Visual trackers improve performance by recovering discarded predictions
P-SRM: Selective Recovery of Rejected Predictions in Visual Tracking
Computer Vision and Pattern Recognition
Summary
Visual tracking systems sometimes reject guesses about where an object is because they think the guess is unreliable. But some of these rejected guesses might actually be correct and helpful. The authors created a method called P-SRM that rechecks these rejected guesses using information from previous successful guesses and the original confidence scores. This method can bring back good predictions that were thrown away, improving the accuracy of visual tracking across different systems and datasets.
What this means in practice
- •For computer vision engineers: Enhance existing visual tracking systems by selectively restoring useful rejected predictions to boost tracking accuracy and robustness.
- •For robotics software teams: Improve object tracking in robotic perception by integrating post-rejection recovery to better handle uncertain sensor data and maintain accurate localization.
Authors
Youbin He, Siwei Wang
Abstract
Many visual tracking methods use rejection mechanisms to suppress unreliable predictions. However, these mechanisms can also reject correctly localized candidates, leaving useful information unused. We investigate how to identify and recover these candidates while preserving native accepted outputs and candidate coordinates. To this end, we propose P-SRM (Post-rejection Selective Recovery Method), which combines spatial responses, past accepted states, and native decision margins to reassess candidates and selectively restore reliable predictions. We evaluate P-SRM on six trackers and four datasets spanning category-specific, point, and generic object tracking. Across all nine configurations, P-SRM improves rejected-candidate ranking and overall tracking performance. These results show that post-rejection verification can identify and recover useful predictions discarded by native rejection, demonstrating the value of reusing rejected information. Project repository: https://github.com/PalestyHR/P-SRM.