English

Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning

Machine Learning 2019-06-26 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large number of network variants, such public-available trained models are often of different architectures, each of which being tailored for a specific task or dataset. In this paper, we study a deep-model reusing task, where we are given as input pre-trained networks of heterogeneous architectures specializing in distinct tasks, as teacher models. We aim to learn a multitalented and light-weight student model that is able to grasp the integrated knowledge from all such heterogeneous-structure teachers, again without accessing any human annotation. To this end, we propose a common feature learning scheme, in which the features of all teachers are transformed into a common space and the student is enforced to imitate them all so as to amalgamate the intact knowledge. We test the proposed approach on a list of benchmarks and demonstrate that the learned student is able to achieve very promising performance, superior to those of the teachers in their specialized tasks.

Keywords

Cite

@article{arxiv.1906.10546,
  title  = {Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning},
  author = {Sihui Luo and Xinchao Wang and Gongfan Fang and Yao Hu and Dapeng Tao and Mingli Song},
  journal= {arXiv preprint arXiv:1906.10546},
  year   = {2019}
}

Comments

IJCAI 2019, 7 pages, the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019)

R2 v1 2026-06-23T10:03:07.317Z