Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of gradient-descent during tracking while pruning its network channel...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jung, Ilchae, You, Kihyun, Noh, Hyeonwoo, Cho, Minsu, Han, Bohyung
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 04.12.2019
Subjects
Adaptation
Computer simulation
Distance learning
Masks
Mathematical models
Parameters
Pruning
Real time
Tracking
Online AccessGet full text

Cover

More Information
Summary:We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of gradient-descent during tracking while pruning its network channels using the target ground-truth at the first frame. Such a learning problem is formulated as a meta-learning task, where a meta-tracker is trained by updating its meta-parameters for initial weights, learning rates, and pruning masks through carefully designed tracking simulations. The integrated meta-tracker greatly improves tracking performance by accelerating the convergence of online learning and reducing the cost of feature computation. Experimental evaluation on the standard datasets demonstrates its outstanding accuracy and speed compared to the state-of-the-art methods.
ISSN:2331-8422