Hoel Kervadec, Jihene Bouchtiba, Christian Desrosiers, Eric Granger, Jose Dolz...
TL;DR基于轮廓空间的边界损失可弥补高度不平衡问题,结合标准区域损失,实现 N 维分割的深度网络架构,显著提高训练稳定性。
Abstract
Widely used loss functions for cnn segmentation, e.g., Dice or cross-entropy,
are based on integrals over the segmentation regions. Unfortunately, for highly
unbalanced segmentations, such regional summations have values that differ by
several orders of magnitude across classes, which