Relaxed Multiple-Instance SVM with Application to Object Discovery

2015/10/05 by Xinggang Wang, Wang, Xinggang, Zhuotun Zhu +5
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.CV #cs.LG

paper · pdf · doi:10.48550/arxiv.1510.01027

arxiv created 2015/10/05 · arxiv updated 2015/10/06

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 jointly optimize the bag label and instance label 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-art results of object discovery on Pascal VOC datasets further confirm the advantages of the proposed method.

Related

• C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
• Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection
• On the Complexity of One-class SVM for Multiple Instance Learning
• A Multiclass Multiple Instance Learning Method with Exact Likelihood
• Multi-view metric learning for multi-instance image classification