Skip to content
[ECCV2018] Distractor-aware Siamese Networks for Visual Object Tracking
Branch: master
Clone or download
Latest commit 167d0db Nov 29, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
code add demo and OTB2015 test (200fps and 0.655AUC). Nov 29, 2018
LICENSE DaSiamRPN VOT2018 Aug 21, 2018 typo Nov 29, 2018 DaSiamRPN VOT2018 Aug 21, 2018
tracker_SiamRPN.m DaSiamRPN VOT2018 Aug 21, 2018
votresult.png DaSiamRPN VOT2018 Aug 21, 2018

🏆News: We won the VOT-18 real-time challenge

🏆News: We won the second place in the VOT-18 long-term challenge


This repository includes PyTorch code for reproducing the results on VOT2018.

Distractor-aware Siamese Networks for Visual Object Tracking

Zheng Zhu*, Qiang Wang*, Bo Li*, Wei Wu, Junjie Yan, and Weiming Hu

European Conference on Computer Vision (ECCV), 2018


SiamRPN formulates the task of visual tracking as a task of localization and identification simultaneously, initially described in an CVPR2018 spotlight paper. (Slides at CVPR 2018 Spotlight)

DaSiamRPN improves the performances of SiamRPN by (1) introducing an effective sampling strategy to control the imbalanced sample distribution, (2) designing a novel distractor-aware module to perform incremental learning, (3) making a long-term tracking extension. ECCV2018. (Slides at VOT-18 Real-time challenge winners talk)


CPU: Intel(R) Core(TM) i7-7700 CPU @ 3.60GHz GPU: NVIDIA GTX1060

  • python2.7
  • pytorch == 0.3.1
  • numpy
  • opencv

Pretrained model for SiamRPN

In our tracker, we use an AlexNet variant as our backbone, which is end-to-end trained for visual tracking. The pretrained model can be downloaded from google drive: SiamRPNBIG.model. Then, you should copy the pretrained model file SiamRPNBIG.model to the subfolder './code', so that the tracker can find and load the pretrained_model.

Detailed steps to install the prerequisites

  • install pytorch, numpy, opencv following the instructions in the Please do not use conda to install.
  • you can alternatively modify /PATH/TO/CODE/FOLDER/ in tracker_SiamRPN.m If the tracker is ready, you will see the tracking results. (EAO: 0.3827)


All results can be downloaded from Google Drive.

A / R / EAO
A / R / EAO
VOT2017 & VOT2018
A / R / EAO
0.58 / 1.13 / 0.349 0.56 / 0.26 / 0.344 0.49 / 0.46 / 0.244 81.9 / 85.0 0.527 / 0.748 0.454 / 0.617
0.63 / 0.66 / 0.446 0.61 / 0.22 / 0.411 0.56 / 0.34 / 0.326 86.5 / 88.0 0.586 / 0.796 0.617 / 0.838
- - 0.59 / 0.28 / 0.383 - - -

Demo and Test on OTB2015

  • To reproduce the reuslts on paper, the pretrained model can be downloaded from Google Drive: SiamRPNOTB.model.
    ⚡️ ⚡️ This model is the fastest (~200fps) Siamese Tracker with AUC of 0.655 on OTB2015. ⚡️ ⚡️

  • You must download OTB2015 dataset (download script) at first.

A simple test example.

cd code

If you want to test the performance on OTB2015, please using the follwing command.

cd code
python OTB2015 "Siam*" 0 1


Licensed under an MIT license.

Citing DaSiamRPN

If you find DaSiamRPN and SiamRPN useful in your research, please consider citing:

  title={Distractor-aware Siamese Networks for Visual Object Tracking},
  author={Zhu, Zheng and Wang, Qiang and Bo, Li and Wu, Wei and Yan, Junjie and Hu, Weiming},
  booktitle={European Conference on Computer Vision},

  title = {High Performance Visual Tracking With Siamese Region Proposal Network},
  author = {Li, Bo and Yan, Junjie and Wu, Wei and Zhu, Zheng and Hu, Xiaolin},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018}
You can’t perform that action at this time.