{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:46:31Z","timestamp":1767339991004,"version":"3.38.0"},"reference-count":44,"publisher":"SAGE Publications","issue":"4-5","license":[{"start":{"date-parts":[[2017,6,8]],"date-time":"2017-06-08T00:00:00Z","timestamp":1496880000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2018,4]]},"abstract":"<jats:p> This paper explores and investigates deep convolutional neural network architectures to increase the efficiency and robustness of semantic segmentation tasks. The proposed solutions are based on up-convolutional networks. We introduce three different architectures in this work. The first architecture, called Part-Net, is designed to tackle the specific problem of human body part segmentation and to provide robustness to overfitting and body part occlusion. The second network, called Fast-Net, is a network specifically designed to provide the smallest computation load without losing representation power. Such an architecture is capable of being run on mobile GPUs. The last architecture, called M-Net, aims to maximize the robustness characteristics of deep semantic segmentation approaches through multiresolution fusion. The networks achieve state-of-the-art performance on the PASCAL Parts dataset and competitive results on the KITTI dataset for road and lane segmentation. Moreover, we introduce a new part segmentation dataset, the Freiburg City dataset, which is designed to bring semantic segmentation to highly realistic robotics scenarios. Additionally, we present results obtained with a ground robot and an unmanned aerial vehicle and a full system to explore the capabilities of human body part segmentation in the context of human\u2013robot interaction. <\/jats:p>","DOI":"10.1177\/0278364917710542","type":"journal-article","created":{"date-parts":[[2017,6,9]],"date-time":"2017-06-09T05:30:36Z","timestamp":1496986236000},"page":"472-491","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":21,"title":["Efficient and robust deep networks for semantic segmentation"],"prefix":"10.1177","volume":"37","author":[{"given":"Gabriel L","family":"Oliveira","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Freiburg, 79100 Freiburg, Germany"}]},{"given":"Claas","family":"Bollen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Freiburg, 79100 Freiburg, Germany"}]},{"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Freiburg, 79100 Freiburg, Germany"}]},{"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Freiburg, 79100 Freiburg, Germany"}]}],"member":"179","published-online":{"date-parts":[[2017,6,8]]},"reference":[{"key":"bibr1-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.13"},{"key":"bibr2-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_28"},{"journal-title":"arXiv","year":"2015","author":"Badrinarayanan V","key":"bibr3-0278364917710542"},{"key":"bibr4-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0449-8"},{"key":"bibr5-0278364917710542","doi-asserted-by":"publisher","DOI":"10.5220\/0005355105100517"},{"key":"bibr6-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.254"},{"key":"bibr7-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"bibr8-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"bibr9-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.84"},{"key":"bibr10-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728473"},{"journal-title":"arXiv","year":"2015","author":"Girshick R","key":"bibr11-0278364917710542"},{"key":"bibr12-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"bibr13-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659988"},{"key":"bibr14-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925974"},{"key":"bibr15-0278364917710542","unstructured":"Jain A, Tompson J, Andriluka M, et al. (2014) Learning human pose estimation features with convolutional networks. In: International conference on learning representations (ICLR), Banff, Canada, 14\u201316 April 2014. Available at: http:\/\/arxiv.org\/abs\/1312.7302"},{"journal-title":"arXiv","year":"2014","author":"Jia Y","key":"bibr16-0278364917710542"},{"key":"bibr17-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"bibr18-0278364917710542","doi-asserted-by":"publisher","DOI":"10.5220\/0005299304860490"},{"key":"bibr19-0278364917710542","first-page":"1097","volume-title":"Advances in neural information processing systems 25 (NIPS 2012)","author":"Krizhevsky A","year":"2012"},{"issue":"10","key":"bibr20-0278364917710542","first-page":"2024","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"38","author":"Liu F","year":"2015"},{"key":"bibr21-0278364917710542","first-page":"04579","volume":"1506","author":"Liu W","year":"2015","journal-title":"arXiv"},{"key":"bibr22-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"bibr23-0278364917710542","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.118"},{"key":"bibr24-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126490"},{"key":"bibr25-0278364917710542","first-page":"488","volume-title":"Neural Information Processing Systems","author":"Matan O","year":"1992"},{"key":"bibr26-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487486"},{"key":"bibr27-0278364917710542","first-page":"4101","volume":"1411","author":"Mohan R","year":"2014","journal-title":"arXiv"},{"key":"bibr28-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.852470"},{"key":"bibr29-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487304"},{"issue":"1","key":"bibr30-0278364917710542","first-page":"82","volume-title":"Proceedings of Machine Learning Research","volume":"32","author":"Pinheiro PHO","year":"2014"},{"key":"bibr31-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553479"},{"key":"bibr32-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"journal-title":"arXiv","year":"2016","author":"Schenck C","key":"bibr33-0278364917710542"},{"journal-title":"arXiv","year":"2014","author":"Sermanet P","key":"bibr34-0278364917710542"},{"key":"bibr35-0278364917710542","first-page":"91","volume-title":"Advances in neural information processing systems 28 (NIPS 2015)","author":"Shaoqing R","year":"2015"},{"key":"bibr36-0278364917710542","first-page":"162","volume-title":"Asian conference on computer vision","volume":"2","author":"Simon M","year":"2014"},{"journal-title":"arXiv","year":"2015","author":"Simonyan K","key":"bibr37-0278364917710542"},{"key":"bibr38-0278364917710542","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.022"},{"key":"bibr39-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"journal-title":"arXiv","year":"2015","author":"Tsogkas S","key":"bibr40-0278364917710542"},{"key":"bibr41-0278364917710542","first-page":"745","volume-title":"Proceedings of the 6th international conference on neural information processing systems","author":"Wolf R","year":"1993"},{"key":"bibr42-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"bibr43-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"bibr44-0278364917710542","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.212"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364917710542","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/0278364917710542","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0278364917710542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T18:41:56Z","timestamp":1740681716000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0278364917710542"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,8]]},"references-count":44,"journal-issue":{"issue":"4-5","published-print":{"date-parts":[[2018,4]]}},"alternative-id":["10.1177\/0278364917710542"],"URL":"https:\/\/doi.org\/10.1177\/0278364917710542","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"type":"print","value":"0278-3649"},{"type":"electronic","value":"1741-3176"}],"subject":[],"published":{"date-parts":[[2017,6,8]]}}}