Relaxed Multiple-Instance SVM with Application to Object Discovery

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.

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• From Captions to Visual Concepts and Back
• Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals

Cited by in corpus (6)

• Revisiting Multiple Instance Neural Networks
• Deep Descriptor Transforming for Image Co-Localization
• Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning
• Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution
• Spatio-Temporal Action Localization in a Weakly Supervised Setting
• Deep Multiple Instance Feature Learning via Variational Autoencoder