Bidirectional Parallel Feature Pyramid Network for Object Detection
Open Access
- 9 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 49422-49432
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 $0.2\sim 2.1$ on the COCO test-dev benchmark without bells and whistles.Keywords
Funding Information
- Shenzhen Science and Technology Program (KQTD20170810150821146)
- Civil Aerospace Technology Advance Research Project of China (D040405)
This publication has 36 references indexed in Scilit:
- Acquisition of Localization Confidence for Accurate Object Detection2018
- ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation2018
- Deep Layer Aggregation2018
- Focal Loss for Dense Object Detection2017
- Feature Pyramid Networks for Object Detection2017
- RON: Reverse Connection with Objectness Prior Networks for Object Detection2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Microsoft COCO: Common Objects in Context2014
- A Real-Time Algorithm for Signal Analysis with the Help of the Wavelet Transform1990