Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate

Seung Il Lee; Hyun Kim

doi:10.1109/ISOCC50952.2020.9332981

Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate

Seung Il Lee, Hyun Kim

Dept. of Electrical and Information Engineering

Seoul National University of Science and Technology (SNUST)

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

3 Scopus citations

Abstract

With the development of GPU and deep learning, there has been great advances in the field of object detection and segmentation. Instance segmentation is one of the most important tasks used in many areas including autonomous vehicles and video surveillance because such areas require both high frames per second (FPS) and high accuracy. In this paper, we propose a method of attaching path aggregation network and attention gate based on real-Time instance segmentation model, YOLACT, to increase the accuracy of instance segmentation. As a result of applying the proposed method to the YOLACT framework, the processing speed drops slightly by 2.7%, but the accuracy increases significantly up to 1.4AP, while still maintaining realtime processing of 32.6FPS.

Original language	English
Title of host publication	Proceedings - International SoC Design Conference, ISOCC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	320-321
Number of pages	2
ISBN (Electronic)	9781728183312
DOIs	https://doi.org/10.1109/ISOCC50952.2020.9332981
State	Published - 21 Oct 2020
Event	17th International System-on-Chip Design Conference, ISOCC 2020 - Yeosu, Korea, Republic of Duration: 21 Oct 2020 → 24 Oct 2020

Publication series

Name	Proceedings - International SoC Design Conference, ISOCC 2020

Conference

Conference	17th International System-on-Chip Design Conference, ISOCC 2020
Country/Territory	Korea, Republic of
City	Yeosu
Period	21/10/20 → 24/10/20

Keywords

deep learning
instance segmentation

Access to Document

10.1109/ISOCC50952.2020.9332981

Cite this

Il Lee, S., & Kim, H. (2020). Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate. In Proceedings - International SoC Design Conference, ISOCC 2020 (pp. 320-321). Article 9332981 (Proceedings - International SoC Design Conference, ISOCC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISOCC50952.2020.9332981

@inproceedings{65ba07f99aa147f788eea5f82acaa495,

title = "Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate",

abstract = "With the development of GPU and deep learning, there has been great advances in the field of object detection and segmentation. Instance segmentation is one of the most important tasks used in many areas including autonomous vehicles and video surveillance because such areas require both high frames per second (FPS) and high accuracy. In this paper, we propose a method of attaching path aggregation network and attention gate based on real-Time instance segmentation model, YOLACT, to increase the accuracy of instance segmentation. As a result of applying the proposed method to the YOLACT framework, the processing speed drops slightly by 2.7\%, but the accuracy increases significantly up to 1.4AP, while still maintaining realtime processing of 32.6FPS.",

keywords = "deep learning, instance segmentation",

author = "\{Il Lee\}, Seung and Hyun Kim",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 17th International System-on-Chip Design Conference, ISOCC 2020 ; Conference date: 21-10-2020 Through 24-10-2020",

year = "2020",

month = oct,

day = "21",

doi = "10.1109/ISOCC50952.2020.9332981",

language = "English",

series = "Proceedings - International SoC Design Conference, ISOCC 2020",

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

pages = "320--321",

booktitle = "Proceedings - International SoC Design Conference, ISOCC 2020",

}

Il Lee, S & Kim, H 2020, Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate. in Proceedings - International SoC Design Conference, ISOCC 2020., 9332981, Proceedings - International SoC Design Conference, ISOCC 2020, Institute of Electrical and Electronics Engineers Inc., pp. 320-321, 17th International System-on-Chip Design Conference, ISOCC 2020, Yeosu, Korea, Republic of, 21/10/20. https://doi.org/10.1109/ISOCC50952.2020.9332981

Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate. / Il Lee, Seung; Kim, Hyun.
Proceedings - International SoC Design Conference, ISOCC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 320-321 9332981 (Proceedings - International SoC Design Conference, ISOCC 2020).

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

TY - GEN

T1 - Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate

AU - Il Lee, Seung

AU - Kim, Hyun

PY - 2020/10/21

Y1 - 2020/10/21

N2 - With the development of GPU and deep learning, there has been great advances in the field of object detection and segmentation. Instance segmentation is one of the most important tasks used in many areas including autonomous vehicles and video surveillance because such areas require both high frames per second (FPS) and high accuracy. In this paper, we propose a method of attaching path aggregation network and attention gate based on real-Time instance segmentation model, YOLACT, to increase the accuracy of instance segmentation. As a result of applying the proposed method to the YOLACT framework, the processing speed drops slightly by 2.7%, but the accuracy increases significantly up to 1.4AP, while still maintaining realtime processing of 32.6FPS.

AB - With the development of GPU and deep learning, there has been great advances in the field of object detection and segmentation. Instance segmentation is one of the most important tasks used in many areas including autonomous vehicles and video surveillance because such areas require both high frames per second (FPS) and high accuracy. In this paper, we propose a method of attaching path aggregation network and attention gate based on real-Time instance segmentation model, YOLACT, to increase the accuracy of instance segmentation. As a result of applying the proposed method to the YOLACT framework, the processing speed drops slightly by 2.7%, but the accuracy increases significantly up to 1.4AP, while still maintaining realtime processing of 32.6FPS.

KW - deep learning

KW - instance segmentation

UR - http://www.scopus.com/inward/record.url?scp=85100754792&partnerID=8YFLogxK

U2 - 10.1109/ISOCC50952.2020.9332981

DO - 10.1109/ISOCC50952.2020.9332981

M3 - Conference contribution

AN - SCOPUS:85100754792

T3 - Proceedings - International SoC Design Conference, ISOCC 2020

SP - 320

EP - 321

BT - Proceedings - International SoC Design Conference, ISOCC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th International System-on-Chip Design Conference, ISOCC 2020

Y2 - 21 October 2020 through 24 October 2020

ER -

Instant and Accurate Instance Segmentation Equipped with Path Aggregation and Attention Gate

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this