Variance of Gradients effectively flags erroneous ground truth labels during echocardiography segmentation training, and refurbishing them with pseudo-labeling boosts performance especially under high error rates on the CAMUS dataset.
Be- yond class-conditional assumption: A primary attempt to combat instance-dependent label noise
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Detecting and refurbishing ground truth errors during training of deep learning-based echocardiography segmentation models
Variance of Gradients effectively flags erroneous ground truth labels during echocardiography segmentation training, and refurbishing them with pseudo-labeling boosts performance especially under high error rates on the CAMUS dataset.