Browsing by Author "Jeong, Won-Ki"
Now showing items 1-5 of 5
-
ColorRL: Reinforced Coloring for End-to-End Instance Segmentation
(2021)Instance segmentation, the task of identifying and separating each individual object of interest in the image, is one of the actively studied research topics in computer vision. Although many feed-forward networks produce ... -
FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics
(2021-05-13)Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput, nano-scale electron microscopy. One of the main challenges in ... -
FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics
(2021-05-13)Cellular-resolution connectomics is an ambitious research direction with the goal of generating comprehensive brain connectivity maps using high-throughput, nano-scale electron microscopy. One of the main challenges in ... -
Reinforced coloring for end-to-end instance segmentation
(2020-05-19)Instance segmentation is one of the actively studied research topics in computer vision in which many objects of interest should be separated individually. While many feed-forward networks produce high-quality segmentation ... -
ZeVis: A Visual Analytics System for Exploration of a Larval Zebrafish Brain in Serial-Section Electron Microscopy Images
(2021-05-26)The automation and improvement of nano-scale electron microscopy imaging technologies have expanded a push in neuroscience to understand brain circuits at the scale of individual cells and their connections. Most of this ...
