Multi-level refinement feature pyramid network for scale imbalance object detection
Object detection becomes a challenge due to diversity of object scales. In general, modern object detectors use feature pyramid to learn multi-scale representation for better results. However, current versions of feature pyramid are insufficient to handle scale imbalance, as it is inefficient to int...
Saved in:
Main Authors: | Aziz, Lubna, Salam, Md. Sah, Sheikh, Usman Ullah, Khan, Surat, Ayub, Huma, Ayub, Sara |
---|---|
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
2021
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/95703/1/MdSahSalam2021_MultiLevelRefinementFeaturePyramid.pdf http://eprints.utm.my/id/eprint/95703/ http://dx.doi.org/10.1109/ACCESS.2021.3130129 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Multi-level refinement enriched feature pyramid network for object detection
by: Aziz, Lubna, et al.
Published: (2021) -
Multi-level refinement enriched feature pyramid network for object detection
by: Aziz, Lubna, et al.
Published: (2021) -
Multi level refinement enriched feature pyramid network for scale and class imbalance in object detection
by: Aziz, Lubna
Published: (2022) -
Exploring deep learning-based architecture, strategies, applications and current trends in generic object detection: A comprehensive review
by: Aziz, Lubna, et al.
Published: (2020) -
An evaluation of feature selection methods on multi-class imbalance and high dimensionality shape-based leaf image features
by: Sainin, Mohd Shamrie, et al.
Published: (2017)