Method of Adaptive Knowledge Distillation from Multi-Teacher to Student Deep Learning Models
Journal of Edge Computing, Vol. 4, No. 2, pp. 159-178
Editorial summary
A compact cardiac MRI classifier learns from multiple teachers while adapting to differences between datasets. Teacher contributions vary for each input, and unlabelled images supplement training. Cross-domain experiments test whether these components help when labelled target data are scarce.
Bibliographic reference
Use the publisher’s record for the citation format required by your journal or organisation.
Oleksandr Chaban, Eduard Manziuk, Pavlo Radiuk. "Method of Adaptive Knowledge Distillation from Multi-Teacher to Student Deep Learning Models". Journal of Edge Computing, Vol. 4, No. 2, pp. 159-178, 2025. https://doi.org/10.55056/jec.978
Test a method against your business task.
Describe the decision your system needs to support and the data you have. We assess whether a method fits, define a prototype and agree how to measure its quality, response time and operating cost.