Name
Abstract | ||
|---|---|---|
Over the past few years, Convolutional Neural Networks (CNNs) have achieved remarkable advancement for the tasks of one-shot image classification. However, the lack of effective attention modeling has limited its performance. In this paper, we propose a Two-branch (
<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b>
ontent-aware and
<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</b>
osition-aware)
<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</b>
ttention (CPA) Network via an Efficient Semantic Coupling module for attention modeling. Specifically, we harness content-aware attention to model the characteristic features (e.g., color, shape, texture) as well as position-aware attention to model the spatial position weights. In addition, we exploit support images to improve the learning of attention for the query images. Similarly, we also use query images to enhance the attention model of the support set. Furthermore, we design a local-global optimizing framework that further improves the recognition accuracy. The extensive experiments on four common datasets (miniImageNet, tieredImageNet, CUB-200-2011, CIFAR-FS) with three popular networks (DPGN, RelationNet and IFSL) demonstrate that our devised CPA module equipped with local-global
<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</b>
wo-stream framework (CPAT) can achieve state-of-the-art performance, with a significant improvement in accuracy of 3.16% on CUB-200-2011 in particular. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/TIP.2021.3124668 | IEEE Transactions on Image Processing |
Keywords | DocType | Volume |
One-shot learning,efficient semantic coupling,content-aware attention,position-aware attention,local-global optimizing framework,two-branch attention network | Journal | 31 |
Issue | ISSN | Citations |
1 | 1057-7149 | 0 |
PageRank | References | Authors |
0.34 | 38 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| li jun | 1 | 93 | 42.84 |
| Duorui Wang | 2 | 0 | 0.34 |
| Xianglong Liu | 3 | 853 | 57.47 |
| Zhiping Shi | 4 | 168 | 43.86 |
| Meng Wang | 5 | 3094 | 167.38 |