Improved model search based on distillation framework

Shunqiang Liu

doi:10.1117/12.2604789

5 October 2021 Improved model search based on distillation framework

Shunqiang Liu

Proceedings Volume 11911, 2nd International Conference on Computer Vision, Image, and Deep Learning; 119111U (2021) https://doi.org/10.1117/12.2604789
Event: 2nd International Conference on Computer Vision, Image and Deep Learning, 2021, Liuzhou, China

Abstract

The model search based on the distillation model framework aims to train the candidate models adequately and guide a correct evaluation of the architecture. This NAS method can easily obtain middle-level monitoring identification indicators, thus significantly improving the effect. However, the model search based on distillation framework also has its shortcomings. First, the supervision indicators differ greatly for various teacher-student models, so how to determine a highly adaptable supervision indicator is a very important issue. Second, different teacher models will introduce biases. Based on the above problems, this paper proposes the following measures. Firstly, this paper adopts a more adaptable supervision index, which can effectively solve the problem that various teacher-student models differ greatly. Secondly, in order to reduce the bias introduced by the teacher model, this paper adopts the largest teacher model as the guidance model in the network training. Finally, this study uses a reinforcement learning algorithm to guide the search in the internal network, and introduce more supervision quantity, which makes the supervision effect between layers more obvious. It can be concluded that the above methods can effectively improve the model performance and consistency.

Citation Download Citation

Shunqiang Liu "Improved model search based on distillation framework", Proc. SPIE 11911, 2nd International Conference on Computer Vision, Image, and Deep Learning, 119111U (5 October 2021); https://doi.org/10.1117/12.2604789

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Integrated modeling

Convolution

Network architectures

Data modeling

Neural networks

Lawrencium

Optimization (mathematics)

Show All Keywords

Keywords/Phrases

Search In:

Publication Years