Research map / Image generation / Editing and style transfer
Saliency-Guided Image Translation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SalG-GAN instead of CycleGAN | image translation conditioned on target saliency · SGIT-S | FID: 34.81 -> 30.51 | Helped |
| Use SalG-GAN instead of CycleGAN | image translation conditioned on target saliency · SGIT-S | SalD-KLD: 0.03 -> 0.02 | Helped |
| Use SalG-GAN instead of CycleGAN | image translation conditioned on target saliency · SGIT-S | F-KLD: 0.28 -> 0.27 | Helped |
| Use SalG-GAN instead of HAG | image translation conditioned on target saliency · SGIT-R | FID: 69.63 -> 48.59 | Helped |
| Use SalG-GAN instead of CycleGAN | image translation conditioned on target saliency · SGIT-R | SalD-KLD: 0.03 -> 0.02 | Helped |
| Use SalG-GAN instead of CycleGAN | image translation conditioned on target saliency · SGIT-R | F-KLD: 0.18 -> 0.14 | Helped |
| Use SalG-GAN instead of HAG | image translation conditioned on target saliency · SGIT-C | FID: 45.21 -> 53.22 | Hurt |
| Use SalG-GAN instead of CycleGAN | image translation conditioned on target saliency · SGIT-C | SalD-KLD: 0.43 -> 0.12 | Helped |
| Use SalG-GAN instead of the baselines | saliency-guided image translation · SGIT-S, SGIT-R, and SGIT-C user study | preference | Helped |
| Use the disentangled saliency-cue representation | SalG-GAN image generation · SGIT-S and SGIT-R | diversity | Helped |
Closest papers by meaning
- DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks (CVPR 2018 · similarity 0.88)
- Unsupervised Attention-guided Image-to-Image Translation (NeurIPS 2018 · similarity 0.87)
- TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning (CVPR 2019 · similarity 0.87)
- Improving Deep Learning Interpretability by Saliency Guided Training (NeurIPS 2021 · similarity 0.86)
- Shallow and Deep Convolutional Networks for Saliency Prediction (CVPR 2016 · similarity 0.86)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.86)
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.