Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913381753028608 |
|---|---|
| author | Liu, Chenying Albrecht, Conrad M Wang, Yi Zhu, Xiao Xiang |
| author_facet | Liu, Chenying Albrecht, Conrad M Wang, Yi Zhu, Xiao Xiang |
| contents | Compared to supervised deep learning, self-supervision provides remote sensing a tool to reduce the amount of exact, human-crafted geospatial annotations. While image-level information for unsupervised pretraining efficiently works for various classification downstream tasks, the performance on pixel-level semantic segmentation lags behind in terms of model accuracy. On the contrary, many easily available label sources (e.g., automatic labeling tools and land cover land use products) exist, which can provide a large amount of noisy labels for segmentation model training. In this work, we propose to exploit noisy semantic segmentation maps for model pretraining. Our experiments provide insights on robustness per network layer. The transfer learning settings test the cases when the pretrained encoders are fine-tuned for different label classes and decoders. The results from two datasets indicate the effectiveness of task-specific supervised pretraining with noisy labels. Our findings pave new avenues to improved model accuracy and novel pretraining strategies for efficient remote sensing image segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16164 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation Liu, Chenying Albrecht, Conrad M Wang, Yi Zhu, Xiao Xiang Computer Vision and Pattern Recognition Compared to supervised deep learning, self-supervision provides remote sensing a tool to reduce the amount of exact, human-crafted geospatial annotations. While image-level information for unsupervised pretraining efficiently works for various classification downstream tasks, the performance on pixel-level semantic segmentation lags behind in terms of model accuracy. On the contrary, many easily available label sources (e.g., automatic labeling tools and land cover land use products) exist, which can provide a large amount of noisy labels for segmentation model training. In this work, we propose to exploit noisy semantic segmentation maps for model pretraining. Our experiments provide insights on robustness per network layer. The transfer learning settings test the cases when the pretrained encoders are fine-tuned for different label classes and decoders. The results from two datasets indicate the effectiveness of task-specific supervised pretraining with noisy labels. Our findings pave new avenues to improved model accuracy and novel pretraining strategies for efficient remote sensing image segmentation. |
| title | Task Specific Pretraining with Noisy Labels for Remote Sensing Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.16164 |