GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on si...
Saved in:
| Published in | IEEE transactions on visualization and computer graphics Vol. 25; no. 1; pp. 310 - 320 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.01.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In this work, we present GAN Lab, the first interactive visualization tool designed for non-experts to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, users can interactively train generative models and visualize the dynamic training process's intermediate results. GAN Lab tightly integrates an model overview graph that summarizes GAN's structure, and a layered distributions view that helps users interpret the interplay between submodels. GAN Lab introduces new interactive experimentation features for learning complex deep learning models, such as step-by-step training at multiple levels of abstraction for understanding intricate training dynamics. Implemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web browsers, without the need for installation or specialized hardware, overcoming a major practical challenge in deploying interactive tools for deep learning. |
|---|---|
| AbstractList | Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In this work, we present GAN Lab, the first interactive visualization tool designed for non-experts to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, users can interactively train generative models and visualize the dynamic training process's intermediate results. GAN Lab tightly integrates an model overview graph that summarizes GAN's structure, and a layered distributions view that helps users interpret the interplay between submodels. GAN Lab introduces new interactive experimentation features for learning complex deep learning models, such as step-by-step training at multiple levels of abstraction for understanding intricate training dynamics. Implemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web browsers, without the need for installation or specialized hardware, overcoming a major practical challenge in deploying interactive tools for deep learning. Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In this work, we present GAN Lab, the first interactive visualization tool designed for non-experts to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, users can interactively train generative models and visualize the dynamic training process's intermediate results. GAN Lab tightly integrates an model overview graph that summarizes GAN's structure, and a layered distributions view that helps users interpret the interplay between submodels. GAN Lab introduces new interactive experimentation features for learning complex deep learning models, such as step-by-step training at multiple levels of abstraction for understanding intricate training dynamics. Implemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web browsers, without the need for installation or specialized hardware, overcoming a major practical challenge in deploying interactive tools for deep learning.Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In this work, we present GAN Lab, the first interactive visualization tool designed for non-experts to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, users can interactively train generative models and visualize the dynamic training process's intermediate results. GAN Lab tightly integrates an model overview graph that summarizes GAN's structure, and a layered distributions view that helps users interpret the interplay between submodels. GAN Lab introduces new interactive experimentation features for learning complex deep learning models, such as step-by-step training at multiple levels of abstraction for understanding intricate training dynamics. Implemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web browsers, without the need for installation or specialized hardware, overcoming a major practical challenge in deploying interactive tools for deep learning. |
| Author | Kahng, Minsuk Wattenberg, Martin Thorat, Nikhil Chau, Duen Horng Viegas, Fernanda B. |
| Author_xml | – sequence: 1 givenname: Minsuk surname: Kahng fullname: Kahng, Minsuk email: kahng@gatech.edu organization: Georgia Inst. of Technol., Atlanta, GA, USA – sequence: 2 givenname: Nikhil surname: Thorat fullname: Thorat, Nikhil email: nsthoratwattenberg@google.com organization: Google Brain, Mountain View, CA, USA – sequence: 3 givenname: Duen Horng surname: Chau fullname: Chau, Duen Horng email: polo@gatech.edu organization: Georgia Inst. of Technol., Atlanta, GA, USA – sequence: 4 givenname: Fernanda B. surname: Viegas fullname: Viegas, Fernanda B. email: viegas@google.com organization: Google Brain, Mountain View, CA, USA – sequence: 5 givenname: Martin surname: Wattenberg fullname: Wattenberg, Martin email: wattenberg@google.com organization: Google Brain, Mountain View, CA, USA |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30130198$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kU9P3DAQxS0E4l_7AapKVSQuXLIdO3Zi94YWWJCW9gIcazn2bBWUdVI7QfDtcdiFAwckS2N5fu_JM--I7PrOIyHfKMwoBfXz9n6-mDGgcsZkyQXADjmkitMcBJS76Q5VlbOSlQfkKMYHAMq5VPvkoACajpKH5O_i7He2NPWv7M47DHEw3jX-Xzbv1n2LT9k5Yp8t0GMwQ_OI2U3nsI3ZGCfo2g_p3b427ps4mja7eOoxNGv0Q-I7_4XsrUwb8eu2HpO7y4vb-VW-_LO4np8tc1soNuTCKOuwrqVQBgtVWSWkQ2erqkYBljMHrhCF5FRWrsSVow4MmLoCLleCu-KYnG58-9D9HzEOet1Ei21rPHZj1AwUlYwBsISefEAfujH49DvNqOBpdVJN1I8tNdZrdLpPQ5nwrN82l4BqA9jQxRhwpW2zmXkIpmk1BT1lpKeM9JSR3maUlPSD8s38M833jaZBxHdecg7AVfECW2ebxg |
| CODEN | ITVGEA |
| CitedBy_id | crossref_primary_10_1016_j_visinf_2018_09_001 crossref_primary_10_1109_TVCG_2024_3456142 crossref_primary_10_1016_j_compag_2021_106183 crossref_primary_10_1109_TII_2020_3046036 crossref_primary_10_1145_3672276 crossref_primary_10_1109_TVCG_2020_3030449 crossref_primary_10_1111_cgf_14418 crossref_primary_10_1177_14738716231216030 crossref_primary_10_1088_1742_6596_1952_3_032031 crossref_primary_10_1109_MCI_2024_3487134 crossref_primary_10_1109_TVCG_2023_3243676 crossref_primary_10_1109_TVCG_2019_2934261 crossref_primary_10_1109_TVCG_2021_3076749 crossref_primary_10_1109_TVCG_2024_3357065 crossref_primary_10_1016_j_inpa_2023_11_002 crossref_primary_10_1016_j_cag_2019_03_009 crossref_primary_10_1109_JAS_2024_124221 crossref_primary_10_1109_TVCG_2022_3146806 crossref_primary_10_1016_j_visinf_2024_10_004 crossref_primary_10_1016_j_visinf_2024_10_002 crossref_primary_10_1007_s11042_024_18665_3 crossref_primary_10_1109_TKDE_2021_3130191 crossref_primary_10_1109_TVCG_2024_3388557 crossref_primary_10_3390_fi16110406 crossref_primary_10_1109_TVCG_2023_3326577 crossref_primary_10_1109_TVCG_2022_3209462 crossref_primary_10_1007_s10489_022_04278_6 crossref_primary_10_1109_TVCG_2019_2934631 crossref_primary_10_1109_TVCG_2022_3148107 crossref_primary_10_1109_TVCG_2019_2934591 crossref_primary_10_1109_TVCG_2020_3030418 crossref_primary_10_1109_TVCG_2021_3057483 crossref_primary_10_4018_IJWLTT_333601 crossref_primary_10_1007_s41095_020_0191_7 crossref_primary_10_3390_s21072514 crossref_primary_10_1109_TVCG_2020_3030384 crossref_primary_10_1109_TVCG_2020_3030461 crossref_primary_10_1111_cgf_14034 crossref_primary_10_1007_s11704_024_3735_7 crossref_primary_10_1109_TVCG_2023_3285210 crossref_primary_10_1109_TVCG_2023_3326921 crossref_primary_10_1016_j_visinf_2022_01_001 crossref_primary_10_1109_TVCG_2020_2969185 crossref_primary_10_1016_j_cag_2024_104058 crossref_primary_10_2478_amns_2020_2_00072 crossref_primary_10_35940_ijitee_F8804_0410621 crossref_primary_10_2139_ssrn_4172218 crossref_primary_10_1002_ail2_36 crossref_primary_10_1109_TVCG_2019_2903943 crossref_primary_10_1080_01969722_2021_1982160 crossref_primary_10_1080_15481603_2022_2163048 crossref_primary_10_1007_s12650_020_00704_4 crossref_primary_10_1109_TVCG_2023_3326591 crossref_primary_10_1515_itit_2022_0034 crossref_primary_10_1016_j_neunet_2019_04_024 crossref_primary_10_1109_TVCG_2019_2934659 crossref_primary_10_1109_ACCESS_2021_3133762 crossref_primary_10_3390_electronics12122563 crossref_primary_10_1145_3458928 crossref_primary_10_1109_TVCG_2020_3012063 crossref_primary_10_1111_cgf_14524 crossref_primary_10_1007_s10639_023_12349_5 crossref_primary_10_1111_cgf_14329 crossref_primary_10_1109_TVCG_2023_3339585 crossref_primary_10_1007_s10462_020_09825_6 crossref_primary_10_1109_TVCG_2020_3028888 crossref_primary_10_1109_TVCG_2022_3219248 crossref_primary_10_1080_01969722_2022_2137640 crossref_primary_10_1109_TASE_2020_2998467 crossref_primary_10_2196_27414 |
| Cites_doi | 10.23915/distill.00002 10.1109/TVCG.2018.2816223 10.1109/TVCG.2017.2744358 10.1109/TVCG.2017.2744158 10.1145/2445196.2445368 10.1109/TVCG.2016.2640960 10.1145/1227504.1227384 10.1006/jvlc.2002.0237 10.23915/distill.00006 10.1109/TVCG.2017.2744683 10.1016/j.visinf.2017.01.006 10.1109/TVCG.2017.2744938 10.1109/TVCG.2010.177 10.1109/TVCG.2017.2744718 10.1145/971300.971432 10.1145/1821996.1821997 10.1016/j.jvlc.2006.03.002 10.1109/MSP.2017.2765202 10.1109/TVCG.2017.2744878 10.1109/TVCG.2008.119 10.1109/18.61115 10.1145/1067445.1067495 10.1109/TVCG.2016.2598831 10.23915/distill.00009 10.1109/CVPR.2015.7298935 10.1109/ICCV.2017.304 10.23915/distill.00005 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TVCG.2018.2864500 |
| DatabaseName | IEEE Xplore (IEEE) IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) 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 | Technology Research Database PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?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://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1941-0506 |
| EndPage | 320 |
| ExternalDocumentID | 30130198 10_1109_TVCG_2018_2864500 8440049 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: NSF grantid: IIS-1563816; CNS-1704701; TWC-1526254 |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL F5P HZ~ H~9 IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNI RNS RZB TN5 VH1 AAYOK AAYXX CITATION RIG NPM RIC Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c392t-5a9cdebb859ae397c958dedc77be50c42d0d35384187d6efd1d0a0ab7048f54d3 |
| IEDL.DBID | RIE |
| ISSN | 1077-2626 1941-0506 |
| IngestDate | Fri Jul 11 13:22:38 EDT 2025 Mon Jun 30 04:44:09 EDT 2025 Wed Feb 19 02:09:30 EST 2025 Tue Jul 01 03:58:53 EDT 2025 Thu Apr 24 23:12:14 EDT 2025 Wed Aug 27 05:50:30 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/OAPA.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c392t-5a9cdebb859ae397c958dedc77be50c42d0d35384187d6efd1d0a0ab7048f54d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/8440049 |
| PMID | 30130198 |
| PQID | 2154050892 |
| PQPubID | 75741 |
| PageCount | 11 |
| ParticipantIDs | crossref_citationtrail_10_1109_TVCG_2018_2864500 proquest_miscellaneous_2091822002 proquest_journals_2154050892 pubmed_primary_30130198 crossref_primary_10_1109_TVCG_2018_2864500 ieee_primary_8440049 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2019-01-01 |
| PublicationDateYYYYMMDD | 2019-01-01 |
| PublicationDate_xml | – month: 01 year: 2019 text: 2019-01-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: New York |
| PublicationTitle | IEEE transactions on visualization and computer graphics |
| PublicationTitleAbbrev | TVCG |
| PublicationTitleAlternate | IEEE Trans Vis Comput Graph |
| PublicationYear | 2019 |
| 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 | victor (ref39) 0 ref35 ref34 olah (ref28) 0 ref37 ref15 ref14 ref30 ref33 yosinski (ref44) 2015 ref10 ref2 karpathy (ref17) 0 carter (ref5) 2017 rosenberg (ref31) 0 ref16 ref19 abadi (ref1) 2016 liu (ref24) 2010; 16 hohman (ref13) 2018 goh (ref7) 2017 smilkov (ref36) 2016 harley (ref11) 2015 goodfellow (ref8) 2016 salimans (ref32) 2016 hindupur (ref12) 0 ref23 lecun (ref18) 0 ref25 theis (ref38) 2016 ref20 ref41 ref22 ref21 ref43 wattenberg (ref42) 2016 ming (ref27) 2017 ref4 ref3 ref6 goodfellow (ref9) 2014 ref40 olah (ref29) 2017 metz (ref26) 2017 |
| References_xml | – year: 2016 ident: ref42 article-title: How to use t-SNE effectively publication-title: Distillation doi: 10.23915/distill.00002 – ident: ref41 doi: 10.1109/TVCG.2018.2816223 – year: 0 ident: ref12 publication-title: The GAN Zoo A list of all named GANs! – year: 2015 ident: ref44 article-title: Understanding neural networks through deep visualization publication-title: Deep Learning Workshop International Conference on Machine Learning (ICML) – year: 0 ident: ref31 publication-title: Machine learning crash course – start-page: 2672 year: 2014 ident: ref9 article-title: Generative adversarial nets publication-title: Advances in Neural Information Processing Systems (NIPS) – ident: ref30 doi: 10.1109/TVCG.2017.2744358 – ident: ref37 doi: 10.1109/TVCG.2017.2744158 – ident: ref10 doi: 10.1145/2445196.2445368 – year: 0 ident: ref17 publication-title: ConvNetJS MNIST demo – year: 0 ident: ref28 publication-title: Neural networks manifolds and topology – ident: ref22 doi: 10.1109/TVCG.2016.2640960 – year: 2016 ident: ref36 article-title: Direct-manipulation visualization of deep networks publication-title: Workshop on Visualization for Deep Learning at the 33rd International Conference on Machine Learning (ICML) – year: 2018 ident: ref13 article-title: Visual analytics in deep learning: An interrogative survey for the next frontiers publication-title: IEEE Transactions on Visualization and Computer Graphics – ident: ref34 doi: 10.1145/1227504.1227384 – ident: ref15 doi: 10.1006/jvlc.2002.0237 – year: 2017 ident: ref7 article-title: Why momentum really works publication-title: Distillation doi: 10.23915/distill.00006 – start-page: 2234 year: 2016 ident: ref32 article-title: Improved techniques for training GANs publication-title: Advances in Neural Information Processing Systems (NIPS) – ident: ref4 doi: 10.1109/TVCG.2017.2744683 – ident: ref23 doi: 10.1016/j.visinf.2017.01.006 – ident: ref20 doi: 10.1109/TVCG.2017.2744938 – volume: 16 start-page: 999 year: 2010 ident: ref24 article-title: Mental models, visual reasoning and interaction in information visualization: A top-down perspective publication-title: IEEE Transactions on Visualization and Computer Graphics doi: 10.1109/TVCG.2010.177 – year: 2016 ident: ref1 publication-title: Tensorflow Large-scale machine learning on heterogeneous distributed systems – ident: ref16 doi: 10.1109/TVCG.2017.2744718 – year: 2017 ident: ref27 article-title: Understanding hidden memories of recurrent neural networks publication-title: IEEE Visual Analytics in Science and Technology – year: 2017 ident: ref26 article-title: Unrolled generative adversarial networks publication-title: International Conference on Learning Representations (ICLR) – ident: ref33 doi: 10.1145/971300.971432 – ident: ref35 doi: 10.1145/1821996.1821997 – ident: ref14 doi: 10.1016/j.jvlc.2006.03.002 – year: 0 ident: ref39 publication-title: Explorable explanations – ident: ref6 doi: 10.1109/MSP.2017.2765202 – ident: ref43 doi: 10.1109/TVCG.2017.2744878 – ident: ref3 doi: 10.1109/TVCG.2008.119 – ident: ref19 doi: 10.1109/18.61115 – ident: ref2 doi: 10.1145/1067445.1067495 – year: 2016 ident: ref38 article-title: A note on the evaluation of generative models publication-title: International Conference on Learning Representations (ICLR) – year: 0 ident: ref18 publication-title: Answer to "what are some recent and potentially upcoming breakthroughs in deep learning?" – ident: ref21 doi: 10.1109/TVCG.2016.2598831 – start-page: 867 year: 2015 ident: ref11 article-title: An interactive node-link visualization of convolutional neural networks publication-title: Proceedings of the 11 th International Symposium on Visual Computing – year: 2017 ident: ref5 article-title: Using artificial intelligence to augment human intelligence publication-title: Distillation doi: 10.23915/distill.00009 – ident: ref40 doi: 10.1109/CVPR.2015.7298935 – year: 2016 ident: ref8 publication-title: Nips 2016 tutorial Generative adversarial networks – ident: ref25 doi: 10.1109/ICCV.2017.304 – year: 2017 ident: ref29 article-title: Research debt publication-title: Distillation doi: 10.23915/distill.00005 |
| SSID | ssj0014489 |
| Score | 2.5792468 |
| Snippet | Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 310 |
| SubjectTerms | Data visualization Deep learning Experimentation explorable explanations Gallium nitride Generative adversarial networks Generators information visualization interactive experimentation Machine learning New technology Training visual analytics |
| Title | GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation |
| URI | https://ieeexplore.ieee.org/document/8440049 https://www.ncbi.nlm.nih.gov/pubmed/30130198 https://www.proquest.com/docview/2154050892 https://www.proquest.com/docview/2091822002 |
| Volume | 25 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB4BJ3poefSx5SFX6gk1izdrJzY3xFOocGIRp0aOPamqrnZRdyNV_fWdcbKBooK4RYoTO5nx-Js3wGer9CB3Mk-8MVmiKuMSY7VPZLCZTZ3KleYE58ur7HykLm717RJ86XJhEDEGn2GfL6MvP0x9zaayfaOY4-wyLJPi1uRqdR4DUjNsE1-YJymh9NaDOZB2__rm6IyDuEw_NZnSkru_DdljRwr3P8dR7K_yNNSMR87pG7hcLLaJNPnZr-dl3_95VMfxpV-zBq9b7CkOG2ZZhyWcbMCrBxUJN-Hb2eGV-OrKAzF6mPUiWGyM8bc4RrwTTalqlpOCW6mNZ4Kj57-LaF10UYCKmx-zmuY6uW8gwBzwFkanJ9dH50nbgiHxBJzmiXbWByxLo61Dgi7eahMw-DwvUUuv0iDDkGSmGpg8ZFiFQZBOujInwVBpFYbvYGUyneAHEJkN3NcedVU6lclgbDWUqiLMFUslpz2QC0oUvq1Pzm0yxkXUU6QtmI4F07Fo6diDve6Ru6Y4x3ODN5kG3cD29_dge0Huot2-s4JwEAFZaSyt6lN3mzYee1PcBKc1jSGkReiKTpQevG_YpHv3grs-_n_OLVilldnGkrMNK_NfNe4QtpmXu5Gp_wLD3PE3 |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3db9MwED-N8QA8MMYYdBtgJJ4Q6ZzUTuy9TWNbt7V9aqc9ETm2M01U7UQbCfHX785Js4EA8RYpTuzkzne_830BfNRCxpnhWWSVSiNRKhMpLW3EnU51YkQmJCU4D0dpfyLOr-TVGnxuc2G89yH4zHfpMvjy3dxWdFS2rwRxnH4Ej1Hvy7jO1mp9Bmho6DrCMIsSxOmNDzPmen98eXRKYVyqm6hUSE7933rks0OT-xeFFDqs_B1sBqVzsgHD1XLrWJNv3WpZdO3P3yo5_u_3vIDnDfpkhzW7bMKan72EZw9qEm7B19PDERuY4oBNHua9MBIcU_-DffH-ltXFqklSMmqmNl0wip-_ZuF80QQRyi5vFhXOdXzfQoB44BVMTo7HR_2oacIQWYROy0gabZ0vCiW18QherJbKeWezrPCSW5E47nooNUWsMpf60sWOG26KDEVDKYXrbcP6bD7zb4Cl2lFney_LwoiUO6XLHhcloq5QLDnpAF9RIrdNhXJqlDHNg6XCdU50zImOeUPHDnxqH7mty3P8a_AW0aAd2Pz-DuytyJ03G3iRIxJCKMuVxlV9aG_j1iN_ipn5eYVjEGshvkKd0oHXNZu0715x186f53wPT_rj4SAfnI0uduEprlLX5zp7sL78Xvm3iHSWxbvA4HeAUPSA |
| 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=GAN+Lab%3A+Understanding+Complex+Deep+Generative+Models+using+Interactive+Visual+Experimentation&rft.jtitle=IEEE+transactions+on+visualization+and+computer+graphics&rft.au=Kahng%2C+Minsuk&rft.au=Thorat%2C+Nikhil&rft.au=Chau%2C+Duen+Horng+Polo&rft.au=Viegas%2C+Fernanda+B.&rft.date=2019-01-01&rft.issn=1077-2626&rft.eissn=1941-0506&rft.volume=25&rft.issue=1&rft.spage=310&rft.epage=320&rft_id=info:doi/10.1109%2FTVCG.2018.2864500&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TVCG_2018_2864500 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-2626&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-2626&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-2626&client=summon |