Title :
Saliency Detection by Multiple-Instance Learning
Author :
Qi Wang ; Yuan Yuan ; Pingkun Yan ; Xuelong Li
Author_Institution :
State Key Lab. of Transient Opt. &Photonics, Xi´an Inst. of Opt. & Precision Mech., Xi´an, China
Abstract :
Saliency detection has been a hot topic in recent years. Its popularity is mainly because of its theoretical meaning for explaining human attention and applicable aims in segmentation, recognition, etc. Nevertheless, traditional algorithms are mostly based on unsupervised techniques, which have limited learning ability. The obtained saliency map is also inconsistent with many properties of human behavior. In order to overcome the challenges of inability and inconsistency, this paper presents a framework based on multiple-instance learning. Low-, mid-, and high-level features are incorporated in the detection procedure, and the learning ability enables it robust to noise. Experiments on a data set containing 1000 images demonstrate the effectiveness of the proposed framework. Its applicability is shown in the context of a seam carving application.
Keywords :
computer vision; image recognition; image segmentation; object detection; unsupervised learning; computer vision; high-level feature; learning ability; low-level feature; mid-level feature; multiple-instance learning; saliency detection; saliency map; seam carving application; unsupervised techniques; Biological system modeling; Feature extraction; Humans; Image color analysis; Image segmentation; Training; Visualization; Attention; computer vision; machine learning; multiple-instance learning (MIL); saliency; saliency map;
Journal_Title :
Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2012.2214210