Corpus ID: 17172607

Learning detectors quickly using structured covariance matrices

@article{Valmadre2014LearningDQ,
  title={Learning detectors quickly using structured covariance matrices},
  author={Jack Valmadre and S. Sridharan and S. Lucey},
  journal={ArXiv},
  year={2014},
  volume={abs/1403.7321}
}
  • Jack Valmadre, S. Sridharan, S. Lucey
  • Published 2014
  • Computer Science
  • ArXiv
  • Computer vision is increasingly becoming interested in the rapid estimation of object detectors. Canonical hard negative mining strategies are slow as they require multiple passes of the large negative training set. Recent work has demonstrated that if the distribution of negative examples is assumed to be stationary, then Linear Discriminant Analysis (LDA) can learn comparable detectors without ever revisiting the negative set. Even with this insight, however, the time to learn a single object… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES
    Use of p-nitrophenyl phosphate for assay of soil phosphatase activity
    2450
    On the bullwhip and inventory variance produced by an ordering policy
    344
    GABAergic modulation of complex spike activity by the cerebellar nucleoolivary pathway in rat.
    199
    Beyond Hard Negative Mining: Efficient Detector Learning via Block-Circulant Decomposition
    92
    Discriminative Decorrelation for Clustering and Classification
    279
    Fast Training of Object Detection Using Stochastic Gradient Descent
    46
    An Optimal Circulant Preconditioner for Toeplitz Systems
    425