Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917391912402944 |
|---|---|
| author | Mano, Takahiro Saito, Reiji Hotta, Kazuhiro |
| author_facet | Mano, Takahiro Saito, Reiji Hotta, Kazuhiro |
| contents | In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to enhance the performance, has gained attention. A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images. However, since ClassMix performs operations using pseudo-labels obtained from unlabeled images, there is a risk of handling inaccurate labels. Additionally, there is a gap in data quality between labeled and unlabeled images, which can impact the feature maps. This study addresses these two issues. First, we propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images. Second, we introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images. Experiments on the Chase and COVID-19 datasets demonstrated an average improvement of 2.07% in mIoU compared to conventional semi-supervised learning methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07122 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator Mano, Takahiro Saito, Reiji Hotta, Kazuhiro Computer Vision and Pattern Recognition Machine Learning In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to enhance the performance, has gained attention. A conventional semi-supervised learning method, ClassMix, pastes class labels predicted from unlabeled images onto other images. However, since ClassMix performs operations using pseudo-labels obtained from unlabeled images, there is a risk of handling inaccurate labels. Additionally, there is a gap in data quality between labeled and unlabeled images, which can impact the feature maps. This study addresses these two issues. First, we propose a method where class labels from labeled images, along with the corresponding image regions, are pasted onto unlabeled images and their pseudo-labeled images. Second, we introduce a method that trains the model to make predictions on unlabeled images more similar to those on labeled images. Experiments on the Chase and COVID-19 datasets demonstrated an average improvement of 2.07% in mIoU compared to conventional semi-supervised learning methods. |
| title | Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.07122 |