Scene understanding for unmanned vehicle using deep learning
In this dissertation, I learned some mainstream deep learning algorithms for scene understanding in the world. By comparing the performance of these algorithms on the PLACE365 dataset, finally proposed a method to use the Transformer layer as a pooling layer, and applied it to some mainstream deep l...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/155393 |
| _version_ | 1826129425904697344 |
|---|---|
| author | Lu, Yizhou |
| author2 | Wang Dan Wei |
| author_facet | Wang Dan Wei Lu, Yizhou |
| author_sort | Lu, Yizhou |
| collection | NTU |
| description | In this dissertation, I learned some mainstream deep learning algorithms for scene understanding in the world. By comparing the performance of these algorithms on the PLACE365 dataset, finally proposed a method to use the Transformer layer as a pooling layer, and applied it to some mainstream deep learning networks for testing. By applying this method to the more classic neural network models such as Resnet18, Alexnet and VGG16, experiments on different datasets have shown that this method has a greater improvement in the accuracy of the model. |
| first_indexed | 2024-10-01T07:40:24Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/155393 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:40:24Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1553932023-07-04T17:09:06Z Scene understanding for unmanned vehicle using deep learning Lu, Yizhou Wang Dan Wei School of Electrical and Electronic Engineering EDWWANG@ntu.edu.sg Engineering::Electrical and electronic engineering In this dissertation, I learned some mainstream deep learning algorithms for scene understanding in the world. By comparing the performance of these algorithms on the PLACE365 dataset, finally proposed a method to use the Transformer layer as a pooling layer, and applied it to some mainstream deep learning networks for testing. By applying this method to the more classic neural network models such as Resnet18, Alexnet and VGG16, experiments on different datasets have shown that this method has a greater improvement in the accuracy of the model. Master of Science (Computer Control and Automation) 2022-02-22T00:27:17Z 2022-02-22T00:27:17Z 2021 Thesis-Master by Coursework Lu, Y. (2021). Scene understanding for unmanned vehicle using deep learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/155393 https://hdl.handle.net/10356/155393 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Lu, Yizhou Scene understanding for unmanned vehicle using deep learning |
| title | Scene understanding for unmanned vehicle using deep learning |
| title_full | Scene understanding for unmanned vehicle using deep learning |
| title_fullStr | Scene understanding for unmanned vehicle using deep learning |
| title_full_unstemmed | Scene understanding for unmanned vehicle using deep learning |
| title_short | Scene understanding for unmanned vehicle using deep learning |
| title_sort | scene understanding for unmanned vehicle using deep learning |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/155393 |
| work_keys_str_mv | AT luyizhou sceneunderstandingforunmannedvehicleusingdeeplearning |