Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2407.05452 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911948248973312 |
|---|---|
| author | Nguyen, Tuan T. Le, Phan Hassan, Yasir Sartipi, Mina |
| author_facet | Nguyen, Tuan T. Le, Phan Hassan, Yasir Sartipi, Mina |
| contents | In this paper, we present the submission to the 5th Annual Smoky Mountains Computational Sciences Data Challenge, Challenge 3. This is the solution for semantic segmentation problem in both real-world and synthetic images from a vehicle s forward-facing camera. We concentrate in building a robust model which performs well across various domains of different outdoor situations such as sunny, snowy, rainy, etc. In particular, our method is developed with two main directions: model development and domain adaptation. In model development, we use the High Resolution Network (HRNet) as the baseline. Then, this baseline s result is processed by two coarse-to-fine models: Object-Contextual Representations (OCR) and Hierarchical Multi-scale Attention (HMA) to get the better robust feature. For domain adaption, we implement the Domain-Based Batch Normalization (DNB) to reduce the distribution shift from diverse domains. Our proposed method yield 81.259 mean intersection-over-union (mIoU) in validation set. This paper studies the effectiveness of employing real-world and synthetic data to handle the domain adaptation in semantic segmentation problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05452 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semantic Segmentation for Real-World and Synthetic Vehicle's Forward-Facing Camera Images Nguyen, Tuan T. Le, Phan Hassan, Yasir Sartipi, Mina Computer Vision and Pattern Recognition In this paper, we present the submission to the 5th Annual Smoky Mountains Computational Sciences Data Challenge, Challenge 3. This is the solution for semantic segmentation problem in both real-world and synthetic images from a vehicle s forward-facing camera. We concentrate in building a robust model which performs well across various domains of different outdoor situations such as sunny, snowy, rainy, etc. In particular, our method is developed with two main directions: model development and domain adaptation. In model development, we use the High Resolution Network (HRNet) as the baseline. Then, this baseline s result is processed by two coarse-to-fine models: Object-Contextual Representations (OCR) and Hierarchical Multi-scale Attention (HMA) to get the better robust feature. For domain adaption, we implement the Domain-Based Batch Normalization (DNB) to reduce the distribution shift from diverse domains. Our proposed method yield 81.259 mean intersection-over-union (mIoU) in validation set. This paper studies the effectiveness of employing real-world and synthetic data to handle the domain adaptation in semantic segmentation problem. |
| title | Semantic Segmentation for Real-World and Synthetic Vehicle's Forward-Facing Camera Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.05452 |