Scene classification based on convolutional neural network
Convolutional Neural Network(CNN) has been widely used in image recognition and classificaiton. The objectives of this project is to implement the mupltiple CNNs on MIT Indoor67 dataset, to evaluate their performance, and therefore gain first hand experience on transfer learning. First, Place205-VG...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/75435 |
| _version_ | 1826113980778676224 |
|---|---|
| author | Zou, Bojing |
| author2 | Jiang Xudong |
| author_facet | Jiang Xudong Zou, Bojing |
| author_sort | Zou, Bojing |
| collection | NTU |
| description | Convolutional Neural Network(CNN) has been widely used in image recognition and classificaiton. The objectives of this project is to implement the mupltiple CNNs on MIT Indoor67 dataset, to evaluate their performance, and therefore gain first hand experience on transfer learning.
First, Place205-VGG CNN model has been used in order to evaluate its performance. Later, after performance evaluation, a relatively new technique CAM has been implemented on CNN, as a result, a heat map will be generated so that human can visualize and indirectly understand the relative importance of feature information learned by CNN. This manoeuvre enables a deeper understanding of CNN’s learning aspect. Second, pre-trained ResNet-152 has been used for fine- tuning, by freezing some low-level layers and training the final classifier, a better classification accuracy is obtained. |
| first_indexed | 2024-10-01T03:31:43Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/75435 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:31:43Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/754352023-07-07T16:06:42Z Scene classification based on convolutional neural network Zou, Bojing Jiang Xudong School of Electrical and Electronic Engineering DRNTU::Engineering DRNTU::Engineering::Electrical and electronic engineering Convolutional Neural Network(CNN) has been widely used in image recognition and classificaiton. The objectives of this project is to implement the mupltiple CNNs on MIT Indoor67 dataset, to evaluate their performance, and therefore gain first hand experience on transfer learning. First, Place205-VGG CNN model has been used in order to evaluate its performance. Later, after performance evaluation, a relatively new technique CAM has been implemented on CNN, as a result, a heat map will be generated so that human can visualize and indirectly understand the relative importance of feature information learned by CNN. This manoeuvre enables a deeper understanding of CNN’s learning aspect. Second, pre-trained ResNet-152 has been used for fine- tuning, by freezing some low-level layers and training the final classifier, a better classification accuracy is obtained. Bachelor of Engineering 2018-05-31T05:43:08Z 2018-05-31T05:43:08Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/75435 en Nanyang Technological University 64 p. application/pdf |
| spellingShingle | DRNTU::Engineering DRNTU::Engineering::Electrical and electronic engineering Zou, Bojing Scene classification based on convolutional neural network |
| title | Scene classification based on convolutional neural network |
| title_full | Scene classification based on convolutional neural network |
| title_fullStr | Scene classification based on convolutional neural network |
| title_full_unstemmed | Scene classification based on convolutional neural network |
| title_short | Scene classification based on convolutional neural network |
| title_sort | scene classification based on convolutional neural network |
| topic | DRNTU::Engineering DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/75435 |
| work_keys_str_mv | AT zoubojing sceneclassificationbasedonconvolutionalneuralnetwork |