A new self-supervised method for supervised learning

Yuhang Yang; Zilin Ding; Xuan Cheng; Xiaomin Wang; Ming Liu

doi:10.1117/12.2626541

20 December 2021 A new self-supervised method for supervised learning

Yuhang Yang, Zilin Ding, Xuan Cheng, Xiaomin Wang, Ming Liu

Proceedings Volume 12155, International Conference on Computer Vision, Application, and Design (CVAD 2021); 121550E (2021) https://doi.org/10.1117/12.2626541
Event: International Conference on Computer Vision, Application, and Design (CVAD 2021), 2021, Sanya, China

Abstract

In traditional self-supervised visual feature learning, convolutional neural networks (ConvNets) trained by a proposed pretext task with only unlabeled data encode high-level semantic visual representations for downstream tasks of interest. The proposed pretext tasks are mostly based on images or videos. In this work, starting from the feature layers, we propose a completely new pretext task formulated within ConvNets, and use it to enhance the supervised learning of fully labeled datasets. We discard the channels on feature maps after particular convolutional layers to generate self-supervised labels, and combine them with the original labels for classification. Our objective is to mine richer feature information by making ConvNets understand which channels are missing at the same time of classification. Experiments show that our improvement is effective across multiple models and datasets.

Citation Download Citation

Yuhang Yang, Zilin Ding, Xuan Cheng, Xiaomin Wang, and Ming Liu "A new self-supervised method for supervised learning", Proc. SPIE 12155, International Conference on Computer Vision, Application, and Design (CVAD 2021), 121550E (20 December 2021); https://doi.org/10.1117/12.2626541

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
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Machine learning

Visualization

Mining

Data modeling

Gallium nitride

Image classification

Video

Show All Keywords

Keywords/Phrases

Search In:

Publication Years