MobileNetV3 for Image Classification
| Autor: | Yuepeng Hu, Siying Qian, Chenran Ning |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Contextual image classification business.industry Computer science Computation Feature extraction Pattern recognition 02 engineering and technology Convolutional neural network Image (mathematics) Convolution 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Mobile device |
| Zdroj: | 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE). |
| DOI: | 10.1109/icbaie52039.2021.9389905 |
| Popis: | Convolution neural network (CNN) is a kind of deep neural networks, which extracts image features through multiple convolution layers and is widely used in image classifications. With the increasing number of image data processed by mobile devices, application of neural network for mobile terminals becomes popular. However, these networks need massive computation and advanced hardware support, making them difficult to adapt to mobile devices. This paper demonstrates that MobileNetV3 can get a superior balance between efficiency and accuracy for real-life image classification tasks on mobile terminals. In our experiments, classification performances are compared among MobileNetV3 and several other commonly used pre-trained CNN models on various image datasets. The chosen datasets are all good representatives of the application scenarios of mobile devices. The result shows that as a lightweight neural network, MobileNetV3 achieved good accuracy performance in an effective manner compared to other large networks. Furthermore, ROC confirmed the advantages of MobileNetV3 over other experimented models. Some conjectures are also brought out about the characteristics of image datasets that are suitable for MobileNetV3. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|