A Semisupervised Learning Scheme with Self-Paced Learning for Classifying Breast Cancer Histopathological Images

Algorithm 1

Self-paced learning workflow.

	input: Deep Learning Network , unlabeled Images , amount
output: Trained Classifier (C)
Train a deep network with labeled samples
fortodo
Test and predict on unlabeled samples ;
Generate pseudolabels for using predictions;
Select pseudolabeled samples after filtering out balancing class-wise scores
Augment labeled training set with selected pseudolabeled samples
Retrain with and pseudolabeled samples
end
;
Return