Combining neural-collapse feature alignment with classifier weight balancing improves closed-set and open-set accuracy for long-tailed medical image classification under semi-supervised learning.
The input images, denoted byY ∈ RH×W×D , are processed to form labelled batchI C and unlabelled batchI U
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets
Combining neural-collapse feature alignment with classifier weight balancing improves closed-set and open-set accuracy for long-tailed medical image classification under semi-supervised learning.