A BiFPN, or Weighted Bi-directional Feature Pyramid Network, is a type of feature pyramid network which allows easy and fast multi-scale feature fusion. It incorporates the multi-level feature fusion idea from FPN, PANet and NAS-FPN that enables information to flow in both the top-down and bottom-up directions, while using regular and efficient connections. It also utilizes a fast normalized fusion technique. Traditional approaches usually treat all features input to the FPN equally, even those with different resolutions. However, input features at different resolutions often have unequal contributions to the output features. Thus, the BiFPN adds an additional weight for each input feature allowing the network to learn the importance of each. All regular convolutions are also replaced with less expensive depthwise separable convolutions.

Comparing with PANet, PANet added an extra bottom-up path for information flow at the expense of more computational cost. Whereas BiFPN optimizes these cross-scale connections by removing nodes with a single input edge, adding an extra edge from the original input to output node if they are on the same level, and treating each bidirectional path as one feature network layer (repeating it several times for more high-level future fusion).

Source: EfficientDet: Scalable and Efficient Object Detection

Latest Papers

PAPER DATE
An Efficient and Scalable Deep Learning Approach for Road Damage Detection
| Sadra Naddaf-shM-Mahdi Naddaf-ShAmir R. KashaniHassan Zargarzadeh
2020-11-18
An original framework for Wheat Head Detection using Deep, Semi-supervised and Ensemble Learning within Global Wheat Head Detection (GWHD) Dataset
Fares FouratiWided SouideneRabah Attia
2020-09-24
PP-YOLO: An Effective and Efficient Implementation of Object Detector
| Xiang LongKaipeng DengGuanzhong WangYang ZhangQingqing DangYuan GaoHui ShenJianguo RenShumin HanErrui DingShilei Wen
2020-07-23
A Refined Deep Learning Architecture for Diabetic Foot Ulcers Detection
Manu GoyalSaeed Hassanpour
2020-07-15
YOLOv4: Optimal Speed and Accuracy of Object Detection
| Alexey BochkovskiyChien-Yao WangHong-Yuan Mark Liao
2020-04-23
EfficientDet: Scalable and Efficient Object Detection
| Mingxing TanRuoming PangQuoc V. Le
2019-11-20

Categories