{"date_created":"2023-08-22T14:09:13Z","month":"06","publication_status":"published","oa":1,"abstract":[{"lang":"eng","text":"Learning meaningful and compact representations with disentangled semantic\r\naspects is considered to be of key importance in representation learning. Since\r\nreal-world data is notoriously costly to collect, many recent state-of-the-art\r\ndisentanglement models have heavily relied on synthetic toy data-sets. In this\r\npaper, we propose a novel data-set which consists of over one million images of\r\nphysical 3D objects with seven factors of variation, such as object color,\r\nshape, size and position. In order to be able to control all the factors of\r\nvariation precisely, we built an experimental platform where the objects are\r\nbeing moved by a robotic arm. In addition, we provide two more datasets which\r\nconsist of simulations of the experimental setup. These datasets provide for\r\nthe first time the possibility to systematically investigate how well different\r\ndisentanglement methods perform on real data in comparison to simulation, and\r\nhow simulated data can be leveraged to build better representations of the real\r\nworld. We provide a first experimental study of these questions and our results\r\nindicate that learned models transfer poorly, but that model and hyperparameter\r\nselection is an effective means of transferring information to the real world."}],"year":"2019","external_id":{"arxiv":["1906.03292"]},"day":"07","publication":"Advances in Neural Information Processing Systems","language":[{"iso":"eng"}],"author":[{"last_name":"Gondal","first_name":"Muhammad Waleed","full_name":"Gondal, Muhammad Waleed"},{"first_name":"Manuel","last_name":"Wüthrich","full_name":"Wüthrich, Manuel"},{"full_name":"Miladinović, Đorđe","first_name":"Đorđe","last_name":"Miladinović"},{"orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco"},{"last_name":"Breidt","first_name":"Martin","full_name":"Breidt, Martin"},{"last_name":"Volchkov","first_name":"Valentin","full_name":"Volchkov, Valentin"},{"first_name":"Joel","last_name":"Akpo","full_name":"Akpo, Joel"},{"full_name":"Bachem, Olivier","last_name":"Bachem","first_name":"Olivier"},{"last_name":"Schölkopf","first_name":"Bernhard","full_name":"Schölkopf, Bernhard"},{"full_name":"Bauer, Stefan","first_name":"Stefan","last_name":"Bauer"}],"main_file_link":[{"url":"https://arxiv.org/abs/1906.03292","open_access":"1"}],"article_processing_charge":"No","citation":{"short":"M.W. Gondal, M. Wüthrich, Đ. Miladinović, F. Locatello, M. Breidt, V. Volchkov, J. Akpo, O. Bachem, B. Schölkopf, S. Bauer, in:, Advances in Neural Information Processing Systems, 2019.","chicago":"Gondal, Muhammad Waleed, Manuel Wüthrich, Đorđe Miladinović, Francesco Locatello, Martin Breidt, Valentin Volchkov, Joel Akpo, Olivier Bachem, Bernhard Schölkopf, and Stefan Bauer. “On the Transfer of Inductive Bias from Simulation to the Real World: A New Disentanglement Dataset.” In <i>Advances in Neural Information Processing Systems</i>, Vol. 32, 2019.","apa":"Gondal, M. W., Wüthrich, M., Miladinović, Đ., Locatello, F., Breidt, M., Volchkov, V., … Bauer, S. (2019). On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. In <i>Advances in Neural Information Processing Systems</i> (Vol. 32). Vancouver, Canada.","ama":"Gondal MW, Wüthrich M, Miladinović Đ, et al. On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. In: <i>Advances in Neural Information Processing Systems</i>. Vol 32. ; 2019.","ieee":"M. W. Gondal <i>et al.</i>, “On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset,” in <i>Advances in Neural Information Processing Systems</i>, Vancouver, Canada, 2019, vol. 32.","ista":"Gondal MW, Wüthrich M, Miladinović Đ, Locatello F, Breidt M, Volchkov V, Akpo J, Bachem O, Schölkopf B, Bauer S. 2019. On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset. Advances in Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems vol. 32.","mla":"Gondal, Muhammad Waleed, et al. “On the Transfer of Inductive Bias from Simulation to the Real World: A New Disentanglement Dataset.” <i>Advances in Neural Information Processing Systems</i>, vol. 32, 2019."},"title":"On the transfer of inductive bias from simulation to the real world: a new disentanglement dataset","intvolume":"        32","publication_identifier":{"isbn":["9781713807933"]},"oa_version":"Preprint","department":[{"_id":"FrLo"}],"user_id":"c635000d-4b10-11ee-a964-aac5a93f6ac1","type":"conference","date_updated":"2023-09-13T09:46:38Z","quality_controlled":"1","conference":{"start_date":"2019-12-08","name":"NeurIPS: Neural Information Processing Systems","location":"Vancouver, Canada","end_date":"2019-12-14"},"date_published":"2019-06-07T00:00:00Z","status":"public","volume":32,"extern":"1","_id":"14190"}