SiamVGG: Visual Tracking using Deeper Siamese Networks

TL;DR

SiamVGG is a deep Siamese network-based visual tracker that combines a VGG-16 backbone with cross-correlation to achieve high accuracy and real-time performance at 50 FPS, outperforming some state-of-the-art methods.

Contribution

The paper introduces SiamVGG, a novel deep Siamese network architecture based on VGG-16 that balances high accuracy with real-time tracking capabilities.

Findings

Achieves state-of-the-art accuracy on multiple datasets.

Runs at 50 FPS on GTX 1080Ti.

Outperforms ECO and C-COT in VOT2017 with 2% higher EAO.

Abstract

Recently, we have seen a rapid development of Deep Neural Network (DNN) based visual tracking solutions. Some trackers combine the DNN-based solutions with Discriminative Correlation Filters (DCF) to extract semantic features and successfully deliver the state-of-the-art tracking accuracy. However, these solutions are highly compute-intensive, which require long processing time, resulting unsecured real-time performance. To deliver both high accuracy and reliable real-time performance, we propose a novel tracker called SiamVGG\footnote{https://github.com/leeyeehoo/SiamVGG}. It combines a Convolutional Neural Network (CNN) backbone and a cross-correlation operator, and takes advantage of the features from exemplary images for more accurate object tracking. The architecture of SiamVGG is customized from VGG-16 with the parameters shared by both exemplary images and desired input video frames. We demonstrate the proposed SiamVGG on OTB-2013/50/100 and VOT 2015/2016/2017 datasets with the state-of-the-art accuracy while maintaining a decent real-time performance of 50 FPS running on a GTX 1080Ti. Our design can achieve 2% higher Expected Average Overlap (EAO) compared to the ECO and C-COT in VOT2017 Challenge.