Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2020
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911457447247872 |
|---|---|
| author | Wu, Yuli Chen, Long Merhof, Dorit |
| author_facet | Wu, Yuli Chen, Long Merhof, Dorit |
| contents | As a proposal-free approach, instance segmentation through pixel embedding learning and clustering is gaining more emphasis. Compared with bounding box refinement approaches, such as Mask R-CNN, it has potential advantages in handling complex shapes and dense objects. In this work, we propose a simple, yet highly effective, architecture for object-aware embedding learning. A distance regression module is incorporated into our architecture to generate seeds for fast clustering. At the same time, we show that the features learned by the distance regression module are able to promote the accuracy of learned object-aware embeddings significantly. By simply concatenating features of the distance regression module to the images as inputs of the embedding module, the mSBD scores on the CVPPP Leaf Segmentation Challenge can be further improved by more than 8% compared to the identical set-up without concatenation, yielding the best overall result amongst the leaderboard at CodaLab. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2007_06660 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation Wu, Yuli Chen, Long Merhof, Dorit Computer Vision and Pattern Recognition As a proposal-free approach, instance segmentation through pixel embedding learning and clustering is gaining more emphasis. Compared with bounding box refinement approaches, such as Mask R-CNN, it has potential advantages in handling complex shapes and dense objects. In this work, we propose a simple, yet highly effective, architecture for object-aware embedding learning. A distance regression module is incorporated into our architecture to generate seeds for fast clustering. At the same time, we show that the features learned by the distance regression module are able to promote the accuracy of learned object-aware embeddings significantly. By simply concatenating features of the distance regression module to the images as inputs of the embedding module, the mSBD scores on the CVPPP Leaf Segmentation Challenge can be further improved by more than 8% compared to the identical set-up without concatenation, yielding the best overall result amongst the leaderboard at CodaLab. |
| title | Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2007.06660 |