Deep Neural Networks Under Stress

In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many datasets. The properties of their features remain, however, largely unstudied under the transfer perspective. In this work, we present an extensive analysis of the resiliency of feature vectors extracted from deep models, with special focus on the trade-off between performance and compression rate. By introducing perturbations to image descriptions extracted from a deep convolutional neural network, we change their precision and number of dimensions, measuring how it affects the final score. We show that deep features are more robust to these disturbances when compared to classical approaches, achieving a compression rate of 98.4%, while losing only 0.88% of their original score for Pascal VOC 2007.

[1]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Natalie D. Enright Jerger,et al.  Reduced-Precision Strategies for Bounded Memory in Deep Neural Nets , 2015, ArXiv.

[4]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[5]  Antonio Torralba,et al.  Recognizing indoor scenes , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Matthieu Cord,et al.  LR-CNN for fine-grained classification with varying resolution , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[7]  Vincent Vanhoucke,et al.  Improving the speed of neural networks on CPUs , 2011 .

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[10]  Matthieu Cord,et al.  Recipe recognition with large multimodal food dataset , 2015, 2015 IEEE International Conference on Multimedia & Expo Workshops (ICMEW).

[11]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[12]  Matthieu Cord,et al.  Exemplar based metric learning for robust visual localization , 2015, 2015 IEEE International Conference on Image Processing (ICIP).

[13]  Stéphane Mallat,et al.  Invariant Scattering Convolution Networks , 2012, IEEE transactions on pattern analysis and machine intelligence.

[14]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[15]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[16]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Andrea Vedaldi,et al.  MatConvNet: Convolutional Neural Networks for MATLAB , 2014, ACM Multimedia.

[18]  Matthieu Cord,et al.  WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Matthieu Cord,et al.  MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[20]  Yoshua Bengio,et al.  Training deep neural networks with low precision multiplications , 2014 .

[21]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[22]  Matthieu Cord,et al.  Pooling in image representation: The visual codeword point of view , 2013, Comput. Vis. Image Underst..