点击次数：

论文类型：期刊论文

发表时间：2018-10-01

发表刊物：IEEE TRANSACTIONS ON IMAGE PROCESSING

收录刊物：SCIE

卷号：27

期号：10

页面范围：5167-5177

ISSN号：1057-7149

关键字：Salient object detection; latent embedding; weakly supervised

摘要：Traditional unsupervised salient object detection methods majorly rely on the pre-defined assumptions about saliency. However, these assumptions may not be sufficient for handling test images of varied content and context. Meanwhile, the supervised models learn saliency knowledge from thousands of annotated images, which are usually expensive to obtain. In this paper, we propose an exemplar-aided salient object detection method, which can complement heuristic saliency assumptions by leveraging only a few exemplar images. This is a challenging task since the appearances between the query images and the exemplars can be quite different. We handle it by learning the matching relationship of the intra-class instances in a latent embedding space in an online fashion. Given a test image and an annotated reference image (retrieved from several exemplar images), our method transfers the foreground and background information of the reference image to the test image via a joint latent embedding of image superpixels. Extensive experiments show that our method can easily improve the performance of existing unsupervised methods even when a very small reference image data set (e.g. one image) is used. In addition, our method is able to attain competitive performance against fully supervised methods.