Continual Learning Method for image classification in computer vision
| dc.contributor.advisor | Yushchenko, Yurii | |
| dc.contributor.author | Kreshchenko, Taras | |
| dc.date.accessioned | 2024-11-11T14:10:46Z | |
| dc.date.available | 2024-11-11T14:10:46Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | The paper explores the hypothesis that Continual Learning (CL) methods can improve the performance of a deep learning model in a traditional machine learning scenario. By augmenting an existing state-of-the-art ML solution to a problem with CL techniques, this research aims to demonstrate that AI can still achieve more accurate and adaptive performance. This hypothesis is tested on a parking lot occupancy detection problem, a binary classification problem that is well-suited to CL due to the continuous stream of image data. Experiments are conducted to compare the proposed CL-based solution and a contemporary solution that is non-CL based. | en_US |
| dc.identifier.uri | https://ekmair.ukma.edu.ua/handle/123456789/32312 | |
| dc.language.iso | en | en_US |
| dc.relation.organisation | НаУКМА | en_US |
| dc.status | first published | en_US |
| dc.subject | deep learning | en_US |
| dc.subject | continual learning | en_US |
| dc.subject | incremental learning | en_US |
| dc.subject | lifelong learning | en_US |
| dc.subject | domain adaptation | en_US |
| dc.subject | contrastive learning | en_US |
| dc.subject | CNN | en_US |
| dc.subject | computer vision | en_US |
| dc.subject | binary classification | en_US |
| dc.subject | parking | en_US |
| dc.subject | occupancy detection | en_US |
| dc.subject | мasters thesis | en_US |
| dc.title | Continual Learning Method for image classification in computer vision | en_US |
| dc.type | Other | en_US |
Files
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: