Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting

Jeong Jun Lee; Seung Il Lee; Hyun Kim

doi:10.1109/ISOCC53507.2021.9613885

Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting

Jeong Jun Lee, 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

In recent years, with the development of GPUs, there are various deep learning models that show excellent performance in the field of computer vision, but these models have a fatal limitation of catastrophic forgetting. Continual learning studies for mitigating the catastrophic forgetting have been conducted on classification tasks, but in real-life, object detection and segmentation tasks are more practical than classification tasks. This paper proposes a catastrophic forgetting solution in the instance segmentation network by extending and applying the catastrophic forgetting solution, which was previously limited to classification, to segmentation tasks.

Original language	English
Title of host publication	Proceedings - International SoC Design Conference 2021, ISOCC 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	85-86
Number of pages	2
ISBN (Electronic)	9781665401746
DOIs	https://doi.org/10.1109/ISOCC53507.2021.9613885
State	Published - 2021
Event	18th International System-on-Chip Design Conference, ISOCC 2021 - Jeju Island, Korea, Republic of Duration: 6 Oct 2021 → 9 Oct 2021

Publication series

Name	Proceedings - International SoC Design Conference 2021, ISOCC 2021

Conference

Conference	18th International System-on-Chip Design Conference, ISOCC 2021
Country/Territory	Korea, Republic of
City	Jeju Island
Period	6/10/21 → 9/10/21

Keywords

catastrophic forgetting
continual learning
Deep learning
Instance Segmentation

Access to Document

10.1109/ISOCC53507.2021.9613885

Cite this

Lee, J. J., Il Lee, S., & Kim, H. (2021). Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting. In Proceedings - International SoC Design Conference 2021, ISOCC 2021 (pp. 85-86). (Proceedings - International SoC Design Conference 2021, ISOCC 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISOCC53507.2021.9613885

@inproceedings{ebec88cfefc44e8d84cfe3764583b71f,

title = "Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting",

abstract = "In recent years, with the development of GPUs, there are various deep learning models that show excellent performance in the field of computer vision, but these models have a fatal limitation of catastrophic forgetting. Continual learning studies for mitigating the catastrophic forgetting have been conducted on classification tasks, but in real-life, object detection and segmentation tasks are more practical than classification tasks. This paper proposes a catastrophic forgetting solution in the instance segmentation network by extending and applying the catastrophic forgetting solution, which was previously limited to classification, to segmentation tasks.",

keywords = "catastrophic forgetting, continual learning, Deep learning, Instance Segmentation",

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

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 18th International System-on-Chip Design Conference, ISOCC 2021 ; Conference date: 06-10-2021 Through 09-10-2021",

year = "2021",

doi = "10.1109/ISOCC53507.2021.9613885",

language = "English",

series = "Proceedings - International SoC Design Conference 2021, ISOCC 2021",

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

pages = "85--86",

booktitle = "Proceedings - International SoC Design Conference 2021, ISOCC 2021",

}

Lee, JJ, Il Lee, S & Kim, H 2021, Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting. in Proceedings - International SoC Design Conference 2021, ISOCC 2021. Proceedings - International SoC Design Conference 2021, ISOCC 2021, Institute of Electrical and Electronics Engineers Inc., pp. 85-86, 18th International System-on-Chip Design Conference, ISOCC 2021, Jeju Island, Korea, Republic of, 6/10/21. https://doi.org/10.1109/ISOCC53507.2021.9613885

Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting. / Lee, Jeong Jun; Il Lee, Seung; Kim, Hyun.
Proceedings - International SoC Design Conference 2021, ISOCC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 85-86 (Proceedings - International SoC Design Conference 2021, ISOCC 2021).

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

TY - GEN

T1 - Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting

AU - Lee, Jeong Jun

AU - Il Lee, Seung

AU - Kim, Hyun

PY - 2021

Y1 - 2021

N2 - In recent years, with the development of GPUs, there are various deep learning models that show excellent performance in the field of computer vision, but these models have a fatal limitation of catastrophic forgetting. Continual learning studies for mitigating the catastrophic forgetting have been conducted on classification tasks, but in real-life, object detection and segmentation tasks are more practical than classification tasks. This paper proposes a catastrophic forgetting solution in the instance segmentation network by extending and applying the catastrophic forgetting solution, which was previously limited to classification, to segmentation tasks.

AB - In recent years, with the development of GPUs, there are various deep learning models that show excellent performance in the field of computer vision, but these models have a fatal limitation of catastrophic forgetting. Continual learning studies for mitigating the catastrophic forgetting have been conducted on classification tasks, but in real-life, object detection and segmentation tasks are more practical than classification tasks. This paper proposes a catastrophic forgetting solution in the instance segmentation network by extending and applying the catastrophic forgetting solution, which was previously limited to classification, to segmentation tasks.

KW - catastrophic forgetting

KW - continual learning

KW - Deep learning

KW - Instance Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85123380495&partnerID=8YFLogxK

U2 - 10.1109/ISOCC53507.2021.9613885

DO - 10.1109/ISOCC53507.2021.9613885

M3 - Conference contribution

AN - SCOPUS:85123380495

T3 - Proceedings - International SoC Design Conference 2021, ISOCC 2021

SP - 85

EP - 86

BT - Proceedings - International SoC Design Conference 2021, ISOCC 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th International System-on-Chip Design Conference, ISOCC 2021

Y2 - 6 October 2021 through 9 October 2021

ER -

Continual Learning for Instance Segmentation to Mitigate Catastrophic Forgetting

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this