Deep Meta Learning for Real-Time Target-Aware Visual Tracking

TL;DR

This paper introduces a real-time visual tracking method combining Siamese networks with a meta-learner to quickly adapt to target appearance changes without complex re-training, achieving competitive accuracy.

Contribution

The novel integration of a meta-learner with Siamese networks enables instant adaptation to target appearance, reducing computational complexity in real-time tracking.

Findings

Operates at real-time speeds.

Maintains competitive tracking accuracy.

Eliminates need for complex online re-training.

Abstract

In this paper, we propose a novel on-line visual tracking framework based on the Siamese matching network and meta-learner network, which run at real-time speeds. Conventional deep convolutional feature-based discriminative visual tracking algorithms require continuous re-training of classifiers or correlation filters, which involve solving complex optimization tasks to adapt to the new appearance of a target object. To alleviate this complex process, our proposed algorithm incorporates and utilizes a meta-learner network to provide the matching network with new appearance information of the target objects by adding target-aware feature space. The parameters for the target-specific feature space are provided instantly from a single forward-pass of the meta-learner network. By eliminating the necessity of continuously solving complex optimization tasks in the course of tracking, experimental results demonstrate that our algorithm performs at a real-time speed while maintaining competitive performance among other state-of-the-art tracking algorithms.