Select the model who knows the image best: a multi-model method

Yajie Sun; Ying Zhang; Haoqian Wang

doi:10.1117/12.2575325

10 October 2020 Select the model who knows the image best: a multi-model method

Yajie Sun, Ying Zhang, Haoqian Wang

Proceedings Volume 11550, Optoelectronic Imaging and Multimedia Technology VII; 115500O (2020) https://doi.org/10.1117/12.2575325
Event: SPIE/COS Photonics Asia, 2020, Online Only

Abstract

In the current popular visual tasks, one single model is usually used to output the final results. But no model is perfect, in this paper, we propose a simple and general multi-model method. To combine the advantages of multiple models, we design a familiarity prediction network to output the model's familiarity of images, then select the optimal model based on the familiarity value. Since the loss value is a single value, the familiarity value of any task can be reflected in the loss value, so the output of the familiarity prediction network can be regarded as an estimate of the loss value. The accuracy of the multi-model exceeds any single model that composes the multi-model. By limiting the number of feature layers input into the familiarity network, the sacrifice of computation and detection speed is acceptable. Our method is general and task-agnostic, it not only performs well on classification tasks but also on object detection tasks and other vision tasks.

Conference Presentation

Citation Download Citation

Yajie Sun, Ying Zhang, and Haoqian Wang "Select the model who knows the image best: a multi-model method", Proc. SPIE 11550, Optoelectronic Imaging and Multimedia Technology VII, 115500O (10 October 2020); https://doi.org/10.1117/12.2575325

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