Dynamic-budget superpixel active learning for semantic segmentation
IntroductionActive learning can significantly decrease the labeling cost of deep learning workflows by prioritizing the limited labeling budget to high-impact data points that have the highest positive impact on model accuracy. Active learning is especially useful for semantic segmentation tasks whe...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2024.1498956/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553910341304320 |
|---|---|
| author | Yuemin Wang Ian Stavness |
| author_facet | Yuemin Wang Ian Stavness |
| author_sort | Yuemin Wang |
| collection | DOAJ |
| description | IntroductionActive learning can significantly decrease the labeling cost of deep learning workflows by prioritizing the limited labeling budget to high-impact data points that have the highest positive impact on model accuracy. Active learning is especially useful for semantic segmentation tasks where we can selectively label only a few high-impact regions within these high-impact images. Most established regional active learning algorithms deploy a static-budget querying strategy where a fixed percentage of regions are queried in each image. A static budget could result in over- or under-labeling images as the number of high-impact regions in each image can vary.MethodsIn this paper, we present a novel dynamic-budget superpixel querying strategy that can query the optimal numbers of high-uncertainty superpixels in an image to improve the querying efficiency of regional active learning algorithms designed for semantic segmentation.ResultsFor two distinct datasets, we show that by allowing a dynamic budget for each image, the active learning algorithm is more effective compared to static-budget querying at the same low total labeling budget. We investigate both low- and high-budget scenarios and the impact of superpixel size on our dynamic active learning scheme. In a low-budget scenario, our dynamic-budget querying outperforms static-budget querying by 5.6% mIoU on a specialized agriculture field image dataset and 2.4% mIoU on Cityscapes.DiscussionThe presented dynamic-budget querying strategy is simple, effective, and can be easily adapted to other regional active learning algorithms to further improve the data efficiency of semantic segmentation tasks. |
| format | Article |
| id | doaj-art-a767f2b7e0614a658c643f05efffc571 |
| institution | Kabale University |
| issn | 2624-8212 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj-art-a767f2b7e0614a658c643f05efffc5712025-01-09T06:10:47ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-01-01710.3389/frai.2024.14989561498956Dynamic-budget superpixel active learning for semantic segmentationYuemin WangIan StavnessIntroductionActive learning can significantly decrease the labeling cost of deep learning workflows by prioritizing the limited labeling budget to high-impact data points that have the highest positive impact on model accuracy. Active learning is especially useful for semantic segmentation tasks where we can selectively label only a few high-impact regions within these high-impact images. Most established regional active learning algorithms deploy a static-budget querying strategy where a fixed percentage of regions are queried in each image. A static budget could result in over- or under-labeling images as the number of high-impact regions in each image can vary.MethodsIn this paper, we present a novel dynamic-budget superpixel querying strategy that can query the optimal numbers of high-uncertainty superpixels in an image to improve the querying efficiency of regional active learning algorithms designed for semantic segmentation.ResultsFor two distinct datasets, we show that by allowing a dynamic budget for each image, the active learning algorithm is more effective compared to static-budget querying at the same low total labeling budget. We investigate both low- and high-budget scenarios and the impact of superpixel size on our dynamic active learning scheme. In a low-budget scenario, our dynamic-budget querying outperforms static-budget querying by 5.6% mIoU on a specialized agriculture field image dataset and 2.4% mIoU on Cityscapes.DiscussionThe presented dynamic-budget querying strategy is simple, effective, and can be easily adapted to other regional active learning algorithms to further improve the data efficiency of semantic segmentation tasks.https://www.frontiersin.org/articles/10.3389/frai.2024.1498956/fulldynamic-budget queryingsuperpixelregional queryingactive learningsemantic segmentation |
| spellingShingle | Yuemin Wang Ian Stavness Dynamic-budget superpixel active learning for semantic segmentation Frontiers in Artificial Intelligence dynamic-budget querying superpixel regional querying active learning semantic segmentation |
| title | Dynamic-budget superpixel active learning for semantic segmentation |
| title_full | Dynamic-budget superpixel active learning for semantic segmentation |
| title_fullStr | Dynamic-budget superpixel active learning for semantic segmentation |
| title_full_unstemmed | Dynamic-budget superpixel active learning for semantic segmentation |
| title_short | Dynamic-budget superpixel active learning for semantic segmentation |
| title_sort | dynamic budget superpixel active learning for semantic segmentation |
| topic | dynamic-budget querying superpixel regional querying active learning semantic segmentation |
| url | https://www.frontiersin.org/articles/10.3389/frai.2024.1498956/full |
| work_keys_str_mv | AT yueminwang dynamicbudgetsuperpixelactivelearningforsemanticsegmentation AT ianstavness dynamicbudgetsuperpixelactivelearningforsemanticsegmentation |