Abstract | ||
---|---|---|
Object detection in remote sensing images is a challenging task because of the large scale variations across the geospatial objects. The feature pyramid network (FPN) is widely used to alleviate the scale variations problem, however, it only fuses the features from adjacent levels and lacks the information of the entire feature hierarchy. In this paper, we propose a novel and effective feature pyramid aggregation network, called Adaptive Feature Aggregation Network (AFANet). Specifically, we propose the Adaptive Feature Aggregation (AFA) module to adaptively aggregate multi-level features of FPN and introduce the Bottom-up Path to enhance the location information of the entire feature levels. In addition, we use the Receptive Field Block (RFB) module to capture different receptive field features for each level feature map. We evaluate the effectiveness of our AFANet on the DOTA dataset and achieves noticeable performance compared with the baseline. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/IGARSS39084.2020.9323567 | IGARSS 2020 - 2020 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM |
Keywords | DocType | Citations |
Object detection, remote sensing images, adaptive feature aggregation, convolutional neural network | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenliang Sun | 1 | 0 | 0.34 |
Xiangrong Zhang | 2 | 0 | 0.34 |
Tianyang Zhang | 3 | 63 | 8.35 |
Peng Zhu | 4 | 1 | 2.03 |
Li Gao | 5 | 0 | 0.34 |
Xu Tang | 6 | 0 | 0.34 |
Bo Liu | 7 | 0 | 0.34 |