6 papers with code • 1 benchmarks • 2 datasets
There is large consent that successful training of deep networks requires many thousand annotated training samples.
Ranked #1 on Medical Image Segmentation on ISBI 2012 EM Segmentation (Warping Error metric)
We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries.
Ranked #6 on Breast Tumour Classification on PCam
Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear.
Ranked #1 on Colorectal Gland Segmentation: on CRAG
This study is focused on histopathology image analysis applications for which it is desirable that the arbitrary global orientation information of the imaged tissues is not captured by the machine learning models.
Ranked #5 on Breast Tumour Classification on PCam
A multilevel random forest technique in a hierarchical way is proposed.