Extreme Point Supervised Instance Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911901657595904 |
|---|---|
| author | Lee, Hyeonjun Hwang, Sehyun Kwak, Suha |
| author_facet | Lee, Hyeonjun Hwang, Sehyun Kwak, Suha |
| contents | This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box annotation process while offering strong clues for precise segmentation, and thus allows to improve performance at the same annotation cost with box-supervised methods. Our work considers extreme points as a part of the true instance mask and propagates them to identify potential foreground and background points, which are all together used for training a pseudo label generator. Then pseudo labels given by the generator are in turn used for supervised learning of our final model. On three public benchmarks, our method significantly outperforms existing box-supervised methods, further narrowing the gap with its fully supervised counterpart. In particular, our model generates high-quality masks when a target object is separated into multiple parts, where previous box-supervised methods often fail. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20729 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Extreme Point Supervised Instance Segmentation Lee, Hyeonjun Hwang, Sehyun Kwak, Suha Computer Vision and Pattern Recognition This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box annotation process while offering strong clues for precise segmentation, and thus allows to improve performance at the same annotation cost with box-supervised methods. Our work considers extreme points as a part of the true instance mask and propagates them to identify potential foreground and background points, which are all together used for training a pseudo label generator. Then pseudo labels given by the generator are in turn used for supervised learning of our final model. On three public benchmarks, our method significantly outperforms existing box-supervised methods, further narrowing the gap with its fully supervised counterpart. In particular, our model generates high-quality masks when a target object is separated into multiple parts, where previous box-supervised methods often fail. |
| title | Extreme Point Supervised Instance Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.20729 |