发帖
雷达卡
Unsupervised Part Representation by Flow Capsules
Sara Sabour 1 2 Andrea Tagliasacchi 1 2 Soroosh Yazdani 1 Geoffrey E. Hinton 1 2 David J. Fleet 1 2
Abstract
Capsule networks aim to parse images into a hi-
erarchy of objects, parts and relations. While
promising, they remain limited by an inability to
learn effective low level part descriptions. To ad-
dress this issue we propose a way to learn primary
capsule encoders that detect atomic parts from a
...
京公网安备 11010802022788号
