The hidden label-marginal biases of segmentation losses

by   Bingyuan Liu, et al.

Most segmentation losses are arguably variants of the Cross-Entropy (CE) or Dice loss. In the literature, there is no clear consensus as to which of these losses is a better choice, with varying performances for each across different benchmarks and applications. We develop a theoretical analysis that links these two types of losses, exposing their advantages and weaknesses. First, we explicitly demonstrate that CE and Dice share a much deeper connection than previously thought: CE is an upper bound on both logarithmic and linear Dice losses. Furthermore, we provide an information-theoretic analysis, which highlights hidden label-marginal biases : Dice has an intrinsic bias towards imbalanced solutions, whereas CE implicitly encourages the ground-truth region proportions. Our theoretical results explain the wide experimental evidence in the medical-imaging literature, whereby Dice losses bring improvements for imbalanced segmentation. It also explains why CE dominates natural-image problems with diverse class proportions, in which case Dice might have difficulty adapting to different label-marginal distributions. Based on our theoretical analysis, we propose a principled and simple solution, which enables to control explicitly the label-marginal bias. Our loss integrates CE with explicit L_1 regularization, which encourages label marginals to match target class proportions, thereby mitigating class imbalance but without losing generality. Comprehensive experiments and ablation studies over different losses and applications validate our theoretical analysis, as well as the effectiveness of our explicit label-marginal regularizers.


page 2

page 8


On the dice loss gradient and the ways to mimic it

In the past few years, in the context of fully-supervised semantic segme...

Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index

In many medical imaging and classical computer vision tasks, the Dice sc...

Marginal Thresholding in Noisy Image Segmentation

This work presents a study on label noise in medical image segmentation ...

Marginal loss and exclusion loss for partially supervised multi-organ segmentation

Annotating multiple organs in medical images is both costly and time-con...

RankSEG: A Consistent Ranking-based Framework for Segmentation

Segmentation has emerged as a fundamental field of computer vision and n...

Please sign up or login with your details

Forgot password? Click here to reset