Revisiting Superpixels for Active Learning in Semantic Segmentation with Realistic Annotation Costs

Revisiting Superpixels for Active Learning in Semantic Segmentation with Realistic Annotation Costs

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

10.1109/CVPR46437.2021.01084

https://doi.org/10.1109/cvpr46437.2021.01084

Lile Cai, Xun Xu, Jun Hao Liew, Chuan Sheng Foo

13 November 2021

Cai, L., Xu, X., Liew, J. H., & Sheng Foo, C. (2021). Revisiting Superpixels for Active Learning in Semantic Segmentation with Realistic Annotation Costs. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr46437.2021.01084

State-of-the-art methods for semantic segmentation are based on deep neural networks that are known to be data-hungry. Region-based active learning has shown to be a promising method for reducing data annotation costs. A key design choice for region-based AL is whether to use regularly-shaped regions (e.g., rectangles) or irregularly-shaped region (e.g., superpixels). In this work, we address this question under realistic, click-based measurement of annotation costs. In particular, we revisit the use of superpixels and demonstrate that the inappropriate choice of cost measure (e.g., the percentage of labeled pixels), may cause the effectiveness of the superpixel-based approach to be under-estimated. We benchmark the superpixel-based approach against the traditional "rectangle+polygon"-based approach with annotation cost measured in clicks, and show that the former outperforms on both Cityscapes and PASCAL VOC. We further propose a class-balanced acquisition function to boost the performance of the superpixel-based approach and demonstrate its effectiveness on the evaluation datasets. Our results strongly argue for the use of superpixel-based AL for semantic segmentation and highlight the importance of using realistic annotation costs in evaluating such methods.

Publisher Copyright

This research is supported by core funding from: Institute for Infocomm Research
Grant Reference no. :

© 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.

https://oar.a-star.edu.sg/communities-collections/articles/18031

2575-7075
1063-6919

978-1-6654-4509-2
978-1-6654-4510-8

Institute for Infocomm Research