liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Adapting with Confidence: Certainty Weighted Guidance for Domain Adaptation in Remote Sensing Semantic Segmentation
Linköping University, Department of Electrical Engineering, Computer Vision.
Linköping University, Department of Electrical Engineering, Computer Vision.
2025 (English)Independent thesis Advanced level (degree of Master (Two Years)), 28 HE creditsStudent thesis
Abstract [en]

Deep learning-based semantic segmentation methods have proven effective in many remote sensing tasks. However, their performance degrades when data distributions shift, for example, when applying a model to a domain different from the one on which it was trained. This hinders the applicability of said models. In this thesis, we investigate how knowledge about data can be incorporated into domain adaptation methods to improve semantic segmentation performance on the target domain. We propose two frameworks based on adversarial and contrastive learning, incorporating existing data and prior knowledge through a pixel-wise certainty measure. Experimental results show that our methods outperform the baseline by 6.8 percentage points and conventional domain adaptation methods by 2.2 percentage points. Our findings suggest that the contrastive approach is better suited for the task as the tailored loss favors target domain alignment. We also found that an adaptive certainty measure, based on model predictions, was best suited for guiding adaptation. Furthermore, extending the unsupervised module of the methods with more data degrades performance, suggesting that direct supervision is essential for accuracy and stable training. Our methods are effective in scenarios with geographically aligned source and target domains, enabling better segmentation without requiring target annotations. This work contributes to reducing the reliance on extensive manual annotation, thereby lowering the cost and increasing the scalability and adaptability of deep learning models. 

Place, publisher, year, edition, pages
2025. , p. 60
Keywords [en]
Remote Sensing, Domain Adaptation, Machine Learning, Artificial Intelligence, Deep Learning, Semantic Segmentation, Satellite Imagery, Supervised Learning, Unsupervised Learning, Pseudo-labeling, Transfer Learning, Feature Alignment, Adversarial Learning, Contrastive Learning, Prior Knowledge, Semantic Change Detection, Data Scarcity, Computer Vision, Neural Network
National Category
Computer Vision and Learning Systems
Identifiers
URN: urn:nbn:se:liu:diva-214506ISRN: LiTH-ISY-EX--25/5767--SEOAI: oai:DiVA.org:liu-214506DiVA, id: diva2:1965979
External cooperation
Maxar Intelligence
Subject / course
Computer Vision Laboratory
Presentation
2025-06-05, Nollstället, Linköping, 14:00 (English)
Supervisors
Examiners
Available from: 2025-06-09 Created: 2025-06-09 Last updated: 2025-06-09Bibliographically approved

Open Access in DiVA

fulltext(27881 kB)427 downloads
File information
File name FULLTEXT01.pdfFile size 27881 kBChecksum SHA-512
237cd07495dbd3cbea80b0d85644a897fc9c4c22637cb6be03c6110daeef3b096d2d7f65e8ec3928b1d197e4b20dbb0a3a0f0c8fb9b2f603e8a053cf0c81a174
Type fulltextMimetype application/pdf

By organisation
Computer Vision
Computer Vision and Learning Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 427 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 777 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf