Consistency-Guided Meta-learning for Bootstrapping Semi-supervised Medical Image Segmentation
Medical imaging has witnessed remarkable progress but usually requires a large amount of
high-quality annotated data which is time-consuming and costly to obtain. To alleviate this …
high-quality annotated data which is time-consuming and costly to obtain. To alleviate this …
Prototype-based supervised contrastive learning method for noisy label correction in tire defect detection
Y Wang, Y Zhang, Z Jiang, L Zheng… - IEEE Sensors …, 2023 - ieeexplore.ieee.org
The defect detection of industrial products is an essential task in industrial production. In the
field of tire defect detection, X-ray imaging sensors are employed by tire factories to …
field of tire defect detection, X-ray imaging sensors are employed by tire factories to …
Combating medical label noise via robust semi-supervised contrastive learning
Deep learning-based AI diagnostic models rely heavily on high-quality exhaustive-
annotated data for algorithm training but suffer from noisy label information. To enhance the …
annotated data for algorithm training but suffer from noisy label information. To enhance the …
Meta-Learning for Bootstrapping Medical Image Segmentation from Imperfect Supervision
Medical imaging has witnessed remarkable progress but usually requires a large amount of
high-quality annotated data which is time-consuming and costly to obtain. To alleviate the …
high-quality annotated data which is time-consuming and costly to obtain. To alleviate the …
Biquality learning: from weakly supervised learning to distribution shifts
P Nodet - 2023 - theses.hal.science
The field of Learning with weak supervision is called Weakly Supervised Learning and
aggregates a variety of situations where the collected ground truth is imperfect. The …
aggregates a variety of situations where the collected ground truth is imperfect. The …