MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916105612689408 |
|---|---|
| author | Ayobi, Nicolás Pérez-Rondón, Alejandra Rodríguez, Santiago Arbeláez, Pablo |
| author_facet | Ayobi, Nicolás Pérez-Rondón, Alejandra Rodríguez, Santiago Arbeláez, Pablo |
| contents | We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the instance-level nature of the task by employing a masked attention module that generates and classifies a set of fine instrument region proposals. Our method incorporates long-term video-level information through video transformers to improve temporal consistency and enhance mask classification. We validate our approach in the two standard public benchmarks, Endovis 2017 and Endovis 2018. Our experiments demonstrate that MATIS' per-frame baseline outperforms previous state-of-the-art methods and that including our temporal consistency module boosts our model's performance further. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_09514 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation Ayobi, Nicolás Pérez-Rondón, Alejandra Rodríguez, Santiago Arbeláez, Pablo Computer Vision and Pattern Recognition We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS exploits the instance-level nature of the task by employing a masked attention module that generates and classifies a set of fine instrument region proposals. Our method incorporates long-term video-level information through video transformers to improve temporal consistency and enhance mask classification. We validate our approach in the two standard public benchmarks, Endovis 2017 and Endovis 2018. Our experiments demonstrate that MATIS' per-frame baseline outperforms previous state-of-the-art methods and that including our temporal consistency module boosts our model's performance further. |
| title | MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.09514 |