Robust visual tracking with channel attention and focal loss
Date
2020
Authors
Li, Dongdong
Wen, Gongjian
Kuai, Yangliu
Zhu, Lingxiao
Porikli, Fatih
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Abstract
Recently, the tracking community leads a fashion of end-to-end feature representation learning for visual
tracking. Previous works treat all feature channels and training samples equally during training. This ignores channel interdependencies and foreground–background data imbalance, thus limiting the tracking
performance. To tackle these problems, we introduce channel attention and focal loss into the network
design to enhance feature representation learning. Specifically, a Squeeze-and-Excitation (SE) block is coupled to each convolutional layer to generate channel attention. Channel attention reflects the channelwise importance of each feature channel and is used for feature weighting in online tracking. To alleviate
the foreground–background data imbalance, we propose a focal logistic loss by adding a modulating factor to the logistic loss, with two tunable focusing parameters. The focal logistic loss down-weights the
loss assigned to easy examples in the background area. Both the SE block and focal logistic loss are computationally lightweight and impose only a slight increase in model complexity. Extensive experiments
are performed on three challenging tracking datasets including OTB100, UAV123 and TC128. Experimental results demonstrate that the enhanced tracker achieves significant performance improvement while
running at a real-time frame-rate of 66 fps.
Description
Keywords
Visual tracking, Channel attention, Focal logistic loss
Citation
Collections
Source
Neurocomputing
Type
Journal article
Book Title
Entity type
Access Statement
License Rights
Restricted until
2099-12-31
Downloads
File
Description