Year: 2014
Type: conference-paper
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
Source: HAL
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2587023323