Corpus ID: 53841545

Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks

@article{Linsley2018RobustNC,
  title={Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks},
  author={Drew Linsley and J. Kim and D. Berson and Thomas Serre},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.11356}
}
Recent successes in deep learning have started to impact neuroscience. Of particular significance are claims that current segmentation algorithms achieve "super-human" accuracy in an area known as connectomics. However, as we will show, these algorithms do not effectively generalize beyond the particular source and brain tissues used for training -- severely limiting their usability by the broader neuroscience community. To fill this gap, we describe a novel connectomics challenge for source… Expand
6 Citations
Segmentation-Enhanced CycleGAN
  • 15
  • PDF
Recurrent neural circuits for contour detection
  • 7
  • PDF
Beyond the feedforward sweep: feedback computations in the visual cortex
  • G. Kreiman, T. Serre
  • Computer Science, Medicine
  • Annals of the New York Academy of Sciences
  • 2020
  • 13
  • PDF
Stable and expressive recurrent vision models
  • 6
  • PDF

References

SHOWING 1-10 OF 81 REFERENCES
High-precision automated reconstruction of neurons with flood-filling networks
  • 138
  • Highly Influential
  • PDF
Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection
  • 41
  • PDF
Task-Driven Convolutional Recurrent Models of the Visual System
  • 83
  • PDF
A visual motion detection circuit suggested by Drosophila connectomics
  • 547
  • PDF
Squeeze-and-Excitation Networks
  • 3,872
  • PDF
...
1
2
3
4
5
...