Content‐augmented feature pyramid network with light linear spatial transformers for object detection
Abstract As one of the prevalent components, feature pyramid network (FPN) is widely used in current object detection models for improving multi‐scale object detection performance. However, its feature fusion mode is still in a misaligned and local manner, thus limiting the representation power. To...
Main Authors: | Yongxiang Gu, Xiaolin Qin, Yuncong Peng, Lu Li |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2022-11-01
|
Series: | IET Image Processing |
Online Access: | https://doi.org/10.1049/ipr2.12575 |
Similar Items
-
Adaptive learning feature pyramid for object detection
by: Fukoeng Wong, et al.
Published: (2019-12-01) -
DCIFPN: Deformable cross‐scale interaction feature pyramid network for object detection
by: Junrui Xiao, et al.
Published: (2023-07-01) -
SPT:Swin Pyramid Transformer for Object Detection of Remote Sensing
by: CAI Xiao, CEHN Zhihua, SHENG Bin
Published: (2023-01-01) -
SEFPN: Scale-Equalizing Feature Pyramid Network for Object Detection
by: Zhiqiang Zhang, et al.
Published: (2021-10-01) -
SSRDet: Small Object Detection Based on Feature Pyramid Network
by: Lijuan Zhang, et al.
Published: (2023-01-01)