BROWSE
Detail
Conference Paper
Deep Learning Model Generalization with Ensemble in Endoscopic Images
- Authors
- Ayoung Hong, Giwan Lee, Hyunseok Lee, Jihyun Seo, Doyeob Yeo
- Issue Date
- 2021-04
- Citation
- International Endoscopy Computer Vision Challenge and Workshop (EndoCV) 2021, pp.80-89
- Language
- English
- Type
- Conference Paper
- Abstract
- Owing to the rapid development of deep learning technologies in recent years, autonomous diagnostic systems are widely used to detect abnormal lesions such as polyps in endoscopic images. However, the image characteristics, such as the contrast and illuminance, vary significantly depending on the center from which the data was acquired; this affects the generalization performance of the diagnostic method. In this paper, we propose an ensemble learning method based on k-fold cross-validation to improve the generalization performance of polyp detection and polyp segmentation in endoscopic images. Weighted box fusion methods were used to ensemble the bounding boxes obtained from each detection model trained for data from each center. The segmentation results of the data center-specific model were averaged to generate the final ensemble mask. We used a Mask R-CNN-based model for both the detection and segmentation tasks. The proposed method achieved a score of 0.7269 on the detection task and 0.7423 ± 0.2839 on the segmentation task in Round 1 of the EndoCV2021 challenge.
- KSP Keywords
- Bounding Box, Cross validation(CV), Data center, Detection model, Detection task, Diagnostic method, Ensemble learning method, Fusion method, Generalization performance, K-fold cross validation, Learning Technology
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
