2020/2021
Simple Fusion of Object Detectors for Improved Performance and Faster Deployment
IEEE Access*, 2021(9): 33235-33254
Author(s) | Chan-Tong Lam,
Jose Gaspar, Wei Ke, Marcus Im |
---|---|
Summary | Object detectors often suffer from multiple performance limitations which may be attenuated with larger training datasets, improved training techniques, and complex detection models. However, such strategies are complex and time-consuming for applications requiring fast deployments. We propose a Simple Fusion of Object Detectors (SFOD) late ensemble method to combine existing pre-trained, off-the-shelf, fine-tuned object detectors and leverage on their divergences to improve the overall detection performance. Comprehensive experimental evaluations, based on PASCAL VOC07 challenge, demonstrate SFOD's ability to improve mean average precision ( mAP) for different fusion sizes and base detector combinations, reaching an absolute 84.08% mAP and an improvement of 3.97% mAP. The improvements extend to most classes, fusion sizes, and base detector combinations, revealing AP improvements up to 17.35% over baselines, for particular object classes. Practical application evaluations, based on optimal threshold selection, also reveal improvements of 10.54% and 8.36% of mean recall ( mR) and mAP, respectively. Our approach does not require additional training and is quickly deployable, yet providing a few adjustable hyperparameters to optimize the recall-precision relation for specific applications. Improvements obtained from our proposed SFOD fusion pipeline span across a broad range of object classes and are important for a wide variety of critical applications where every successful detection is treasured.
|
* IFR: Top 34.43% in Engineering, Electrical & Electronic; 39.56% in Telecommunications; 40.12% in Computer Science Information Systems.
Also listed in Scopus, EI.