SED: Searching Enhanced Decoder with switchable skip connection for semantic segmentation

Neural architecture search (NAS) has shown excellent performance. However, existing semantic segmentation models rely heavily on pre-training on Image-Net or COCO and mainly focus on the designing of decoders. Directly training the encoder–decoder architecture search models from scratch to SOTA for...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Pattern recognition Jg. 149; S. 110196
Hauptverfasser: Zhang, Xian, Quan, Zhibin, Li, Qiang, Zhu, Dejun, Yang, Wankou
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.05.2024
Schlagworte:
ISSN:0031-3203, 1873-5142
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Neural architecture search (NAS) has shown excellent performance. However, existing semantic segmentation models rely heavily on pre-training on Image-Net or COCO and mainly focus on the designing of decoders. Directly training the encoder–decoder architecture search models from scratch to SOTA for semantic segmentation requires even thousands GPU days, which greatly limits the application of NAS. To address this issue, we propose a novel neural architecture Search framework for Enhanced Decoder (SED). Utilizing the pre-trained hand-designing backbone and the searching space composed of light-weight cells, SED searches for a decoder which can perform high-quality segmentation. Furthermore, we attach switchable skip connection operations to search space, expanding the diversity of possible network structure. The parameters of backbone and operations selected in searching phrase are copied to retraining process. As a result, searching, pruning and retraining can be done in just 1 day. The experimental results show that the SED proposed in this paper only needs 1/4 of the parameters and calculation in contrast to hand-designing decoder, and obtains higher segmentation accuracy on Cityscapes. Transferring the same decoder architecture to other datasets, such as: Pascal VOC 2012, Camvid, ADE20K proves the robustness of SED. •For the task of image semantic segmentation, we propose a gradient-based, pre-trainable neural network architecture search framework SED. In this paper we simultaneously considering decoder and skip connection search. Our method maximizes the advantages of NAS and pre- trained backbone.•SED can compress the retraining iterations to several thousands. The whole searching, pruning, retraining process can be compressed into 1 day. Furthermore, after searching on Cityscapes, the searched network architecture can achieve 80.2% mIoU.
AbstractList Neural architecture search (NAS) has shown excellent performance. However, existing semantic segmentation models rely heavily on pre-training on Image-Net or COCO and mainly focus on the designing of decoders. Directly training the encoder–decoder architecture search models from scratch to SOTA for semantic segmentation requires even thousands GPU days, which greatly limits the application of NAS. To address this issue, we propose a novel neural architecture Search framework for Enhanced Decoder (SED). Utilizing the pre-trained hand-designing backbone and the searching space composed of light-weight cells, SED searches for a decoder which can perform high-quality segmentation. Furthermore, we attach switchable skip connection operations to search space, expanding the diversity of possible network structure. The parameters of backbone and operations selected in searching phrase are copied to retraining process. As a result, searching, pruning and retraining can be done in just 1 day. The experimental results show that the SED proposed in this paper only needs 1/4 of the parameters and calculation in contrast to hand-designing decoder, and obtains higher segmentation accuracy on Cityscapes. Transferring the same decoder architecture to other datasets, such as: Pascal VOC 2012, Camvid, ADE20K proves the robustness of SED. •For the task of image semantic segmentation, we propose a gradient-based, pre-trainable neural network architecture search framework SED. In this paper we simultaneously considering decoder and skip connection search. Our method maximizes the advantages of NAS and pre- trained backbone.•SED can compress the retraining iterations to several thousands. The whole searching, pruning, retraining process can be compressed into 1 day. Furthermore, after searching on Cityscapes, the searched network architecture can achieve 80.2% mIoU.
ArticleNumber 110196
Author Zhang, Xian
Quan, Zhibin
Li, Qiang
Zhu, Dejun
Yang, Wankou
Author_xml – sequence: 1
  givenname: Xian
  surname: Zhang
  fullname: Zhang, Xian
  organization: School of Automation, Southeast University, Nanjing 210096, China
– sequence: 2
  givenname: Zhibin
  surname: Quan
  fullname: Quan, Zhibin
  organization: School of Automation, Southeast University, Nanjing 210096, China
– sequence: 3
  givenname: Qiang
  surname: Li
  fullname: Li, Qiang
  email: liqiang3@sensetime.com
  organization: SenseTime Research, China
– sequence: 4
  givenname: Dejun
  surname: Zhu
  fullname: Zhu, Dejun
  organization: State Key Laboratory of Hydroscience and Engineering, Department of Hydraulic Engineering, Tsinghua University, Beijing 100084, China
– sequence: 5
  givenname: Wankou
  surname: Yang
  fullname: Yang, Wankou
  email: wkyang@seu.edu.cn
  organization: School of Automation, Southeast University, Nanjing 210096, China
BookMark eNqFkE1LAzEQhoNUsK3-Aw_5A1uTTfajPQjS1g8oeKgePIVsMummtklJFsV_b5b15EEvM8PMvC8zzwSNnHeA0DUlM0poebOfnWSn_G6Wk5zNaOrNyzM0pnXFsoLyfITGhDCasZywCzSJcU8IrdJgjN6269UCb0EG1Vq3w2vXSqdA4xUoryHgT9u1OKaoWtkcAMd3e8LKOweqs95h4wOOcJSusyoVuyO4TvaTS3Ru5CHC1U-eotf79cvyMds8Pzwt7zaZYqTsMt6woiI115KB1lVNGsMIB1OquVGyrgrDS8p10aQdnpcVz5WWcyg0kQCVYWyKFoOvCj7GAEYoO1zQBWkPghLRQxJ7MUASPSQxQEpi_kt8CvYow9d_sttBBumxDwtBRGWh52ZD4iK0t38bfAPpA4Z2
CitedBy_id crossref_primary_10_1016_j_engappai_2025_110045
crossref_primary_10_1002_mp_18041
crossref_primary_10_1016_j_patcog_2024_110545
crossref_primary_10_1007_s40747_024_01520_1
crossref_primary_10_1016_j_eswa_2024_125964
crossref_primary_10_3390_rs17060952
crossref_primary_10_1007_s00530_024_01605_4
crossref_primary_10_1016_j_asej_2025_103683
crossref_primary_10_1016_j_neucom_2025_129593
crossref_primary_10_3390_rs16173266
crossref_primary_10_1016_j_eswa_2025_126563
Cites_doi 10.1109/ICCV.2019.00200
10.1609/aaai.v31i1.11231
10.1109/ICCV.2019.00690
10.1109/CVPR.2016.90
10.1109/ICCV.2019.00533
10.1109/CVPR42600.2020.00939
10.1109/CVPR.2017.549
10.1109/CVPR.2017.106
10.1109/CVPR.2017.660
10.1016/j.patcog.2022.108652
10.1109/CVPR.2017.195
10.1109/CVPR.2018.00747
10.1109/TPAMI.2017.2699184
10.1016/j.patcog.2020.107622
10.1109/CVPR52688.2022.01553
10.1109/CVPR.2016.350
10.1016/j.patcog.2022.109020
10.1109/ICCV.2019.00685
10.1109/CVPR.2019.00064
10.1109/CVPR.2015.7298965
10.1109/CVPR.2019.00584
10.1109/ICCV48922.2021.00717
10.1007/978-3-030-01219-9_25
10.1609/aaai.v32i1.11709
10.1109/TPAMI.2016.2644615
10.1007/978-3-030-01261-8_20
10.1109/CVPR.2017.544
10.1109/ICCV.2015.123
10.1109/CVPR.2019.01191
10.1109/CVPR.2018.00907
10.1109/TIP.2003.819861
10.1007/s11263-014-0733-5
10.1007/978-3-540-88682-2_5
10.1016/j.patcog.2021.108290
10.1109/CVPR.2017.634
10.1109/CVPR.2018.00813
10.1109/CVPR.2017.243
10.1109/ICCV.2019.00069
10.1109/CVPR.2019.00017
10.1109/CVPRW56347.2022.00309
10.1016/j.patcog.2022.109193
10.1109/ICCV48922.2021.00714
10.1109/CVPR42600.2020.00858
10.1109/ICCV.2019.00926
10.1016/j.patcog.2022.109215
10.1109/CVPR.2019.00975
10.1007/978-3-030-01234-2_49
ContentType Journal Article
Copyright 2023 Elsevier Ltd
Copyright_xml – notice: 2023 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2023.110196
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID 10_1016_j_patcog_2023_110196
S0031320323008932
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-4b357084da3edd780bf304ef6c9fca875f4614d5b084426742cda9e5d0aee7f33
ISICitedReferencesCount 12
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001149608600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 07:25:48 EST 2025
Tue Nov 18 21:14:54 EST 2025
Sat Mar 02 16:00:59 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Semantic segmentation
NAS
Encoder-decoder model
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-4b357084da3edd780bf304ef6c9fca875f4614d5b084426742cda9e5d0aee7f33
ParticipantIDs crossref_citationtrail_10_1016_j_patcog_2023_110196
crossref_primary_10_1016_j_patcog_2023_110196
elsevier_sciencedirect_doi_10_1016_j_patcog_2023_110196
PublicationCentury 2000
PublicationDate May 2024
2024-05-00
PublicationDateYYYYMMDD 2024-05-01
PublicationDate_xml – month: 05
  year: 2024
  text: May 2024
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2024
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Jain, Singh, Orlov, Huang, Li, Walton, Shi (b5) 2021
L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 801–818.
Luo, Tian, Qin, Chen, Liu (b20) 2018; 31
Simonyan, Zisserman (b63) 2014
Paszke, Gross, Massa, Lerer, Bradbury, Chanan, Killeen, Lin, Gimelshein, Antiga (b50) 2019; 32
Wang, Bovik, Sheikh, Simoncelli (b33) 2004; 13
Yang, Yang, Cui (b28) 2022; 128
S. Xie, R. Girshick, P. Dollár, Z. Tu, K. He, Aggregated residual transformations for deep neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1492–1500.
Bao, Dong, Piao, Wei (b10) 2021
H. Zhang, H. Zhang, C. Wang, J. Xie, Co-occurrent Features in Semantic Segmentation, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019.
G. Lin, A. Milan, C. Shen, I. Reid, Refinenet: Multi-path refinement networks for high-resolution semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1925–1934.
Zhang, Li, Quan, Yang (b31) 2023; 133
K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009.
H. Zhang, C. Wu, Z. Zhang, Y. Zhu, H. Lin, Z. Zhang, Y. Sun, T. He, J. Mueller, R. Manmatha, et al., Resnest: Split-attention networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2736–2746.
H. Zhang, K. Dana, J. Shi, Z. Zhang, X. Wang, A. Tyagi, A. Agrawal, Context encoding for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7151–7160.
Wang, Zhang, Cui, Yin, Zhang (b27) 2023; 136
Chen, Collins, Zhu, Papandreou, Zoph, Schroff, Adam, Shlens (b21) 2018; 31
Y. Zhang, Z. Qiu, J. Liu, T. Yao, D. Liu, T. Mei, Customizable architecture search for semantic segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11641–11650.
B. Zoph, V. Vasudevan, J. Shlens, Q.V. Le, Learning transferable architectures for scalable image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8697–8710.
Li, Gong, Zhu (b29) 2023; 136
Zhou, Wu, Zhang, Kang, Ge, Latecki (b60) 2022; 122
H. Li, P. Xiong, H. Fan, J. Sun, DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019.
C. Yu, J. Wang, C. Peng, C. Gao, G. Yu, N. Sang, Bisenet: Bilateral segmentation network for real-time semantic segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 325–341.
Baker, Gupta, Naik, Raskar (b18) 2016
Zhao, Wang, Yang, Cai (b66) 2019; 32
M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, B. Schiele, The cityscapes dataset for semantic urban scene understanding, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3213–3223.
Liu, Simonyan, Yang (b19) 2018
Badrinarayanan, Kendall, Cipolla (b62) 2017; 39
Kingma, Ba (b49) 2014
Y. Li, L. Song, Y. Chen, Z. Li, X. Zhang, X. Wang, J. Sun, Learning dynamic routing for semantic segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8553–8562.
S. Choi, J.T. Kim, J. Choo, Cars can’t fly up in the sky: Improving urban-scene segmentation via height-driven attention networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9373–9383.
G.J. Brostow, J. Shotton, J. Fauqueur, R. Cipolla, Segmentation and Recognition Using Structure from Motion Point Clouds, in: ECCV (1), 2008, pp. 44–57.
F. Chollet, Xception: Deep learning with depthwise separable convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1251–1258.
Z. Jin, T. Gong, D. Yu, Q. Chu, J. Wang, C. Wang, J. Shao, Mining contextual information beyond image for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 7231–7241.
Chen, Papandreou, Kokkinos, Murphy, Yuille (b7) 2017; 40
J. Fu, J. Liu, Y. Wang, Y. Li, Y. Bao, J. Tang, H. Lu, Adaptive context network for scene parsing, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6748–6757.
H. Zhao, X. Qi, X. Shen, J. Shi, J. Jia, Icnet for real-time semantic segmentation on high-resolution images, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 405–420.
R. Strudel, R. Garcia, I. Laptev, C. Schmid, Segmenter: Transformer for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 7262–7272.
Chen, Papandreou, Schroff, Adam (b13) 2017
H. Cai, T. Chen, W. Zhang, Y. Yu, J. Wang, Efficient architecture search by network transformation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, No. 1, 2018.
X. Ding, Y. Guo, G. Ding, J. Han, Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 1911–1920.
Yu, Koltun (b35) 2015
C. Szegedy, S. Ioffe, V. Vanhoucke, A. Alemi, Inception-v4, inception-resnet and the impact of residual connections on learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, No. 1, 2017.
Ronneberger, Fischer, Brox (b4) 2015
T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117–2125.
Ramachandran, Parmar, Vaswani, Bello, Levskaya, Shlens (b34) 2019; 32
K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5693–5703.
X. Wang, R. Girshick, A. Gupta, K. He, Non-Local Neural Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018.
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
C. Liu, L.-C. Chen, F. Schroff, H. Adam, W. Hua, A.L. Yuille, L. Fei-Fei, Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019.
G. Lin, A. Milan, C. Shen, I. Reid, RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017.
K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1026–1034.
Everingham, Eslami, Van Gool, Williams, Winn, Zisserman (b45) 2015; 111
Z. Huang, X. Wang, L. Huang, C. Huang, Y. Wei, W. Liu, CCNet: Criss-Cross Attention for Semantic Segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV, 2019.
H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2881–2890.
B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso, A. Torralba, Scene parsing through ade20k dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 633–641.
Zoph, Le (b23) 2016
Yuan, Huang, Guo, Zhang, Chen, Wang (b37) 2021
J. Long, E. Shelhamer, T. Darrell, Fully Convolutional Networks for Semantic Segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2015.
X. Li, Z. Zhong, J. Wu, Y. Yang, Z. Lin, H. Liu, Expectation-Maximization Attention Networks for Semantic Segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV, 2019.
Lin, Maire, Belongie, Hays, Perona, Ramanan, Dollár, Zitnick (b57) 2014
G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.
Lian, Pang, Han, Pan (b61) 2021; 110
Yuan, Chen, Wang (b55) 2020
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b36) 2017; 30
T. Takikawa, D. Acuna, V. Jampani, S. Fidler, Gated-scnn: Gated shape cnns for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 5229–5238.
F. Zhang, Y. Chen, Z. Li, Z. Hong, J. Liu, F. Ma, J. Han, E. Ding, Acfnet: Attentional class feature network for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6798–6807.
Liu (10.1016/j.patcog.2023.110196_b19) 2018
10.1016/j.patcog.2023.110196_b1
10.1016/j.patcog.2023.110196_b2
10.1016/j.patcog.2023.110196_b3
10.1016/j.patcog.2023.110196_b39
10.1016/j.patcog.2023.110196_b8
10.1016/j.patcog.2023.110196_b9
10.1016/j.patcog.2023.110196_b6
Kingma (10.1016/j.patcog.2023.110196_b49) 2014
10.1016/j.patcog.2023.110196_b44
10.1016/j.patcog.2023.110196_b43
10.1016/j.patcog.2023.110196_b42
10.1016/j.patcog.2023.110196_b48
Yang (10.1016/j.patcog.2023.110196_b28) 2022; 128
10.1016/j.patcog.2023.110196_b47
10.1016/j.patcog.2023.110196_b46
10.1016/j.patcog.2023.110196_b41
Wang (10.1016/j.patcog.2023.110196_b27) 2023; 136
10.1016/j.patcog.2023.110196_b40
Yu (10.1016/j.patcog.2023.110196_b35) 2015
Ramachandran (10.1016/j.patcog.2023.110196_b34) 2019; 32
Bao (10.1016/j.patcog.2023.110196_b10) 2021
Badrinarayanan (10.1016/j.patcog.2023.110196_b62) 2017; 39
10.1016/j.patcog.2023.110196_b12
10.1016/j.patcog.2023.110196_b56
10.1016/j.patcog.2023.110196_b11
Li (10.1016/j.patcog.2023.110196_b29) 2023; 136
10.1016/j.patcog.2023.110196_b54
10.1016/j.patcog.2023.110196_b53
10.1016/j.patcog.2023.110196_b16
10.1016/j.patcog.2023.110196_b15
10.1016/j.patcog.2023.110196_b59
10.1016/j.patcog.2023.110196_b14
10.1016/j.patcog.2023.110196_b58
Lin (10.1016/j.patcog.2023.110196_b57) 2014
10.1016/j.patcog.2023.110196_b52
10.1016/j.patcog.2023.110196_b51
Zoph (10.1016/j.patcog.2023.110196_b23) 2016
Chen (10.1016/j.patcog.2023.110196_b13) 2017
Baker (10.1016/j.patcog.2023.110196_b18) 2016
10.1016/j.patcog.2023.110196_b17
Chen (10.1016/j.patcog.2023.110196_b7) 2017; 40
Everingham (10.1016/j.patcog.2023.110196_b45) 2015; 111
10.1016/j.patcog.2023.110196_b67
10.1016/j.patcog.2023.110196_b22
10.1016/j.patcog.2023.110196_b65
Paszke (10.1016/j.patcog.2023.110196_b50) 2019; 32
10.1016/j.patcog.2023.110196_b64
10.1016/j.patcog.2023.110196_b26
10.1016/j.patcog.2023.110196_b25
Yuan (10.1016/j.patcog.2023.110196_b37) 2021
Simonyan (10.1016/j.patcog.2023.110196_b63) 2014
10.1016/j.patcog.2023.110196_b24
Lian (10.1016/j.patcog.2023.110196_b61) 2021; 110
Jain (10.1016/j.patcog.2023.110196_b5) 2021
Chen (10.1016/j.patcog.2023.110196_b21) 2018; 31
10.1016/j.patcog.2023.110196_b32
10.1016/j.patcog.2023.110196_b38
Yuan (10.1016/j.patcog.2023.110196_b55) 2020
Luo (10.1016/j.patcog.2023.110196_b20) 2018; 31
Zhang (10.1016/j.patcog.2023.110196_b31) 2023; 133
Wang (10.1016/j.patcog.2023.110196_b33) 2004; 13
Zhao (10.1016/j.patcog.2023.110196_b66) 2019; 32
10.1016/j.patcog.2023.110196_b30
Vaswani (10.1016/j.patcog.2023.110196_b36) 2017; 30
Ronneberger (10.1016/j.patcog.2023.110196_b4) 2015
Zhou (10.1016/j.patcog.2023.110196_b60) 2022; 122
References_xml – year: 2016
  ident: b18
  article-title: Designing neural network architectures using reinforcement learning
– reference: T. Takikawa, D. Acuna, V. Jampani, S. Fidler, Gated-scnn: Gated shape cnns for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 5229–5238.
– volume: 30
  year: 2017
  ident: b36
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 31
  year: 2018
  ident: b21
  article-title: Searching for efficient multi-scale architectures for dense image prediction
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2014
  ident: b49
  article-title: Adam: A method for stochastic optimization
– volume: 128
  year: 2022
  ident: b28
  article-title: Searching part-specific neural fabrics for human pose estimation
  publication-title: Pattern Recognit.
– reference: G. Lin, A. Milan, C. Shen, I. Reid, Refinenet: Multi-path refinement networks for high-resolution semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1925–1934.
– reference: Y. Zhang, Z. Qiu, J. Liu, T. Yao, D. Liu, T. Mei, Customizable architecture search for semantic segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11641–11650.
– reference: K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5693–5703.
– reference: K. He, X. Zhang, S. Ren, J. Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1026–1034.
– year: 2016
  ident: b23
  article-title: Neural architecture search with reinforcement learning
– year: 2021
  ident: b10
  article-title: Beit: Bert pre-training of image transformers
– reference: H. Zhang, C. Wu, Z. Zhang, Y. Zhu, H. Lin, Z. Zhang, Y. Sun, T. He, J. Mueller, R. Manmatha, et al., Resnest: Split-attention networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2736–2746.
– reference: F. Chollet, Xception: Deep learning with depthwise separable convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1251–1258.
– reference: G.J. Brostow, J. Shotton, J. Fauqueur, R. Cipolla, Segmentation and Recognition Using Structure from Motion Point Clouds, in: ECCV (1), 2008, pp. 44–57.
– reference: Z. Jin, T. Gong, D. Yu, Q. Chu, J. Wang, C. Wang, J. Shao, Mining contextual information beyond image for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 7231–7241.
– reference: J. Fu, J. Liu, Y. Wang, Y. Li, Y. Bao, J. Tang, H. Lu, Adaptive context network for scene parsing, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6748–6757.
– reference: B. Zoph, V. Vasudevan, J. Shlens, Q.V. Le, Learning transferable architectures for scalable image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8697–8710.
– volume: 32
  year: 2019
  ident: b34
  article-title: Stand-alone self-attention in vision models
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: Z. Huang, X. Wang, L. Huang, C. Huang, Y. Wei, W. Liu, CCNet: Criss-Cross Attention for Semantic Segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV, 2019.
– reference: Y. Li, L. Song, Y. Chen, Z. Li, X. Zhang, X. Wang, J. Sun, Learning dynamic routing for semantic segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8553–8562.
– reference: H. Zhao, X. Qi, X. Shen, J. Shi, J. Jia, Icnet for real-time semantic segmentation on high-resolution images, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 405–420.
– volume: 32
  year: 2019
  ident: b50
  article-title: Pytorch: An imperative style, high-performance deep learning library
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 133
  year: 2023
  ident: b31
  article-title: Pyramid geometric consistency learning for semantic segmentation
  publication-title: Pattern Recognit.
– volume: 110
  year: 2021
  ident: b61
  article-title: Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation
  publication-title: Pattern Recognit.
– reference: G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.
– reference: H. Cai, T. Chen, W. Zhang, Y. Yu, J. Wang, Efficient architecture search by network transformation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, No. 1, 2018.
– reference: H. Li, P. Xiong, H. Fan, J. Sun, DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019.
– reference: L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 801–818.
– volume: 31
  year: 2018
  ident: b20
  article-title: Neural architecture optimization
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: X. Li, Z. Zhong, J. Wu, Y. Yang, Z. Lin, H. Liu, Expectation-Maximization Attention Networks for Semantic Segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV, 2019.
– reference: K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
– volume: 40
  start-page: 834
  year: 2017
  end-page: 848
  ident: b7
  article-title: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– reference: H. Zhao, J. Shi, X. Qi, X. Wang, J. Jia, Pyramid scene parsing network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2881–2890.
– volume: 32
  year: 2019
  ident: b66
  article-title: Region mutual information loss for semantic segmentation
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 136
  year: 2023
  ident: b27
  article-title: FP-DARTS: Fast parallel differentiable neural architecture search for image classification
  publication-title: Pattern Recognit.
– reference: K. He, X. Chen, S. Xie, Y. Li, P. Dollár, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000–16009.
– year: 2018
  ident: b19
  article-title: Darts: Differentiable architecture search
– reference: X. Ding, Y. Guo, G. Ding, J. Han, Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 1911–1920.
– reference: R. Strudel, R. Garcia, I. Laptev, C. Schmid, Segmenter: Transformer for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 7262–7272.
– reference: C. Liu, L.-C. Chen, F. Schroff, H. Adam, W. Hua, A.L. Yuille, L. Fei-Fei, Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019.
– start-page: 173
  year: 2020
  end-page: 190
  ident: b55
  article-title: Object-contextual representations for semantic segmentation
  publication-title: European Conference on Computer Vision
– reference: C. Szegedy, S. Ioffe, V. Vanhoucke, A. Alemi, Inception-v4, inception-resnet and the impact of residual connections on learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, No. 1, 2017.
– volume: 122
  year: 2022
  ident: b60
  article-title: Contextual ensemble network for semantic segmentation
  publication-title: Pattern Recognit.
– reference: G. Lin, A. Milan, C. Shen, I. Reid, RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2017.
– reference: J. Long, E. Shelhamer, T. Darrell, Fully Convolutional Networks for Semantic Segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2015.
– reference: M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, B. Schiele, The cityscapes dataset for semantic urban scene understanding, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3213–3223.
– reference: S. Choi, J.T. Kim, J. Choo, Cars can’t fly up in the sky: Improving urban-scene segmentation via height-driven attention networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9373–9383.
– start-page: 1
  year: 2021
  end-page: 24
  ident: b37
  article-title: OCNet: Object context for semantic segmentation
  publication-title: Int. J. Comput. Vis.
– reference: B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso, A. Torralba, Scene parsing through ade20k dataset, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 633–641.
– year: 2017
  ident: b13
  article-title: Rethinking atrous convolution for semantic image segmentation
– start-page: 234
  year: 2015
  end-page: 241
  ident: b4
  article-title: U-net: Convolutional networks for biomedical image segmentation
  publication-title: International Conference on Medical Image Computing and Computer-Assisted Intervention
– reference: H. Zhang, H. Zhang, C. Wang, J. Xie, Co-occurrent Features in Semantic Segmentation, in: The IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2019.
– reference: F. Zhang, Y. Chen, Z. Li, Z. Hong, J. Liu, F. Ma, J. Han, E. Ding, Acfnet: Attentional class feature network for semantic segmentation, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6798–6807.
– volume: 39
  start-page: 2481
  year: 2017
  end-page: 2495
  ident: b62
  article-title: Segnet: A deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– reference: C. Yu, J. Wang, C. Peng, C. Gao, G. Yu, N. Sang, Bisenet: Bilateral segmentation network for real-time semantic segmentation, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 325–341.
– volume: 13
  start-page: 600
  year: 2004
  end-page: 612
  ident: b33
  article-title: Image quality assessment: from error visibility to structural similarity
  publication-title: IEEE Trans. Image Process.
– year: 2014
  ident: b63
  article-title: Very deep convolutional networks for large-scale image recognition
– year: 2021
  ident: b5
  article-title: Semask: Semantically masked transformers for semantic segmentation
– year: 2015
  ident: b35
  article-title: Multi-scale context aggregation by dilated convolutions
– reference: S. Xie, R. Girshick, P. Dollár, Z. Tu, K. He, Aggregated residual transformations for deep neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1492–1500.
– volume: 111
  start-page: 98
  year: 2015
  end-page: 136
  ident: b45
  article-title: The pascal visual object classes challenge: A retrospective
  publication-title: Int. J. Comput. Vis.
– reference: H. Zhang, K. Dana, J. Shi, Z. Zhang, X. Wang, A. Tyagi, A. Agrawal, Context encoding for semantic segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7151–7160.
– reference: T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117–2125.
– start-page: 740
  year: 2014
  end-page: 755
  ident: b57
  article-title: Microsoft coco: Common objects in context
  publication-title: European Conference on Computer Vision
– volume: 136
  year: 2023
  ident: b29
  article-title: Neural operator search
  publication-title: Pattern Recognit.
– reference: X. Wang, R. Girshick, A. Gupta, K. He, Non-Local Neural Networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018.
– ident: 10.1016/j.patcog.2023.110196_b32
  doi: 10.1109/ICCV.2019.00200
– ident: 10.1016/j.patcog.2023.110196_b43
  doi: 10.1609/aaai.v31i1.11231
– ident: 10.1016/j.patcog.2023.110196_b54
  doi: 10.1109/ICCV.2019.00690
– ident: 10.1016/j.patcog.2023.110196_b1
  doi: 10.1109/CVPR.2016.90
– ident: 10.1016/j.patcog.2023.110196_b53
  doi: 10.1109/ICCV.2019.00533
– ident: 10.1016/j.patcog.2023.110196_b52
  doi: 10.1109/CVPR42600.2020.00939
– ident: 10.1016/j.patcog.2023.110196_b67
  doi: 10.1109/CVPR.2017.549
– ident: 10.1016/j.patcog.2023.110196_b41
  doi: 10.1109/CVPR.2017.106
– start-page: 740
  year: 2014
  ident: 10.1016/j.patcog.2023.110196_b57
  article-title: Microsoft coco: Common objects in context
– start-page: 234
  year: 2015
  ident: 10.1016/j.patcog.2023.110196_b4
  article-title: U-net: Convolutional networks for biomedical image segmentation
– ident: 10.1016/j.patcog.2023.110196_b6
  doi: 10.1109/CVPR.2017.660
– volume: 128
  issn: 0031-3203
  year: 2022
  ident: 10.1016/j.patcog.2023.110196_b28
  article-title: Searching part-specific neural fabrics for human pose estimation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2022.108652
– volume: 32
  year: 2019
  ident: 10.1016/j.patcog.2023.110196_b34
  article-title: Stand-alone self-attention in vision models
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.patcog.2023.110196_b15
  doi: 10.1109/CVPR.2017.195
– year: 2014
  ident: 10.1016/j.patcog.2023.110196_b49
– ident: 10.1016/j.patcog.2023.110196_b51
  doi: 10.1109/CVPR.2018.00747
– volume: 40
  start-page: 834
  issue: 4
  year: 2017
  ident: 10.1016/j.patcog.2023.110196_b7
  article-title: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2017.2699184
– volume: 110
  year: 2021
  ident: 10.1016/j.patcog.2023.110196_b61
  article-title: Cascaded hierarchical atrous spatial pyramid pooling module for semantic segmentation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2020.107622
– year: 2018
  ident: 10.1016/j.patcog.2023.110196_b19
– ident: 10.1016/j.patcog.2023.110196_b11
  doi: 10.1109/CVPR52688.2022.01553
– ident: 10.1016/j.patcog.2023.110196_b30
  doi: 10.1109/CVPR.2016.350
– volume: 133
  issn: 0031-3203
  year: 2023
  ident: 10.1016/j.patcog.2023.110196_b31
  article-title: Pyramid geometric consistency learning for semantic segmentation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2022.109020
– ident: 10.1016/j.patcog.2023.110196_b56
  doi: 10.1109/ICCV.2019.00685
– volume: 31
  year: 2018
  ident: 10.1016/j.patcog.2023.110196_b20
  article-title: Neural architecture optimization
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.patcog.2023.110196_b59
  doi: 10.1109/CVPR.2019.00064
– ident: 10.1016/j.patcog.2023.110196_b3
  doi: 10.1109/CVPR.2015.7298965
– ident: 10.1016/j.patcog.2023.110196_b9
  doi: 10.1109/CVPR.2019.00584
– ident: 10.1016/j.patcog.2023.110196_b8
  doi: 10.1109/ICCV48922.2021.00717
– ident: 10.1016/j.patcog.2023.110196_b65
  doi: 10.1007/978-3-030-01219-9_25
– ident: 10.1016/j.patcog.2023.110196_b26
  doi: 10.1609/aaai.v32i1.11709
– year: 2014
  ident: 10.1016/j.patcog.2023.110196_b63
– year: 2017
  ident: 10.1016/j.patcog.2023.110196_b13
– volume: 39
  start-page: 2481
  issue: 12
  year: 2017
  ident: 10.1016/j.patcog.2023.110196_b62
  article-title: Segnet: A deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2644615
– volume: 31
  year: 2018
  ident: 10.1016/j.patcog.2023.110196_b21
  article-title: Searching for efficient multi-scale architectures for dense image prediction
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.patcog.2023.110196_b40
  doi: 10.1007/978-3-030-01261-8_20
– ident: 10.1016/j.patcog.2023.110196_b47
  doi: 10.1109/CVPR.2017.544
– year: 2021
  ident: 10.1016/j.patcog.2023.110196_b10
– volume: 32
  year: 2019
  ident: 10.1016/j.patcog.2023.110196_b66
  article-title: Region mutual information loss for semantic segmentation
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2016
  ident: 10.1016/j.patcog.2023.110196_b18
– start-page: 1
  year: 2021
  ident: 10.1016/j.patcog.2023.110196_b37
  article-title: OCNet: Object context for semantic segmentation
  publication-title: Int. J. Comput. Vis.
– ident: 10.1016/j.patcog.2023.110196_b48
  doi: 10.1109/ICCV.2015.123
– ident: 10.1016/j.patcog.2023.110196_b22
  doi: 10.1109/CVPR.2019.01191
– ident: 10.1016/j.patcog.2023.110196_b25
  doi: 10.1109/CVPR.2018.00907
– year: 2016
  ident: 10.1016/j.patcog.2023.110196_b23
– volume: 13
  start-page: 600
  issue: 4
  year: 2004
  ident: 10.1016/j.patcog.2023.110196_b33
  article-title: Image quality assessment: from error visibility to structural similarity
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2003.819861
– volume: 30
  year: 2017
  ident: 10.1016/j.patcog.2023.110196_b36
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 111
  start-page: 98
  issue: 1
  year: 2015
  ident: 10.1016/j.patcog.2023.110196_b45
  article-title: The pascal visual object classes challenge: A retrospective
  publication-title: Int. J. Comput. Vis.
  doi: 10.1007/s11263-014-0733-5
– ident: 10.1016/j.patcog.2023.110196_b46
  doi: 10.1007/978-3-540-88682-2_5
– volume: 122
  year: 2022
  ident: 10.1016/j.patcog.2023.110196_b60
  article-title: Contextual ensemble network for semantic segmentation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2021.108290
– volume: 32
  year: 2019
  ident: 10.1016/j.patcog.2023.110196_b50
  article-title: Pytorch: An imperative style, high-performance deep learning library
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.patcog.2023.110196_b44
  doi: 10.1109/CVPR.2017.634
– year: 2015
  ident: 10.1016/j.patcog.2023.110196_b35
– ident: 10.1016/j.patcog.2023.110196_b38
  doi: 10.1109/CVPR.2018.00813
– start-page: 173
  year: 2020
  ident: 10.1016/j.patcog.2023.110196_b55
  article-title: Object-contextual representations for semantic segmentation
– ident: 10.1016/j.patcog.2023.110196_b2
  doi: 10.1109/CVPR.2017.243
– ident: 10.1016/j.patcog.2023.110196_b16
  doi: 10.1109/ICCV.2019.00069
– ident: 10.1016/j.patcog.2023.110196_b12
  doi: 10.1109/CVPR.2019.00017
– ident: 10.1016/j.patcog.2023.110196_b42
  doi: 10.1109/CVPRW56347.2022.00309
– volume: 136
  issn: 0031-3203
  year: 2023
  ident: 10.1016/j.patcog.2023.110196_b27
  article-title: FP-DARTS: Fast parallel differentiable neural architecture search for image classification
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2022.109193
– ident: 10.1016/j.patcog.2023.110196_b39
  doi: 10.1109/ICCV48922.2021.00714
– ident: 10.1016/j.patcog.2023.110196_b24
  doi: 10.1109/CVPR42600.2020.00858
– ident: 10.1016/j.patcog.2023.110196_b17
  doi: 10.1109/ICCV.2019.00926
– volume: 136
  issn: 0031-3203
  year: 2023
  ident: 10.1016/j.patcog.2023.110196_b29
  article-title: Neural operator search
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2022.109215
– ident: 10.1016/j.patcog.2023.110196_b58
  doi: 10.1109/CVPR.2017.549
– ident: 10.1016/j.patcog.2023.110196_b64
  doi: 10.1109/CVPR.2019.00975
– ident: 10.1016/j.patcog.2023.110196_b14
  doi: 10.1007/978-3-030-01234-2_49
– year: 2021
  ident: 10.1016/j.patcog.2023.110196_b5
SSID ssj0017142
Score 2.501219
Snippet Neural architecture search (NAS) has shown excellent performance. However, existing semantic segmentation models rely heavily on pre-training on Image-Net or...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 110196
SubjectTerms Encoder-decoder model
NAS
Semantic segmentation
Title SED: Searching Enhanced Decoder with switchable skip connection for semantic segmentation
URI https://dx.doi.org/10.1016/j.patcog.2023.110196
Volume 149
WOSCitedRecordID wos001149608600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELbKwoFLHzzE0od84JpVEnvXMTdUtmqrCoGg1cIlchx7N0sxq31U_PyOY-dBqWg5cLGixHaizKfxePzNDEIHekBB82oZDDRlAeXK5oCMBkFMGOdSMJGVpRN-fGMnJ8loxE89rWhRlhNgxiR3d3z2rKKGeyBsGzr7BHHXk8INuAahQwtih_a_BH8-PLbbfMcjto6AoZm4Y_5jZQPY556WDq2clIFTi-tiZunnRsmaebhQN_DPCwkX4xsfn2TaluxpmZjTBsN4BlJznl87oUct7J2tnKv1alJkRcMDKskEZ9Bv3IxeOUU4XZm2TyKmDQOw0rMkCkgcknt61uUm9ZoSzI7I1bJ9oMSdP2Ham8FidDvu2QLvvab7_ZzZf6xlNcOwIq9NUzdLamdJ3SxraD1mfZ500PrRl-Hoa33qxCLqssv7r69CLUs-4MOv-bsp0zJPLl6jl35fgY8cHt6gF8psoVdVzQ7sVfg2ugR4HOIaHLgCB_bgwBYcuAEHtuDADTgwgANX4MBtcOyg75-GFx8_B768RiBhn7gMaEb6LExoLojKc5aEmSYhVXoguZYC9rGagu2W9zPoA3Yco7HMBVf9PBRKMU3ILuqYW6P2EM4jAc8iqiWHlVcmXMRUioxxCQsKD2UXkepPpdLnnrclUH6mj8mpi4J61MzlXvlHf1YJIfX2o7MLU0DWoyP3n_imt2izgf071FnOV-o92pC_lsVi_sHD6jcET5QR
linkProvider Elsevier
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=SED%3A+Searching+Enhanced+Decoder+with+switchable+skip+connection+for+semantic+segmentation&rft.jtitle=Pattern+recognition&rft.au=Zhang%2C+Xian&rft.au=Quan%2C+Zhibin&rft.au=Li%2C+Qiang&rft.au=Zhu%2C+Dejun&rft.date=2024-05-01&rft.issn=0031-3203&rft.volume=149&rft.spage=110196&rft_id=info:doi/10.1016%2Fj.patcog.2023.110196&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patcog_2023_110196
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon