Name
Abstract | ||
|---|---|---|
Attention mechanism has shown excellent performance in many computer vision tasks, while the previous literature may not adequately consider different types of attention mechanisms or is individual elaborate designed for a certain network. In this paper, a general yet effective multipath attention mechanism (MAM) to explore the effect of visual attention for image recognition is proposed. In contrast with other attentions that leverage global pooling, the main advantage is that the MAM considers both the correlation of featuremaps and different scale structural information into account. The backbone representations are enhanced by adding MAM laterally along independent and separate dimensions, channel and spatial. Due to only a simple and unified calculation block is generated, MAM can be flexibly integrated into various CNNs within few parameters and trained together end-to-end. Furthermore, the topology structures of attention path arrangement are investigated using different connection schemes. Experimental results on several image recognition datasets show that the model outperforms various existing models. Finally, performance improvement through visualisation is intuitively discussed. The source code for the proposed attention module is publicly available. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1049/ipr2.12370 | IET IMAGE PROCESSING |
DocType | Volume | Issue |
Journal | 16 | 3 |
ISSN | Citations | PageRank |
1751-9659 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hao Zhang | 1 | 0 | 0.68 |
| Guoqin Peng | 2 | 0 | 0.34 |
| Zhichao Wu | 3 | 0 | 0.34 |
| Jian Gong | 4 | 0 | 0.34 |
| Dan Xu | 5 | 201 | 52.67 |
| Hongzhen Shi | 6 | 0 | 0.68 |