当前位置: X-MOL 学术Image Vis. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Fast and robust visual tracking with hard balanced focal loss and guided domain adaption
Image and Vision Computing ( IF 4.7 ) Pub Date : 2020-05-14 , DOI: 10.1016/j.imavis.2020.103929
Hengcheng Fu , Wuneng Zhou , Xiaofeng Wang , Huanlong Zhang

Recently, Siamese networks based trackers have shown excellent performance in accuracy and speed. However, previous studies treat all training samples equally and use the general feature space without adapting to the specific video during tracking. These trackers ignore the class data imbalance during training and the feature space difference between the generic domain and the current tracking target domain, which limits the robustness of trackers. In this paper, we propose an algorithm for learning a discriminative and self-adaptive feature representation, in order to achieve accurate and robust tracking. During the off-line training stage, a hard balanced focal loss function is utilized to solve the positive–negative samples imbalance and the hard-easy negative samples imbalance. During the tracking phase, an off-line trained guided domain adaptation module is embedded into the Siamese networks, which can quickly transfer the feature space from the general domain to the current video domain by adjusting the search branch channel weights. Our networks are trained in an end-to-end manner and without online updating. Our tracker runs at 130 FPS while achieving favorable performance against the state-of-the-art methods on OTB-2013, OTB-2015, VOT-2016, VOT-2017, GOT-10 K and TC-128 benchmarks.



中文翻译:

快速,强大的视觉跟踪,具有硬平衡的焦点损失和引导域自适应

最近,基于暹罗网络的跟踪器在准确性和速度方面都表现出出色的性能。但是,先前的研究均等地对待所有训练样本,并在跟踪过程中使用通用特征空间而不适应特定视频。这些跟踪器会忽略训练期间的类数据不平衡以及通用域和当前跟踪目标域之间的特征空间差异,这限制了跟踪器的健壮性。在本文中,我们提出了一种用于学习判别和自适应特征表示的算法,以实现精确而鲁棒的跟踪。在离线训练阶段,硬平衡失焦功能可用于解决正负样本失衡和难易负样本失衡。在跟踪阶段,暹罗网络中嵌入了离线训练的指导域自适应模块,该模块可以通过调整搜索分支通道权重,将特征空间从通用域快速转移到当前视频域。我们的网络以端到端的方式进行培训,而无需在线更新。我们的跟踪器以130 FPS的速度运行,同时在OTB-2013,OTB-2015,VOT-2016,VOT-2017,GOT-10 K和TC-128基准测试中,与最先进的方法相比,具有出色的性能。

更新日期:2020-05-14
down
wechat
bug