AI Paper Atlas

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

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
train with saliency-guided photometric edit augmentationSimpleNet, TempSAL, DeepGaze IIE, UNISAL and Ours · SALICON validationKL, 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 validationKL: 0.191 -> 0.179Improved
classical augmentations (rotation, crop, shear, etc.) instead of saliency-guided edits (ablation)saliency models · SALICONsaliency metricsHurt
horizontal flip augmentation (ablation)saliency models · SALICONsaliency metricsNo clear effect
channel-wise scaling and edit constraining (2 std) of latent edits (ablation)image editing · qualitativeedit naturalnessImproved
edit photometric properties in a region to increase saliencysaliency predictions · eye-tracking user study (8 participants, 150 images)fixation on edited region: p-value < 0.05Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy