Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessment
Amirsaeed Yazdani (Pennsylvania State University),* Xuelu Li (Amazon), Vishal Monga (The Pennsylvania State University)
The 34th British Machine Vision Conference
Abstract
Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and different ways of defining ``sample'' (pixels, areas, etc.), leaving the interpretation of the data distribution ambiguous. We propose ``Maturity-Aware Distribution Breakdown-based Active Learning'' (MADBAL), an AL method that benefits from a hierarchical approach to define a multiview data distribution, which takes into account the different "sample" definitions jointly, hence able to select the most impactful segmentation pixels with comprehensive understanding. MADBAL also features a novel uncertainty formulation, where AL supporting modules are included to sense the features' maturity whose weighted influence continuously contributes to the uncertainty detection. In this way, MADBAL makes significant performance leaps even in the early AL stage, hence reducing the training burden significantly. It outperforms state-of-the-art methods on Cityscapes and PASCAL VOC datasets as verified in our extensive experiments.Video
Citation
@inproceedings{Yazdani_2023_BMVC,
author = {Amirsaeed Yazdani and Xuelu Li and Vishal Monga},
title = {Maturity-Aware Active Learning for Semantic Segmentation with Hierarchically-Adaptive Sample Assessment},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0437.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by