BAOD: Budget-Aware Object Detection

Abstract
We study the problem of object detection from a novel perspective in which annotation budget constraints are taken into consideration, appropriately coined Budget Aware Object Detection (BAOD). When provided with a fixed budget, we propose a strategy for building a diverse and informative dataset that can be used to optimally train a robust detector. We investigate both optimization and learning-based methods to sample which images to annotate and what type of annotation (strongly or weakly supervised) to annotate them with. We adopt a hybrid supervised learning framework to train the object detector from both these types of annotation. We conduct a comprehensive empirical study showing that a handcrafted optimization method outperforms other selection techniques including random sampling, uncertainty sampling and active learning. By combining an optimal image/annotation selection scheme with hybrid supervised learning to solve the BAOD problem, we show that one can achieve the performance of a strongly supervised detector on PASCAL-VOC 2007 while saving 12.8% of its original annotation budget. Furthermore, when 100% of the budget is used, it surpasses this performance by 2.0 mAP percentage points.

Citation
Pardo, A., Xu, M., Thabet, A., Arbelaez, P., & Ghanem, B. (2021). BAOD: Budget-Aware Object Detection. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). doi:10.1109/cvprw53098.2021.00137

Publisher
IEEE

Conference/Event Name
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

DOI
10.1109/CVPRW53098.2021.00137

arXiv
1904.05443

Additional Links
https://ieeexplore.ieee.org/document/9523033/https://ieeexplore.ieee.org/document/9523033/https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9523033

Permanent link to this record