Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation

by   Bin Yan, et al.
Dalian University of Technology

In recent years, the multiple-stage strategy has become a popular trend for visual tracking. This strategy first utilizes a base tracker to coarsely locate the target and then exploits a refinement module to obtain more accurate results. However, existing refinement modules suffer from the limited transferability and precision. In this work, we propose a novel, flexible and accurate refinement module called Alpha-Refine, which exploits a precise pixel-wise correlation layer together with a spatial-aware non-local layer to fuse features and can predict three complementary outputs: bounding box, corners and mask. To wisely choose the most adequate output, we also design a light-weight branch selector module. We apply the proposed Alpha-Refine module to five famous and state-of-the-art base trackers: DiMP, ATOM, SiamRPN++, RTMDNet and ECO. The comprehensive experiments on TrackingNet, LaSOT and VOT2018 benchmarks demonstrate that our approach significantly improves the tracking performance in comparison with other existing refinement methods. The source codes will be available at


page 3

page 4

page 9


Video Annotation for Visual Tracking via Selection and Refinement

Deep learning based visual trackers entail offline pre-training on large...

Discriminative Segmentation Tracking Using Dual Memory Banks

Existing template-based trackers usually localize the target in each fra...

Target Transformed Regression for Accurate Tracking

Accurate tracking is still a challenging task due to appearance variatio...

TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator

In a generic object tracking, depth (D) information provides informative...

Towards Accurate Pixel-wise Object Tracking by Attention Retrieval

The encoding of the target in object tracking moves from the coarse boun...

Transforming Model Prediction for Tracking

Optimization based tracking methods have been widely successful by integ...

Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises

Adversarial attack of CNN aims at deceiving models to misbehave by addin...

Please sign up or login with your details

Forgot password? Click here to reset