A Classifier-guided Approach for Top-down Salient Object Detection
This work addresses salient object detection for computer vision applications, but it is incremental as it builds on existing methods with hybrid improvements.
The paper tackles top-down salient object detection by integrating a classifier trained on category-aware sparse codes to identify and update inaccurate saliency models, resulting in improved detection on Graz-02 and PASCAL VOC-07 datasets.
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.