Name
Abstract | ||
|---|---|---|
•A novel DBI-GAN model is designed to generate high quality augment samples for knowledge distillation.•A new knowledge distillation scheme is proposed based on the DBI-GAN.•A new loss function is proposed for the student network optimization based on the train-set consisting of original samples and the synthesized DBIs.•Our scheme achieves better performance compared with some state-of-the-art methods on benchmark datasets. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1016/j.neucom.2021.10.097 | Neurocomputing |
Keywords | DocType | Volume |
Knowledge distillation,Decision boundary instance,Generative adversarial network | Journal | 487 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 5 | |