Modelling local deep convolutional neural network features to improve fine-grained image classification

@article{Ge2015ModellingLD,
  title={Modelling local deep convolutional neural network features to improve fine-grained image classification},
  author={ZongYuan Ge and Chris McCool and Conrad Sanderson and Peter I. Corke},
  journal={2015 IEEE International Conference on Image Processing (ICIP)},
  year={2015},
  pages={4112-4116}
}
We propose a local modelling approach using deep convolutional neural networks (CNNs) for fine-grained image classification. Recently, deep CNNs trained from large datasets have considerably improved the performance of object recognition. However, to date there has been limited work using these deep CNNs as local feature extractors. This partly stems from CNNs having internal representations which are high dimensional, thereby making such representations difficult to model using stochastic… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 5 times over the past 90 days. VIEW TWEETS
17 Extracted Citations
17 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.
Showing 1-10 of 17 extracted citations

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 17 references

Introduction to Statistical Pattern Recognition, pages 399–417

  • K. Fukunaga
  • Elsevier, second edition,
  • 1990
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…