Research map / Image generation / Autoregressive and latent generation
Saliency Preservation in Low-Resolution Grayscale Images
Shivanthan Yohanandan, Andy Song, Adrian G. Dyer, Dacheng Tao
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 |
|---|---|---|---|
| convert high-res color to low-res grayscale (120x64) | saliency FCN / fixation maps · Inter-observer consistency (10 images) | NSS: 1.17 -> 1.33 | No clear effect |
| convert high-res color to low-res grayscale | saliency FCN / fixation maps · Inter-observer consistency (10 images) | jAUC: 0.70 -> 0.71 | No clear effect |
| convert high-res color to low-res grayscale | saliency FCN / fixation maps · Inter-observer consistency (10 images) | KL: 20.03 -> 20.15 | No clear effect |
| train saliency FCN on low-res grayscale instead of high-res color | saliency FCN / fixation maps · CAT2000 saliency model | accuracy (NSS, Judd-AUC, SIM, CC) | No clear effect |
| train saliency FCN on low-res grayscale instead of high-res color | saliency FCN / fixation maps · CAT2000 saliency model | detection time: 114 -> 12 ms | Improved |
| train saliency FCN on low-res grayscale instead of high-res color | saliency FCN / fixation maps · CAT2000 saliency model | training time: more than 14x faster | Improved |
| convert high-res color to low-res grayscale | saliency FCN / fixation maps · CAT2000 fixation maps (20 images) | jAUC / SIM / CC: 0.88, 0.85, 0.92 | No clear effect |
Closest papers by meaning
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (TPAMI 2019 · similarity 0.86)
- Hierarchical Image Saliency Detection on Extended CSSD (TPAMI 2016 · similarity 0.85)
- Dynamic Whitening Saliency (TPAMI 2016 · similarity 0.85)
- Deep Saliency Prior for Reducing Visual Distraction (CVPR 2022 · similarity 0.84)
- A Thorough Benchmark and a New Model for Light Field Saliency Detection (TPAMI 2023 · similarity 0.84)
- Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks (CVPR 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.
