Information-Maximizing Sampling to Promote Tracking-by-Detection

TL;DR

This paper introduces an information-maximizing sampling method for tracking-by-detection that actively selects challenging samples to improve classifier robustness, resulting in superior performance on benchmark videos.

Contribution

It proposes a novel active sampling strategy that exploits classifier feedback to select informative samples, enhancing tracking robustness.

Findings

Outperforms state-of-the-art trackers on benchmark datasets.

Active sampling improves robustness against tracking challenges.

Demonstrates effectiveness of adversarial sampling in tracking.

Abstract

The performance of an adaptive tracking-by-detection algorithm not only depends on the classification and updating processes but also on the sampling. Typically, such trackers select their samples from the vicinity of the last predicted object location, or from its expected location using a pre-defined motion model, which does not exploit the contents of the samples nor the information provided by the classifier. We introduced the idea of most informative sampling, in which the sampler attempts to select samples that trouble the classifier of a discriminative tracker. We then proposed an active discriminative co-tracker that embed an adversarial sampler to increase its robustness against various tracking challenges. Experiments show that our proposed tracker outperforms state-of-the-art trackers on various benchmark videos.