Updating the VESICLE-CNN Synapse Detector
This provides a practical improvement for neuroscience researchers using electron microscopy data, though it is incremental as it updates an existing method.
The researchers tackled the slow test-time performance of the VESICLE-CNN synapse detector by updating it to a fully convolutional architecture with dilated convolutions, achieving a 600× speedup while maintaining original performance.
We present an updated version of the VESICLE-CNN algorithm presented by Roncal et al. (2014). The original implementation makes use of a patch-based approach. This methodology is known to be slow due to repeated computations. We update this implementation to be fully convolutional through the use of dilated convolutions, recovering the expanded field of view achieved through the use of strided maxpools, but without a degradation of spatial resolution. This updated implementation performs as well as the original implementation, but with a $600\times$ speedup at test time. We release source code and data into the public domain.