Mitigating the challenges of distribution shift under strong computational constraints
This thesis explores the use of unsupervised methods to address the challenges of distribution shift under strong computational constraints in deep learning vision tasks. Through a series of contributions, it demonstrates the effectiveness of unsupervised learning in enabling efficient and adaptable...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2024
|
| Subjects: |