Enhanced Semantic Segmentation Pipeline for WeatherProof Dataset Challenge
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929377030176768 |
|---|---|
| author | Zhang, Nan Zhang, Xidan Wei, Jianing Wang, Fangjun Tan, Zhiming |
| author_facet | Zhang, Nan Zhang, Xidan Wei, Jianing Wang, Fangjun Tan, Zhiming |
| contents | This report describes the winning solution to the WeatherProof Dataset Challenge (CVPR 2024 UG2+ Track 3). Details regarding the challenge are available at https://cvpr2024ug2challenge.github.io/track3.html. We propose an enhanced semantic segmentation pipeline for this challenge. Firstly, we improve semantic segmentation models, using backbone pretrained with Depth Anything to improve UperNet model and SETRMLA model, and adding language guidance based on both weather and category information to InternImage model. Secondly, we introduce a new dataset WeatherProofExtra with wider viewing angle and employ data augmentation methods, including adverse weather and super-resolution. Finally, effective training strategies and ensemble method are applied to improve final performance further. Our solution is ranked 1st on the final leaderboard. Code will be available at https://github.com/KaneiGi/WeatherProofChallenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03799 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhanced Semantic Segmentation Pipeline for WeatherProof Dataset Challenge Zhang, Nan Zhang, Xidan Wei, Jianing Wang, Fangjun Tan, Zhiming Computer Vision and Pattern Recognition Artificial Intelligence This report describes the winning solution to the WeatherProof Dataset Challenge (CVPR 2024 UG2+ Track 3). Details regarding the challenge are available at https://cvpr2024ug2challenge.github.io/track3.html. We propose an enhanced semantic segmentation pipeline for this challenge. Firstly, we improve semantic segmentation models, using backbone pretrained with Depth Anything to improve UperNet model and SETRMLA model, and adding language guidance based on both weather and category information to InternImage model. Secondly, we introduce a new dataset WeatherProofExtra with wider viewing angle and employ data augmentation methods, including adverse weather and super-resolution. Finally, effective training strategies and ensemble method are applied to improve final performance further. Our solution is ranked 1st on the final leaderboard. Code will be available at https://github.com/KaneiGi/WeatherProofChallenge. |
| title | Enhanced Semantic Segmentation Pipeline for WeatherProof Dataset Challenge |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2406.03799 |