Multi-scale gridded Gabor attention for cirrus 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_ | 1866929418285350912 |
|---|---|
| author | Richards, Felix Paiement, Adeline Xie, Xianghua Sola, Elisabeth Duc, Pierre-Alain |
| author_facet | Richards, Felix Paiement, Adeline Xie, Xianghua Sola, Elisabeth Duc, Pierre-Alain |
| contents | In this paper, we address the challenge of segmenting global contaminants in large images. The precise delineation of such structures requires ample global context alongside understanding of textural patterns. CNNs specialise in the latter, though their ability to generate global features is limited. Attention measures long range dependencies in images, capturing global context, though at a large computational cost. We propose a gridded attention mechanism to address this limitation, greatly increasing efficiency by processing multi-scale features into smaller tiles. We also enhance the attention mechanism for increased sensitivity to texture orientation, by measuring correlations across features dependent on different orientations, in addition to channel and positional attention. We present results on a new dataset of astronomical images, where the task is segmenting large contaminating dust clouds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08852 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-scale gridded Gabor attention for cirrus segmentation Richards, Felix Paiement, Adeline Xie, Xianghua Sola, Elisabeth Duc, Pierre-Alain Computer Vision and Pattern Recognition Instrumentation and Methods for Astrophysics In this paper, we address the challenge of segmenting global contaminants in large images. The precise delineation of such structures requires ample global context alongside understanding of textural patterns. CNNs specialise in the latter, though their ability to generate global features is limited. Attention measures long range dependencies in images, capturing global context, though at a large computational cost. We propose a gridded attention mechanism to address this limitation, greatly increasing efficiency by processing multi-scale features into smaller tiles. We also enhance the attention mechanism for increased sensitivity to texture orientation, by measuring correlations across features dependent on different orientations, in addition to channel and positional attention. We present results on a new dataset of astronomical images, where the task is segmenting large contaminating dust clouds. |
| title | Multi-scale gridded Gabor attention for cirrus segmentation |
| topic | Computer Vision and Pattern Recognition Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2407.08852 |