Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning

In recent years, Convolutional Neural Network (CNN) based trackers have achieved state-of-the-art performance on multiple benchmark datasets. Most of these trackers train a binary classifier to distinguish the target from its background. However, they suffer from two limitations. Firstly, these trackers cannot effectively handle significant appearance variations due to the limited number of positive samples. Secondly, there exists a significant imbalance of gradient contributions between easy and hard samples, where the easy samples usually dominate the computation of gradient. In this paper, we propose a robust tracking method via Statistical Positive sample generation and Gradient Aware learning (SPGA) to address the above two limitations. To enrich the diversity of positive samples, we present an effective and efficient statistical positive sample generation algorithm to generate positive samples in the feature space. Furthermore, to handle the issue of imbalance between easy and hard samples, we propose a gradient sensitive loss to harmonize the gradient contributions between easy and hard samples. Extensive experiments on three challenging benchmark datasets including OTB50, OTB100 and VOT2016 demonstrate that the proposed SPGA performs favorably against several state-of-the-art trackers.

[1]  Alexander C. Berg,et al.  Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers , 2018, ECCV.

[2]  Michael Felsberg,et al.  Accurate Scale Estimation for Robust Visual Tracking , 2014, BMVC.

[3]  David Zhang,et al.  Deep Location-Specific Tracking , 2017, ACM Multimedia.

[4]  Tomasz Maciejewski,et al.  Local neighbourhood extension of SMOTE for mining imbalanced data , 2011, 2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM).

[5]  Yu Liu,et al.  Gradient Harmonized Single-stage Detector , 2018, AAAI.

[6]  Michael Felsberg,et al.  Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking , 2016, ECCV.

[7]  Arnold W. M. Smeulders,et al.  UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking , 2016 .

[8]  Xin Jin,et al.  Extracting Features of Interest from Small Deep Networks for Efficient Visual Tracking , 2018, PCM.

[9]  Simone Calderara,et al.  Visual Tracking: An Experimental Survey , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Honggang Zhang,et al.  Deep Attentive Tracking via Reciprocative Learning , 2018, NeurIPS.

[11]  Yi Liu,et al.  Robust Correlation Filter Tracking with Shepherded Instance-Aware Proposals , 2018, ACM Multimedia.

[12]  Rui Caseiro,et al.  High-Speed Tracking with Kernelized Correlation Filters , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Luca Bertinetto,et al.  Fully-Convolutional Siamese Networks for Object Tracking , 2016, ECCV Workshops.

[14]  Junliang Xing,et al.  Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  John K Kruschke,et al.  Bayesian data analysis. , 2010, Wiley interdisciplinary reviews. Cognitive science.

[16]  Michael Felsberg,et al.  Learning Spatially Regularized Correlation Filters for Visual Tracking , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[17]  Ming-Hsuan Yang,et al.  Object Tracking Benchmark , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Bruce A. Draper,et al.  Visual object tracking using adaptive correlation filters , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Michael Felsberg,et al.  Unveiling the Power of Deep Tracking , 2018, ECCV.

[20]  Michael Felsberg,et al.  Convolutional Features for Correlation Filter Based Visual Tracking , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[21]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Qiang Wang,et al.  DCFNet: Discriminant Correlation Filters Network for Visual Tracking , 2017, ArXiv.

[23]  Rynson W. H. Lau,et al.  CREST: Convolutional Residual Learning for Visual Tracking , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[24]  Yi Wu,et al.  Online Object Tracking: A Benchmark , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Rynson W. H. Lau,et al.  VITAL: VIsual Tracking via Adversarial Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Jin Young Choi,et al.  Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Zhenyu He,et al.  The Visual Object Tracking VOT2016 Challenge Results , 2016, ECCV Workshops.

[28]  Jianbing Shen,et al.  Triplet Loss in Siamese Network for Object Tracking , 2018, ECCV.