RT Book,_Section
T1 SID4VAM: a benchmark dataset with synthetic images for visual attention modeling
A1 Berga, David
A1 Fernández Vidal, Xosé Ramón
A1 Otazu, Xavier
A1 Pardo López, Xosé Manuel
K1 Visualization
K1 Task analysis
K1 Computational modeling
K1 Measurement
K1 Gaze tracking
K1 Predictive models
K1 Benchmark testing
AB A benchmark of saliency models performance with a synthetic image dataset is provided. Model performance is evaluated through saliency metrics as well as the influence of model inspiration and consistency with human psychophysics. SID4VAM is composed of 230 synthetic images, with known salient regions. Images were generated with 15 distinct types of low-level features (e.g. orientation, brightness, color, size...) with a target-distractor popout type of synthetic patterns. We have used Free-Viewing and Visual Search task instructions and 7 feature contrasts for each feature category. Our study reveals that state-ofthe- art Deep Learning saliency models do not perform well with synthetic pattern images, instead, models with Spectral/ Fourier inspiration outperform others in saliency metrics and are more consistent with human psychophysical experimentation. This study proposes a new way to evaluate saliency models in the forthcoming literature, accounting for synthetic images with uniquely low-level feature contexts, distinct from previous eye tracking image datasets.
PB IEEE
SN 978-1-7281-4803-8
SN 2380-7504
YR 2019
FD 2019
LK https://hdl.handle.net/10347/38255
UL https://hdl.handle.net/10347/38255
LA eng
NO D. Berga, X. R. F. Vidal, X. Otazu and X. M. Pardo, "SID4VAM: A Benchmark Dataset With Synthetic Images for Visual Attention Modeling," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, pp. 8788-8797, doi: 10.1109/ICCV.2019.00888
NO This is the author’s version of the work. The definitive version was published in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), available online at 10.1109/ICCV.2019.00888
NO This work was funded by the MINECO (DPI2017- 89867-C2-1-R, TIN2015-71130-REDT), AGAUR (2017- SGR-649), CERCA Programme / Generalitat de Catalunya, in part by Xunta de Galicia under Project ED431C2017/69, in part by the Conseller´ıa de Cultura, Educación e Ordenación Universitaria (accreditation 20162019, ED431G/08) and the European Regional Development Fund, and in part by Xunta de Galicia and the European Union (European Social Fund). We also acknowledge the generous GPU support from NVIDIA
DS Minerva
RD 24 abr 2026