TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)

Min Seok Lee; Woo Seok Shin; Sung Won Han

TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)

Min Seok Lee, Woo Seok Shin, Sung Won Han

School of Industrial Management Engineering

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

40 Citations (Scopus)

Abstract

Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge features and aggregating multi-level features to improve SOD performance. However, both performance gain and computational efficiency cannot be achieved, which has motivated us to study the inefficiencies in existing encoder-decoder structures to avoid this trade-off. We propose TRACER which excludes multi-decoder structures and minimizes the learning parameters usage by employing attention guided tracing modules (ATMs).

Original language	English
Title of host publication	IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations
Publisher	Association for the Advancement of Artificial Intelligence
Pages	12993-12994
Number of pages	2
ISBN (Electronic)	1577358767, 9781577358763
Publication status	Published - 2022 Jun 30
Event	36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online Duration: 2022 Feb 22 → 2022 Mar 1

Publication series

Name	Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Volume	36

Conference

Conference	36th AAAI Conference on Artificial Intelligence, AAAI 2022
City	Virtual, Online
Period	22/2/22 → 22/3/1

Bibliographical note

Publisher Copyright:
Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

Artificial Intelligence

Cite this

Lee, M. S., Shin, W. S., & Han, S. W. (2022). TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract). In IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations (pp. 12993-12994). (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022; Vol. 36). Association for the Advancement of Artificial Intelligence.

TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract). / Lee, Min Seok; Shin, Woo Seok; Han, Sung Won.
IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations. Association for the Advancement of Artificial Intelligence, 2022. p. 12993-12994 (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022; Vol. 36).

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

Lee, MS, Shin, WS & Han, SW 2022, TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract). in IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations. Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022, vol. 36, Association for the Advancement of Artificial Intelligence, pp. 12993-12994, 36th AAAI Conference on Artificial Intelligence, AAAI 2022, Virtual, Online, 22/2/22.

Lee MS, Shin WS, Han SW. TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract). In IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations. Association for the Advancement of Artificial Intelligence. 2022. p. 12993-12994. (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022).

Lee, Min Seok ; Shin, Woo Seok ; Han, Sung Won. / TRACER : Extreme Attention Guided Salient Object Tracing Network (Student Abstract). IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations. Association for the Advancement of Artificial Intelligence, 2022. pp. 12993-12994 (Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022).

@inproceedings{1c2b5e6ca1a5422b9bfdb6dd80e503e4,

title = "TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)",

abstract = "Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge features and aggregating multi-level features to improve SOD performance. However, both performance gain and computational efficiency cannot be achieved, which has motivated us to study the inefficiencies in existing encoder-decoder structures to avoid this trade-off. We propose TRACER which excludes multi-decoder structures and minimizes the learning parameters usage by employing attention guided tracing modules (ATMs).",

author = "Lee, {Min Seok} and Shin, {Woo Seok} and Han, {Sung Won}",

note = "Publisher Copyright: Copyright {\textcopyright} 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 36th AAAI Conference on Artificial Intelligence, AAAI 2022 ; Conference date: 22-02-2022 Through 01-03-2022",

year = "2022",

month = jun,

day = "30",

language = "English",

series = "Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022",

publisher = "Association for the Advancement of Artificial Intelligence",

pages = "12993--12994",

booktitle = "IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations",

}

TY - GEN

T1 - TRACER

T2 - 36th AAAI Conference on Artificial Intelligence, AAAI 2022

AU - Lee, Min Seok

AU - Shin, Woo Seok

AU - Han, Sung Won

PY - 2022/6/30

Y1 - 2022/6/30

N2 - Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge features and aggregating multi-level features to improve SOD performance. However, both performance gain and computational efficiency cannot be achieved, which has motivated us to study the inefficiencies in existing encoder-decoder structures to avoid this trade-off. We propose TRACER which excludes multi-decoder structures and minimizes the learning parameters usage by employing attention guided tracing modules (ATMs).

AB - Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge features and aggregating multi-level features to improve SOD performance. However, both performance gain and computational efficiency cannot be achieved, which has motivated us to study the inefficiencies in existing encoder-decoder structures to avoid this trade-off. We propose TRACER which excludes multi-decoder structures and minimizes the learning parameters usage by employing attention guided tracing modules (ATMs).

UR - http://www.scopus.com/inward/record.url?scp=85137784978&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85137784978

T3 - Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022

SP - 12993

EP - 12994

BT - IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations

PB - Association for the Advancement of Artificial Intelligence

Y2 - 22 February 2022 through 1 March 2022

ER -

TRACER: Extreme Attention Guided Salient Object Tracing Network (Student Abstract)

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this