Promoting rotational-invariance in object recognition despite experience with only a single view.pdfVIP
- 1、本文档共7页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 5、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 6、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 7、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 8、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
Promoting rotational-invariance in object recognition despite experience with only a single view.pdf
Behavioural Processes 123 (2016) 107–113
Contents lists available at ScienceDirect
Behavioural Processes
journal homepage: /locate/behavproc
Promoting rotational-invariance in object recognition despite experience with only a single view
Fabian A. Soto a,?, Edward A. Wasserman b
a Department of Psychology, Florida International University, Miami, FL 33199, USA b Department of Psychological and Brain Sciences, University of Iowa, Iowa City, IA 52242, USA
article info
Article history: Received 17 July 2015 Received in revised form 3 November 2015 Accepted 4 November 2015 Available online 28 November 2015
Keywords: Object recognition View invariance Learning Evolution of visual cognition
abstract
Different processes are assumed to underlie invariant object recognition across af?ne transformations,
such as changes in size, and non-af?ne transformations, such as rotations in depth. From this perspec-
tive, promoting invariant object recognition across rotations in depth requires visual experience with the
object from multiple viewpoints. One learning mechanism potentially contributing to invariant recogni-
tion is the error-driven learning of associations between relatively view-invariant visual properties and
motor responses or object labels. This account uniquely predicts that experience with af?ne transfor-
mations of a single object view may also promote view-invariance, if view-invariant properties are also
invariant across such af?ne transformations. We empirically con?rmed this prediction in both people and
pigeons, thereby suggesting that: (a) the hypothesized mechanism participates in view-invariance learn-
ing, (b) this mechanism is present across distantly-related vertebrates, and (c) the distinction between
af?ne and non-af?ne transformations may not be fundamental for biological visual systems, as previously
assumed.
? 2015 Elsevier B.V. All rights reserved.
1. Introduction
Keen interest exists in discovering how organisms achieve object recognition that is
您可能关注的文档
- Nonlinear dynamic modeling of rotor system supported by angular contact ball bearings.pdf
- Nonoverlapped view management for augmented reality by tabletop projection.pdf
- Nonsmooth Contact Dynamics for the large-scale simulation of granular material.pdf
- Normal and tangential stiffnesses of rough surfaces in contact via an imperfect interface model.pdf
- Normal stiffness and damping at lightly loaded rough planar contacts.pdf
- North Brazil current rings viewed by TRMM Microwave Imager SST and the influence of the Amazon Plume.pdf
- Novel approach for fabrication of buried contact silicon nanowire solar cells with improved performance.pdf
- Novel method for the design and assessment of direct contact membrane distillation modules.pdf
- Nuclear analysis and shielding optimisation in support of the ITER In-Vessel Viewing System design.pdf
- Nuclear waste viewed in a new light; a synchrotron study of uranium encapsulated in grout.pdf
文档评论(0)