STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains

04/23/2021
by   Fabian Gröger, et al.
14

We propose an unsupervised domain adaptation (UDA) approach for white matter hyperintensity (WMH) segmentation, which uses Self-Training with Uncertainty DEpendent Label refinement (STRUDEL). Self-training has recently been introduced as a highly effective method for UDA, which is based on self-generated pseudo labels. However, pseudo labels can be very noisy and therefore deteriorate model performance. We propose to predict the uncertainty of pseudo labels and integrate it in the training process with an uncertainty-guided loss function to highlight labels with high certainty. STRUDEL is further improved by incorporating the segmentation output of an existing method in the pseudo label generation that showed high robustness for WMH segmentation. In our experiments, we evaluate STRUDEL with a standard U-Net and a modified network with a higher receptive field. Our results on WMH segmentation across datasets demonstrate the significant improvement of STRUDEL with respect to standard self-training.

READ FULL TEXT

page 2

page 12

research
08/27/2020

Instance Adaptive Self-Training for Unsupervised Domain Adaptation

The divergence between labeled training data and unlabeled testing data ...
research
03/17/2023

Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding

Predicting attention regions of interest is an important yet challenging...
research
10/21/2021

RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation

Unsupervised Domain Adaptation (UDA) for point cloud classification is a...
research
12/09/2020

Two-phase Pseudo Label Densification for Self-training based Domain Adaptation

Recently, deep self-training approaches emerged as a powerful solution t...
research
10/29/2021

Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels

This paper focuses on camouflaged object detection (COD), which is a tas...
research
03/30/2023

Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels

Unsupervised word segmentation in audio utterances is challenging as, in...
research
10/08/2021

Field Extraction from Forms with Unlabeled Data

We propose a novel framework to conduct field extraction from forms with...

Please sign up or login with your details

Forgot password? Click here to reset