Supervised pyramid network based on semantic consistency for object detection

Feature pyramid network is widely used in image understanding tasks based on multi-scale feature learning. The latest multi-scale feature learning focuses on the interactive integration of features in semantic features and detail features. Feature pyramid network complements multi-scale information...

Full description

Saved in:
Bibliographic Details
Main Authors: DAI Rui, XU Pengyue, LI Jie, HE Lihuo
Format: Article
Language:zho
Published: EDP Sciences 2024-10-01
Series:Xibei Gongye Daxue Xuebao
Subjects:
Online Access:https://www.jnwpu.org/articles/jnwpu/full_html/2024/05/jnwpu2024425p959/jnwpu2024425p959.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846125795488038912
author DAI Rui
XU Pengyue
LI Jie
HE Lihuo
author_facet DAI Rui
XU Pengyue
LI Jie
HE Lihuo
author_sort DAI Rui
collection DOAJ
description Feature pyramid network is widely used in image understanding tasks based on multi-scale feature learning. The latest multi-scale feature learning focuses on the interactive integration of features in semantic features and detail features. Feature pyramid network complements multi-scale information semantic features and detail features through feature interpolation and summation of adjacent layers. Due to the existence of nonlinear operation and convolution layers with different output dimensions, the relationship among different levels is much more complex, and pixel by pixel summation is suboptimal method. A supervised feature pyramid network based on semantic consistency for object detection is proposed. The present method is composed of asymmetric convolution lateral connection and multi-scale semantic features augmentation. The asymmetric convolution lateral connection improves the generalization of features to various pose objects by learning the feature maps of different receptive fields. The multi-scale semantic features augmentation network improves the detail expression ability of high-level features by supplementing the low-level information for the high-level feature map. Moreover, the present method can provide a better trade-off between accuracy and detection performance. Experiments conduct on the MSCOCO dataset, and the results show that the proposed object detection method's accuracy is improved by 2.6% without increasing extra FLOPs.
format Article
id doaj-art-de773c3fa1a24f96bf3fb41ee3b73d53
institution Kabale University
issn 1000-2758
2609-7125
language zho
publishDate 2024-10-01
publisher EDP Sciences
record_format Article
series Xibei Gongye Daxue Xuebao
spelling doaj-art-de773c3fa1a24f96bf3fb41ee3b73d532024-12-13T10:05:05ZzhoEDP SciencesXibei Gongye Daxue Xuebao1000-27582609-71252024-10-0142595996810.1051/jnwpu/20244250959jnwpu2024425p959Supervised pyramid network based on semantic consistency for object detectionDAI Rui0XU Pengyue1LI Jie2HE Lihuo3School of Electronic Engineering, Xidian UniversitySchool of Electronic Engineering, Xidian UniversitySchool of Electronic Engineering, Xidian UniversitySchool of Electronic Engineering, Xidian UniversityFeature pyramid network is widely used in image understanding tasks based on multi-scale feature learning. The latest multi-scale feature learning focuses on the interactive integration of features in semantic features and detail features. Feature pyramid network complements multi-scale information semantic features and detail features through feature interpolation and summation of adjacent layers. Due to the existence of nonlinear operation and convolution layers with different output dimensions, the relationship among different levels is much more complex, and pixel by pixel summation is suboptimal method. A supervised feature pyramid network based on semantic consistency for object detection is proposed. The present method is composed of asymmetric convolution lateral connection and multi-scale semantic features augmentation. The asymmetric convolution lateral connection improves the generalization of features to various pose objects by learning the feature maps of different receptive fields. The multi-scale semantic features augmentation network improves the detail expression ability of high-level features by supplementing the low-level information for the high-level feature map. Moreover, the present method can provide a better trade-off between accuracy and detection performance. Experiments conduct on the MSCOCO dataset, and the results show that the proposed object detection method's accuracy is improved by 2.6% without increasing extra FLOPs.https://www.jnwpu.org/articles/jnwpu/full_html/2024/05/jnwpu2024425p959/jnwpu2024425p959.html目标检测语义一致性特征金字塔网络
spellingShingle DAI Rui
XU Pengyue
LI Jie
HE Lihuo
Supervised pyramid network based on semantic consistency for object detection
Xibei Gongye Daxue Xuebao
目标检测
语义一致性
特征金字塔网络
title Supervised pyramid network based on semantic consistency for object detection
title_full Supervised pyramid network based on semantic consistency for object detection
title_fullStr Supervised pyramid network based on semantic consistency for object detection
title_full_unstemmed Supervised pyramid network based on semantic consistency for object detection
title_short Supervised pyramid network based on semantic consistency for object detection
title_sort supervised pyramid network based on semantic consistency for object detection
topic 目标检测
语义一致性
特征金字塔网络
url https://www.jnwpu.org/articles/jnwpu/full_html/2024/05/jnwpu2024425p959/jnwpu2024425p959.html
work_keys_str_mv AT dairui supervisedpyramidnetworkbasedonsemanticconsistencyforobjectdetection
AT xupengyue supervisedpyramidnetworkbasedonsemanticconsistencyforobjectdetection
AT lijie supervisedpyramidnetworkbasedonsemanticconsistencyforobjectdetection
AT helihuo supervisedpyramidnetworkbasedonsemanticconsistencyforobjectdetection