Two-level hierarchical feature learning for image classification

Guang-hui SONG; Xiao-gang JIN; Gen-lang CHEN; Yan NIE

doi:10.1631/FITEE.1500346

Your Location：

Home >

Browse articles >

Two-level hierarchical feature learning for image classification

Regular Papers | Updated：2022-05-19

- Two-level hierarchical feature learning for image classification
- 基于两级层次特征学习的图像分类方法
- Frontiers of Information Technology & Electronic Engineering Vol. 17, Issue 9, Pages: 897-906(2016)
- Affiliations：
  
  1College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
  2Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, China
  3College of Science and Technology, Ningbo University, Ningbo 315100, China
- Author bio：
  
  E-mail:xiaogangj@cise.zju.edu.cn
- Funds：
- DOI：10.1631/FITEE.1500346
  CLC： TP391.4
- Received：20 October 2015，
  
  Accepted：10 April 2016，
  
  Published：2016-09
- Accepted：
Scan QR Code
Guang-hui SONG, Xiao-gang JIN, Gen-lang CHEN, et al. Two-level hierarchical feature learning for image classification[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(9): 897-906.
DOI：

Guang-hui SONG, Xiao-gang JIN, Gen-lang CHEN, et al. Two-level hierarchical feature learning for image classification[J]. Frontiers of Information Technology & Electronic Engineering, 2016, 17(9): 897-906. DOI： 10.1631/FITEE.1500346.

摘要

在图像分类任务中，不同类别之间的相似度是不同的，样本经常被误分到相似度较高的类别中。为了区分高度相似类别中的样本，需要更加具体的图像特征，以便于分类器能够提高分类性能。本文提出了一种新颖、有效的基于深度卷积神经网络的两级层次特征学习框架。首先，不同层次的深度特征抽取器使用迁移学习方法进行训练。然后，从全部类别中抽取的通用特征和从高度相似类别中抽取的具体特征被融合成一个特征向量，并将其输入线性分类器进行分类。最后，基于Caltech-256、Oxford Flower-102和Tasmania Coral Point Count三个图像数据集的实验证明，通过两级层次特征学习的深度特征的表达能力十分强大，与传统的扁平多分类方法相比，我们提出的方法能有效地提高分类精度。

Abstract

In some image classification tasks

similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories

more specific features are required so that the classifier can improve the classification performance. In this paper

we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network (CNN)

which is simple and effective. First

the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second

the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally

experiments using the Caltech-256

Oxford Flower-102

and Tasmania Coral Point Count (CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.

关键词

Keywords

references

A Angelova , , , S Zhu , , , Y Lin . . Image segmentation for large-scale subcategory flower recognition. Proc . . IEEE Workshop on Applications of Computer Vision , , 2013 . . 39 - - 45 . . DOI: 10.1109/WACV.2013.6474997 http://doi.org/10.1109/WACV.2013.6474997 . .

N Barrett , , , L Meyer , , , N Hill , , , 等 . . Methods for the Processing and Scoring of AUV Digital Imagery from South Eastern Tasmania . . Technical Report. University of Tasmania, Hobart , , 2011 . . .

M.S Bewley , , , B Douillard , , , N Nourani-Vatani , , , 等 . . Automated species detection: an experimental approach to kelp detection from sea-floor AUV images . . Proc. Australasian Conf. on Robotics and Automation , , 2012 . . 1 - - 10 . . . .

M.S Bewley , , , N Nourani-Vatani , , , D Rao , , , 等 . . Hierarchical classification in AUV imagery . . Proc. 9th Int. Conf. on Field and Service Robotics , , 2015 . . 3 - - 16 . . DOI: 10.1007/978-3-319-07488-7_1 http://doi.org/10.1007/978-3-319-07488-7_1 . .

Y Cai , , , M.L Yang , , , J Li . . Multiclass classification based on a deep convolutional network for head pose estimation . . Front. Inform. Technol. Electron. Eng. , , 2015 . . 16 ( ( 11 ): ): 930 - - 939 . . DOI: 10.1631/FITEE.1500125 http://doi.org/10.1631/FITEE.1500125 . .

J Deng , , , S Satheesh , , , A.C Berg , , , 等 . . Fast and balanced: efficient label tree learning for large scale object recognition . . Advances in Neural Information Processing Systems , , 2011 . . 24 567 - - 575 . . . .

J Deng , , , N Ding , , , Y.Q Jia , , , 等 . . Large-scale object classification using label relation graphs . . Proc. 13th European Conf. on Computer Vision , , 2014 . . 48 - - 64 . . DOI: 10.1007/978-3-319-10590-1_4 http://doi.org/10.1007/978-3-319-10590-1_4 . .

J Donahue , , , Y Jia , , , O Vinyals , , , 等 . . DeCAF: a deep convolutional activation feature for generic visual recognition . . Proc. 31st Int. Conf. on Machine Learning , , 2014 . . 1 - - 9 . . . .

R Fergus , , , H Bernal , , , Y Weiss , , , 等 . . Semantic label sharing for learning with many categories . . Proc. 11th European Conf. on Computer Vision , , 2010 . . 762 - - 775 . . DOI: 10.1007/978-3-642-15549-9_55 http://doi.org/10.1007/978-3-642-15549-9_55 . .

Z.Y Ge , , , C McCool , , , C Sanderson , , , 等 . . Subset feature learning for fine-grained category classification . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition Workshops , , 2015 . . 46 - - 52 . . DOI: 10.1109/CVPRW.2015.7301271 http://doi.org/10.1109/CVPRW.2015.7301271 . .

R Girshick , , , J Donahue , , , T Darrell , , , 等 . . Rich feature hierarchies for accurate object detection and semantic segmentation . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition , , 2014 . . 580 - - 587 . . DOI: 10.1109/cvpr.2014.81 http://doi.org/10.1109/cvpr.2014.81 . .

G Griffin , , , P Perona . . Learning and using taxonomies for fast visual categorization . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition , , 2008 . . 1 - - 8 . . DOI: 10.1109/cvpr.2008.4587410 http://doi.org/10.1109/cvpr.2008.4587410 . .

A Krizhevsky , , , I Sutskever , , , G.E Hinton . . ImageNet classification with deep convolutional neural networks . . Advances in Neural Information Processing Systems , , 2012 . . 25 1097 - - 1105 . . . .

B.Y Liu , , , F Sadeghi , , , M Tappen , , , 等 . . Probabilistic label trees for efficient large scale image classification . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition , , 2013 . . 843 - - 850 . . DOI: 10.1109/CVPR.2013.114 http://doi.org/10.1109/CVPR.2013.114 . .

M.E Nilsback . . An Automatic Visual Flora-Segmentation and Classification of Flower Images . . PhD Thesis, University of Oxford, UK , , 2009 . . .

M.E Nilsback , , , A Zisserman . . Automated flower classification over a large number of classes . . Proc. 6th Indian Conf. on Computer Vision , , 2008 . . 722 - - 729 . . DOI: 10.1109/ICVGIP.2008.47 http://doi.org/10.1109/ICVGIP.2008.47 . .

A.S Razavian , , , H Azizpour , , , J Sullivan , , , 等 . . CNN features off-the-shelf: an astounding baseline for recognition . . Proc. IEEE Conf. on Computer Vision and Pattern Recognition Workshops , , 2014 . . 512 - - 519 . . DOI: 10.1109/CVPRW.2014.131 http://doi.org/10.1109/CVPRW.2014.131 . .

N Srivastava , , , R.R Salakhutdinov . . Discriminative transfer learning with tree-based priors . . Advances in Neural Information Processing Systems , , 2013 . . 26 2094 - - 2102 . . . .

A.M Tousch , , , S Herbin , , , J.Y Audibert . . Semantic hierarchies for image annotation: a survey . . Patt. Recogn. , , 2012 . . 45 ( ( 1 ): ): 333 - - 345 . . DOI: 10.1016/j.patcog.2011.05.017 http://doi.org/10.1016/j.patcog.2011.05.017 . .

Z.C Yan , , , H Zhang , , , R Piramuthu , , , 等 . . HDCNN: hierarchical deep convolutional neural networks for large scale visual recognition . . Proc. Int. Conf. on Computer Vision , , 2015 . . 2740 - - 2748 . . . .

J Yosinski , , , J Clune , , , Y Bengio , , , 等 . . How transferable are features in deep neural networks? . . Advances in Neural Information Processing Systems , , 2014 . . 27 3320 - - 3328 . . . .

M.D Zeiler , , , R Fergus . . Visualizing and understanding convolutional networks . . Proc. 13th European Conf. on Computer Vision , , 2014 . . 818 - - 833 . . DOI: 10.1007/978-3-319-10590-1_53 http://doi.org/10.1007/978-3-319-10590-1_53 . .

B Zhao , , , F Li , , , E.P Xing . . Large-scale category structure aware image categorization . . Advances in Neural Information Processing Systems , , 2011 . . 24 1251 - - 1259 . . . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Frequency-learning adversarial networks based on transfer learning for cross-scenario signal modulation classification

Transfer learning with a spatiotemporal graph convolution network for city flow prediction

A software defect prediction method with metric compensation based on feature selection and transfer learning

Texture branch network for chronic kidney disease screening based on ultrasound images

A saliency and Gaussian net model for retinal vessel segmentation

Related Author

Wenrui DING

Yufeng WANG

Duona ZHANG

Zeqi SHAO

Jing XIAO

Qinyan MA

Yang CAO

Binkun LIU

Related Institution

Institute of Unmanned System, Beihang University

School of Artificial Intelligence and Computer Science, North China University of Technology

School of Electronic and Information Engineering, Beihang University

Institute of Advanced Technology, University of Science and Technology of China

Institute of Artificial Intelligence, Hefei Comprehensive National Science Center

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰