Skip to Main content Skip to Navigation
Conference papers

Deep Neural Networks Under Stress

Abstract : In recent years, deep architectures have been used for transfer learning with state-of-the-art performance in many data-sets. 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download
Contributor : Micael Carvalho Connect in order to contact the contributor
Submitted on : Thursday, June 30, 2016 - 5:43:45 PM
Last modification on : Friday, January 8, 2021 - 5:34:10 PM
Long-term archiving on: : Saturday, October 1, 2016 - 1:15:28 PM


Files produced by the author(s)



Micael Carvalho, Matthieu Cord, Sandra Avila, Nicolas Thome, Eduardo Valle. Deep Neural Networks Under Stress. IEEE International Conference on Image Processing (ICIP 2016), Sep 2016, Phoenix, AZ, United States. ⟨10.1109/ICIP.2016.7533200⟩. ⟨hal-01340298⟩



Record views


Files downloads