Bayesian Active Learning for Semantic Segmentation

Fully supervised training of semantic segmentation models is costly and challenging because each pixel within an image needs to be labeled. Therefore, the sparse pixel-level annotation methods have been introduced to train models with a subset of pixels within each image. We introduce a Bayesian act...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Didari, Sima, Hu, Wenjun, Jae Oh Woo, Heng Hao, Moon, Hankyu, Seungjai Min
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 03.08.2024
Subjects
Bayesian analysis
Image annotation
Image segmentation
Pixels
Semantic segmentation
Online AccessGet full text

Cover

More Information
Summary:Fully supervised training of semantic segmentation models is costly and challenging because each pixel within an image needs to be labeled. Therefore, the sparse pixel-level annotation methods have been introduced to train models with a subset of pixels within each image. We introduce a Bayesian active learning framework based on sparse pixel-level annotation that utilizes a pixel-level Bayesian uncertainty measure based on Balanced Entropy (BalEnt) [84]. BalEnt captures the information between the models' predicted marginalized probability distribution and the pixel labels. BalEnt has linear scalability with a closed analytical form and can be calculated independently per pixel without relational computations with other pixels. We train our proposed active learning framework for Cityscapes, Camvid, ADE20K and VOC2012 benchmark datasets and show that it reaches supervised levels of mIoU using only a fraction of labeled pixels while outperforming the previous state-of-the-art active learning models with a large margin.
ISSN:2331-8422