DeepAI AI Chat
Log In Sign Up

Top-Down Saliency Detection Driven by Visual Classification

by   Francesca Murabito, et al.
University of Catania

This paper presents an approach for top-down saliency detection guided by visual classification tasks. We first learn how to compute visual saliency when a specific visual task has to be accomplished, as opposed to most state-of-the-art methods which assess saliency merely through bottom-up principles. Afterwards, we investigate if and to what extent visual saliency can support visual classification in nontrivial cases. To achieve this, we propose SalClassNet, a CNN framework consisting of two networks jointly trained: a) the first one computing top-down saliency maps from 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 subjects to look at images from the Stanford Dogs dataset, with the objective of distinguishing dog breeds. Performance analysis on our dataset and other saliency bench-marking datasets, such as POET, showed that SalClassNet out-performs state-of-the-art saliency detectors, such as SalNet and SALICON. Finally, we analyzed the performance of SalClassNet in a fine-grained recognition task and found out that it generalizes better than existing visual classifiers. The achieved results, thus, demonstrate that 1) conditioning saliency detectors with object classes reaches state-of-the-art performance, and 2) providing explicitly top-down saliency maps to visual classifiers enhances classification accuracy.


page 1

page 4

page 7

page 8


Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains

Most of the saliency methods are evaluated on their ability to generate ...

OpenSalicon: An Open Source Implementation of the Salicon Saliency Model

In this technical report, we present our publicly downloadable implement...

Towards Mesh Saliency Detection in 6 Degrees of Freedom

Traditional 3D mesh saliency detection algorithms and corresponding data...

Classifying Eye-Tracking Data Using Saliency Maps

A plethora of research in the literature shows how human eye fixation pa...

TSG: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

The explanation for deep neural networks has drawn extensive attention i...

Understanding Visual Saliency in Mobile User Interfaces

For graphical user interface (UI) design, it is important to understand ...

Improving Landmark Recognition using Saliency detection and Feature classification

Image Landmark Recognition has been one of the most sought-after classif...