MearcAll papers

arXiv 1505.04597 · cs.CV

U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger, Philipp Fischer, Thomas Brox

Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.

No reproduction recordedclm_c176c5f6
To this end, we propose the use of a weighted loss, where the separating background labels between touching cells obtain a large weight in the loss function.

Introduction · page 3 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_c7f54835
For a network with our architecture (alternating convolution and ReLU layers) this can be achieved by drawing the initial weights from a Gaussian distribution with a standard deviation of √ … (excerpt)

Training · page 5 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_9eec9d71
We demonstrate the application of the u-net to three different segmentation tasks.

Experiments · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_3dd15c8b
The u-net (averaged over 7 rotated versions of the input data) achieves without any further pre- or postprocessing a warping error of 0.0003529 (the new best score, see Table 1) … (excerpt)

Experiments · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_151d1ac4
In terms of rand error the only better performing T able 1.

Experiments · page 6 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_9590f053
Here we achieve an average IOU (“intersection over union”) of 92%, which is significantly better than the second best algorithm with 83% (see Table 2).

Experiments · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_5076b34e
Here we achieve an average IOU of 77.5% which is significantly better than the second best algorithm with 46%.

Experiments · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_9e31fd36
Thanks to data augmentation with elastic defor- 1 The authors of this algorithm have submitted 78 different solutions to achieve this result.

Conclusion · page 7 · Automated extraction, not reviewed · 0 reviewed reproductions

Reproduced one of these claims?

Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1505.04597) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.