TY  - JOUR
AU  - Carola Figueroa Flores
AU  - David Berga
AU  - Joost Van de Weijer
AU  - Bogdan Raducanu
PY  - 2021//
TI  - Saliency for free: Saliency prediction as a side-effect of object recognition
T2  - PRL
JO  - Pattern Recognition Letters
SP  - 1
EP  - 7
VL  - 150
KW  - Saliency maps
KW  - Unsupervised learning
KW  - Object recognition
N2  - Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects instead of the background. So far, computational methods for saliency estimation required the explicit generation of a saliency map, process which is usually achieved via eyetracking experiments on still images. This is a tedious process that needs to be repeated for each new dataset. In the current paper, we demonstrate that is possible to automatically generate saliency maps without ground-truth. In our approach, saliency maps are learned as a side effect of object recognition. Extensive experiments carried out on both real and synthetic datasets demonstrated that our approach is able to generate accurate saliency maps, achieving competitive results when compared with supervised methods.
UR  - https://doi.org/10.1016/j.patrec.2021.05.015
L1  - http://refbase.cvc.uab.es/files/FBW2021.pdf
N1  - LAMP; 600.147; 600.120
ID  - Carola Figueroa Flores2021
ER  -