Instance Segmentation based Object Detection with Enhanced Path Aggregation Network

Ade Indra Onthoni; Prasan Kumar Sahoo

doi:10.1109/LA-CCI58595.2023.10409479

Instance Segmentation based Object Detection with Enhanced Path Aggregation Network

Ade Indra Onthoni, Prasan Kumar Sahoo

Department of Computer Science and Information Engineering

Chang Gung University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Multi-scale networks rely heavily on the aggregation process to aggregate feature information into other feature maps. However, it has disadvantages in aggregating information, where the localization information becomes inconsistent. An Enhancing Path Aggregation Network through concatenation and attention mechanism is proposed here to improve the aggregation path for generating the feature maps in multi-scale network. This approach helps to keep information consistently during the process of aggregation. The proposed model is evaluated using the COCO dataset, which achieves significant improvements on several metrics.

Original language	English
Title of host publication	2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350348071
DOIs	https://doi.org/10.1109/LA-CCI58595.2023.10409479
State	Published - 2023
Event	2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023 - Recife-Pe, Brazil Duration: 29 10 2023 → 01 11 2023

Publication series

Name	2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023

Conference

Conference	2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023
Country/Territory	Brazil
City	Recife-Pe
Period	29/10/23 → 01/11/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Computer Vision
Multi-Scale Feature Map
Object Detection

Access to Document

10.1109/LA-CCI58595.2023.10409479

Cite this

Onthoni, A. I., & Sahoo, P. K. (2023). Instance Segmentation based Object Detection with Enhanced Path Aggregation Network. In 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023 (2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/LA-CCI58595.2023.10409479

@inproceedings{b2606635fe004c4184e3958972a61074,

title = "Instance Segmentation based Object Detection with Enhanced Path Aggregation Network",

abstract = "Multi-scale networks rely heavily on the aggregation process to aggregate feature information into other feature maps. However, it has disadvantages in aggregating information, where the localization information becomes inconsistent. An Enhancing Path Aggregation Network through concatenation and attention mechanism is proposed here to improve the aggregation path for generating the feature maps in multi-scale network. This approach helps to keep information consistently during the process of aggregation. The proposed model is evaluated using the COCO dataset, which achieves significant improvements on several metrics.",

keywords = "Computer Vision, Multi-Scale Feature Map, Object Detection",

author = "Onthoni, {Ade Indra} and Sahoo, {Prasan Kumar}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023 ; Conference date: 29-10-2023 Through 01-11-2023",

year = "2023",

doi = "10.1109/LA-CCI58595.2023.10409479",

language = "英语",

series = "2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023",

address = "美国",

}

Onthoni, AI & Sahoo, PK 2023, Instance Segmentation based Object Detection with Enhanced Path Aggregation Network. in 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023. 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023, Recife-Pe, Brazil, 29/10/23. https://doi.org/10.1109/LA-CCI58595.2023.10409479

Instance Segmentation based Object Detection with Enhanced Path Aggregation Network. / Onthoni, Ade Indra; Sahoo, Prasan Kumar.
2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Instance Segmentation based Object Detection with Enhanced Path Aggregation Network

AU - Onthoni, Ade Indra

AU - Sahoo, Prasan Kumar

PY - 2023

Y1 - 2023

N2 - Multi-scale networks rely heavily on the aggregation process to aggregate feature information into other feature maps. However, it has disadvantages in aggregating information, where the localization information becomes inconsistent. An Enhancing Path Aggregation Network through concatenation and attention mechanism is proposed here to improve the aggregation path for generating the feature maps in multi-scale network. This approach helps to keep information consistently during the process of aggregation. The proposed model is evaluated using the COCO dataset, which achieves significant improvements on several metrics.

AB - Multi-scale networks rely heavily on the aggregation process to aggregate feature information into other feature maps. However, it has disadvantages in aggregating information, where the localization information becomes inconsistent. An Enhancing Path Aggregation Network through concatenation and attention mechanism is proposed here to improve the aggregation path for generating the feature maps in multi-scale network. This approach helps to keep information consistently during the process of aggregation. The proposed model is evaluated using the COCO dataset, which achieves significant improvements on several metrics.

KW - Computer Vision

KW - Multi-Scale Feature Map

KW - Object Detection

UR - http://www.scopus.com/inward/record.url?scp=85185225545&partnerID=8YFLogxK

U2 - 10.1109/LA-CCI58595.2023.10409479

DO - 10.1109/LA-CCI58595.2023.10409479

M3 - 会议稿件

AN - SCOPUS:85185225545

T3 - 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023

BT - 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023

Y2 - 29 October 2023 through 1 November 2023

ER -

Onthoni AI, Sahoo PK. Instance Segmentation based Object Detection with Enhanced Path Aggregation Network. In 2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE Latin American Conference on Computational Intelligence, LA-CCI 2023). doi: 10.1109/LA-CCI58595.2023.10409479

Instance Segmentation based Object Detection with Enhanced Path Aggregation Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this