activity
20182024
most citedPutting An End to End-to-End: Gradient-Isolated Learning of Representations

79 citations · 331 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

2 papers · 1 filter

cs.CV2018★ 15 cited

Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks

Jasper Linmans, Jim Winkens, Bastiaan S. Veeling +2

We propose a semantic segmentation model that exploits rotation and reflection symmetries. We demonstrate significant gains in sample efficiency due to increased weight sharing, as…

cs.CV2018★ 2 cited

Rotation Equivariant CNNs for Digital Pathology

Bastiaan S. Veeling, Jasper Linmans, Jim Winkens +2

We propose a new model for digital pathology segmentation, based on the observation that histopathology images are inherently symmetric under rotation and reflection. Utilizing rec…