[Paper note] Feature Pyramid Networks for Object Detection

最新推荐文章于 2022-09-14 12:51:15 发布

原创最新推荐文章于 2022-09-14 12:51:15 发布 · 1.6k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#cnn #物体检测 #深度学习

paper-note 专栏收录该内容

20 篇文章

订阅专栏

本文介绍了一种用于目标检测的特征金字塔网络（FPN），该方法通过在网络中进行多尺度操作来提高检测精度。FPN利用了卷积神经网络各层级的特征，并通过最近邻上采样融合不同分辨率的特征图。实验表明，FPN在COCO数据集上的表现超越了2016年的冠军方案。

                    
                        
                    
                    paper
 
Intuition 
Multi-scale is important in traditional methods
Current detection system use single shot CNN to save time and memory (Faster R-CNN)
CNN is capable of representing higher-level semantics, but not all levels are semantically strong
Single Shot Detector (SSD) is one of the first attempts at using ConvNet’s pyramidal feature, but they add new layers after high up layer, which may lose information in high-resolution feature map
Main contribution: perform multi-scale in the network
 
Model 
Feature Pyramid Network (FPN) building block 
 
  
The feature maps in the picture above are from the last layer of each stage in ConvNet
Nearest neighbor upsampling
Denotes final set of feature maps as 
     
      {P2,P3,P4,P5}
     , corresponding to 
     
      {C2,C3,C4,C5}
     
FPN in Region Proposal Network (RPN) 
 
  Replacing single-scale feature map with FPN
Anchors with different aspect ratios: 1:2, 1:1, 2:1
15 anchors over the pyramid
FPN in Fast R-CNN
 
Experiment 
Evaluate on COCO minival set
Surpass 2016 COCO winner
Lateral and top-down connection is helpful

                