Name
Abstract | ||
|---|---|---|
Defocus blur detection is a challenging task because of obscure homogenous regions and interferences of background clutter. Most existing deep learning-based methods mainly focus on building wider or deeper network to capture multi-level features, neglecting to extract the feature relationships of intermediate layers, thus hindering the discriminative ability of network. Moreover, fusing features at different levels have been demonstrated to be effective. However, direct integrating without distinction is not optimal because low-level features focus on fine details only and could be distracted by background clutters. To address these issues, we propose the Multi-Attention Network for stronger discriminative learning and spatial guided low-level feature learning. Specifically, a channel-wise attention module is applied to both high-level and low-level feature maps to capture channel-wise global dependencies. In addition, a spatial attention module is employed to low-level features maps to emphasize effective detailed information. Experimental results show the performance of our network is superior to the state-of-the-art algorithms. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/MMSP48831.2020.9287072 | 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP) |
Keywords | DocType | ISSN |
defocus blur detection,obscure homogenous regions,background clutter,multilevel features,intermediate layers,discriminative learning,low-level feature learning,channel-wise attention module,low-level feature maps,channel-wise global dependencies,spatial attention module,MultiANet,multiattention network,background clutters,feature relationship extraction | Conference | 2163-3517 |
ISBN | Citations | PageRank |
978-1-7281-9323-6 | 0 | 0.34 |
References | Authors | |
4 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zeyu Jiang | 1 | 0 | 2.37 |
| Xun Xu | 2 | 60 | 5.61 |
| Chao Zhang | 3 | 939 | 103.66 |
| Ce Zhu | 4 | 1473 | 117.79 |