clm_c176c5f6To 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.
arXiv 1505.04597 · cs.CV
Read on arXiv · arXiv non-exclusive license
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.
clm_c176c5f6To 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.
res_c7f54835For 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)
clm_9eec9d71We demonstrate the application of the u-net to three different segmentation tasks.
res_3dd15c8bThe 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)
res_151d1ac4In terms of rand error the only better performing T able 1.
res_9590f053Here we achieve an average IOU (“intersection over union”) of 92%, which is significantly better than the second best algorithm with 83% (see Table 2).
res_5076b34eHere we achieve an average IOU of 77.5% which is significantly better than the second best algorithm with 46%.
res_9e31fd36Thanks to data augmentation with elastic defor- 1 The authors of this algorithm have submitted 78 different solutions to achieve this result.
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.