Research map / Image generation / GANs
Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
Chao Wang, Haiyong Zheng, Zhibin Yu, Ziqiang Zheng, 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 operation (ablation) | DRPAN · Cityscapes real to semantic labels | Class IOU: 0.39 -> 0.43 | Improved |
| add fake-mask operation (ablation) | DRPAN · Cityscapes real to semantic labels | per-class accuracy: 0.48 -> 0.52 | Improved |
| add fake-mask operation (ablation) | DRPAN · Cityscapes semantic labels to photo (FCN-8s score) | per-class accuracy: 0.22 -> 0.24 | Improved |
| add fake-mask operation (ablation) | DRPAN · Cityscapes semantic labels to photo (AMT) | % Turkers labeled real: 14.3% -> 18.2% | Improved |
| add fake-mask operation (ablation) | DRPAN · Maps to aerial (AMT) | % Turkers labeled real: 31.7% -> 33.4% | Improved |
| add fake-mask operation (ablation) | DRPAN · Cityscapes semantic labels to photo (FCN-8s score) | Class IOU: 0.19 -> 0.19 | No clear effect |
| add fake-mask operation (ablation) | DRPAN (w/o mask) · Single image de-raining | PSNR: 25.51 -> 25.87 | Improved |
| shrink discriminative region from 128 to 16 (ablation) | DRPAN · Single image de-raining | PSNR: 25.87 -> 26.20 | Improved |
| shrink discriminative region from 16 to 32 (ablation) | DRPAN · Single image de-raining | SSIM: 0.8712 -> 0.8788 | Improved |
| add reviser and L1 loss to continued PatchGAN training (ablation) | PatchGAN · Facades (qualitative) | visual artifacts | Improved |
| continue training PatchGAN with L1 loss on discriminative region (ablation) | PatchGAN · Facades (qualitative) | visual artifacts | No clear effect |
| DRPAN instead of Pix2pix | Pix2pix · Cityscapes real to semantic labels | per-pixel accuracy: 0.83 -> 0.88 | Improved |
Closest papers by meaning
- Discriminative Region Proposal Adversarial Network for High-Quality Image-to-Image Translation (IJCV 2019 · 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)
- Unsupervised Image-to-Image Translation Networks (NeurIPS 2017 · similarity 0.89)
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation (CVPR 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.
