Box-Level Class-Balanced Sampling For Active Object Detection

Page view(s)
15
Checked on Jan 31, 2025
Box-Level Class-Balanced Sampling For Active Object Detection
Title:
Box-Level Class-Balanced Sampling For Active Object Detection
Journal Title:
2024 IEEE International Conference on Image Processing (ICIP)
Publication Date:
27 September 2024
Citation:
Liao, J., Xu, X., Foo, C.-S., & Cai, L. (2024). Box-Level Class-Balanced Sampling For Active Object Detection. 2024 IEEE International Conference on Image Processing (ICIP), 2018, 701–707. https://doi.org/10.1109/icip51287.2024.10648281
Abstract:
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most informative boxes to label and supplementing the sparsely-labelled image with pseudo labels, has been shown to be more cost-effective than selecting and labelling the entire image. In box-level AL for object detection, we observe that models at early stage can only perform well on majority classes, making the pseudo labels severely class-imbalanced. We propose a class-balanced sampling strategy to select more objects from minority classes for labelling, so as to make the final training data, i.e., ground truth labels obtained by AL and pseudo labels, more class-balanced to train a better model. We also propose a task-aware soft pseudo labelling strategy to increase the accuracy of pseudo labels. We evaluate our method on public benchmarking datasets and show that our method achieves state-of-the-art performance.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - Career Development Fund
Grant Reference no. : C210812052
Description:
© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2381-8549