yichuan9527 / SiamDW

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

we are hiring talented interns: [e-mail]

News

• ☀️☀️ We add the results on VOT-18, VOT-19, GOT10K, VISDRONE19, LaSOT datasets.
• ☀️☀️ The training and test code of SiamFC+ and SiamRPN+ have been released.
• ☀️☀️ Our paper have been accepted by CVPR2019 (Oral).
• ☀️☀️ We provide a parameter tuning toolkit for siamese tracking framework.

Introduction

Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed. However, the backbone network utilized in these trackers is still the classical AlexNet, which does not fully take advantage of the capability of modern deep neural networks.

Our proposals improve the performances of fully convolutional siamese trackers by,

1. introducing CIR and CIR-D units to unveil the power of deeper and wider networks like ResNet and Inceptipon;
2. designing backbone networks according to the analysis on internal network factors (e.g. receptive field, stride, output feature size), which affect tracking performances.

Main Results

Main results on VOT and OTB

Models	OTB13	OTB15	VOT15	VOT16	VOT17
Alex-FC	0.608	0.579	0.289	0.235	0.188
Alex-RPN	-	0.637	0.349	0.344	0.244
CIResNet22-FC	0.663	0.644	0.318	0.303	0.234
CIResIncep22-FC	0.662	0.642	0.310	0.295	0.236
CIResNext23-FC	0.659	0.633	0.297	0.278	0.229
CIResNet22-RPN	0.674	0.666	0.381	0.376	0.294

Main results trained with GOT-10k (SiamFC)

Models	OTB13	OTB15	VOT15	VOT16	VOT17
Alex-FC	-	-	-	-	0.188
CIResNet22-FC	0.664	0.654	0.361	0.335	0.266
CIResNet22W-FC	0.689	0.674	0.368	0.352	0.269
CIResIncep22-FC	0.673	0.650	0.332	0.305	0.251
CIResNext22-FC	0.668	0.651	0.336	0.304	0.246
Raw Results	📎 OTB2013	📎 OTB2015	📎 VOT15	📎 VOT16	📎 VOT17

• Some reproduced results listed above are slightly better than the ones in the paper.
• Recently we found that training on GOT10K dataset can achieve better performance for SiamFC. So we provide the results being trained on GOT10K.
• Download pretrained on GOT10K model.

New added results

Benchmark	VOT18	VOT19	GOT10K	VISDRONE19	LaSOT
Performance	0.270	0.242	0.416	0.383	0.387
Raw Results	📎 VOT18	📎 VOT19	📎 GOT10K	📎 VISDRONE	📎 LaSOT

• We add resutls of SiamFCRes22W on recent benchmarks.

Environment

The code is developed with Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz GPU: NVIDIA .GTX1080

Quick Start

Test

See details in test.md

Train

See details in train.md

☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️☁️

Citation

If any part of our paper and code is helpful to your work, please generously cite with:

@InProceedings{Zhang_2019_CVPR,
author = {Zhang, Zhipeng and Peng, Houwen},
title = {Deeper and Wider Siamese Networks for Real-Time Visual Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
} 

License

Licensed under an MIT license.