A Classifier-guided Approach for Top-down Salient Object Detection

TL;DR

This paper introduces a top-down salient object detection framework that integrates a classifier with saliency models, using category-aware sparse coding to improve accuracy and efficiency, and refines saliency maps through classification feedback.

Contribution

It presents a novel classifier-guided approach that tightly couples image classification with saliency detection using category-aware sparse codes and saliency-weighted max-pooling.

Findings

Improved saliency detection accuracy on Graz-02 and PASCAL VOC-07 datasets.

Category-aware sparse coding enhances classification and saliency model updates.

Saliency-weighted max-pooling boosts image classification performance.

Abstract

We propose a framework for top-down salient object detection that incorporates a tightly coupled image classification module. The classifier is trained on novel category-aware sparse codes computed on object dictionaries used for saliency modeling. A misclassification indicates that the corresponding saliency model is inaccurate. Hence, the classifier selects images for which the saliency models need to be updated. The category-aware sparse coding produces better image classification accuracy as compared to conventional sparse coding with a reduced computational complexity. A saliency-weighted max-pooling is proposed to improve image classification, which is further used to refine the saliency maps. Experimental results on Graz-02 and PASCAL VOC-07 datasets demonstrate the effectiveness of salient object detection. Although the role of the classifier is to support salient object detection, we evaluate its performance in image classification and also illustrate the utility of thresholded saliency maps for image segmentation.