Corpus ID: 14942666

A Gaussian Approximation of Feature Space for Fast Image Similarity

@inproceedings{Gharbi2012AGA,
  title={A Gaussian Approximation of Feature Space for Fast Image Similarity},
  author={M. Gharbi and Tomasz Malisiewicz and Sylvain Paris and F. Durand},
  year={2012}
}
  • M. Gharbi, Tomasz Malisiewicz, +1 author F. Durand
  • Published 2012
  • Mathematics
  • We introduce a fast technique for the robust computation of image similarity. It builds on a re-interpretation of the recent exemplar-based SVM approach, where a linear SVM is trained at a query point and distance is computed as the dot product with the normal to the separating hyperplane. Although exemplar-based SVM is slow because it requires a new training for each exemplar, the latter approach has shown robustness for image retrieval and object classification, yielding state-ofthe-art… CONTINUE READING

    Figures and Tables from this paper.

    Blocks That Shout: Distinctive Parts for Scene Classification
    • 394
    • PDF
    Learning High-level Features for Satellite Image Classification With Limited Labeled Samples
    • 111
    • Highly Influenced
    • PDF
    Painting-to-3D model alignment via discriminative visual elements
    • 103
    • Highly Influenced
    • PDF
    Kernel Square-Loss Exemplar Machines for Image Retrieval
    • 6
    • PDF
    Writer Identification Using GMM Supervectors and Exemplar-SVMs
    • 47
    • PDF
    Document Retrieval with Unlimited Vocabulary
    • 7
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES
    Histograms of oriented gradients for human detection
    • 25,758
    • PDF
    Ensemble of exemplar-SVMs for object detection and beyond
    • 812
    • PDF
    Data-driven visual similarity for cross-domain image matching
    • 239
    • PDF
    Recognition by association via learning per-exemplar distances
    • 160
    • PDF
    Image Retrieval and Classification Using Local Distance Functions
    • 232
    • PDF
    Discriminative Decorrelation for Clustering and Classification
    • 282
    • PDF
    Pattern Classification
    • 8,701
    • PDF
    Discriminant Adaptive Nearest Neighbor Classification
    • 859
    • PDF
    Detecting Irregularities in Images and in Video
    • 301
    • PDF