Refine
Document Type
- conference proceeding (presentation, abstract) (11) (remove)
Has Fulltext
- no (11)
Is part of the Bibliography
- no (11)
Keywords
- Deep Learning (3)
- Künstliche Intelligenz (2)
- Artificial Intelligence (1)
- Celiac Disease (1)
- Endoscopy (1)
- Eosinophilic Esophagitis (1)
- Speiseröhrenkrankheit (1)
- Surgical instrument segmentation (1)
- robot-assisted surgery (1)
- smoke simulation (1)
Institute
- Regensburg Medical Image Computing (ReMIC) (11) (remove)
Begutachtungsstatus
- peer-reviewed (9)
Pixel-level classification is an essential part of computer vision. For learning from labeled data, many powerful deep learning models have been developed recently. In this work, we augment such supervised segmentation models by allowing them to learn from unlabeled data. Our semi-supervised approach, termed Error-Correcting Supervision, leverages a collaborative strategy. Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network.