Structured Siamese Network for Real-Time Visual Tracking

Zhang, Yunhua; Wang, Lijun; Qi, Jinqing; Wang, Dong; Feng, Mengyang; Lu, Huchuan

doi:10.1007/978-3-030-01240-3_22

Cited by 239 publications

(113 citation statements)

References 34 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…Previous methods [2,12,13,20,40,42] commonly utilize the classic and relatively shallow AlexNet [18] as the backbone network ϕ in this framework. In our work, we study the problem of how to design and leverage a more advanced ConvNet ϕ to learn an effective model θ that enhances tracking robustness and accuracy.…”

Section: Background On Siamese Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Zhang

Peng

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

917

491

View full text Add to dashboard Cite

Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed. However, the backbone networks used in Siamese trackers are relatively shallow, such as AlexNet [18], which does not fully take advantage of the capability of modern deep neural networks. In this paper, we investigate how to leverage deeper and wider convolutional neural networks to enhance tracking robustness and accuracy. We observe that direct replacement of backbones with existing powerful architectures, such as ResNet [14] and Inception [33], does not bring improvements. The main reasons are that 1) large increases in the receptive field of neurons lead to reduced feature discriminability and localization precision; and 2) the network padding for convolutions induces a positional bias in learning. To address these issues, we propose new residual modules to eliminate the negative impact of padding, and further design new architectures using these modules with controlled receptive field size and network stride. The designed architectures are lightweight and guarantee real-time tracking speed when applied to SiamFC [2] and SiamRPN [20]. Experiments show that solely due to the proposed network architectures, our SiamFC+ and SiamRPN+ obtain up to 9.8%/5.7% (AUC), 23.3%/8.8% (EAO) and 24.4%/25.0% (EAO) relative improvements over the original versions [2, 20] on the OTB-15, VOT-16 and VOT-17 datasets, respectively.

show abstract

Section: Background On Siamese Trackingmentioning

confidence: 99%

“…Recently, trackers based on Siamese networks [2,7,12,13,20,34,40] have drawn great attention due to their high speed and accuracy. However, the backbone network utilized in these trackers is still the classical AlexNet [18], * corresponding author Here, width refers to the number of branches in a module.…”

Section: Introductionmentioning

confidence: 99%

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Zhang

Peng

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

917

491

View full text Add to dashboard Cite

show abstract

“…As shown in Table 2, the performance of our UDT tracker is comparable with the baseline trackers (e.g., SiamFC). The improved UDT+ tracker performs favorably against state-of-the-art fully-supervised trackers including SA-Siam [15], Struct-Siam [60] and MemTrack [58]. Attribute Analysis.…”

Section: State-of-the-art Comparisonmentioning

confidence: 99%

Unsupervised Deep Tracking

Wang

Song

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

396

227

View full text Add to dashboard Cite

We propose an unsupervised visual tracking method in this paper. Different from existing approaches using extensive annotated data for supervised learning, our CNN model is trained on large-scale unlabeled videos in an unsupervised manner. Our motivation is that a robust tracker should be effective in both the forward and backward predictions (i.e., the tracker can forward localize the target object in successive frames and backtrace to its initial position in the first frame). We build our framework on a Siamese correlation filter network, which is trained using unlabeled raw videos. Meanwhile, we propose a multiple-frame validation method and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of fully supervised trackers, which require complete and accurate labels during training. Furthermore, unsupervised framework exhibits a potential in leveraging unlabeled or weakly labeled data to further improve the tracking accuracy. * Y. Song and W. Liu are the corresponding authors. This work is done when N. Wang is an intern in Tencent AI Lab. The source code and results are available at https://github.com/594422814/UDT. Supervised Training: Annotated sequences Forward tracking Unsupervised Training: Unlabeled sequences Forward and Backward tracking

show abstract

“…SiamFC [2] 0.607 0.516 0.582 86 DSiamM [16] 0.656 --25 RASNet [51] 0.670 -0.642 83 SiamRPN [27] 0.658 0.592 0.637 200 SA-Siam [18] 0.677 0.610 0.657 50 StructSiam [59] 0.637 -0.621 45 MemTrack [54] 0.642 -0.626 50 DaSiamRPN [60] 0.656 0.602 0.658 160 Siam-BM [17] 0.684 0.617 0.662 48…”

Section: Siamfc-based Trackersmentioning

confidence: 99%

SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

Wang

Luo

Xiong

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

245

135

View full text Add to dashboard Cite

The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power. In this paper, we propose a SiamFC-based tracker, named SPM-Tracker, to tackle this challenge. The basic idea is to address the two requirements in two separate matching stages. Robustness is strengthened in the coarse matching (CM) stage through generalized training while discrimination power is enhanced in the fine matching (FM) stage through a distance learning network. The two stages are connected in series as the input proposals of the FM stage are generated by the CM stage. They are also connected in parallel as the matching scores and box location refinements are fused to generate the final results. This innovative series-parallel structure takes advantage of both stages and results in superior performance. The proposed SPM-Tracker, running at 120fps on GPU, achieves an AUC of 0.687 on OTB-100 and an EAO of 0.434 on VOT-16, exceeding other real-time trackers by a notable margin.

show abstract

Structured Siamese Network for Real-Time Visual Tracking

Cited by 239 publications

References 34 publications

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Unsupervised Deep Tracking

SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

Contact Info

Product

Resources

About