Fully Convolutional Networks for Automatically Generating Image Masks to Train Mask R-CNN

no code implementations • 3 Mar 2020 • Hao Wu, Jan Paul Siebert, Xiangrong Xu

This paper proposes a novel automatically generating image masks method for the state-of-the-art Mask R-CNN deep learning method.

Object object-detection +2

Efficient Egocentric Visual Perception Combining Eye-tracking, a Software Retina and Deep Learning

no code implementations • 5 Sep 2018 • Nina Hristozova, Piotr Ozimek, Jan Paul Siebert

We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space-variant imaging architecture of the mammalian retina with Deep Learning methods.

General Classification