Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
This work addresses sample efficiency for semantic segmentation tasks, particularly in medical imaging like histopathology, but it is incremental as it extends existing group equivariant CNN frameworks.
The authors tackled the problem of sample efficiency in semantic segmentation by exploiting rotation and reflection symmetries, resulting in significant gains in sample efficiency and improved robustness to symmetry transformations, as demonstrated on cancer metastases detection in histopathology images.
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 well as improvements in robustness to symmetry transformations. The group equivariant CNN framework is extended for segmentation by introducing a new equivariant (G->Z2)-convolution that transforms feature maps on a group to planar feature maps. Also, equivariant transposed convolution is formulated for up-sampling in an encoder-decoder network. To demonstrate improvements in sample efficiency we evaluate on multiple data regimes of a rotation-equivariant segmentation task: cancer metastases detection in histopathology images. We further show the effectiveness of exploiting more symmetries by varying the size of the group.