Object Detection and Semantic Segmentation Using Self-Supervised Learning
In this thesis, three well known self-supervised methods have been implemented and trained on road scene images. The three so called pretext tasks RotNet, MoCov2, and DeepCluster were used to train a neural network self-supervised. The self-supervised trained networks where then evaluated on differe...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
Linköpings universitet, Datorseende
2021
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-180815 |