Self-supervised learning is a promising unsupervised learning framework that has achieved success with large floating point networks. But such networks are not readily deployable to edge devices. To accelerate deployment of models with the benefit of unsupervised representation learning to such resource limited devices for various downstream tasks, we propose a self-supervised learning method for binary networks that uses a moving target network. In particular, we propose to Jointly train a randomly initialized classifier, attached to a pretrained floating point feature extractor, with a binary network. Additionally, we propose a feature similarity loss, a dynamic loss balancing and modified multi-stage training to further improve the accuracy, and call our method BURN. Our empirical validations over five downstream tasks using seven datasets show that BURN outperforms self-supervised baselines for binary networks and sometimes outperforms supervised pretraining. Code is availabe at https://github.com/naver-ai/burn.
|Title of host publication||Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022|
|Publisher||IEEE Computer Society|
|Number of pages||10|
|Publication status||Published - 2022|
|Event||2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States|
Duration: 2022 Jun 19 → 2022 Jun 24
|Name||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Conference||2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022|
|Period||22/6/19 → 22/6/24|
Bibliographical noteFunding Information:
Acknowledgement. The authors thank Jung-Woo Ha for the valuable discussions. This work was partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No.2022R1A2C4002300) and Institute for Information & communications Technology Promotion (IITP) grants funded by the Korea government (MSIT) (No.2020-0-01361-003 and 2019-0-01842, Artificial Intelligence Graduate School Program (Yonsei University, GIST), and No.2021-0-02068 Artificial Intelligence Innovation Hub).
© 2022 IEEE.
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition