Deformable Part Models with CNN Features

Pierre-André Savalle (1) , Stavros Tsogkas (1, 2) , George Papandreou (3) , Iasonas Kokkinos (1, 2)

1 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
2 CVN - Centre de vision numérique
3 Toyota Technological Institute

In this work we report on progress in integrating deep convo-lutional 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 currently top-performing R-CNN method of [4], suggesting that more radical changes to DPMs may be needed.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Pierre-André Savalle, Stavros Tsogkas, George Papandreou, Iasonas Kokkinos. Deformable Part Models with CNN Features. European Conference on Computer Vision, Parts and Attributes Workshop, Sep 2014, Zurich, Switzerland. ⟨hal-01109290⟩