Technical report on target classification in SAR track
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914783599525888 |
|---|---|
| author | Xu, Haonan Yinan, Han Si, Haotian Yang, Yang |
| author_facet | Xu, Haonan Yinan, Han Si, Haotian Yang, Yang |
| contents | This report proposes a robust method for classifying oceanic and atmospheric phenomena using synthetic aperture radar (SAR) imagery. Our proposed method leverages the powerful pre-trained model Swin Transformer v2 Large as the backbone and employs carefully designed data augmentation and exponential moving average during training to enhance the model's generalization capability and stability. In the testing stage, a method called ReAct is utilized to rectify activation values and utilize Energy Score for more accurate measurement of model uncertainty, significantly improving out-of-distribution detection performance. Furthermore, test time augmentation is employed to enhance classification accuracy and prediction stability. Comprehensive experimental results demonstrate that each additional technique significantly improves classification accuracy, confirming their effectiveness in classifying maritime and atmospheric phenomena in SAR imagery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02361 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Technical report on target classification in SAR track Xu, Haonan Yinan, Han Si, Haotian Yang, Yang Image and Video Processing This report proposes a robust method for classifying oceanic and atmospheric phenomena using synthetic aperture radar (SAR) imagery. Our proposed method leverages the powerful pre-trained model Swin Transformer v2 Large as the backbone and employs carefully designed data augmentation and exponential moving average during training to enhance the model's generalization capability and stability. In the testing stage, a method called ReAct is utilized to rectify activation values and utilize Energy Score for more accurate measurement of model uncertainty, significantly improving out-of-distribution detection performance. Furthermore, test time augmentation is employed to enhance classification accuracy and prediction stability. Comprehensive experimental results demonstrate that each additional technique significantly improves classification accuracy, confirming their effectiveness in classifying maritime and atmospheric phenomena in SAR imagery. |
| title | Technical report on target classification in SAR track |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2405.02361 |