Skip to main content

2018 | OriginalPaper | Buchkapitel

Multi-level Semantic Representation for Flower Classification

verfasst von : Chuang Lin, Hongxun Yao, Wei Yu, Wenbo Tang

Erschienen in: Advances in Multimedia Information Processing – PCM 2017

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Fine-grained classification is challenging since sub-categories have little intra-class variances and large intra-class variations. The task of flower classification can be achieved through highlighting the discriminative parts. Most traditional methods trained Convolutional Neural Networks (CNN) to handle the variations of pose, color and rotation, which only utilize single-level semantic information. In this paper, we propose a fine-grained classification approach with multi-level semantic representation. With the complementary strengths of multi-level semantic representation, we attempt to capture the subtle differences between sub-categories. One object-level model and multiple part-level model are trained as a multi-scale classifier. We test our method on the Oxford Flower dataset with 102 categories, and our result achieves the best performance over other state-of-the-art approaches.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-UCSD birds 200. 2010. In: Chen, W.-K. (ed.) Linear Networks and Systems, Wadsworth, Belmont, pp. 123–135 (1993) Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., Perona, P.: Caltech-UCSD birds 200. 2010. In: Chen, W.-K. (ed.) Linear Networks and Systems, Wadsworth, Belmont, pp. 123–135 (1993)
2.
Zurück zum Zitat Angelova, A., Zhu, S.: Efficient object detection and segmentation for fine-grained recognition. In: CVPR (2013) Angelova, A., Zhu, S.: Efficient object detection and segmentation for fine-grained recognition. In: CVPR (2013)
3.
Zurück zum Zitat Chai, Y., Rahtu, E., Lempitsky, V., Van Gool, L., Zisserman, A.: TriCoS: a tri-level class-discriminative co-segmentation method for image classification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 794–807. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33718-5_57CrossRef Chai, Y., Rahtu, E., Lempitsky, V., Van Gool, L., Zisserman, A.: TriCoS: a tri-level class-discriminative co-segmentation method for image classification. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 794–807. Springer, Heidelberg (2012). https://​doi.​org/​10.​1007/​978-3-642-33718-5_​57CrossRef
4.
Zurück zum Zitat Gavves, E., Fernando, B., Snoek, C.G.M., Smeulders, A.W.M., Tuytelaars, T.: Fine-grained categorization by alignments. In: ICCV, pp. 1713–1720 (2013) Gavves, E., Fernando, B., Snoek, C.G.M., Smeulders, A.W.M., Tuytelaars, T.: Fine-grained categorization by alignments. In: ICCV, pp. 1713–1720 (2013)
5.
Zurück zum Zitat LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRef LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRef
6.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of NIPS, pp. 1106–1114 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of NIPS, pp. 1106–1114 (2012)
7.
Zurück zum Zitat Ciresan, D.C., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proceedings of CVPR, pp. 3642–3649 (2012) Ciresan, D.C., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proceedings of CVPR, pp. 3642–3649 (2012)
8.
Zurück zum Zitat Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: Proceedings CVPR, pp. 3626–3633 (2013) Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: Proceedings CVPR, pp. 3626–3633 (2013)
9.
Zurück zum Zitat Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of CVPR, pp. 248–255 (2009) Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of CVPR, pp. 248–255 (2009)
10.
Zurück zum Zitat Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional neural networks. arXiv preprint arXiv:1311.2901 (2013) Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional neural networks. arXiv preprint arXiv:​1311.​2901 (2013)
11.
Zurück zum Zitat Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition. arXiv preprint arXiv:1403.6382 (2014) Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition. arXiv preprint arXiv:​1403.​6382 (2014)
12.
Zurück zum Zitat Wah, C., Branson, S., Welinder, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011) Wah, C., Branson, S., Welinder, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 dataset (2011)
13.
Zurück zum Zitat Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Perona, P.: Caltech-UCSD birds 200 (2010) Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Perona, P.: Caltech-UCSD birds 200 (2010)
14.
Zurück zum Zitat Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.-F.: Dataset for fine-grained image categorization. In: First Workshop on Fine-Grained Visual Categorization, CVPR (2011) Khosla, A., Jayadevaprakash, N., Yao, B., Li, F.-F.: Dataset for fine-grained image categorization. In: First Workshop on Fine-Grained Visual Categorization, CVPR (2011)
15.
Zurück zum Zitat Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2009)CrossRef Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31(2), 210–227 (2009)CrossRef
16.
Zurück zum Zitat Yang, M., Zhang, L., Feng, X., Zhang, D.: Sparse representation based fisher discrimination dictionary learning for image classification. Int. J. Comput. Vis. 109(3), 209–232 (2014)MathSciNetCrossRef Yang, M., Zhang, L., Feng, X., Zhang, D.: Sparse representation based fisher discrimination dictionary learning for image classification. Int. J. Comput. Vis. 109(3), 209–232 (2014)MathSciNetCrossRef
17.
Zurück zum Zitat Qian, Q., Jin, R.: Fine-grained visual categorization via multi-stage metric learning. In: CVPR (2015) Qian, Q., Jin, R.: Fine-grained visual categorization via multi-stage metric learning. In: CVPR (2015)
18.
Zurück zum Zitat Parkhi, O.M., Vedaldi, A., Jawahar, C., Zisserman, A.: The truth about cats and dogs. In: ICCV, pp. 1427–1434. IEEE (2011) Parkhi, O.M., Vedaldi, A., Jawahar, C., Zisserman, A.: The truth about cats and dogs. In: ICCV, pp. 1427–1434. IEEE (2011)
19.
Zurück zum Zitat Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR (2012) Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR (2012)
20.
Zurück zum Zitat Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011) Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Technical report CNS-TR-2011-001, California Institute of Technology (2011)
21.
Zurück zum Zitat Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: Proceedings of the 31st International Conference on Machine Learning, pp. 647−655. ACM, Beijing (2014) Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: Proceedings of the 31st International Conference on Machine Learning, pp. 647−655. ACM, Beijing (2014)
23.
Zurück zum Zitat Simon, M., Rodner, E.: Neural activation constellations: unsupervised part model discovery with convolutional networks. In: ICCV (2015) Simon, M., Rodner, E.: Neural activation constellations: unsupervised part model discovery with convolutional networks. In: ICCV (2015)
24.
Zurück zum Zitat Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRef Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRef
25.
Zurück zum Zitat Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher Kernel for large-scale image classification. In: Proceedings ECCV, pp. 143–156 (2010) Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher Kernel for large-scale image classification. In: Proceedings ECCV, pp. 143–156 (2010)
26.
Zurück zum Zitat Cimpoi, M., Maji, S., Vedaldi, A.: Deep filter banks for texture recognition and segmentation. In: CVPR (2015) Cimpoi, M., Maji, S., Vedaldi, A.: Deep filter banks for texture recognition and segmentation. In: CVPR (2015)
27.
Zurück zum Zitat Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR (2014) Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR (2014)
29.
Zurück zum Zitat Lin, K., Yang, H.-F., Chen, C.-S.: Flower classification with few training examples via recalling visual patterns from deep CNN. In: IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP) (2015) Lin, K., Yang, H.-F., Chen, C.-S.: Flower classification with few training examples via recalling visual patterns from deep CNN. In: IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP) (2015)
30.
Zurück zum Zitat Song, X., Jiang, S., Herranz, L.: Multi-scale multi-feature context modeling for scene recognition in the semantic manifold. IEEE Trans. Image Process. 26(6), 2721–2735 (2017)MathSciNetCrossRef Song, X., Jiang, S., Herranz, L.: Multi-scale multi-feature context modeling for scene recognition in the semantic manifold. IEEE Trans. Image Process. 26(6), 2721–2735 (2017)MathSciNetCrossRef
Metadaten
Titel
Multi-level Semantic Representation for Flower Classification
verfasst von
Chuang Lin
Hongxun Yao
Wei Yu
Wenbo Tang
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-319-77380-3_31

Neuer Inhalt