Relaxed Multiple-Instance SVM With Application to Object Discovery

Xinggang Wang; Zhuotun Zhu; Cong Yao; Xiang Bai

ICCV 2015poster111 citations

Relaxed Multiple-Instance SVM With Application to Object Discovery

Xinggang Wang, Zhuotun Zhu, Cong Yao, Xiang Bai

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.

BibTeX

@inproceedings{iccv2015_relaxedmultiplei,
  title = {Relaxed Multiple-Instance SVM With Application to Object Discovery},
  author = {Xinggang Wang and Zhuotun Zhu and Cong Yao and Xiang Bai},
  booktitle = {ICCV 2015},
  year = {2015}
}