Speeding-up a convolutional neural network by connecting an SVM network

Jérôme Pasquet 1 Marc Chaumont 1 Gérard Subsol 1 Mustapha Derras 2
1 ICAR - Image & Interaction
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : Deep neural networks yield positive object detection results in aerial imaging. To deal with the massive computational time required , we propose to connect an SVM Network to the different feature maps of a CNN. After the training of this SVM Network, we use an activation path to cross the network in a predefined order. We stop the crossing as quickly as possible. This early exit from the CNN allows us to reduce the computational burden. Experimental results are obtained for an industrial application in urban object detection. We show that potentially the computation cost could be reduced by 98%. Additionally, performance is slightly improved; for example, for a 55% recall, precision increases by 5%.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

Contributor : Marc Chaumont <>
Submitted on : Thursday, September 29, 2016 - 5:20:25 PM
Last modification on : Monday, February 18, 2019 - 6:43:20 PM
Long-term archiving on: Friday, December 30, 2016 - 3:13:21 PM


Files produced by the author(s)




Jérôme Pasquet, Marc Chaumont, Gérard Subsol, Mustapha Derras. Speeding-up a convolutional neural network by connecting an SVM network. ICIP: International Conference on Image Processing, Sep 2016, Phoenix, AZ, United States. pp.2286-2290, ⟨10.1109/ICIP.2016.7532766⟩. ⟨hal-01374118⟩



Record views


Files downloads