Saliency for free: Saliency prediction as a side-effect of object recognition
This addresses the need for costly eye-tracking data in saliency prediction, offering a more efficient approach for computer vision applications.
The paper tackles the problem of generating saliency maps without needing ground-truth data by training an object recognition network with a saliency branch, achieving competitive results on real and synthetic datasets.
Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects. Neural networks for saliency estimation require ground truth saliency maps for training which are usually achieved via eyetracking experiments. In the current paper, we demonstrate that saliency maps can be generated as a side-effect of training an object recognition deep neural network that is endowed with a saliency branch. Such a network does not require any ground-truth saliency maps for training.Extensive experiments carried out on both real and synthetic saliency datasets demonstrate that our approach is able to generate accurate saliency maps, achieving competitive results on both synthetic and real datasets when compared to methods that do require ground truth data.