Research map / Image generation / Text-to-image diffusion
Data Augmentation via Latent Diffusion for Saliency Prediction
Bahar Aydemir, Deblina Bhattacharjee, Tong Zhang, Mathieu Salzmann, Sabine Süsstrunk
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 |
|---|---|---|---|
| train with saliency-guided photometric edit augmentation | SimpleNet, TempSAL, DeepGaze IIE, UNISAL and Ours · SALICON validation | KL, NSS, CC, SIM: KL 0.193 -> 0.185 (SimpleNet), 0.314 -> 0.258 (DeepGaze IIE) | Improved |
| add augmentation to the proposed diffusion saliency model (ablation) | Ours · SALICON validation | KL: 0.191 -> 0.179 | Improved |
| classical augmentations (rotation, crop, shear, etc.) instead of saliency-guided edits (ablation) | saliency models · SALICON | saliency metrics | Hurt |
| horizontal flip augmentation (ablation) | saliency models · SALICON | saliency metrics | No clear effect |
| channel-wise scaling and edit constraining (2 std) of latent edits (ablation) | image editing · qualitative | edit naturalness | Improved |
| edit photometric properties in a region to increase saliency | saliency predictions · eye-tracking user study (8 participants, 150 images) | fixation on edited region: p-value < 0.05 | Improved |
Closest papers by meaning
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (TPAMI 2019 · similarity 0.89)
- SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization (ICLR 2021 · similarity 0.88)
- Modeling Saliency Dataset Bias (ICCV 2025 · similarity 0.88)
- Energy-Based Generative Cooperative Saliency Prediction (AAAI 2022 · similarity 0.88)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.88)
- ADD: Attribution-Driven Data Augmentation Framework for Boosting Image Super-Resolution (CVPR 2025 · 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.
