Deformable Part Models with CNN Features
Pierre-André Savalle, Stavros Tsogkas, George Papandreou, Iasonas Kokkinos · HAL (Le Centre pour la Communication Scientifique Directe) · 2014
Abstract. 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 Neu-ral Network (CNN) features, obtained from the top-most, fifth, convolu-tional 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. 1