Unsupervised Class Generation to Expand Semantic Segmentation Datasets
Semantic segmentation is a computer vision task where classification is performed at the pixel level. Due to this, the process of labeling images for semantic segmentation is time-consuming and expensive. To mitigate this cost there has been a surge in the use of synthetically generated data—usually...
Saved in:
| Main Authors: | Javier Montalvo, Álvaro García-Martín, Pablo Carballeira, Juan C. SanMiguel |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/6/172 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhanced unsupervised domain adaptation with iterative pseudo-label refinement for inter-event oil spill segmentation in SAR images
by: Guangyan Cui, et al.
Published: (2025-05-01) -
Training marine species object detectors with synthetic images and unsupervised domain adaptation
by: Heather Doig, et al.
Published: (2025-07-01) -
Exploring unsupervised feature extraction algorithms: tackling high dimensionality in small datasets
by: Hongqi Niu, et al.
Published: (2025-07-01) -
Unsupervised SAR Fine-Grained Ship Classification via Spherical Metric Refinement With Deep Subdomain Adaptation
by: Zhichao Han, et al.
Published: (2025-01-01) -
Speckle-Driven Unsupervised Despeckling for SAR Images
by: Fuyu Bo, et al.
Published: (2025-01-01)