| Home | << 1 >> |
|
| Record | Links | |||||
|---|---|---|---|---|---|---|
Author  |
Alex Gomez-Villa; Bartlomiej Twardowski; Lu Yu; Andrew Bagdanov; Joost Van de Weijer |
 
 |
||||
| Title | Continually Learning Self-Supervised Representations With Projected Functional Regularization | Type | Conference Article | |||
| Year | 2022 | Publication | CVPR 2022 Workshop on Continual Learning (CLVision, 3rd Edition) | Abbreviated Journal | ||
| Volume | Issue | Pages | 3866-3876 | |||
| Keywords | Computer vision; Conferences; Self-supervised learning; Image representation; Pattern recognition | |||||
| Abstract | Recent self-supervised learning methods are able to learn high-quality image representations and are closing the gap with supervised approaches. However, these methods are unable to acquire new knowledge incrementally – they are, in fact, mostly used only as a pre-training phase over IID data. In this work we investigate self-supervised methods in continual learning regimes without any replay
mechanism. We show that naive functional regularization,also known as feature distillation, leads to lower plasticity and limits continual learning performance. Instead, we propose Projected Functional Regularization in which a separate temporal projection network ensures that the newly learned feature space preserves information of the previous one, while at the same time allowing for the learning of new features. This prevents forgetting while maintaining the plasticity of the learner. Comparison with other incremental learning approaches applied to self-supervision demonstrates that our method obtains competitive performance in different scenarios and on multiple datasets. |
|||||
| Address | New Orleans, USA; 20 June 2022 | |||||
| Corporate Author | Thesis | |||||
| Publisher | Place of Publication | Editor | ||||
| Language | Summary Language | Original Title | ||||
| Series Editor | Series Title | Abbreviated Series Title | ||||
| Series Volume | Series Issue | Edition | ||||
| ISSN | ISBN | Medium | ||||
| Area | Expedition | Conference | CVPRW | |||
| Notes | LAMP: 600.147; 600.120;CIC | Approved | no | |||
| Call Number | Admin @ si @ GTY2022 | Serial | 3704 | |||
| Permanent link to this record | ||||||