MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914820968677376 |
|---|---|
| author | Wang, Ke-Lei Chou, Pin-Hsuan Chou, Young-Ching Liu, Chia-Jen Lin, Cheng-Kuan Tseng, Yu-Chee |
| author_facet | Wang, Ke-Lei Chou, Pin-Hsuan Chou, Young-Ching Liu, Chia-Jen Lin, Cheng-Kuan Tseng, Yu-Chee |
| contents | While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free design and a single-stage framework that conducts detection and segmentation at one time, PolarMask is proved to be able to balance efficiency and accuracy. Hence, it can be easily connected with other downstream real-time applications. In this work, we observe that there are two deficiencies associated with PolarMask: (i) inability of representing concave objects and (ii) inefficiency in using ray regression. We propose MP-PolarMask (Multi-Point PolarMask) by taking advantage of multiple Polar systems. The main idea is to extend from one main Polar system to four auxiliary Polar systems, thus capable of representing more complicated convex-and-concave-mixed shapes. We validate MP-PolarMask on both general objects and food objects of the COCO dataset, and the results demonstrate significant improvement of 13.69% in AP_L and 7.23% in AP over PolarMask with 36 rays. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01356 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images Wang, Ke-Lei Chou, Pin-Hsuan Chou, Young-Ching Liu, Chia-Jen Lin, Cheng-Kuan Tseng, Yu-Chee Computer Vision and Pattern Recognition While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free design and a single-stage framework that conducts detection and segmentation at one time, PolarMask is proved to be able to balance efficiency and accuracy. Hence, it can be easily connected with other downstream real-time applications. In this work, we observe that there are two deficiencies associated with PolarMask: (i) inability of representing concave objects and (ii) inefficiency in using ray regression. We propose MP-PolarMask (Multi-Point PolarMask) by taking advantage of multiple Polar systems. The main idea is to extend from one main Polar system to four auxiliary Polar systems, thus capable of representing more complicated convex-and-concave-mixed shapes. We validate MP-PolarMask on both general objects and food objects of the COCO dataset, and the results demonstrate significant improvement of 13.69% in AP_L and 7.23% in AP over PolarMask with 36 rays. |
| title | MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.01356 |