Hyperspherically regularized networks for self-supervision
Bootstrap Your Own Latent (BYOL) introduced an approach to self-supervised learning avoiding the contrastive paradigm and subsequently removing the computational burden of negative sampling associated with such methods. However, we empirically find that the image representations produced under the B...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier Ltd
2022
|
| Subjects: | |
| Online Access: | View Fulltext in Publisher |