Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest. However, existing tracking approaches rely on customized sub-modules and need prior knowledge for architecture selection, hindering the tracking development in a more general system. This paper presents a Simplified Tracking architecture (SimTrack) by leveraging a transformer backbone for joint feature extraction and interaction. Unlike existing Siamese trackers, we serialize the input images and concatenate them directly before the one-branch backbone. Feature interaction in the backbone helps to remove well-designed interaction modules and produce a more efficient and effective framework. To reduce the information loss from down-sampling in vision transformers, we further propose a foveal window strategy, providing more diverse input patches with acceptable computational costs. Our SimTrack improves the baseline with 2.5%/2.6% AUC gains on LaSOT/TNL2K and gets results competitive with other specialized tracking algorithms without bells and whistles.
@article{arxiv.2203.05328,
title = {Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking},
author = {Boyu Chen and Peixia Li and Lei Bai and Lei Qiao and Qiuhong Shen and Bo Li and Weihao Gan and Wei Wu and Wanli Ouyang},
journal= {arXiv preprint arXiv:2203.05328},
year = {2022}
}