Exploring Spatial Diversity for Region-Based Active Learning

Page view(s)
45
Checked on Sep 23, 2023
Exploring Spatial Diversity for Region-Based Active Learning
Title:
Exploring Spatial Diversity for Region-Based Active Learning
Journal Title:
IEEE Transactions on Image Processing
Publication Date:
19 October 2021
Citation:
Cai, L., Xu, X., Zhang, L., & Foo, C.-S. (2021). Exploring Spatial Diversity for Region-Based Active Learning. IEEE Transactions on Image Processing, 30, 8702–8712. doi:10.1109/tip.2021.3120041
Abstract:
State-of-the-art methods for semantic segmentation are based on deep neural networks trained on large-scale labeled datasets. Acquiring such datasets would incur large annotation costs, especially for dense pixel-level prediction tasks like semantic segmentation. We consider region-based active learning as a strategy to reduce annotation costs while maintaining high performance. In this setting, batches of informative image regions instead of entire images are selected for labeling. Importantly, we propose that enforcing local spatial diversity is beneficial for active learning in this case, and to incorporate spatial diversity along with the traditional active selection criterion, e.g., data sample uncertainty, in a unified optimization framework for region-based active learning. We apply this framework to the Cityscapes and PASCAL VOC datasets and demonstrate that the inclusion of spatial diversity effectively improves the performance of uncertainty-based and feature diversity-based active learning methods. Our framework achieves 95% performance of fully supervised methods with only 5 − 9% of the labeled pixels, outperforming all state-of-the-art region-based active learning methods for semantic segmentation.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H6b0151
Description:
© 2021 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:
1057-7149
1941-0042
Files uploaded:

File Size Format Action
tip-23158-2020-exploring-spatial-diversity-for-region-based-active-learning.pdf 7.72 MB PDF Request a copy