Title | ||
---|---|---|
Segmenting Neuronal Structure in 3D Optical Microscope Images via Knowledge Distillation with Teacher-Student Network |
Abstract | ||
---|---|---|
Three-dimensional (3D) volumetric neural image segmentation is crucial to reconstructing accurate neuron structures. However, due to the structural complexity of neurons and the diverse imaging qualities of the microscopes, it is challenging to achieve both accuracy and efficiency. In this paper, we propose a teacher-student learning framework for fast neuron segmentation. The segmentation inference is performed using a light-weighted student network which benefits from knowledge distillation of a teacher network with a higher capacity. Evaluated on the Janelia dataset from the BigNeuron project, our proposed framework achieves competitive performance for segmentation accuracy while reducing the computational cost to facilitate large-scale processing. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ISBI.2019.8759326 | 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) |
Keywords | Field | DocType |
Teacher-student Network,Knowledge Distillation,Neuronal Image Segmentation,BigNeuron | Computer vision,Market segmentation,Optical microscope,Pattern recognition,Segmentation,Inference,Computer science,Image segmentation,Distillation,Microscope,Artificial intelligence | Conference |
ISSN | ISBN | Citations |
1945-7928 | 978-1-5386-3642-8 | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Heng Wang | 1 | 71 | 4.89 |
Donghao Zhang | 2 | 36 | 8.73 |
Yang Song | 3 | 379 | 53.25 |
Siqi Liu | 4 | 108 | 15.57 |
Yue Wang | 5 | 97 | 10.65 |
David Dagan Feng | 6 | 3329 | 413.76 |
Hanchuan Peng | 7 | 3930 | 182.27 |
Weidong Cai | 8 | 938 | 86.65 |