Instance Significance Guided Multiple Instance Boosting for Robust Visual Tracking

TL;DR

This paper introduces an enhanced online MILBoost framework for visual tracking that incorporates instance significance estimation, leading to improved robustness and performance in challenging scenarios.

Contribution

It extends MILBoost by integrating instance significance coefficients estimated via Bayesian methods, improving classifier selection and tracking accuracy.

Findings

Outperforms existing MIL-based trackers

Effective in challenging tracking scenarios

Improves robustness against drifting

Abstract

Multiple Instance Learning (MIL) recently provides an appealing way to alleviate the drifting problem in visual tracking. Following the tracking-by-detection framework, an online MILBoost approach is developed that sequentially chooses weak classifiers by maximizing the bag likelihood. In this paper, we extend this idea towards incorporating the instance significance estimation into the online MILBoost framework. First, instead of treating all instances equally, with each instance we associate a significance-coefficient that represents its contribution to the bag likelihood. The coefficients are estimated by a simple Bayesian formula that jointly considers the predictions from several standard MILBoost classifiers. Next, we follow the online boosting framework, and propose a new criterion for the selection of weak classifiers. Experiments with challenging public datasets show that the proposed method outperforms both existing MIL based and boosting based trackers.