Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking

By Boyu Chen, Peixia Li, Lei Bai, Leixian Qiao, Qiuhong Shen, Bo Li, Weihao Gan, Wei Wu, Wanli Ouyang. European Conference on Computer Vision, 2022

325 citations recorded by the source corpus.

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.

View Paper: https://www.semanticscholar.org/paper/04ea6fc31a1196264a15fa9912b1ff06d6f70220