Food-101 - Mining Discriminative Components with Random Forests

@inproceedings{Bossard2014Food101M,
  title={Food-101 - Mining Discriminative Components with Random Forests},
  author={Lukas Bossard and Matthieu Guillaumin and Luc Van Gool},
  booktitle={ECCV},
  year={2014}
}
In this paper we address the problem of automatically recognizing pictured dishes. To this end, we introduce a novel method to mine discriminative parts using Random Forests (rf), which allows us to mine for parts simultaneously for all classes and to share knowledge among them. To improve efficiency of mining and classification, we only consider patches that are aligned with image superpixels, which we call components. To measure the performance of our rf component mining for food recognition… CONTINUE READING
BETA

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • With an average accuracy of 50.76%, our model outperforms alternative classification methods except for cnn, including svm classification on Improved Fisher Vectors and existing discriminative part-mining algorithms by 11.88% and 8.13%, respectively.

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Blocks That Shout: Distinctive Parts for Scene Classification

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Harvesting Mid-level Visual Concepts from Large-Scale Internet Images

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Learning Collections of Part Models for Object Recognition

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Learning Discriminative Part Detectors for Image Classification and Cosegmentation

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Randomized Clustering Forests for Image Classification

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2008
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…