Adversarial Feature Sampling Learning for Efficient Visual Tracking

TL;DR

This paper introduces an efficient visual tracking method that uses feature sampling and adversarial augmentation to reduce computation and improve performance, achieving comparable results to state-of-the-art methods.

Contribution

It proposes a novel sampling approach on deep features combined with adversarial training to enhance tracking efficiency and accuracy.

Findings

Achieves comparable accuracy to state-of-the-art trackers.

Significantly accelerates tracking-by-detection methods.

Demonstrates effectiveness on benchmark datasets.

Abstract

The tracking-by-detection framework usually consist of two stages: drawing samples around the target object in the first stage and classifying each sample as the target object or background in the second stage. Current popular trackers based on tracking-by-detection framework typically draw samples in the raw image as the inputs of deep convolution networks in the first stage, which usually results in high computational burden and low running speed. In this paper, we propose a new visual tracking method using sampling deep convolutional features to address this problem. Only one cropped image around the target object is input into the designed deep convolution network and the samples is sampled on the feature maps of the network by spatial bilinear resampling. In addition, a generative adversarial network is integrated into our network framework to augment positive samples and improve the tracking performance. Extensive experiments on benchmark datasets demonstrate that the proposed method achieves a comparable performance to state-of-the-art trackers and accelerates tracking-by-detection trackers based on raw-image samples effectively.