Consistent Recurrent Neural Networks For 3d Neuron Segmentation.

@article{Gonda2021ConsistentRN,
  title={Consistent Recurrent Neural Networks For 3d Neuron Segmentation.},
  author={Felix Gonda and D. Wei and H. Pfister},
  journal={2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
  year={2021},
  pages={1012-1016}
}
We present a recurrent network for 3D reconstruction of neurons that sequentially generates binary masks for every object in an image with spatio-temporal consistency. Our network models consistency in two parts: (i) local, which allows exploring non-occluding and temporally-adjacent object relationships with bi-directional recurrence. (ii) non-local, which allows exploring long-range object relationships in the temporal domain with skip connections. Our proposed network is end-to-end trainable… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 18 REFERENCES
RVOS: End-To-End Recurrent Network for Video Object Segmentation
A Deep Structured Learning Approach Towards Automating Connectome Reconstruction from 3D Electron Micrographs
Flood-Filling Networks
Crowdsourcing the creation of image segmentation algorithms for connectomics
Superhuman Accuracy on the SNEMI3D Connectomics Challenge
Saturated Reconstruction of a Volume of Neocortex
A Multi-Pass Approach to Large-Scale Connectomics
Deep Residual Learning for Image Recognition
...
1
2
...