SAModified: A Foundation Model-Based Zero-Shot Approach for Refining Noisy Land-Use Land-Cover Maps
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929635029155840 |
|---|---|
| author | Pekhale, Sparsh Sathish, Rakshith Basavaraju, Sathisha Sharma, Divya |
| author_facet | Pekhale, Sparsh Sathish, Rakshith Basavaraju, Sathisha Sharma, Divya |
| contents | Land-use and land cover (LULC) analysis is critical in remote sensing, with wide-ranging applications across diverse fields such as agriculture, utilities, and urban planning. However, automating LULC map generation using machine learning is rendered challenging due to noisy labels. Typically, the ground truths (e.g. ESRI LULC, MapBioMass) have noisy labels that hamper the model's ability to learn to accurately classify the pixels. Further, these erroneous labels can significantly distort the performance metrics of a model, leading to misleading evaluations. Traditionally, the ambiguous labels are rectified using unsupervised algorithms. These algorithms struggle not only with scalability but also with generalization across different geographies. To overcome these challenges, we propose a zero-shot approach using the foundation model, Segment Anything Model (SAM), to automatically delineate different land parcels/regions and leverage them to relabel the unsure pixels by using the local label statistics within each detected region. We achieve a significant reduction in label noise and an improvement in the performance of the downstream segmentation model by $\approx 5\%$ when trained with denoised labels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12552 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SAModified: A Foundation Model-Based Zero-Shot Approach for Refining Noisy Land-Use Land-Cover Maps Pekhale, Sparsh Sathish, Rakshith Basavaraju, Sathisha Sharma, Divya Computer Vision and Pattern Recognition Artificial Intelligence Land-use and land cover (LULC) analysis is critical in remote sensing, with wide-ranging applications across diverse fields such as agriculture, utilities, and urban planning. However, automating LULC map generation using machine learning is rendered challenging due to noisy labels. Typically, the ground truths (e.g. ESRI LULC, MapBioMass) have noisy labels that hamper the model's ability to learn to accurately classify the pixels. Further, these erroneous labels can significantly distort the performance metrics of a model, leading to misleading evaluations. Traditionally, the ambiguous labels are rectified using unsupervised algorithms. These algorithms struggle not only with scalability but also with generalization across different geographies. To overcome these challenges, we propose a zero-shot approach using the foundation model, Segment Anything Model (SAM), to automatically delineate different land parcels/regions and leverage them to relabel the unsure pixels by using the local label statistics within each detected region. We achieve a significant reduction in label noise and an improvement in the performance of the downstream segmentation model by $\approx 5\%$ when trained with denoised labels. |
| title | SAModified: A Foundation Model-Based Zero-Shot Approach for Refining Noisy Land-Use Land-Cover Maps |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.12552 |