Unifying and Merging Well-trained Deep Neural Networks for Inference Stage

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the represent...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-05
Main Authors: Yi-Min, Chou, Yi-Ming, Chan, Jia-Hong, Lee, Chih-Yi Chiu, Chu-Song, Chen
Format: Article
Language:English
Subjects:
Inference
Neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights. The shared weights are further re-trained to fine-tune the performance of the merged model. The proposed method effectively produces a compact model that may run original tasks simultaneously on resource-limited devices. As it preserves the general architectures and leverages the co-used weights of well-trained networks, a substantial training overhead can be reduced to shorten the system development time. Experimental results demonstrate a satisfactory performance and validate the effectiveness of the method.
ISSN:2331-8422