Learning Semantic Segmentation with Query Points Supervision on Aerial Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910556526477312 |
|---|---|
| author | Rivier, Santiago Hinojosa, Carlos Giancola, Silvio Ghanem, Bernard |
| author_facet | Rivier, Santiago Hinojosa, Carlos Giancola, Silvio Ghanem, Bernard |
| contents | Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most of these methods are typically trained in fully supervised settings that require high-quality pixel-level annotations, which are expensive and time-consuming to obtain. In this work, we present a weakly supervised learning algorithm to train semantic segmentation algorithms that only rely on query point annotations instead of full mask labels. Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation. Specifically, we generate superpixels and extend the query point labels into those superpixels that group similar meaningful semantics. Then, we train semantic segmentation models supervised with images partially labeled with the superpixel pseudo-labels. We benchmark our weakly supervised training approach on an aerial image dataset and different semantic segmentation architectures, showing that we can reach competitive performance compared to fully supervised training while reducing the annotation effort. The code of our proposed approach is publicly available at: https://github.com/santiago2205/LSSQPS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_05490 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning Semantic Segmentation with Query Points Supervision on Aerial Images Rivier, Santiago Hinojosa, Carlos Giancola, Silvio Ghanem, Bernard Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most of these methods are typically trained in fully supervised settings that require high-quality pixel-level annotations, which are expensive and time-consuming to obtain. In this work, we present a weakly supervised learning algorithm to train semantic segmentation algorithms that only rely on query point annotations instead of full mask labels. Our proposed approach performs accurate semantic segmentation and improves efficiency by significantly reducing the cost and time required for manual annotation. Specifically, we generate superpixels and extend the query point labels into those superpixels that group similar meaningful semantics. Then, we train semantic segmentation models supervised with images partially labeled with the superpixel pseudo-labels. We benchmark our weakly supervised training approach on an aerial image dataset and different semantic segmentation architectures, showing that we can reach competitive performance compared to fully supervised training while reducing the annotation effort. The code of our proposed approach is publicly available at: https://github.com/santiago2205/LSSQPS. |
| title | Learning Semantic Segmentation with Query Points Supervision on Aerial Images |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2309.05490 |