Exemplar-driven top-down saliency detection via deep association

• Main Authors: HE, Shengfeng, LAU, Rynson W. H., YANG, Qingxiong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2016
• Subjects: Computer vision; Visualization; Feature extraction; Network architecture; Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces; Systems Architecture
• Online Access: https://ink.library.smu.edu.sg/sis_research/8427; https://ink.library.smu.edu.sg/context/sis_research/article/9430/viewcontent/He_Exemplar_Driven_Top_Down_Saliency_CVPR_2016_paper.pdf
• Institution: Singapore Management University

Top-down saliency detection is a knowledge-driven search task. While some previous methods aim to learn this "knowledge" from category-specific data, others transfer existing annotations in a large dataset through appearance matching. In contrast, we propose in this paper a locateby-exemplar strategy. This approach is challenging, as we only use a few exemplars (up to 4) and the appearances among the query object and the exemplars can be very different. To address it, we design a two-stage deep model to learn the intra-class association between the exemplars and query objects. The first stage is for learning object-to-object association, and the second stage is to learn background discrimination. Extensive experimental evaluations show that the proposed method outperforms different baselines and the category-specific models. In addition, we explore the influence of exemplar properties, in terms of exemplar number and quality. Furthermore, we show that the learned model is a universal model and offers great generalization to unseen objects.