You are here

Home » Content

ORTA SEVİYE VERİ TEMSİLİNDE DENETİMSİZ NİTELİK ÖĞRENİMİ

UNSUPERVISED FEATURE LEARNING FOR MID-LEVEL DATA REPRESENTATION

Journal Name:

  • Journal of Naval Sciences And Engineering

Publication Year:

  • 2016

Key Words:

Keywords (Original Language):

Author Name
Abstract (2. Language): 
Attribute based approaches are commonly used in recent years instead of low level features for image classification which is one of the most important problems in the field of computer vision. The most important advantage of attribute based approach is that learning can be performed similar to human by using attributes which makes sense for people. In this study, unsupervised attributes are developed in order to avoid human related problems in supervised attribute learning. In our proposed work, the attributes are generated as random binary and relative definitions. The process of random attribute generation simplifies the data modeling when compared to other work in the literature. In addition, a major problem which is the increasing the numbers of attributes in attribute based approaches is eliminated owing to the increasing the numbers of attributes easily. Furthermore, attributes are selected more wisely using simple applicable algorithm to improve the discriminative capacity of randomly generated attribute set for image classification. The proposed approaches are evaluated with the other similar attribute based studies comparatively in the literature based on the same data set (OSR-Open Scene Recognition). Experiments show that noteworthy performance increase is achieved.
Bookmark/Search this post with
Abstract (Original Language): 
Bilgisayarla görme alanındaki en önemli problemlerden birisi olan imge sınıflandırma için öznitelik tabanlı klasik yaklaşımların yanı sıra nitelik tabanlı yaklaşımlar son yıllarda sıklıkla kullanılmaya başlanmıştır. Nitelik tabanlı yaklaşımların en önemli avantajı, insanlar için anlam ifade eden niteliklerin kullanılması vasıtasıyla insanoğluna benzer bir öğrenme yapılabilmesidir. Bu çalışmada, denetimli nitelik öğrenme sürecinde insan faktörü sebebiyle oluşabilecek sorunlardan kaçınmak amacıyla denetimsiz yaklaşım geliştirilmiştir. Denetimsiz yaklaşımımızda niteliklerin ikili ve göreceli olarak rastgele üretilmesi sayesinde nitelik öğrenme süreci, literatürdeki diğer denetimli ve denetimsiz yaklaşımlara göre daha kolay hale gelmiştir. Ayrıca, nitelik sayısının basit bir şekilde artırılması ile nitelik tabanlı yaklaşımlarda büyük bir problem olan nitelik sayısının artırılması basitleştirilmiştir. Rastgele üretilen nitelik kümesinin imge sınıflandırma için ayırt etme kapasitesini artırmak maksadıyla, rastgele üretilen nitelikler arasından en iyileri kolay uygulanabilir bir algoritma sayesinde seçilmiştir. Çalışmada önerilen yaklaşımlar literatürdeki diğer benzer nitelik tabanlı çalışmalarla aynı veri kümesi (OSR-Açık Alan Tanıma - Open Scene Recognition) üzerinden ve farklı sınıflandırıcılar kullanılarak test edilmiştir. Yapılan deneylerde denetimsiz öğrenilen göreceli niteliklerin dikkate değer bir performans artışı sağladığı görülmüştür.
FULL TEXT (PDF): 
PDF icon arastirmax-orta-seviye-veri-temsilinde-denetimsiz-nitelik-ogrenimi.pdf
  • 1
51
79
  • Turkish

REFERENCES

References: 

[1] Ferrari V. and Zisserman A. “Learning visual attributes” Advances in
Neural Information Processing Systems, Vancouver CA, December 2007.
[2] Lampert C.H., Nickisch H. and Harmeling S. “Attribute-Based
classification for zero-shot visual object categorization” IEEE Transactions on
Pattern Analysis and Machine Intelligence, vol. 36, no. 3, 2014.
[3] Lampert C. H., Nickisch H., and Harmeling S. "Learning To Detect Unseen
Object Classes by Between-Class Attribute Transfer" Proc. IEEE Conf.
Computer Vision and Pattern Recognition (CVPR), 2009.
Emrah ERGÜL, Mehmet KARAYEL, Oğuzhan TİMUŞ, Erkan KIYAK
76
[4] Farhadi A., Endres I. and Hoiem D. “Attribute-centric recognition for crosscategory
generalization” CVPR, 2010.
[5] Farhadi A., Endres I., Hoiem D. and Forsyth D. “Describing objects by
their attributes” CVPR 2009.
[6] Parikh D. and Grauman K. “Relative attributes” Int’l Conference on
Computer Vision (ICCV), 2011.
[7] Sharma G., Jurie F., and Schmid C. “Expanded parts model for human
attribute and action recognition in still images” CVPR, pp. 652 – 659, 2013.
[8] Akata Z., Perronnin F., Harchaoui Z. and Schmid C. “Label-embedding for
attribute-based classification” CVPR, pp. 819 – 826, 2013.
[9] Tamara L.B., Alexander C.B. and Jonathan S. “Automatic attribute
discovery and characterization from noisy web data” ECCV, pp. 663-676,
2010.
[10] Russakovsky O. and Fei-Fei L. “Attribute learning in large-scale datasets”
ECCV Workshops, pp. 1-14, 2010.
[11] Biswas A. and Parikh D. “Simultaneous active learning of classifiers &
attributes via relative feedback” CVPR, 2013.
[12] Parkash A. and Parikh D. “Attributes for Classifier Feedback” European
Conference on Computer Vision (ECCV), vol. 3, pp. 354-368, 2012.
[13] Rastegari M., Diba A., Parikh D., Farhadi A. “Multi-attribute queries: To
merge or not to Merge” CVPR, 2013.
[14] Kumar N., Berg A.C., Belhumeur P. N., and Nayar S. K. “Attribute and
smile classifiers for face verification” ICCV, 2009.
Unsupervised Feature Learning For Mid-Level Data Representation
77
[15] Ma S., Sclaroff S. and Cinbis N.I. "Unsupervised learning of
discriminative relative visual attributes" ECCV Workshop on Parts and
Attributes, 2012.
[16] Karayel M. and Arica N. “Random attributes for image classification”
IEEE 21th Conference on Signal Processing and Communications
Applications, 2013.
[17] Wang Y. and Mori G. “A discriminative latent model of object classes and
attributes” ECCV, pp. 155-168, 2010.
[18] Yu F.X., Ji R., Tsai M., Ye G. and Chang S. “Weak attributes for largescale
image retrieval” CVPR, 2012.
[19] Chen K., Gong S., Xiang T. and Loy C.C. “Cumulative attribute space for
age and crowd density estimation” CVPR, pp. 2467 – 2474, 2013.
[20] Yu F.X., Cao L., Feris R.S., Smith J.R. and Chang S. “Designing categorylevel
attributes for discriminative visual recognition” CVPR, 2013.
[21] Li W., Yu Q., Sawhney H. and Vasconcelos N. “Recognizing activities via
bag of words for attribute dynamics” CVPR, pp. 2587 – 2594, 2013.
[22] Ma Z., Yang Y., Xu Z., Sebe N., Yan S. and Hauptmann A.G. “Complex
event detection via multi-source video attributes” CVPR, 2013.
[23] Chen H., Gallagher A. and Girod B. “What's in a name: first names as
facial attributes” CVPR, 2013.
[24] Sadovnik A., Gallagher A. and Chen T. "It's not polite to point: describing
people with uncertain attributes" CVPR, 2013.
[25] Choi J., Rastegari M., Farhadi A. and Davis L.S. “Adding unlabeled
samples to categories by learned attributes” CVPR, 2013.
Emrah ERGÜL, Mehmet KARAYEL, Oğuzhan TİMUŞ, Erkan KIYAK
78
[26] Wah C. and Belongie S. “Attribute-based detection of unfamiliar classes
with humans in the loop” CVPR, pp. 779 – 786, 2013.
[27] Wang S., Joo J., Wang Y., and Zhu S.C. “Weakly supervised learning for
attribute localization in outdoor scenes” CVPR, 2013.
[28] Saleh B., Farhadi A. and Elgammal A. “Object-centric anomaly detection
by attribute-based reasoning,” CVPR, 2013.
[29] Bosch A., Xavier M. and Marti R. “A review: which is the best way to
organize/classify images by content?” Image and Vision Computing, 2006.
[30] Ergül E., Ertürk S. and Arica N. “Unsupervised Relative Attribute
Extraction” IEEE 21th Conference on Signal Processing and Communications
Applications, 2013.
[31] Chang C.C. and Lin C.J. “LIBSVM : A library for support vector
machines” ACM Transactions on Intelligent Systems and Technology, pp. 1-27,
2011.
[32] Shrivastava A., Singh S. and Gupta A. "Constrained semi-supervised
learning using attributes and comparative attributes", ECCV, vol 3, pp. 369-
383. 2012.
[33] Yu, A., and Grauman, ,K., “Just Noticeable Differences in Visual
Attributes” ICCV, 2015.
[34] Verma, Y., and Jawahar, C.V., “Exploring Locally Rigid Discriminative
Patches for Learning Relative Attributes” ICCV, 2015.
[35] Alpaydın E., “Support Vector Machines,” in Introduction to machine
Learning, The MIT Press, London, 2004, pp. 218-225.
Unsupervised Feature Learning For Mid-Level Data Representation
79
[36] Cortes C. and Vapnik V., "Support-vector networks," Machine
Learning, vol. 20, no. 3, pp. 273-297, 1995.
[37] Waikato University, Waikato Environment for Knowledge Analysis
(Weka) Versiyon 3.7.11, Waikato University, Hamilton, 2014.
[38] Coates A., Lee H. and Andrew Y. Ng. “An analysis of single-layer
networks in unsupervised feature Learning,” International Conference on
Artificial Intelligence and Statistics (AISTATS), 2011.

Thank you for copying data from http://www.arastirmax.com