Can Image Retrieval help Visual Saliency Detection?
This work addresses the problem of accurately detecting salient objects in images for computer vision applications, representing an incremental improvement over existing methods.
The paper tackled visual saliency detection by proposing an image retrieval framework that combines external saliency maps from similar images with internal contrast-based maps, achieving favorable performance against state-of-the-art methods on challenging datasets.
We propose a novel image retrieval framework for visual saliency detection using information about salient objects contained within bounding box annotations for similar images. For each test image, we train a customized SVM from similar example images to predict the saliency values of its object proposals and generate an external saliency map (ES) by aggregating the regional scores. To overcome limitations caused by the size of the training dataset, we also propose an internal optimization module which computes an internal saliency map (IS) by measuring the low-level contrast information of the test image. The two maps, ES and IS, have complementary properties so we take a weighted combination to further improve the detection performance. Experimental results on several challenging datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.