End-to-End Instance Segmentation and Counting with Recurrent Attention End-to-End Instance Segmentation and Counting with Recurrent Attention
Paper summary This combines the ideas of recurrent attention to perform object detection in an image \cite{1406.6247} for multiple objects \cite{1412.7755} with semantic segmentation \cite{1505.04366}. Segmenting subregions is to avoid a global resolution bias (the object would take up the majority of pixels) and to allow multiple scales of objects to be segmented. Here is a video that demos the method described in the paper: https://youtu.be/BMVDhTjEfBU
arxiv.org
arxiv-sanity.com
scholar.google.com
End-to-End Instance Segmentation and Counting with Recurrent Attention
Mengye Ren and Richard S. Zemel
arXiv e-Print archive - 2016 via arXiv
Keywords: cs.LG, cs.CV

more

Loading...
Your comment:


Short Science allows researchers to publish paper summaries that are voted on and ranked!
About