Learning Online for Unified Segmentation and Tracking Models

TL;DR

This paper introduces TrackMLP, a meta-learning approach that enhances online learning for unified segmentation and tracking models, significantly improving target-background discrimination and tracking performance.

Contribution

The paper proposes TrackMLP, a novel meta-learning method enabling online learning from limited information for unified segmentation and tracking models, achieving state-of-the-art results.

Findings

Achieves state-of-the-art tracking performance on VOT datasets.

Outperforms baseline models with 6-7% higher average overlaps.

Demonstrates strong target-background discriminability with limited prior info.

Abstract

Tracking requires building a discriminative model for the target in the inference stage. An effective way to achieve this is online learning, which can comfortably outperform models that are only trained offline. Recent research shows that visual tracking benefits significantly from the unification of visual tracking and segmentation due to its pixel-level discrimination. However, it imposes a great challenge to perform online learning for such a unified model. A segmentation model cannot easily learn from prior information given in the visual tracking scenario. In this paper, we propose TrackMLP: a novel meta-learning method optimized to learn from only partial information to resolve the imposed challenge. Our model is capable of extensively exploiting limited prior information hence possesses much stronger target-background discriminability than other online learning methods. Empirically, we show that our model achieves state-of-the-art performance and tangible improvement over competing models. Our model achieves improved average overlaps of66.0%,67.1%, and68.5% in VOT2019, VOT2018, and VOT2016 datasets, which are 6.4%,7.3%, and6.4% higher than our baseline. Code will be made publicly available.