Deformable Part Models with CNN Features

@inproceedings{Savalle2014DeformablePM,
  title={Deformable Part Models with CNN Features},
  author={Pierre-Andr{\'e} Savalle and Stavros Tsogkas and George Papandreou and Iasonas Kokkinos},
  year={2014}
}
In this work we report on progress in integrating deep convolutional features with Deformable Part Models (DPMs). We substitute the Histogram-of-Gradient features of DPMs with Convolutional Neural Network (CNN) features, obtained from the top-most, fifth, convolutional layer of Krizhevsky’s network [8]. We demonstrate that we thereby obtain a substantial boost in performance (+14.5 mAP) when compared to the baseline HOG-based models. This only partially bridges the gap between DPMs and the… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.
24 Citations
13 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 24 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 13 references

Similar Papers

Loading similar papers…