OverSegNet: A convolutional encoder–decoder network for image over-segmentation
Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes a fully convolutional deep network, named OverSegNet, for image over-segmentation. OverSegNet consists of an encoder and a decoder, which ar...
Uloženo v:
| Vydáno v: | Computers & electrical engineering Ročník 107; s. 108610 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.04.2023
|
| Témata: | |
| ISSN: | 0045-7906, 1879-0755 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes a fully convolutional deep network, named OverSegNet, for image over-segmentation. OverSegNet consists of an encoder and a decoder, which are designed for the two core parts of over-segmentation, i.e., feature representation and pixel–superpixel association, respectively. To obtain edge-sensitive and noise-insusceptible feature representation, the encoder is endowed with rich over-segmentation-specific convolutional kernels via over-parametrization followed by task-driven neural network search (NAS). The decoder adopts a multi-scale convolutional structure with cross-large-scale connections, to achieve pixel–superpixel association in a coarse-to-fine feed-forward manner while eliminating accumulation errors. We conduct rich ablation studies to verify the effectiveness of the specially designed encoder and decoder. Experiments on both the BSDS500 dataset and NYUv2 dataset show that the proposed OverSegNet is fast, obtains state-of-the-art accuracy and has good generalization ability. Using semantic segmentation and disparity estimation as examples, we also verify the proposed OverSegNet in downstream applications. |
|---|---|
| AbstractList | Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes a fully convolutional deep network, named OverSegNet, for image over-segmentation. OverSegNet consists of an encoder and a decoder, which are designed for the two core parts of over-segmentation, i.e., feature representation and pixel–superpixel association, respectively. To obtain edge-sensitive and noise-insusceptible feature representation, the encoder is endowed with rich over-segmentation-specific convolutional kernels via over-parametrization followed by task-driven neural network search (NAS). The decoder adopts a multi-scale convolutional structure with cross-large-scale connections, to achieve pixel–superpixel association in a coarse-to-fine feed-forward manner while eliminating accumulation errors. We conduct rich ablation studies to verify the effectiveness of the specially designed encoder and decoder. Experiments on both the BSDS500 dataset and NYUv2 dataset show that the proposed OverSegNet is fast, obtains state-of-the-art accuracy and has good generalization ability. Using semantic segmentation and disparity estimation as examples, we also verify the proposed OverSegNet in downstream applications. |
| ArticleNumber | 108610 |
| Author | Ma, Wei Li, Peng |
| Author_xml | – sequence: 1 givenname: Peng surname: Li fullname: Li, Peng – sequence: 2 givenname: Wei orcidid: 0000-0001-9652-4260 surname: Ma fullname: Ma, Wei email: mawei@bjut.edu.cn |
| BookMark | eNqNkEtOwzAURS1UJNrCHsICUvypHYcJqiooSBUVAsZW4jxHLqldOaGIGXtgh6wElzBAjDp6P92rd88IDZx3gNA5wROCibhYT7TfbKEBDa6eUExZ3EtB8BEaEpnlKc44H6AhxlOeZjkWJ2jUtmscZ0HkED2sdhAeob6H7jKZJdq7nW9eO-td0STgtK8gfH18VvDTJQ66Nx9eEuNDYjdFDYmP-rSFegOuK_a6U3RsiqaFs986Rs8310_z23S5WtzNZ8tUM0q6tCq5KYuMVUJqZoAAYYIyKWieEWIkl4ayDMoKhMgJlzTejSymjJY542AyNkZXva8Ovm0DGKVt_0EXCtsogtWekFqrP4TUnpDqCUWH_J_DNsRQ4f0g7bzXQoy4sxBUq23kBZUNoDtVeXuAyzfnH4yT |
| CitedBy_id | crossref_primary_10_1016_j_asoc_2024_111467 crossref_primary_10_1016_j_compeleceng_2025_110360 crossref_primary_10_1109_TIP_2023_3290523 crossref_primary_10_1007_s11042_023_17659_x |
| Cites_doi | 10.1007/978-3-319-24574-4_28 10.1007/978-3-319-46448-0_36 10.1109/TPAMI.2016.2644615 10.1007/978-3-642-33715-4_54 10.1109/ICCV48922.2021.00699 10.1109/TPAMI.2012.120 10.1016/j.cviu.2017.03.007 10.1109/TIP.2022.3152004 10.1007/978-3-030-01234-2_22 10.1109/TPAMI.2010.161 10.1109/ICCV.2015.238 10.1016/j.inffus.2020.08.014 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.compeleceng.2023.108610 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1879-0755 |
| ExternalDocumentID | 10_1016_j_compeleceng_2023_108610 S0045790623000356 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABEFU ABFNM ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFFNX 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 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG ROL RPZ RXW SBC SDF SDG SDP SES SET SEW SPC SPCBC SST SSV SSZ T5K TAE TN5 UHS VOH WH7 WUQ XPP ZMT ~G- ~S- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c321t-db5fba73d68c3fe1e136238629711f858f237ebde6691582e13f8a432b935ef73 |
| ISICitedReferencesCount | 7 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000931799500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0045-7906 |
| IngestDate | Tue Nov 18 21:27:31 EST 2025 Sat Nov 29 07:27:07 EST 2025 Fri Feb 23 02:38:12 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Non-iterative deep clustering Image over-segmentation Encoder–decoder architecture Superpixel segmentation NAS encoder |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c321t-db5fba73d68c3fe1e136238629711f858f237ebde6691582e13f8a432b935ef73 |
| ORCID | 0000-0001-9652-4260 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_compeleceng_2023_108610 crossref_primary_10_1016_j_compeleceng_2023_108610 elsevier_sciencedirect_doi_10_1016_j_compeleceng_2023_108610 |
| PublicationCentury | 2000 |
| PublicationDate | April 2023 2023-04-00 |
| PublicationDateYYYYMMDD | 2023-04-01 |
| PublicationDate_xml | – month: 04 year: 2023 text: April 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Computers & electrical engineering |
| PublicationYear | 2023 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Jampani V, Sun D, Liu M-Y, Yang M-H, Kautz J. Superpixel sampling networks. In: European conference on computer vision. 2018, p. 352–68. Chang, Chen (b22) 2018 Chen, Kundu, Zhu, Berneshawi, Ma, Fidler (b20) 2015; 28 Wang Y, Wei Y, Qian X, Zhu L, Yang Y. AINet: association implantation for superpixel segmentation. In: IEEE/CVF international conference on computer vision. 2021, p. 7058–67. Arbelaez, Maire, Fowlkes, Malik (b17) 2010; 33 Achanta, Susstrunk (b3) 2017 Yao, Boben, Fidler, Urtasun (b8) 2015 Yang, Sun, Jin, Zhou (b14) 2020 Li, Chen (b2) 2015 Ma, Gong, Xu, Zhang (b6) 2020; 64 Ma, Xu, Ma, Zhang, Zha (b7) 2022; 31 Achanta, Shaji, Smith, Lucchi, Fua, Süsstrunk (b1) 2012; 34 Kingma, Ba (b16) 2014 Gadde R, Jampani V, Kiefel M, Kappler D, Gehler PV. Superpixel convolutional networks using bilateral inceptions. In: European conference on computer vision. 2016, p. 597–613. Mayer, Ilg, Hausser, Fischer, Cremers, Dosovitskiy (b23) 2016 Yang, Sun, Jin, Zhou (b5) 2020 Badrinarayanan, Kendall, Cipolla (b12) 2017; 39 Zhang C, Li Z, Cheng Y, Cai R, Chao H, Rui Y. Meshstereo: A global stereo model with mesh alignment regularization for view interpolation. In: International conference on computer vision. 2015, p. 2057–65. Liu, Tuzel, Ramalingam, Chellappa (b9) 2011 Silberman N, Hoiem D, Kohli P, Fergus R. Indoor segmentation and support inference from RGBD images. In: European conference on computer vision. 2012, p. 746–60. Tu, Liu, Jampani, Sun, Chien, Yang (b10) 2018 Stutz, Hermans, Leibe (b15) 2018; 166 Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. 2015, p. 234–41. Achanta (10.1016/j.compeleceng.2023.108610_b1) 2012; 34 10.1016/j.compeleceng.2023.108610_b4 Ma (10.1016/j.compeleceng.2023.108610_b7) 2022; 31 Kingma (10.1016/j.compeleceng.2023.108610_b16) 2014 Chang (10.1016/j.compeleceng.2023.108610_b22) 2018 10.1016/j.compeleceng.2023.108610_b19 10.1016/j.compeleceng.2023.108610_b18 Chen (10.1016/j.compeleceng.2023.108610_b20) 2015; 28 Yang (10.1016/j.compeleceng.2023.108610_b14) 2020 Liu (10.1016/j.compeleceng.2023.108610_b9) 2011 Stutz (10.1016/j.compeleceng.2023.108610_b15) 2018; 166 10.1016/j.compeleceng.2023.108610_b13 10.1016/j.compeleceng.2023.108610_b11 Li (10.1016/j.compeleceng.2023.108610_b2) 2015 Yao (10.1016/j.compeleceng.2023.108610_b8) 2015 10.1016/j.compeleceng.2023.108610_b21 Mayer (10.1016/j.compeleceng.2023.108610_b23) 2016 Badrinarayanan (10.1016/j.compeleceng.2023.108610_b12) 2017; 39 Yang (10.1016/j.compeleceng.2023.108610_b5) 2020 Achanta (10.1016/j.compeleceng.2023.108610_b3) 2017 Ma (10.1016/j.compeleceng.2023.108610_b6) 2020; 64 Arbelaez (10.1016/j.compeleceng.2023.108610_b17) 2010; 33 Tu (10.1016/j.compeleceng.2023.108610_b10) 2018 |
| References_xml | – start-page: 568 year: 2018 end-page: 576 ident: b10 article-title: Learning superpixels with segmentation-aware affinity loss publication-title: Computer vision and pattern recognition – start-page: 1356 year: 2015 end-page: 1363 ident: b2 article-title: Superpixel segmentation using linear spectral clustering publication-title: Computer vision and pattern recognition – volume: 34 start-page: 2274 year: 2012 end-page: 2282 ident: b1 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans Pattern Anal Mach Intell – start-page: 13964 year: 2020 end-page: 13973 ident: b5 article-title: Superpixel segmentation with fully convolutional networks publication-title: Computer vision and pattern recognition – year: 2014 ident: b16 article-title: Adam: A method for stochastic optimization – volume: 166 start-page: 1 year: 2018 end-page: 27 ident: b15 article-title: Superpixels: An evaluation of the state-of-the-art publication-title: Comput Vis Image Underst – reference: Gadde R, Jampani V, Kiefel M, Kappler D, Gehler PV. Superpixel convolutional networks using bilateral inceptions. In: European conference on computer vision. 2016, p. 597–613. – reference: Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. 2015, p. 234–41. – reference: Zhang C, Li Z, Cheng Y, Cai R, Chao H, Rui Y. Meshstereo: A global stereo model with mesh alignment regularization for view interpolation. In: International conference on computer vision. 2015, p. 2057–65. – volume: 28 start-page: 424 year: 2015 end-page: 432 ident: b20 article-title: 3d object proposals for accurate object class detection publication-title: Adv Neural Inf Process Syst – volume: 39 start-page: 2481 year: 2017 end-page: 2495 ident: b12 article-title: SegNet: A deep convolutional encoder-decoder architecture for image segmentation publication-title: IEEE Trans Pattern Anal Mach Intell – reference: Silberman N, Hoiem D, Kohli P, Fergus R. Indoor segmentation and support inference from RGBD images. In: European conference on computer vision. 2012, p. 746–60. – start-page: 5410 year: 2018 end-page: 5418 ident: b22 article-title: Pyramid stereo matching network publication-title: Computer vision and pattern recognition – year: 2020 ident: b14 article-title: Superpixel segmentation with fully convolutional networks publication-title: Computer vision and pattern recognition – reference: Jampani V, Sun D, Liu M-Y, Yang M-H, Kautz J. Superpixel sampling networks. In: European conference on computer vision. 2018, p. 352–68. – volume: 33 start-page: 898 year: 2010 end-page: 916 ident: b17 article-title: Contour detection and hierarchical image segmentation publication-title: IEEE Trans Pattern Anal Mach Intell – reference: Wang Y, Wei Y, Qian X, Zhu L, Yang Y. AINet: association implantation for superpixel segmentation. In: IEEE/CVF international conference on computer vision. 2021, p. 7058–67. – volume: 64 start-page: 238 year: 2020 end-page: 251 ident: b6 article-title: Multi-scale spatial context-based semantic edge detection publication-title: Inf Fusion – start-page: 2947 year: 2015 end-page: 2955 ident: b8 article-title: Real-time coarse-to-fine topologically preserving segmentation publication-title: Computer vision and pattern recognition – start-page: 4040 year: 2016 end-page: 4048 ident: b23 article-title: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation publication-title: Computer vision and pattern recognition – start-page: 4651 year: 2017 end-page: 4660 ident: b3 article-title: Superpixels and polygons using simple non-iterative clustering publication-title: Computer vision and pattern recognition – start-page: 2097 year: 2011 end-page: 2104 ident: b9 article-title: Entropy rate superpixel segmentation publication-title: Computer vision and pattern recognition – volume: 31 start-page: 2081 year: 2022 end-page: 2093 ident: b7 article-title: Progressive feature learning for facade parsing with occlusions publication-title: IEEE Trans Image Process – year: 2020 ident: 10.1016/j.compeleceng.2023.108610_b14 article-title: Superpixel segmentation with fully convolutional networks – start-page: 2947 year: 2015 ident: 10.1016/j.compeleceng.2023.108610_b8 article-title: Real-time coarse-to-fine topologically preserving segmentation – ident: 10.1016/j.compeleceng.2023.108610_b13 doi: 10.1007/978-3-319-24574-4_28 – ident: 10.1016/j.compeleceng.2023.108610_b19 doi: 10.1007/978-3-319-46448-0_36 – start-page: 568 year: 2018 ident: 10.1016/j.compeleceng.2023.108610_b10 article-title: Learning superpixels with segmentation-aware affinity loss – volume: 39 start-page: 2481 issue: 12 year: 2017 ident: 10.1016/j.compeleceng.2023.108610_b12 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 – start-page: 4040 year: 2016 ident: 10.1016/j.compeleceng.2023.108610_b23 article-title: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation – ident: 10.1016/j.compeleceng.2023.108610_b18 doi: 10.1007/978-3-642-33715-4_54 – start-page: 4651 year: 2017 ident: 10.1016/j.compeleceng.2023.108610_b3 article-title: Superpixels and polygons using simple non-iterative clustering – ident: 10.1016/j.compeleceng.2023.108610_b11 doi: 10.1109/ICCV48922.2021.00699 – volume: 34 start-page: 2274 issue: 11 year: 2012 ident: 10.1016/j.compeleceng.2023.108610_b1 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2012.120 – volume: 166 start-page: 1 year: 2018 ident: 10.1016/j.compeleceng.2023.108610_b15 article-title: Superpixels: An evaluation of the state-of-the-art publication-title: Comput Vis Image Underst doi: 10.1016/j.cviu.2017.03.007 – volume: 31 start-page: 2081 year: 2022 ident: 10.1016/j.compeleceng.2023.108610_b7 article-title: Progressive feature learning for facade parsing with occlusions publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2022.3152004 – start-page: 13964 year: 2020 ident: 10.1016/j.compeleceng.2023.108610_b5 article-title: Superpixel segmentation with fully convolutional networks – start-page: 2097 year: 2011 ident: 10.1016/j.compeleceng.2023.108610_b9 article-title: Entropy rate superpixel segmentation – volume: 28 start-page: 424 year: 2015 ident: 10.1016/j.compeleceng.2023.108610_b20 article-title: 3d object proposals for accurate object class detection publication-title: Adv Neural Inf Process Syst – ident: 10.1016/j.compeleceng.2023.108610_b4 doi: 10.1007/978-3-030-01234-2_22 – start-page: 1356 year: 2015 ident: 10.1016/j.compeleceng.2023.108610_b2 article-title: Superpixel segmentation using linear spectral clustering – year: 2014 ident: 10.1016/j.compeleceng.2023.108610_b16 – volume: 33 start-page: 898 issue: 5 year: 2010 ident: 10.1016/j.compeleceng.2023.108610_b17 article-title: Contour detection and hierarchical image segmentation publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2010.161 – ident: 10.1016/j.compeleceng.2023.108610_b21 doi: 10.1109/ICCV.2015.238 – volume: 64 start-page: 238 year: 2020 ident: 10.1016/j.compeleceng.2023.108610_b6 article-title: Multi-scale spatial context-based semantic edge detection publication-title: Inf Fusion doi: 10.1016/j.inffus.2020.08.014 – start-page: 5410 year: 2018 ident: 10.1016/j.compeleceng.2023.108610_b22 article-title: Pyramid stereo matching network |
| SSID | ssj0004618 |
| Score | 2.3488088 |
| Snippet | Efficient and differentiable image over-segmentation is key to superpixel-based research and applications but remains a challenging problem. The paper proposes... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 108610 |
| SubjectTerms | Encoder–decoder architecture Image over-segmentation NAS encoder Non-iterative deep clustering Superpixel segmentation |
| Title | OverSegNet: A convolutional encoder–decoder network for image over-segmentation |
| URI | https://dx.doi.org/10.1016/j.compeleceng.2023.108610 |
| Volume | 107 |
| WOSCitedRecordID | wos000931799500001&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: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-0755 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004618 issn: 0045-7906 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1db9MwFL0aHULwgMbHxBhMRuINZVriJLanvVRoiE1QQAzRtyhOrqdOLFRrQXvcf9g_3C_h-qNNypg2kHiJWlfXdnJOnWvr3HsBXuKWqWh7rKNU14I2KFkaqczkUaJlrcpKG1O6QOF3YjCQw6H6GCKuJ66cgGgaeXqqxv8VamojsG3o7F_APe-UGugzgU5Xgp2uNwL-A834Mx4O0B_6OV15GJDgsHkrbc6QoHHgNbrvrxovB3eqw9GxFfJYbWc0wcPjEJ3UdP3YWTGIiaOOr6Xj4MY2v-Fc6zPyQuC25b3zWL_iqHvmkPCOVCWso6lNdLmVL6yjvnxtWAltBScvWL20SPvzgiP7jMd2gjT-ph1ls7VZTIz92wtrLiOcKdSOik5Xhe2q8F3dguVEZEr2YLm_tzvc70TMxv4dHe7jDrxolX9XzOvPnkvHGzlYgfthG8H6Hv4HsITNQ7jXSS75CD61RNhmfbZAAxZocHF2HgjAAgEYEYA5ArBLBHgMX97sHrx-G4UCGlHFk3ga1TozuhS8zmXFDcYYk7vCaQ-rRBwbmUmTcIG6xjxXcSYT-t3IMuWJVjxDI_gq9JrvDT4BVgqyr02NMs_TKkUlFGrBK8xSlRos10DOHk5RhezytsjJt-JakNYgmZuOfYqVmxjtzBAogq_ofcCCWHa9-dN_GXMd7rZ_hmfQm578wOdwu_o5HU1ONgLFfgGCcJNa |
| 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=OverSegNet%3A+A+convolutional+encoder%E2%80%93decoder+network+for+image+over-segmentation&rft.jtitle=Computers+%26+electrical+engineering&rft.au=Li%2C+Peng&rft.au=Ma%2C+Wei&rft.date=2023-04-01&rft.issn=0045-7906&rft.volume=107&rft.spage=108610&rft_id=info:doi/10.1016%2Fj.compeleceng.2023.108610&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_compeleceng_2023_108610 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0045-7906&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0045-7906&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0045-7906&client=summon |