Indexed by:会议论文
First Author:Zhu,Zhuotun,Wang,Xinggang
Correspondence Author:Bai,Xiang
Co-author:Yao,Cong
Journal:2015 IEEE International Conference on Computer Vision (ICCV)
Date of Publication:2015-12-07
Abstract:Multiple-instance learning (MIL) has served as an important tool for a wide range of vision applications, for instance, image classification, object detection, and visual tracking. In this paper, we propose a novel method to solve the classical MIL problem, named relaxed multiple-instance SVM (RMI-SVM). We treat the positiveness of instance as a continuous variable, use Noisy-OR model to enforce the MIL constraints, and optimize them jointly in a unified framework. The optimization problem can be efficiently solved using stochastic gradient decent. The extensive experiments demonstrate that RMI-SVM consistently achieves superior performance on various benchmarks for MIL. Moreover, we simply applied RMI-SVM to a challenging vision task, common object discovery. The state-of-the arts results of object discovery on PASCAL VOC datasets further confirm the advantages of the proposed method.