U-Net: Convolutional Networks for Biomedical Image Segmentation
Olaf Ronneberger, Philipp Fischer, Thomas Brox
Summary
The paper introduces U-Net, an encoder-decoder convolutional network with a contracting path to capture context and a symmetric expanding path with skip connections for precise localization. Combined with heavy data augmentation, the architecture trains end-to-end from very few annotated images. It won the ISBI cell-tracking and neuronal-structure segmentation challenges and segments a 512x512 image in under a second on a GPU.
Key findings
- Symmetric encoder-decoder design with skip connections enables precise pixel-level segmentation.
- Aggressive data augmentation lets the network train effectively from very small annotated datasets.
- Won the 2015 ISBI cell tracking challenge and the ISBI neuronal structure segmentation challenge by a large margin, with fast inference (<1s per 512x512 image).
Subjects & keywords
Cite this paper
Olaf Ronneberger, Philipp Fischer, & Thomas Brox (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), LNCS vol. 9351, pp. 234-241. https://doi.org/10.1007/978-3-319-24574-4_28
@inproceedings{ronneberger2015unet,
author = {Olaf Ronneberger and Philipp Fischer and Thomas Brox},
title = {U-Net: Convolutional Networks for Biomedical Image Segmentation},
booktitle = {Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), LNCS vol. 9351, pp. 234-241},
year = {2015},
doi = {10.1007/978-3-319-24574-4_28},
url = {https://doi.org/10.1007/978-3-319-24574-4_28}
}