3 papers
eess.IV2020
Classification of Diabetic Retinopathy Using Unlabeled Data and Knowledge Distillation
Sajjad Abbasi, Mohsen Hajabdollahi, Pejman Khadivi +4
Knowledge distillation allows transferring knowledge from a pre-trained model to another. However, it suffers from limitations, and constraints related to the two models need to be…
cs.CV2020
Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer
Sajjad Abbasi, Mohsen Hajabdollahi, Nader Karimi +2
Convolutional neural networks (CNNs) are extensively beneficial for medical image processing. Medical images are plentiful, but there is a lack of annotated data. Transfer learning…
cs.CV2019
Modeling Teacher-Student Techniques in Deep Neural Networks for Knowledge Distillation
Sajjad Abbasi, Mohsen Hajabdollahi, Nader Karimi +1
Knowledge distillation (KD) is a new method for transferring knowledge of a structure under training to another one. The typical application of KD is in the form of learning a smal…