DeepAI
Log In Sign Up

Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations

04/12/2021
by   Mobarakol Islam, et al.
4

The task of image segmentation is inherently noisy due to ambiguities regarding the exact location of boundaries between anatomical structures. We argue that this information can be extracted from the expert annotations at no extra cost, and when integrated into state-of-the-art neural networks, it can lead to improved calibration between soft probabilistic predictions and the underlying uncertainty. We built upon label smoothing (LS) where a network is trained on 'blurred' versions of the ground truth labels which has been shown to be effective for calibrating output predictions. However, LS is not taking the local structure into account and results in overly smoothed predictions with low confidence even for non-ambiguous regions. Here, we propose Spatially Varying Label Smoothing (SVLS), a soft labeling technique that captures the structural uncertainty in semantic segmentation. SVLS also naturally lends itself to incorporate inter-rater uncertainty when multiple labelmaps are available. The proposed approach is extensively validated on four clinical segmentation tasks with different imaging modalities, number of classes and single and multi-rater expert annotations. The results demonstrate that SVLS, despite its simplicity, obtains superior boundary prediction with improved uncertainty and model calibration.

READ FULL TEXT

page 3

page 6

page 8

page 10

06/06/2019

When Does Label Smoothing Help?

The generalization and learning speed of a multi-class neural network ca...
10/31/2021

Incorporating Boundary Uncertainty into loss functions for biomedical image segmentation

Manual segmentation is used as the gold-standard for evaluating neural n...
02/15/2022

Label fusion and training methods for reliable representation of inter-rater uncertainty

Medical tasks are prone to inter-rater variability due to multiple facto...
06/24/2020

Class-Similarity Based Label Smoothing for Generalized Confidence Calibration

Since modern neural networks are known to be overconfident, several tech...
07/23/2018

Clearing noisy annotations for computed tomography imaging

One of the problems on the way to successful implementation of neural ne...
12/12/2020

Normalized Label Distribution: Towards Learning Calibrated, Adaptable and Efficient Activation Maps

The vulnerability of models to data aberrations and adversarial attacks ...
12/14/2022

Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Expert

Equipping predicted segmentation with calibrated uncertainty is essentia...