ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking
Preprint
Abstract
Recently, the transformer has enabled the speed-oriented trackers to approach state-of-the-art (SOTA) performance with high-speed thanks to the smaller input size or the lighter feature extraction backbone, though they still substantially lag behind their corresponding performance-oriented versions. In this paper, we demonstrate that it is possible to narrow or even close this gap while achieving high tracking speed based on the smaller input size. To this end, we non-uniformly resize the cropped image to have a smaller input size while the resolution of the area where the target is more likely to appear is higher and vice versa. This enables us to solve the dilemma of attending to a larger visual field while retaining more raw information for the target despite a smaller input size. Our formulation for the non-uniform resizing can be efficiently solved through quadratic programming (QP) and naturally integrated into most of the crop-based local trackers. Comprehensive experiments on five challenging datasets based on two kinds of transformer trackers, \ie, OSTrack and TransT, demonstrate consistent improvements over them. In particular, applying our method to the speed-oriented version of OSTrack even outperforms its performance-oriented counterpart by 0.6% AUC on TNL2K, while running 50% faster and saving over 55% MACs. Codes and models are available at https://github.com/Kou-99/ZoomTrack.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework2022
- FEAR: Fast, Efficient, Accurate and Robust Visual Tracker2022
- Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking2022
- A new framework for understanding vision from the perspective of the primary visual cortexCurrent Opinion in Neurobiology, 2019
- Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition2019
- SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks2019
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking2019
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild2018
- Learning to Zoom: A Saliency-Based Sampling Layer for Neural Networks2018
- A Benchmark and Simulator for UAV Tracking2016