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. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPRW53098.2021.00137 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | Volume | ISSN |
Journal | abs/1904.05443 | 2160-7508 |
Citations | PageRank | References |
0 | 0.34 | 20 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alejandro Pardo | 1 | 0 | 0.34 |
Mengmeng Xu | 2 | 3 | 2.75 |
Ali K. Thabet | 3 | 19 | 7.10 |
Pablo Arbelaez | 4 | 3626 | 173.00 |
Bernard Ghanem | 5 | 1487 | 81.44 |