Relaxed Multiple-Instance SVM with Application to Object Discovery
This addresses object discovery in vision tasks, but appears incremental as it builds on classical MIL methods.
The paper tackled the multiple-instance learning problem by proposing a relaxed multiple-instance SVM method, which achieved superior performance on various benchmarks and state-of-the-art results in object discovery on Pascal VOC datasets.
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.