상세정보
학술지
Multiple Flow-based Knowledge Transfer via Adversarial Networks
- 발행일
- 201909
- 출처
- Electronics Letters, v.55 no.18, pp.989-992
- ISSN
- 0013-5194
- 출판사
- IET
- 초록
- The authors propose a new knowledge transfer method coupled with a generative adversarial network (GAN) when multiple-flow-based knowledge is considered in a teacher?뱒tudent framework using a residual network (ResNet). In this method, several independent discriminators adapting multilayer-perceptron-based structures were designed for flow-based knowledge transfer. The proposed GAN-based optimisation alternatively updates the multiple discriminators and a student ResNet such that the flow-based features of the student ResNet are generated as closely as possible to the real features of a teacher ResNet. The experiments demonstrate that the student ResNet trained using the proposed method more accurately captures the distribution of the flow-based teacher knowledge than the l2-distance-based training method. In addition, the proposed method provided better classification accuracy than the existing GAN-based knowledge transfer method.
- KSP 제안 키워드
- Coupled with, Distance-based, Flow-based, GaN-Based, Knowledge transfer, Residual Network, Transfer method, classification accuracy, generative adversarial network, training method