PoolNet+: Exploring the Potential of Pooling for Salient Object Detection

We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 45; H. 1; S. 887 - 904
Hauptverfasser: Liu, Jiang-Jiang, Hou, Qibin, Liu, Zhi-Ang, Cheng, Ming-Ming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Applications programs
Artificial neural networks
Convolutional neural networks
Corresponding states
Edge detection
feature aggregation
Feature extraction
global guidance
Image edge detection
Image segmentation
mobile application
Mobile computing
Modules
Object detection
Object recognition
pooling techniques
Salience
Salient object detection
Semantics
Task analysis
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a <inline-formula><tex-math notation="LaTeX">300 \times 400</tex-math> <mml:math><mml:mrow><mml:mn>300</mml:mn><mml:mo>×</mml:mo><mml:mn>400</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href="cheng-ieq1-3140168.gif"/> </inline-formula> image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/ .
AbstractList We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a 300 ×400 image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/.
We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a 300 ×400 image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/.We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a 300 ×400 image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/.
We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a <inline-formula><tex-math notation="LaTeX">300 \times 400</tex-math> <mml:math><mml:mrow><mml:mn>300</mml:mn><mml:mo>×</mml:mo><mml:mn>400</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href="cheng-ieq1-3140168.gif"/> </inline-formula> image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/ .
We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a [Formula Omitted] image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/ .
Author Liu, Jiang-Jiang
Cheng, Ming-Ming
Hou, Qibin
Liu, Zhi-Ang
Author_xml – sequence: 1
  givenname: Jiang-Jiang
  orcidid: 0000-0002-1341-2763
  surname: Liu
  fullname: Liu, Jiang-Jiang
  email: j04.liu@gmail.com
  organization: College of Computer Science, Nankai University, Nankai, China
– sequence: 2
  givenname: Qibin
  orcidid: 0000-0002-8388-8708
  surname: Hou
  fullname: Hou, Qibin
  email: andrewhoux@gmail.com
  organization: College of Computer Science, Nankai University, Nankai, China
– sequence: 3
  givenname: Zhi-Ang
  orcidid: 0000-0002-3319-4492
  surname: Liu
  fullname: Liu, Zhi-Ang
  email: liuzhiang@mail.nankai.edu.cn
  organization: College of Computer Science, Nankai University, Nankai, China
– sequence: 4
  givenname: Ming-Ming
  orcidid: 0000-0001-5550-8758
  surname: Cheng
  fullname: Cheng, Ming-Ming
  email: cmm@nankai.edu.cn
  organization: College of Computer Science, Nankai University, Nankai, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/34982676$$D View this record in MEDLINE/PubMed
BookMark eNp9kcFu1DAQhi1URLeFFwAJReJSCWXxjB3H5laVAisVuhLlbDnJBLzKxovjleDt67BLDz1wGs3M98-M5j9jJ2MYibGXwJcA3Ly7W19-WS2RIywFSA5KP2ELBMVLgwZP2CKXsNQa9Sk7m6YN5yArLp6xUyGNRlWrBVutQxi-Unr7vrj-vRtC9OOPIv2kYh0Sjcm7oQh9MUNzow-x-OYGnzvFbbOhNhUfKOXgw_icPe3dMNGLYzxn3z9e3119Lm9uP62uLm_KFpVKZQuIrmsa0VW8rwUi9lCbuqOaEwGXKDNBVV3l3DQtx07oSjmQWoDqZCXO2cVh7i6GX3uakt36qaVhcCOF_WRRgTKVktWMvnmEbsI-jvk6i7WsFXBuIFOvj9S-2VJnd9FvXfxj_z0pA3gA2himKVL_gAC3sxP2rxN2dsIencgi_UjU-uTmR6Xo_PB_6auD1BPRwy6jlOFaiHsGopLx
CODEN ITPIDJ
CitedBy_id crossref_primary_10_3389_fpls_2025_1614929
crossref_primary_10_1007_s11432_024_4449_7
crossref_primary_10_1007_s40747_024_01519_8
crossref_primary_10_1109_TMM_2023_3291823
crossref_primary_10_1109_LSP_2024_3477254
crossref_primary_10_3390_app13179496
crossref_primary_10_3390_coatings12111730
crossref_primary_10_1016_j_knosys_2024_111597
crossref_primary_10_1109_JSTARS_2025_3582927
crossref_primary_10_1016_j_imavis_2024_105154
crossref_primary_10_1007_s10489_024_05860_w
crossref_primary_10_1109_TIP_2024_3486225
crossref_primary_10_1145_3640816
crossref_primary_10_1016_j_eswa_2025_129605
crossref_primary_10_1109_TCSVT_2024_3417607
crossref_primary_10_3390_app12157781
crossref_primary_10_1109_TCSVT_2023_3307693
crossref_primary_10_1016_j_jksuci_2023_101838
crossref_primary_10_1109_TMM_2025_3535386
crossref_primary_10_1016_j_knosys_2024_112852
crossref_primary_10_3390_electronics12224583
crossref_primary_10_1016_j_neunet_2024_106144
crossref_primary_10_1016_j_isprsjprs_2023_11_002
crossref_primary_10_3390_app15031649
crossref_primary_10_3390_s24061901
crossref_primary_10_3390_s24041117
crossref_primary_10_1109_TCSVT_2023_3312859
crossref_primary_10_3390_electronics13244915
crossref_primary_10_1145_3674836
crossref_primary_10_1109_ACCESS_2024_3358825
crossref_primary_10_1016_j_patcog_2025_111804
crossref_primary_10_1007_s10489_023_04982_x
crossref_primary_10_1016_j_neunet_2024_106751
crossref_primary_10_1016_j_patcog_2023_110074
crossref_primary_10_1007_s11263_025_02482_8
crossref_primary_10_1109_TIP_2022_3232209
crossref_primary_10_32604_cmc_2024_057833
crossref_primary_10_1016_j_knosys_2024_111617
crossref_primary_10_1109_TPAMI_2024_3516874
crossref_primary_10_1109_JIOT_2024_3458096
crossref_primary_10_1016_j_optlastec_2025_113429
crossref_primary_10_3390_s22249667
crossref_primary_10_1016_j_neucom_2023_126530
crossref_primary_10_1016_j_imavis_2024_105048
crossref_primary_10_1109_JSEN_2025_3576077
crossref_primary_10_3390_rs14174219
crossref_primary_10_1007_s10489_024_05569_w
crossref_primary_10_1109_TPAMI_2023_3234586
crossref_primary_10_1109_LSP_2024_3465351
crossref_primary_10_1016_j_jvcir_2024_104271
crossref_primary_10_1109_TCE_2023_3345939
crossref_primary_10_1109_TGRS_2023_3332282
crossref_primary_10_1016_j_patcog_2025_112118
crossref_primary_10_1109_TPAMI_2024_3476683
crossref_primary_10_1007_s12559_025_10410_8
crossref_primary_10_1049_ipr2_12895
crossref_primary_10_1016_j_patcog_2024_110330
crossref_primary_10_1007_s11263_024_02058_y
crossref_primary_10_1109_TPAMI_2025_3583968
crossref_primary_10_1109_TITS_2023_3293822
crossref_primary_10_1016_j_engappai_2025_111480
crossref_primary_10_1109_JSEN_2024_3401722
crossref_primary_10_3390_electronics11142209
crossref_primary_10_1109_TIM_2025_3574913
crossref_primary_10_3390_diagnostics13162714
crossref_primary_10_1109_TMM_2024_3410542
crossref_primary_10_1088_1742_6596_3072_1_012004
crossref_primary_10_1109_TIP_2023_3308295
crossref_primary_10_1109_TPAMI_2024_3510793
crossref_primary_10_1109_TGRS_2024_3398820
crossref_primary_10_1007_s40747_025_02015_3
crossref_primary_10_1109_TAES_2024_3453218
crossref_primary_10_1007_s00138_024_01552_0
crossref_primary_10_1109_TIM_2025_3556823
crossref_primary_10_1109_LGRS_2022_3220601
crossref_primary_10_1109_TASE_2023_3346887
crossref_primary_10_1109_TGRS_2024_3487244
crossref_primary_10_1109_TCSVT_2024_3436148
crossref_primary_10_1109_TIM_2025_3600718
crossref_primary_10_1145_3624747
crossref_primary_10_1109_TIE_2023_3342312
crossref_primary_10_1007_s10489_025_06635_7
crossref_primary_10_1007_s11042_023_15981_y
crossref_primary_10_1145_3624984
crossref_primary_10_3390_s25113551
crossref_primary_10_1016_j_neunet_2025_108097
crossref_primary_10_1109_TCSVT_2022_3233131
crossref_primary_10_1109_TITS_2023_3342811
crossref_primary_10_1109_TWC_2025_3542426
crossref_primary_10_1016_j_engappai_2024_108530
crossref_primary_10_1109_TCSVT_2024_3502244
crossref_primary_10_1016_j_knosys_2025_113515
crossref_primary_10_1109_ACCESS_2023_3344644
crossref_primary_10_3390_aerospace10050488
crossref_primary_10_1109_TPAMI_2024_3368158
crossref_primary_10_1287_ijoc_2023_0034
crossref_primary_10_1016_j_neunet_2025_107445
crossref_primary_10_1049_ipr2_13136
crossref_primary_10_1016_j_patcog_2024_110600
crossref_primary_10_1109_TIV_2024_3351271
crossref_primary_10_1109_TETCI_2024_3380442
crossref_primary_10_1109_TAI_2023_3333827
crossref_primary_10_1007_s11042_025_20888_x
crossref_primary_10_1109_TIP_2023_3293759
crossref_primary_10_1109_TPAMI_2023_3264571
crossref_primary_10_1007_s00530_024_01356_2
Cites_doi 10.1109/CVPR.2017.660
10.1007/978-3-030-01267-0_22
10.1109/ICCV.2019.00736
10.1109/CVPR.2018.00330
10.1109/CVPR.2015.7298938
10.1109/TIP.2018.2874279
10.1109/CVPR.2017.698
10.1109/CVPR.2019.00834
10.1109/TPAMI.2016.2636150
10.1007/s41095-019-0149-9
10.1007/978-3-030-58536-5_21
10.1109/CVPR.2013.407
10.1109/TPAMI.2021.3051099
10.1109/TPAMI.2010.161
10.1109/CVPR.2018.00081
10.1109/CVPR.2017.404
10.1109/CVPR.2014.43
10.1007/s11263-015-0822-0
10.1109/TPAMI.2017.2700300
10.1007/978-3-030-01240-3_15
10.1109/CVPR.2016.618
10.1109/TPAMI.2017.2703082
10.1109/TPAMI.1986.4767851
10.1109/WACV.2019.00171
10.1109/CVPR.2016.90
10.1109/TPAMI.2018.2878849
10.1109/CVPR.2019.00612
10.1109/CVPR.2015.7298965
10.1007/978-3-319-46493-0_50
10.1109/TIP.2015.2487833
10.1109/CVPR.2012.6247743
10.1109/TPAMI.2017.2662005
10.1109/CVPR.2013.271
10.1109/ICCV.2019.00733
10.1109/CVPR.2017.106
10.1109/ICCV.2017.31
10.1109/TPAMI.2014.2377715
10.1109/CVPR42600.2020.01011
10.1109/CVPR.2019.00403
10.1109/CVPR.2019.00404
10.1109/CVPR42600.2020.00406
10.1109/ICRA.2016.7487379
10.1109/CVPR.2015.7298731
10.1145/1833349.1778820
10.1109/CVPR.2019.00172
10.1109/ICCV.2019.00345
10.1109/ICCV.2019.00389
10.1109/ICCV.2015.164
10.1109/CVPR.2017.34
10.1109/CVPR.2018.00474
10.1109/CVPR.2018.00326
10.1109/CVPR.2019.00766
10.1109/CVPR.2006.298
10.1109/TPAMI.2018.2815688
10.1109/TIP.2012.2199502
10.1109/CVPR.2014.119
10.1109/CVPR.2016.80
10.1109/TPAMI.2018.2840724
10.1109/CVPR.2016.58
10.1109/ICCV.2017.32
10.1109/ICCV.2017.436
10.1109/CVPR.2019.00320
10.1109/TPAMI.2021.3107956
10.1007/978-3-319-46493-0_28
10.1109/CVPR.2018.00187
10.1109/TPAMI.2004.1273918
10.1109/TPAMI.2019.2905607
10.1007/s11263-021-01490-8
10.1109/CVPR.2013.153
10.1109/ICCV.2013.370
10.1109/TPAMI.2014.2345401
10.1109/ICCV.2017.433
10.1109/CVPR.2016.32
10.1109/CVPR.2017.191
10.1109/5.726791
10.1109/CVPR.2019.00154
10.1109/CVPR.2016.28
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TPAMI.2021.3140168
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library (IEL) (UW System Shared)
CrossRef
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic

Technology Research Database
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 2160-9292
1939-3539
EndPage 904
ExternalDocumentID 34982676
10_1109_TPAMI_2021_3140168
9669083
Genre orig-research
Journal Article
GrantInformation_xml – fundername: New Generation of AI
  grantid: 2018AAA0100400
– fundername: National Natural Science Foundation of China; NSFC
  grantid: 61922046
  funderid: 10.13039/501100001809
GroupedDBID ---
-DZ
-~X
.DC
0R~
29I
4.4
53G
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
IEDLZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
UHB
~02
AAYXX
CITATION
5VS
9M8
AAYOK
ABFSI
ADRHT
AETEA
AETIX
AGSQL
AI.
AIBXA
ALLEH
FA8
H~9
IBMZZ
ICLAB
IFJZH
NPM
RIG
RNI
RZB
VH1
XJT
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c266t-c122adbb3d50f73222f1797de70ee10424c12e57570e9bc02d3856a148316d453
IEDL.DBID RIE
ISSN 0162-8828
1939-3539
IngestDate Thu Oct 02 11:58:45 EDT 2025
Sun Nov 09 05:38:06 EST 2025
Thu Apr 03 07:12:26 EDT 2025
Sat Nov 29 02:58:19 EST 2025
Tue Nov 18 21:01:02 EST 2025
Wed Aug 27 02:14:46 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c266t-c122adbb3d50f73222f1797de70ee10424c12e57570e9bc02d3856a148316d453
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-1341-2763
0000-0002-3319-4492
0000-0002-8388-8708
0000-0001-5550-8758
PMID 34982676
PQID 2747610091
PQPubID 85458
PageCount 18
ParticipantIDs pubmed_primary_34982676
crossref_primary_10_1109_TPAMI_2021_3140168
crossref_citationtrail_10_1109_TPAMI_2021_3140168
ieee_primary_9669083
proquest_journals_2747610091
proquest_miscellaneous_2616956455
PublicationCentury 2000
PublicationDate 2023-Jan.-1
2023-1-1
2023-Jan
20230101
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-Jan.-1
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev TPAMI
PublicationTitleAlternate IEEE Trans Pattern Anal Mach Intell
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref56
ref12
ref59
ref15
ref58
ref14
ref53
ref55
ref11
ref10
krizhevsky (ref77) 2012
ref17
ref16
ref19
ref18
simonyan (ref71) 2015
ref51
ref50
zhou (ref72) 2015
ref46
ref89
ref45
ref48
ref47
shen (ref65) 2015
ref86
ref42
ref85
ref41
ref88
ref44
ref87
ref43
ref49
kokkinos (ref90) 2016
ref8
ref7
ref9
ref4
ref3
ref6
ronneberger (ref13) 2015
ref5
ref82
ref81
ref40
ref84
ref83
ganin (ref64) 2014
ref80
ref79
ref35
ref34
ref37
ref36
ref75
ref74
ref30
ref33
ref76
ref32
gayoung (ref31) 2016
ref1
ref39
ref38
hong (ref2) 2015
lecun (ref52) 1990
ref70
ref73
ref68
ref24
li (ref29) 2015
ref67
ref23
ref26
ref69
ref25
ref20
ref63
ref66
ref22
ref21
kingma (ref78) 2015
ref28
ref27
ranzato (ref54) 2007
ref60
ref62
ref61
References_xml – ident: ref15
  doi: 10.1109/CVPR.2017.660
– ident: ref82
  doi: 10.1007/978-3-030-01267-0_22
– ident: ref49
  doi: 10.1109/ICCV.2019.00736
– year: 2015
  ident: ref71
  article-title: Very deep convolutional networks for large-scale image recognition
  publication-title: Proc Int Conf Learn Representations
– ident: ref12
  doi: 10.1109/CVPR.2018.00330
– ident: ref33
  doi: 10.1109/CVPR.2015.7298938
– ident: ref68
  doi: 10.1109/TIP.2018.2874279
– ident: ref20
  doi: 10.1109/CVPR.2017.698
– ident: ref50
  doi: 10.1109/CVPR.2019.00834
– ident: ref8
  doi: 10.1109/TPAMI.2016.2636150
– ident: ref38
  doi: 10.1007/s41095-019-0149-9
– ident: ref9
  doi: 10.1007/978-3-030-58536-5_21
– ident: ref75
  doi: 10.1109/CVPR.2013.407
– ident: ref39
  doi: 10.1109/TPAMI.2021.3051099
– ident: ref61
  doi: 10.1109/TPAMI.2010.161
– ident: ref16
  doi: 10.1109/CVPR.2018.00081
– ident: ref76
  doi: 10.1109/CVPR.2017.404
– ident: ref74
  doi: 10.1109/CVPR.2014.43
– ident: ref32
  doi: 10.1007/s11263-015-0822-0
– ident: ref89
  doi: 10.1109/TPAMI.2017.2700300
– ident: ref45
  doi: 10.1007/978-3-030-01240-3_15
– ident: ref34
  doi: 10.1109/CVPR.2016.618
– ident: ref55
  doi: 10.1109/TPAMI.2017.2703082
– ident: ref59
  doi: 10.1109/TPAMI.1986.4767851
– ident: ref56
  doi: 10.1109/WACV.2019.00171
– ident: ref70
  doi: 10.1109/CVPR.2016.90
– ident: ref69
  doi: 10.1109/TPAMI.2018.2878849
– ident: ref48
  doi: 10.1109/CVPR.2019.00612
– ident: ref36
  doi: 10.1109/CVPR.2015.7298965
– ident: ref19
  doi: 10.1007/978-3-319-46493-0_50
– ident: ref37
  doi: 10.1109/TIP.2015.2487833
– ident: ref28
  doi: 10.1109/CVPR.2012.6247743
– start-page: 84
  year: 2012
  ident: ref77
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Proc Adv Neural Inform Process Syst
– ident: ref6
  doi: 10.1109/TPAMI.2017.2662005
– ident: ref26
  doi: 10.1109/CVPR.2013.271
– ident: ref42
  doi: 10.1109/ICCV.2019.00733
– ident: ref14
  doi: 10.1109/CVPR.2017.106
– ident: ref21
  doi: 10.1109/ICCV.2017.31
– ident: ref63
  doi: 10.1109/TPAMI.2014.2377715
– ident: ref22
  doi: 10.1109/CVPR42600.2020.01011
– ident: ref43
  doi: 10.1109/CVPR.2019.00403
– start-page: 1185
  year: 2007
  ident: ref54
  article-title: Sparse feature learning for deep belief networks
  publication-title: Proc Adv Neural Inform Process Syst
– ident: ref1
  doi: 10.1109/CVPR.2019.00404
– ident: ref58
  doi: 10.1109/CVPR42600.2020.00406
– ident: ref7
  doi: 10.1109/ICRA.2016.7487379
– ident: ref30
  doi: 10.1109/CVPR.2015.7298731
– ident: ref4
  doi: 10.1145/1833349.1778820
– ident: ref46
  doi: 10.1109/CVPR.2019.00172
– ident: ref57
  doi: 10.1109/ICCV.2019.00345
– year: 2015
  ident: ref78
  article-title: Adam: A method for stochastic optimization
  publication-title: Proc Int Conf Learn Representation
– ident: ref83
  doi: 10.1109/ICCV.2019.00389
– ident: ref66
  doi: 10.1109/ICCV.2015.164
– ident: ref11
  doi: 10.1109/CVPR.2017.34
– year: 2016
  ident: ref90
  article-title: Pushing the boundaries of boundary detection using deep learning
– ident: ref73
  doi: 10.1109/CVPR.2018.00474
– ident: ref17
  doi: 10.1109/CVPR.2018.00326
– ident: ref47
  doi: 10.1109/CVPR.2019.00766
– ident: ref62
  doi: 10.1109/CVPR.2006.298
– ident: ref10
  doi: 10.1109/TPAMI.2018.2815688
– start-page: 3982
  year: 2015
  ident: ref65
  article-title: DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– start-page: 597
  year: 2015
  ident: ref2
  article-title: Online tracking by learning discriminative saliency map with convolutional neural network
  publication-title: Proc Int Conf Mach Learn
– ident: ref5
  doi: 10.1109/TIP.2012.2199502
– ident: ref86
  doi: 10.1109/CVPR.2014.119
– ident: ref18
  doi: 10.1109/CVPR.2016.80
– ident: ref3
  doi: 10.1109/TPAMI.2018.2840724
– ident: ref41
  doi: 10.1109/CVPR.2016.58
– ident: ref24
  doi: 10.1109/ICCV.2017.32
– ident: ref81
  doi: 10.1109/ICCV.2017.436
– ident: ref44
  doi: 10.1109/CVPR.2019.00320
– ident: ref85
  doi: 10.1109/TPAMI.2021.3107956
– ident: ref35
  doi: 10.1007/978-3-319-46493-0_28
– ident: ref23
  doi: 10.1109/CVPR.2018.00187
– ident: ref60
  doi: 10.1109/TPAMI.2004.1273918
– start-page: 536
  year: 2014
  ident: ref64
  article-title: N^ 4-fields: Neural network nearest neighbor fields for image transforms
  publication-title: Proc Asian Conf Comput Vis
– start-page: 5455
  year: 2015
  ident: ref29
  article-title: Visual saliency based on multiscale deep features
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref51
  doi: 10.1109/TPAMI.2019.2905607
– ident: ref80
  doi: 10.1007/s11263-021-01490-8
– ident: ref79
  doi: 10.1109/CVPR.2013.153
– ident: ref27
  doi: 10.1109/ICCV.2013.370
– ident: ref25
  doi: 10.1109/TPAMI.2014.2345401
– year: 2015
  ident: ref72
  article-title: Object detectors emerge in deep scene CNNs
  publication-title: Proc Int Conf Learn Representations
– ident: ref40
  doi: 10.1109/ICCV.2017.433
– start-page: 234
  year: 2015
  ident: ref13
  article-title: U-Net: Convolutional networks for biomedical image segmentation
  publication-title: Proc Int Conf Med Image Comput Comput -Assist Interv
– start-page: 660
  year: 2016
  ident: ref31
  article-title: Deep saliency with encoded low level distance map and high level features
  publication-title: Proc IEEE Conf Comput Vis Pattern Recognit
– ident: ref88
  doi: 10.1109/CVPR.2016.32
– start-page: 396
  year: 1990
  ident: ref52
  article-title: Handwritten digit recognition with a back-propagation network
  publication-title: Proc Adv Neural Inform Process Syst
– ident: ref67
  doi: 10.1109/CVPR.2017.191
– ident: ref53
  doi: 10.1109/5.726791
– ident: ref84
  doi: 10.1109/CVPR.2019.00154
– ident: ref87
  doi: 10.1109/CVPR.2016.28
SSID ssj0014503
Score 2.6998951
Snippet We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 887
SubjectTerms Applications programs
Artificial neural networks
Convolutional neural networks
Corresponding states
Edge detection
feature aggregation
Feature extraction
global guidance
Image edge detection
Image segmentation
mobile application
Mobile computing
Modules
Object detection
Object recognition
pooling techniques
Salience
Salient object detection
Semantics
Task analysis
Title PoolNet+: Exploring the Potential of Pooling for Salient Object Detection
URI https://ieeexplore.ieee.org/document/9669083
https://www.ncbi.nlm.nih.gov/pubmed/34982676
https://www.proquest.com/docview/2747610091
https://www.proquest.com/docview/2616956455
Volume 45
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2160-9292
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014503
  issn: 0162-8828
  databaseCode: RIE
  dateStart: 19790101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjB9W19EcGbVtNN2zTexAd6cF1QYW-lTVIQpBXt-vudSR_sQQVvLZmkJTNDvi-TzAAcR4LrTOrQ1zxDghIhhlOxCf0sVrkoED9oblyxCTkaJZOJGs_BaX8XxlrrDp_ZM3p0sXxT6SltlZ0jNFcIGeZhXkrZ3NXqIwZh5KogI4JBD0ca0V2Q4er8eXz5cI9UcBggQ0U-EVORPhEqRNaUamRmPXIFVn7Hmm7NuR38729XYaXFluyyMYY1mLPlOgy6ug2sdeN1WJ5JQrgB9-OqehvZ-uSC9QfyGMJCNq5qOkqEI1YFIyFqQIzLnhC7Ywt7zGkTh13b2p3nKjfh5fbm-erObwss-BrX5drXwXCYmTwXJuKFpJhLgf4pjZXc2oCCoihhEdDhu8o1HxqRRHGGDEoEqNBIbMFCWZV2B1hheCYKrbCjDGNeJHmSBUZwy3VihSo8CLppTnWbfZyKYLyljoVwlTotpaSltNWSByd9n_cm98af0hukg16ynX4P9jttpq17fqZExRE3Ilby4KhvRseiaElW2mqKMnEQK8q1E3mw3VhBP3ZnPLs_f3MPlqgqfbNTsw8L9cfUHsCi_qpfPz8O0XonyaGz3m8WT-Z3
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9swED_SdNDuYemabvOatRrsrXMjW_5S38K60tA2CyyDvhlbkmEQ7JI4-_t3J3_Qh22wNxudZKPTod9Pd7oD-BQKrrJYBa7iGRKUEDGcjHTgZpHMRYH4QXFti03Ei0Xy-CiXA_jc34UxxtjgM3NJj9aXryu1o6OyKUJziZBhD_bDIPC95rZW7zMIQlsHGTEM2jgSie6KDJfT1XL2MEcy6HvIUZFRRFSmTwQSsTUlG3m2I9kSK39Hm3bXuRn93_8ewasWXbJZsxxew8CUxzDqKjew1pCP4eWzNIRjmC-rar0w9cUV60PyGAJDtqxqCibCEauCkRA1IMpl3xG9Ywv7ltMxDrs2tY3oKk_gx83X1Zdbty2x4CrcmWtXeb6f6TwXOuRFTF6XAi001ibmxnjkFkUJg5AO32WuuK9FEkYZcijhoUpD8QaGZVWad8AKzTNRKIkd4yDiRZInmacFN1wlRsjCAa-b5lS1-cepDMY6tTyEy9RqKSUtpa2WHLjo-zw12Tf-KT0mHfSS7fQ7MOm0mbYGuk2JjCNyRLTkwMe-GU2L_CVZaaodykReJCnbTujA22YV9GN3i-f9n795Dge3q4f79H6-uDuFQ6pR35zbTGBYb3bmA7xQv-qf282ZXcO_Ac086NY
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=PoolNet%2B%3A+Exploring+the+Potential+of+Pooling+for+Salient+Object+Detection&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Liu%2C+Jiang-Jiang&rft.au=Hou%2C+Qibin&rft.au=Liu%2C+Zhi-Ang&rft.au=Cheng%2C+Ming-Ming&rft.date=2023-01-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=45&rft.issue=1&rft.spage=887&rft.epage=904&rft_id=info:doi/10.1109%2FTPAMI.2021.3140168&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2021_3140168
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon