Bidirectional Parallel Feature Pyramid Network for Object Detection
TL;DR: BPFPN as mentioned in this paper proposes a cross-level Channel Attention-Refinement (ClCSAR) block and Weighted Parallel Feature Aggregation (WPFA) block to capture multi-scale spatial information from each level of FPN effectively.
read more
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 ~ 2.1 on the COCO test-dev benchmark without bells and whistles.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
AMA-Det: Enhancing Shared Head of One-Stage Object Detection With Adaptation, Merging, and Alignment
01 Jan 2023
TL;DR: AMA-Det as mentioned in this paper proposes a focused feature adaptation method by softening the supervision of the proposal points, which can predict sampling points focused above the assigned objects with excellent alignment and consistency.
2
Multi-branch dilation convolution CenterNet for object detection of underwater vehicles
TL;DR: A novel object detection method, multi-branch dilation convolution CenterNet, is proposed to improve detection precision for underwater vehicles, leveraging dilation convolution and multi-branch structure to enhance feature extraction and separation of foreground and background.
Weighted Feature detection Mechanism for Internet of Vehicles over Heterogeneous Vehicular Network
Giuditta Giardini
- 04 Jun 2023
TL;DR: In this article , a hybrid attribute-feature detection method is proposed for IoV big data in a multi-source, heterogeneous environment to address the issue of inefficiency and inability to provide satisfactory vehicle operation services.
Automated Bone Age Assessment: A New Three-Stage Assessment Method from Coarse to Fine
TL;DR: In this paper , a hierarchical convolutional neural network was proposed to detect the regions of interest (ROI) and classify the bone grade, which achieved good performance in bone age assessment and was superior to existing fine-grained image classification methods.
References
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
- 06 Sep 2014
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin,Piotr Dollár,Ross Girshick,Kaiming He,Bharath Hariharan,Serge Belongie +5 more
- 21 Jul 2017
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Focal Loss for Dense Object Detection
Tsung-Yi Lin,Priya Goyal,Ross Girshick,Kaiming He,Piotr Dollár +4 more
- 07 Aug 2017
TL;DR: This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
•Posted Content
Squeeze-and-Excitation Networks
TL;DR: Squeeze-and-excitation (SE) as mentioned in this paper adaptively recalibrates channel-wise feature responses by explicitly modeling interdependencies between channels, which can be stacked together to form SENet architectures.
18.9K