@article{14945,
  author = {Francesca Murabito and Concetto Spampinato and Simone Palazzo and Daniela Giordano and Konstantin Pogorelov and Michael Riegler},
  title = {Top-Down Saliency Detection Driven by Visual Classification},
  abstract = {This paper presents an approach for saliency detection able to emulate the integration of the top-down (task-controlled) and bottom-up (sensory information) processes involved in human visual attention. In particular, we first learn how to generate saliency when a specific visual task has to be accomplished. Afterwards, we investigate if and to what extentthe learned saliency maps can support visual classification in nontrivial cases. To achieve this, we propose SalClass-Net, a CNN framework consisting of two networks jointly trained: a) the first one computing top-down saliency mapsfrom input images, and b) the second one exploiting the computed saliency maps for visual classification.To test our approach, we collected a dataset of eye-gaze maps, using a Tobii T60 eye tracker, by asking several subjectsto look at images from the Stanford Dogs dataset, with the objective of distinguishing dog breeds.Performance analysis on our dataset and other saliency benchmarking datasets, such as POET, showed that Sal-ClassNet outperforms state-of-the-art saliency detectors, such as SalNet and SALICON. Finally, we also analyzedthe performance of SalClassNet in a fine-grained recognition task and found out that it yields enhanced classificationaccuracy compared to Inception and VGG-19 classifiers. The achieved results, thus, demonstrate that 1) condition-ing saliency detectors with object classes reaches state-of-the-art performance, and 2) explicitly providing top-downsaliency maps to visual classifiers enhances accuracy.},
  year = {2018},
  journal = {Computer Vision and Image Understanding},
  volume = {172},
  pages = {67-76},
  publisher = {Elsevier},
  doi = {10.1016/j.cviu.2018.03.005},
}