Transformed Dynamic Feature Pyramid for Small Object Detection

The low resolution and less feature information of small targets make it difficult to recognize and locate, which greatly hinders the improvement of object detection accuracy. In this paper, an object detection model (TDFP) based on CNN and transformer was established, which combines local and globa...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2021, Vol.9, p.134649-134659
Main Authors: Liang, Hong, Yang, Ying, Zhang, Qian, Feng, Linxia, Ren, Jie, Liang, Qiyao
Format: Article
Language:English
Subjects:
Accuracy
Backbone
Context
Convolutional neural networks
cross-scale transformation
Detectors
Feature extraction
Local and global context information
Object detection
Object recognition
single-scale transformation
Target detection
Task analysis
Training
Transformations
transformed feature pyramid
transformer module
Transformers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The low resolution and less feature information of small targets make it difficult to recognize and locate, which greatly hinders the improvement of object detection accuracy. In this paper, an object detection model (TDFP) based on CNN and transformer was established, which combines local and global context to establish the connection between features. In the proposed transformed dynamic feature pyramid network, a transformer module was designed to dynamically transform and fuse the multi-scale features generated by the backbone to generate a transformed feature pyramid with richer multi-scale features and context information. In this transformation process, gate block is used to dynamically select single-scale transformation or cross-scale transformation to achieve an optimal style of transformation and fusion of multi-scale features. The experimental results show that the model improves the small targets detection accuracy based on CNN and transformer. Based on the backbone ResNeXt-101, TDFP achieves 46.2% AP and 26.3% AP S on MS COCO, and takes the amount of computation as a loss constraint to achieve a better balance between detection accuracy and computational complexity.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3116324