Proceedings ArticleDOI
BAFPN: An Optimization for YOLO
Hehe Li,Xin Li,LianFeng Li,Junbin Pan,Shujia Zhu,Jinwei Du,Peng Wang +6 more
- pp 1-5
Reads0
Chats0
TLDR
BAFPN is a new bidirectional Feature Pyramid Network that constructs accurate object detection networks based on YOLOv4 by implementing Adaptively Spatial Feature Fusion and Exponential Moving Average is used to improve the network performance.Abstract:
Object detection is essential in Computer Vision and is widely applied in all areas. This paper proposes a method called BAFPN. BAFPN is a new bidirectional Feature Pyramid Network that constructs accurate object detection networks based on YOLOv4 by implementing Adaptively Spatial Feature Fusion. Besides, Exponential Moving Average is used to improve the network performance. The developed network not only maintains high computing speed but also enhances the mAP by 4.3% when testing with the MS COCO dataset and when comparing it to the original YOLOv4. To further improve the performance, the trained model was pruned using the Batch Normalization layer's scaling factor, achieving an 18% reduction in size and improving object detection speed.read more
Citations
More filters
Journal ArticleDOI
YOLO based deep learning on needle-type dashboard recognition for autopilot maneuvering system
Chia Ming Chang,Yuan-Dean Liou,Yi-Cheng Huang,Shang-En Shen,PeiJou Yu,Ting Hsueh Chuang,Shean Juinn Chiou +6 more
TL;DR: In this paper , a modified YOLO-based object detection model was implemented to recognize the airspeed readings from the needle-type dashboard, which was replaced by a single camera and a powerful edge computer for future autopilot maneuvering purpose.
References
More filters
Posted Content
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Batch Normalization as mentioned in this paper normalizes layer inputs for each training mini-batch to reduce the internal covariate shift in deep neural networks, and achieves state-of-the-art performance on ImageNet.
Proceedings ArticleDOI
Feature Pyramid Networks for Object Detection
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.
Posted Content
YOLOv3: An Incremental Improvement.
Joseph Redmon,Ali Farhadi +1 more
TL;DR: The authors present some updates to YOLO!
Proceedings ArticleDOI
Aggregated Residual Transformations for Deep Neural Networks
TL;DR: ResNeXt as discussed by the authors is a simple, highly modularized network architecture for image classification, which is constructed by repeating a building block that aggregates a set of transformations with the same topology.
Journal ArticleDOI
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
TL;DR: This work equips the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement, and develops a new network structure, called SPP-net, which can generate a fixed-length representation regardless of image size/scale.