Feature distillation with mixup for unsupervised continual learning

Yiyan Gao

doi:10.1117/12.3005825

10 October 2023 Feature distillation with mixup for unsupervised continual learning

Yiyan Gao

Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 1279925 (2023) https://doi.org/10.1117/12.3005825
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia

Abstract

We learn feature representations on unlabeled task sequences. In order to make the disparity between unsupervised representational learning and continuous learning narrow, interpolate examples of current and previous tasks to build new examples. On this basis, we suggest a innovative knowledge extraction method which takes into account feature location and distance function of the extraction. We use the position before ReLU as the distillation point and design a new margin ReLU function. This allows for the centralization of useful information in the middle of the network and further performance improvement, minimizing the forgetting of past activities while increasing learning of new ones.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yiyan Gao "Feature distillation with mixup for unsupervised continual learning", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 1279925 (10 October 2023); https://doi.org/10.1117/12.3005825

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