| Autor: |
Chu Yuezhong, Wang Jiaqing, Liu Heng |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
Advances in Multimedia, Vol 2022 (2022) |
| Druh dokumentu: |
article |
| ISSN: |
1687-5699 |
| DOI: |
10.1155/2022/9973814 |
| Popis: |
Feature fusion is an important part of building high-precision convolutional neural networks. In the field of image classification, though widely used in processing multiscale features of the same layer and short connections in the same receptive field, feature fusion is rarely used in long connection operations across receptive fields. In order to fuse the high- and low-level features of image classification, a feature fusion module SCFF (selective cross-layer feature fusion) for long connections is designed in this work. The SCFF can connect the long-distance feature maps in different receptive fields in a top-down order and apply the self-attention mechanism to fuse them two by two. The final fusion result is used as the input of the classifier. In order to verify the effectiveness of the model, the image classification experiment was done on a number of typical datasets. The experimental results prove that the model can fit the existing convolutional neural network well and effectively improve the classification accuracy of the convolutional network only at the cost of a small amount of calculation. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Plný text