Show simple item record

dc.contributor.authorVondrick, Carl
dc.contributor.authorPirsiavash, Hamed
dc.contributor.authorOliva, Aude
dc.contributor.authorTorralba, Antonio
dc.descriptionAdvances in Neural Information Processing Systems 28 (NIPS 2015).en_US
dc.description.abstractAlthough the human visual system can recognize many concepts under challengingconditions, it still has some biases. In this paper, we investigate whether wecan extract these biases and transfer them into a machine recognition system.We introduce a novel method that, inspired by well-known tools in humanpsychophysics, estimates the biases that the human visual system might use forrecognition, but in computer vision feature spaces. Our experiments aresurprising, and suggest that classifiers from the human visual system can betransferred into a machine with some success. Since these classifiers seem tocapture favorable biases in the human visual system, we further present an SVMformulation that constrains the orientation of the SVM hyperplane to agree withthe bias from human visual system. Our results suggest that transferring thishuman bias into machines may help object recognition systems generalize acrossdatasets and perform better when very little training data is available.en_US
dc.description.sponsorshipFunding for this research was partially supported by a Google PhD Fellowship to CV, and a Google research award and ONR MURI N000141010933 to AT.en_US
dc.format.extent9 pagesen_US
dc.genreconference papers and proceedingsen_US
dc.identifier.citationCarl Vondrick,, Learning visual biases from human imagination, Advances in Neural Information Processing Systems 28 (NIPS 2015),
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.subjecthuman imaginationen_US
dc.subjectvisual biasesen_US
dc.subjectcomputer visionen_US
dc.titleLearning visual biases from human imaginationen_US

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record