SUN: A Bayesian framework for saliency using natural statistics. We propose a definition of saliency by considering what the visual system is trying to optimize when directing attention. The resulting model is a Bayesian framework from which bottom-up saliency emerges naturally as the self-information of visual features, and overall saliency (incorporating top-down information with bottom-up saliency) emerges as the pointwise mutual information between the features and the target when searching for a target. An implementation of our framework demonstrates that our model’s bottom-up saliency maps perform as well as or better than existing algorithms in predicting people’s fixations in free viewing. Unlike existing saliency measures, which depend on the statistics of the particular image being viewed, our measure of saliency is derived from natural image statistics, obtained in advance from a collection of natural images. For this reason, we call our model SUN (Saliency Using Natural statistics). A measure of saliency based on natural image statistics, rather than based on a single test image, provides a straightforward explanation for many search asymmetries observed in humans; the statistics of a single test image lead to predictions that are not consistent with these asymmetries. In our model, saliency is computed locally, which is consistent with the neuroanatomy of the early visual system and results in an efficient algorithm with few free parameters.

References in zbMATH (referenced in 13 articles )

Showing results 1 to 13 of 13.
Sorted by year (citations)

  1. Singh, Surya Kant; Srivastava, Rajeev: A novel probabilistic contrast-based complex salient object detection (2019)
  2. Calden Wloka, Toni Kunić, Iuliia Kotseruba, Ramin Fahimi, Nicholas Frosst, Neil D. B. Bruce, John K. Tsotsos: SMILER: Saliency Model Implementation Library for Experimental Research (2018) arXiv
  3. Sen, Debashis; Kankanhalli, Mohan S.: Early biological vision inspired system for salience computation in images (2018)
  4. Liu, Qingjie; Huang, Di; Wang, Yunhong; Wei, Hong; Tang, Yuanyan: Built-up area detection based on a Bayesian saliency model (2017)
  5. Bhattacharya, Bhaskar; Hughes, Gareth: On shape properties of the receiver operating characteristic curve (2015)
  6. Qi, Wei; Cheng, Ming-Ming; Borji, Ali; Lu, Huchuan; Bai, Lian-Fa: Saliencyrank: two-stage manifold ranking for salient object detection (2015)
  7. Tian, Yonghong; Li, Jia; Yu, Shui; Huang, Tiejun: Learning complementary saliency priors for foreground object segmentation in complex scenes (2015)
  8. Li, Jia; Tian, Yonghong; Huang, Tiejun: Visual saliency with statistical priors (2014)
  9. Hou, Weilong; Gao, Xinbo; Tao, Dacheng; Li, Xuelong: Visual saliency detection using information divergence (2013) ioport
  10. Li, Zhidong; Wang, Weihong; Wang, Yang; Chen, Fang; Wang, Yi: Visual tracking by proto-objects (2013) ioport
  11. Liang, Zhen; Chi, Zheru; Fu, Hong; Feng, Dagan: Salient object detection using content-sensitive hypergraph representation and partitioning (2012) ioport
  12. Vikram, Tadmeri Narayan; Tscherepanow, Marko; Wrede, Britta: A saliency map based on sampling an image into random rectangular regions of interest (2012) ioport
  13. Bhattacharya, Bhaskar; Hughes, Gareth: Symmetry of receiver operating characteristic curves and Kullback-Leibler divergences between the signal and noise populations (2011)