The Impact of Semi-Supervised Learning on Line Segment Detection
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_ | 1866913573601542144 |
|---|---|
| author | Engman, Johanna Åström, Karl Oskarsson, Magnus |
| author_facet | Engman, Johanna Åström, Karl Oskarsson, Magnus |
| contents | In this paper we present a method for line segment detection in images, based on a semi-supervised framework. Leveraging the use of a consistency loss based on differently augmented and perturbed unlabeled images with a small amount of labeled data, we show comparable results to fully supervised methods. This opens up application scenarios where annotation is difficult or expensive, and for domain specific adaptation of models. We are specifically interested in real-time and online applications, and investigate small and efficient learning backbones. Our method is to our knowledge the first to target line detection using modern state-of-the-art methodologies for semi-supervised learning. We test the method on both standard benchmarks and domain specific scenarios for forestry applications, showing the tractability of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04596 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Impact of Semi-Supervised Learning on Line Segment Detection Engman, Johanna Åström, Karl Oskarsson, Magnus Computer Vision and Pattern Recognition Machine Learning In this paper we present a method for line segment detection in images, based on a semi-supervised framework. Leveraging the use of a consistency loss based on differently augmented and perturbed unlabeled images with a small amount of labeled data, we show comparable results to fully supervised methods. This opens up application scenarios where annotation is difficult or expensive, and for domain specific adaptation of models. We are specifically interested in real-time and online applications, and investigate small and efficient learning backbones. Our method is to our knowledge the first to target line detection using modern state-of-the-art methodologies for semi-supervised learning. We test the method on both standard benchmarks and domain specific scenarios for forestry applications, showing the tractability of the proposed method. |
| title | The Impact of Semi-Supervised Learning on Line Segment Detection |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2411.04596 |