- An encoding layer that can improve CNN performance on Image classification tasks.
| Pre-trained CNN | Pooling/Encoding layer | Accuracy |
|---|---|---|
| MoblieNet | Avg-pooling | 93.3% |
| MoblieNet | NetVLAD | 95.7% |
| MoblieNet | Spatial-NetVLAD | 96.7% |
| Pre-trained CNN | Pooling/Encoding layer | Accuracy |
|---|---|---|
| Vgg16 | Avg-pooling | 78.3% |
| Vgg16 | NetVLAD | 79.7% |
| Vgg16 | Spatial-NetVLAD | 86.9% |
- Madhan Chandrasekharan ,"Fish Classification-Transfer Learning Tensorflow" on Kaggle, 2021
- crlz182 , "Netvlad-Keras" on Github, 2019
- Yann Henon ,"keras-spp" on Github, 2017
- Email: [email protected]