Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets
Authors:
- 6 October 2024
- book chapter
- Published by Springer Nature
- p. 145-154
Abstract
No abstract availableKeywords
All Related Versions
This publication has 11 references indexed in Scilit:
- SelfMix: A Self-adaptive Data Augmentation Method for Lesion Segmentation2022
- Detecting Outliers with Poisson Image Interpolation2021
- CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation2021
- ComplexMix: Semi-Supervised Semantic Segmentation Via Mask-Based Data Augmentation2021
- AbdomenCT-1K: Is Abdominal Organ Segmentation a Solved Problem?IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation2021
- ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Image Inpainting for Irregular Holes Using Partial Convolutions2018