0.73 | Improved |
| add fake-mask (ablation) | DRPAN · Cityscapes labels to photo AMT | % Turkers labeled real: 14.3% -> 18.2% | Improved |
| add fake-mask (ablation) | DRPAN · Maps to aerial AMT | % Turkers labeled real: 31.7% -> 33.4% | Improved |
| use DRPAN instead of Pix2pix | DRPAN · Cityscapes labels to photo AMT | % Turkers labeled real: 5.3% -> 18.2% | Improved |
| use DRPAN instead of classification with rebalancing | DRPAN · ImageNet colorization AMT | % Turkers labeled real: 29.7% -> 27.8% | No clear effect |
| use DRPAN instead of Pix2pix | DRPAN · Cityscapes real to labels | per-pixel accuracy: 0.83 -> 0.88 | Improved |
Closest papers by meaning
- Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation (ECCV 2018 · similarity 0.99)
- TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning (CVPR 2019 · similarity 0.90)
- Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation (CVPR 2020 · similarity 0.90)
- AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation (ECCV 2018 · similarity 0.89)
- Self-Supervised Dense Consistency Regularization for Image-to-Image Translation (CVPR 2022 · similarity 0.89)
- Theoretical Analysis of Image-to-Image Translation with Adversarial Learning (ICML 2018 · similarity 0.89)
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.
