Fully-Convolutional Siamese Networks for Object Tracking

TL;DR

This paper introduces a fully-convolutional Siamese network for object tracking that operates in real-time and achieves state-of-the-art results by leveraging deep learning trained on large datasets.

Contribution

It presents a novel end-to-end trained Siamese network for object tracking that is both fast and highly effective, improving over previous online-only models.

Findings

Operates at frame-rates beyond real-time

Achieves state-of-the-art performance on multiple benchmarks

Simplifies the tracking process with a fully-convolutional architecture

Abstract

The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself. Despite the success of these methods, their online-only approach inherently limits the richness of the model they can learn. Recently, several attempts have been made to exploit the expressive power of deep convolutional networks. However, when the object to track is not known beforehand, it is necessary to perform Stochastic Gradient Descent online to adapt the weights of the network, severely compromising the speed of the system. In this paper we equip a basic tracking algorithm with a novel fully-convolutional Siamese network trained end-to-end on the ILSVRC15 dataset for object detection in video. Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.