{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T01:45:44Z","timestamp":1648950344556},"reference-count":37,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2020,6,1]]},"DOI":"10.1587\/transinf.2019mvp0016","type":"journal-article","created":{"date-parts":[[2020,5,31]],"date-time":"2020-05-31T22:10:02Z","timestamp":1590963002000},"page":"1247-1256","source":"Crossref","is-referenced-by-count":0,"title":["Instance Segmentation by Semi-Supervised Learning and Image Synthesis"],"prefix":"10.1587","volume":"E103.D","author":[{"given":"Takeru","family":"OBA","sequence":"first","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norimichi","family":"UKITA","sequence":"additional","affiliation":[{"name":"Toyota Technological Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] J. Tremblay, A. Prakash, D. Acuna, M. Brophy, V. Jampani, C. Anil, T. To, E. Cameracci, S. Boochoon, and S. Birchfield, \u201cTraining deep networks with synthetic data: Bridging the reality gap by domain randomization,\u201d CVPR Workshops, pp.969-977, 2018. 10.1109\/cvprw.2018.00143","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] C. Rosenberg, M. Hebert, and H. Schneiderman, \u201cSemi-supervised self-training of object detection models,\u201d WACV\/MOTION, pp.29-36, 2005. 10.1109\/acvmot.2005.107","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] S. Vijayanarasimhan and K. Grauman, \u201cLarge-scale live active learning: Training object detectors with crawled data and crowds,\u201d IJCV, vol.108, no.1-2, pp.97-114, 2014. 10.1007\/s11263-014-0721-9","DOI":"10.1007\/s11263-014-0721-9"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] X. Chen, A. Shrivastava, and A. Gupta, \u201cNeil: Extracting visual knowledge from web data,\u201d ICCV, pp.1409-1416, 2013. 10.1109\/iccv.2013.178","DOI":"10.1109\/ICCV.2013.178"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] X. Chen and A. Gupta, \u201cWebly supervised learning of convolutional networks,\u201d ICCV, pp.1431-1439, 2015. 10.1109\/iccv.2015.168","DOI":"10.1109\/ICCV.2015.168"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] J. Long, E. Shelhamer, and T. Darrell, \u201cFully convolutional networks for semantic segmentation,\u201d CVPR, pp.3431-3440, 2015. 10.1109\/cvpr.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] O. Ronneberger, P. Fischer, and T. Brox, \u201cU-net: Convolutional networks for biomedical image segmentation,\u201d MICCAI, pp.234-241, 2015. 10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"8","unstructured":"[8] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster r-cnn: Towards real-time object detection with region proposal networks,\u201d NIPS, pp.91-99, 2015."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A.C. Berg, \u201cSsd: Single shot multibox detector,\u201d ECCV, pp.21-37, 2016. 10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, \u201cYou only look once: Unified, real-time object detection,\u201d CVPR, pp.779-788, 2016. 10.1109\/cvpr.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"11","unstructured":"[11] J. Redmon and A. Farhadi, \u201cYOLO9000: better, faster, stronger,\u201d CVPR, pp.6517-6525."},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] J. Dai, K. He, and J. Sun, \u201cInstance-aware semantic segmentation via multi-task network cascades,\u201d CVPR, pp.3150-3158, 2016. 10.1109\/cvpr.2016.343","DOI":"10.1109\/CVPR.2016.343"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Y. Li, H. Qi, J. Dai, X. Ji, and Y. Wei, \u201cFully convolutional instance-aware semantic segmentation,\u201d CVPR, pp.2359-2367, 2017. 10.1109\/cvpr.2017.472","DOI":"10.1109\/CVPR.2017.472"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] K. He, G. Gkioxari, P. Doll\u00e1r, and R. Girshick, \u201cMask r-cnn,\u201d ICCV, pp.2961-2969, 2017. 10.1109\/iccv.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] A. Kirillov, E. Levinkov, B. Andres, B. Savchynskyy, and C. Rother, \u201cInstancecut: from edges to instances with multicut,\u201d CVPR, pp.5008-5017, 2017. 10.1109\/cvpr.2017.774","DOI":"10.1109\/CVPR.2017.774"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] D. Novotny, S. Albanie, D. Larlus, and A. Vedaldi, \u201cSemi-convolutional operators for instance segmentation,\u201d ECCV, pp.86-102, 2018.","DOI":"10.1007\/978-3-030-01246-5_6"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] K. Bousmalis, N. Silberman, D. Dohan, D. Erhan, and D. Krishnan, \u201cUnsupervised pixel-level domain adaptation with generative adversarial networks,\u201d CVPR, pp.3722-3731, 2017. 10.1109\/cvpr.2017.18","DOI":"10.1109\/CVPR.2017.18"},{"key":"18","unstructured":"[18] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, \u201cGenerative adversarial nets,\u201d NIPS, pp.2672-2680, 2014."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Z. Ren and Y. Jae Lee, \u201cCross-domain self-supervised multi-task feature learning using synthetic imagery,\u201d CVPR, pp.762-771, 2018. 10.1109\/cvpr.2018.00086","DOI":"10.1109\/CVPR.2018.00086"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] J. Tobin, R. Fong, A. Ray, J. Schneider, W. Zaremba, and P. Abbeel, \u201cDomain randomization for transferring deep neural networks from simulation to the real world,\u201d IROS, pp.23-30, 2017. 10.1109\/iros.2017.8202133","DOI":"10.1109\/IROS.2017.8202133"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] D. Dwibedi, I. Misra, and M. Hebert, \u201cCut, paste and learn: Surprisingly easy synthesis for instance detection,\u201d ICCV, pp.1301-1310, 2017. 10.1109\/iccv.2017.146","DOI":"10.1109\/ICCV.2017.146"},{"key":"22","unstructured":"[22] X. Zhu, \u201cSemi-supervised learning literature survey,\u201d Computer Science, University of Wisconsin-Madison, 2006."},{"key":"23","unstructured":"[23] W. Hung, Y. Tsai, Y. Liou, Y. Lin, and M. Yang, \u201cAdversarial learning for semi-supervised semantic segmentation,\u201d BMVC, p.65, 2018."},{"key":"24","unstructured":"[24] Y.T. Hu, J.B. Huang, and A. Schwing, \u201cMaskrnn: Instance level video object segmentation,\u201d NIPS, pp.325-334, 2017."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] X. Zhao, S. Liang, and Y. Wei, \u201cPseudo mask augmented object detection,\u201d CVPR, pp.4061-4070, 2018. 10.1109\/cvpr.2018.00427","DOI":"10.1109\/CVPR.2018.00427"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] Y. Boykov and V. Kolmogorov, \u201cAn experimental comparison of min-cut\/max-flow algorithms for energy minimization in vision,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.26, no.9, pp.1124-1137, 2004. 10.1109\/tpami.2004.60","DOI":"10.1109\/TPAMI.2004.60"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] J. Ahn, S. Cho, and S. Kwak, \u201cWeakly supervised learning of instance segmentation with inter-pixel relations,\u201d CVPR, June 2019. 10.1109\/cvpr.2019.00231","DOI":"10.1109\/CVPR.2019.00231"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] Y. Zhou, Y. Zhu, Q. Ye, Q. Qiu, and J. Jiao, \u201cWeakly supervised instance segmentation using class peak response,\u201d CVPR, pp.3791-3800, 2018. 10.1109\/cvpr.2018.00399","DOI":"10.1109\/CVPR.2018.00399"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] X. Zhang, Y. Wei, G. Kang, Y. Yang, and T. Huang, \u201cSelf-produced guidance for weakly-supervised object localization,\u201d ECCV, pp.597-613, 2018.","DOI":"10.1007\/978-3-030-01258-8_37"},{"key":"30","unstructured":"[30] AUTODESK, \u201cRecap.\u201d https:\/\/www.autodesk.co.jp\/products\/recap\/overview."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll\u00e1r, and C.L. Zitnick, \u201cMicrosoft coco: Common objects in context,\u201d ECCV, pp.740-755, 2014. 10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] C. Zhou and R.C. Paffenroth, \u201cAnomaly detection with robust deep autoencoders,\u201d SIGKDD, pp.665-674, 2017. 10.1145\/3097983.3098052","DOI":"10.1145\/3097983.3098052"},{"key":"33","unstructured":"[33] B. Zhou, A. Lapedriza, A. Khosla, A. Oliva, and A. Torralba, \u201cPlaces: A 10 million image database for scene recognition,\u201d PAMI, vol.40, no.6, pp.1452-1464, 2017."},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, and A. Vedaldi, \u201cDescribing textures in the wild,\u201d CVPR, pp.3606-3613, 2014. 10.1109\/cvpr.2014.461","DOI":"10.1109\/CVPR.2014.461"},{"key":"35","unstructured":"[35] W. Abdulla, \u201cMask r-cnn for object detection and instance segmentation on keras and tensorflow,\u201d 2017. https:\/\/github.com\/matterport\/Mask_RCNN."},{"key":"36","unstructured":"[36] \u201cGoogle images download.\u201d https:\/\/github.com\/hardikvasa\/google-images-download."},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] X. Guo, X. Liu, E. Zhu, and J. Yin, \u201cDeep clustering with convolutional autoencoders,\u201d NIPS, pp.373-382, 2017.","DOI":"10.1007\/978-3-319-70096-0_39"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0016\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,6]],"date-time":"2020-06-06T03:28:28Z","timestamp":1591414108000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/6\/E103.D_2019MVP0016\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,1]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019mvp0016","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,1]]}}}