Real-Time MDNet

TL;DR

This paper introduces a real-time visual tracking algorithm based on MDNet that significantly accelerates processing speed while maintaining high accuracy, outperforming existing methods on multiple benchmarks.

Contribution

It presents a novel approach to speed up MDNet by optimizing feature extraction and learning discriminative models, achieving approximately 25 times faster performance with similar accuracy.

Findings

Achieves 25x speed-up over MDNet

Outperforms state-of-the-art real-time trackers

Maintains high accuracy across multiple benchmarks

Abstract

We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning.