Memory-efficient NBNN image classification메모리 효율적인 NBNN 이미지 분류

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 403
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorYoon, Sung-eui-
dc.contributor.advisor윤성의-
dc.contributor.authorLee, YoonSeok-
dc.contributor.author이윤석-
dc.date.accessioned2017-03-29T02:40:24Z-
dc.date.available2017-03-29T02:40:24Z-
dc.date.issued2016-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=663490&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/221889-
dc.description학위논문(석사) - 한국과학기술원 : 전산학부, 2016.8 ,[iii, 15 p. :]-
dc.description.abstractNBNN is a simple image classifier based on identifying nearest neighbors. NBNN uses original image descriptors (e.g., SIFTs) without vector quantization for preserving the discriminative power of descriptors and has a powerful generalization characteristic. However, it has a distinct disadvantage-
dc.description.abstractits memory requirement can be prohibitively high as we have a large amount of data. We identify this problem of NBNN techniques and we apply a binary code embedding technique, i.e., spherical hashing, to encode data compactly without a significant loss of classification accuracy. We also propose to use an inverted index to identify nearest neighbors among those binarized image descriptors. To demonstrate benefits of our method, we apply our method to two of existing NBNN techniques with a image dataset. By using 64~bit lengths, we are able to observe 16 times memory reduction with a higher performance without a significant loss of classification accuracy. This result is thanks to our compact encoding of image descriptors without losing much information of original image descriptors.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectImage classification-
dc.subjectNBNN-
dc.subjecthashing-
dc.subjectmemory efficiency-
dc.subjectindexing-
dc.subject이미지 분류-
dc.subject해싱-
dc.subject메모리 효율성-
dc.subject인덱싱-
dc.titleMemory-efficient NBNN image classification-
dc.title.alternative메모리 효율적인 NBNN 이미지 분류-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전산학부,-
Appears in Collection
CS-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0