Abstract | ||
---|---|---|
State-of-the-art Feature Pyramid Networks (FPNs) often focus on extracting features across different levels. In this paper, we propose a novel architecture, Bidirectional Parallel Feature Pyramid Network (BPFPN), to capture multi-scale spatial information from each level of FPN effectively. BPFPN consists of two blocks: Cross-level Channel Attention-Refinement (ClCSAR) Block and Weighted Parallel Feature Aggregation (WPFA) Block. ClCSAR block uses a channel attention mechanism to strengthen the context information of lower-level feature with aid from the upper-level feature. WPFA block exploits discriminating information from variable receptive fields via integrating multi-branch by employing dilated convolutions and using attention mechanisms to capture the salient dependencies over branches. Considering the incremental computation, we also give a lightweight version of BPFPN, namely BPFPN-Lite, integrated with an Efficient WPFA (E-WPFA) to improve detection accuracy while maintaining efficiency. Our proposed network can be easily plugged into existing object detection models and outperforms different feature pyramids methods by 0.2 similar to 2.1 on the COCO test-dev benchmark without bells and whistles. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/ACCESS.2022.3173732 | IEEE ACCESS |
Keywords | DocType | Volume |
Object detection, feature pyramid network, dilated convolution | Journal | 10 |
ISSN | Citations | PageRank |
2169-3536 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhengning Zhang | 1 | 0 | 0.34 |
Lizhu Zhang | 2 | 292 | 42.16 |
Yue Wang | 3 | 121 | 24.26 |
Pengming Feng | 4 | 0 | 0.34 |
Baochen Sun | 5 | 0 | 0.34 |