English

SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking

Computer Vision and Pattern Recognition 2019-12-16 v2

Abstract

By decomposing the visual tracking task into two subproblems as classification for pixel category and regression for object bounding box at this pixel, we propose a novel fully convolutional Siamese network to solve visual tracking end-to-end in a per-pixel manner. The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction. Our framework takes ResNet-50 as backbone. Different from state-of-the-art trackers like Siamese-RPN, SiamRPN++ and SPM, which are based on region proposal, the proposed framework is both proposal and anchor free. Consequently, we are able to avoid the tricky hyper-parameter tuning of anchors and reduce human intervention. The proposed framework is simple, neat and effective. Extensive experiments and comparisons with state-of-the-art trackers are conducted on many challenging benchmarks like GOT-10K, LaSOT, UAV123 and OTB-50. Without bells and whistles, our SiamCAR achieves the leading performance with a considerable real-time speed.

Keywords

Cite

@article{arxiv.1911.07241,
  title  = {SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking},
  author = {Dongyan Guo and Jun Wang and Ying Cui and Zhenhua Wang and Shengyong Chen},
  journal= {arXiv preprint arXiv:1911.07241},
  year   = {2019}
}
R2 v1 2026-06-23T12:18:22.875Z