Meta-tracker: Fast and Robust Online Adaptation for Visual Object Trackers

Park, Eunbyung; Berg, Alexander C.

doi:10.1007/978-3-030-01219-9_35

Cited by 169 publications

(135 citation statements)

References 40 publications

Supporting

Mentioning

135

Contrasting

Order By: Relevance

“…This method fails to accumulate information from multiple frames. The meta-tracker of [33] extends the initialization of the target model in the first frame by a pre-trained approach, but still need a linear update in on-line tracking. Yao et al [46] propose to learn the updating coefficients for CF trackers using SGD offline.…”

Section: Related Workmentioning

confidence: 99%

Learning the Model Update for Siamese Trackers

Zhang

González-García

Weijer

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

313

140

View full text Add to dashboard Cite

Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time. While such an approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update. Therefore, we propose to replace the handcrafted update function with a method which learns to update. We use a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame. The UpdateNet is compact and can easily be integrated into existing Siamese trackers. We demonstrate the generality of the proposed approach by applying it to two Siamese trackers, SiamFC and DaSiamRPN. Extensive experiments on VOT2016, VOT2018, LaSOT, and TrackingNet datasets demonstrate that our UpdateNet effectively predicts the new target template, outperforming the standard linear update. On the large-scale TrackingNet dataset, our UpdateNet improves the results of DaSiamRPN with an absolute gain of 3.9% in terms of success score. Code and models are available at https://github.com/zhanglichao/ updatenet.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning the Model Update for Siamese Trackers

Zhang

González-García

Weijer

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

313

140

View full text Add to dashboard Cite

show abstract

“…We evaluated the proposed method on several wellknown benchmarks, including OTB2013/OTB2015 [81,82], VOT2017/VOT2018 [33,34] and TrackingNet Test dataset [55], and compared it with a number of state-of-theart trackers, such as VITAL [68], MetaT [58], ECO [13], MCPF [89], CREST [67], BACF [31], CFNet [73], CACF [54], ACFN [11], CSRDCF [49], C-COT [51], Staple [4], SiamFC [5], SRDCF [15], KCF [27], SAMF [41], DSST [16] and other advanced trackers in VOT challenges, i.e., CFCF [23], CFWCR [25], LSART [69], UPDT [6], SiamRPN [91], MFT [34] and LADCF [83].…”

Section: Implementation and Evaluation Settingsmentioning

confidence: 99%

Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking

Feng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

169

112

View full text Add to dashboard Cite

We propose a new Group Feature Selection method for Discriminative Correlation Filters (GFS-DCF) based visual object tracking. The key innovation of the proposed method is to perform group feature selection across both channel and spatial dimensions, thus to pinpoint the structural relevance of multi-channel features to the filtering system. In contrast to the widely used spatial regularisation or feature selection methods, to the best of our knowledge, this is the first time that channel selection has been advocated for DCF-based tracking. We demonstrate that our GFS-DCF method is able to significantly improve the performance of a DCF tracker equipped with deep neural network features. In addition, our GFS-DCF enables joint feature selection and filter learning, achieving enhanced discrimination and interpretability of the learned filters.To further improve the performance, we adaptively integrate historical information by constraining filters to be smooth across temporal frames, using an efficient lowrank approximation. By design, specific temporal-spatialchannel configurations are dynamically learned in the tracking process, highlighting the relevant features, and alleviating the performance degrading impact of less discriminative representations and reducing information redundancy. The experimental results obtained on OTB2013, OTB2015, VOT2017, VOT2018 and TrackingNet demonstrate the merits of our GFS-DCF and its superiority over the state-of-the-art trackers. The code is publicly available at https://github.com/XU-TIANYANG/ GFS-DCF.

show abstract

“…Meta Learning for Tracking. Despite the popularity of meta learning in many fields, there are few works [40,29] applying it to visual tracking. Yang et al [40] design a memory structure to dynamically write and read previous templates for model updating.…”

Section: Gradient Exploitingmentioning

confidence: 99%

“…Differently, we focus on exploring the discriminative information of gradients. Eunbyung et al [29] train the initialization parameters of filters with pixel-wise learning rate offline and utilize a matrix multiplication to update the filters. The update is a linear process.…”

Section: Gradient Exploitingmentioning

confidence: 99%

GradNet: Gradient-Guided Network for Visual Object Tracking

Chen

Ouyang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

276

114

View full text Add to dashboard Cite

The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general matching ability of the siamese network. However, this manner cannot capture the temporal variations of targets or background clutter. In this work, we propose a novel gradient-guided network to exploit the discriminative information in gradients and update the template in the siamese network through feed-forward and backward operations. To be specific, the algorithm can utilize the information from the gradient to update the template in the current frame. In addition, a template generalization training method is proposed to better use gradient information and avoid overfitting. To our knowledge, this work is the first attempt to exploit the information in the gradient for template update in siamese-based trackers. Extensive experiments on recent benchmarks demonstrate that our method achieves better performance than other state-of-the-art trackers. The source codes are available at

show abstract

Meta-tracker: Fast and Robust Online Adaptation for Visual Object Trackers

Cited by 169 publications

References 40 publications

Learning the Model Update for Siamese Trackers

Learning the Model Update for Siamese Trackers

Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking

GradNet: Gradient-Guided Network for Visual Object Tracking

Contact Info

Product

Resources

About