Image Segmentation with transformers: An Overview, Challenges and Future
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910786770698240 |
|---|---|
| author | Chetia, Deepjyoti Dutta, Debasish Kalita, Sanjib Kr |
| author_facet | Chetia, Deepjyoti Dutta, Debasish Kalita, Sanjib Kr |
| contents | Image segmentation, a key task in computer vision, has traditionally relied on convolutional neural networks (CNNs), yet these models struggle with capturing complex spatial dependencies, objects with varying scales, need for manually crafted architecture components and contextual information. This paper explores the shortcomings of CNN-based models and the shift towards transformer architectures -to overcome those limitations. This work reviews state-of-the-art transformer-based segmentation models, addressing segmentation-specific challenges and their solutions. The paper discusses current challenges in transformer-based segmentation and outlines promising future trends, such as lightweight architectures and enhanced data efficiency. This survey serves as a guide for understanding the impact of transformers in advancing segmentation capabilities and overcoming the limitations of traditional models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Image Segmentation with transformers: An Overview, Challenges and Future Chetia, Deepjyoti Dutta, Debasish Kalita, Sanjib Kr Computer Vision and Pattern Recognition Image segmentation, a key task in computer vision, has traditionally relied on convolutional neural networks (CNNs), yet these models struggle with capturing complex spatial dependencies, objects with varying scales, need for manually crafted architecture components and contextual information. This paper explores the shortcomings of CNN-based models and the shift towards transformer architectures -to overcome those limitations. This work reviews state-of-the-art transformer-based segmentation models, addressing segmentation-specific challenges and their solutions. The paper discusses current challenges in transformer-based segmentation and outlines promising future trends, such as lightweight architectures and enhanced data efficiency. This survey serves as a guide for understanding the impact of transformers in advancing segmentation capabilities and overcoming the limitations of traditional models. |
| title | Image Segmentation with transformers: An Overview, Challenges and Future |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.09372 |