Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

U-Net: Convolutional Networks for Biomedical Image Segmentation

About

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

Olaf Ronneberger, Philipp Fischer, Thomas Brox• 2015

Related benchmarks

TaskDatasetResultRank
Image ClassificationMNIST (test)
Accuracy96.3
894
Image Super-resolutionSet5
PSNR32.09
774
Image ClassificationFashion MNIST (test)
Accuracy86.2
633
Image ClassificationCIFAR10 (test)
Accuracy52.3
585
Semantic segmentationCityscapes (val)
mIoU49.3
572
Semantic segmentationCityscapes
mIoU67.3
494
Image Super-resolutionUrban100
PSNR25.97
424
Semantic segmentationCamVid (test)
mIoU55.2
411
Anomaly DetectionMVTec-AD (test)
I-AUROC81.9
348
Image DeblurringRealBlur-J (test)
PSNR28.03
259
Showing 10 of 1591 rows
...

Other info

Code

Follow for update