Filters








47,991 Hits in 6.2 sec

On Robustness and Transferability of Convolutional Neural Networks [article]

Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D'Amour, Dan Moldovan, Sylvain Gelly, Neil Houlsby (+2 others)
2021 arXiv   pre-print
Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts.  ...  In this work we study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time and investigate the impact of the pre-training data size,  ...  Imagenet classification with deep convolutional neural networks.  ... 
arXiv:2007.08558v2 fatcat:ylrcyve67baxzkbhuq7xsaucky

A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks [article]

Jacob M. Springer, Melanie Mitchell, Garrett T. Kenyon
2021 arXiv   pre-print
representation-targeted adversarial attacks, even between architectures as different as convolutional neural networks and transformers.  ...  Here, we show that training the source classifier to be "slightly robust" -- that is, robust to small-magnitude adversarial examples -- substantially improves the transferability of class-targeted and  ...  Acknowledgments and Disclosure of Funding The authors would like to thank Rory Soiffer, Juston Moore, and Hadyn Jones for their helpful discussions and comments.  ... 
arXiv:2106.02105v2 fatcat:gjgkossynncw7k6iexown7rlpq

Convolutional neural network transfer learning for robust face recognition in NAO humanoid robot

D. Bussey, A. Glandon, L. Vidyaratne, M. Alam, K. M. Iftekharuddin
2017 2017 IEEE Symposium Series on Computational Intelligence (SSCI)  
Future Research and Applications • Apply transfer learning to the convolutional neural network AlexNet [5] for face recognition tasks. • Compare the performance of the retrained AlexNet to VGG-Face  ...  or a high resolution camera to run through the convolutional neural network. • Extract the features of the input image using the neural networks AlexNet and VGG-Face • Compare the features of the input  ... 
doi:10.1109/ssci.2017.8285347 dblp:conf/ssci/BusseyGVAI17 fatcat:4qyk3daoazakna24ooo6bzwwpy

Titles

2019 2019 4th International Conference on Pattern Recognition and Image Analysis (IPRIA)  
Neural Networks A Variational Pansharpening Algorithm Based on Total Variation and Primal-Dual Optimization A Convolutional Neural Network model based on Neutrosophy for Noisy Speech Recognition GAKH:  ...  Convolutional Neural Networks Sparse Representation-based Multi-focus Image Fusion in a Hybrid of DWT and NSCT Active Transfer Learning for Persian Offline Signature Verification Biologically inspired  ... 
doi:10.1109/pria.2019.8785061 fatcat:e43b5ycj2jfybk4ozrvqzhsk4a

Are Accuracy and Robustness Correlated

Andras Rozsa, Manuel Gunther, Terrance E. Boult
2016 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)  
In this paper, we perform experiments on various adversarial example generation approaches with multiple deep convolutional neural networks including Residual Networks, the best performing models on ImageNet  ...  We compare the adversarial example generation techniques with respect to the quality of the produced images, and measure the robustness of the tested machine learning models to adversarial examples.  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the  ... 
doi:10.1109/icmla.2016.0045 dblp:conf/icmla/RozsaGB16 fatcat:5uipk3eixbez5bydk4qobk7usa

Noise Annoyance Prediction of Urban Substation Based on Transfer Learning and Convolutional Neural Network

Shengping Fan, Jun Li, Linyong Li, Zhigang Chu
2022 Energies  
To accurately assess the degree of noise annoyance caused by substations to surrounding residents, we established a noise annoyance prediction model based on transfer learning and a convolution neural  ...  The resultant convolutional neural network model showed high accuracy and robustness, and the error between the prediction result and the subjective evaluation result was between 2% and 7%.  ...  Conflicts of Interest: The authors declare no potential conflict of interest with respect to the research, authorship, and/or publication of this article.  ... 
doi:10.3390/en15030749 doaj:9b34b1dfbb1a461ba274b26b63d6d877 fatcat:o63z663trbdkvjiqetlhbn44dm

On the transferability of adversarial examples between convex and 01 loss models [article]

Yunzhe Xue, Meiyan Xie, Usman Roshan
2020 arXiv   pre-print
As a result of this non-transferability we show that our dual layer sign activation network with 01 loss can attain robustness on par with simple convolutional networks.  ...  We show intuitively by example how the non-continuity of 01 loss makes adversaries non-transferable in a dual layer neural network.  ...  Comparison to convolutional neural networks We finally compare black box robustness of our 01 loss models to simple convolutional neural networks.  ... 
arXiv:2006.07800v2 fatcat:gjqy6juvijhn7fqqyp5g7xathq

Dropout in Neural Networks Simulates the Paradoxical Effects of Deep Brain Stimulation on Memory [article]

Shawn Zheng Kai Tan, Richard Du, Jose Angelo Udal Perucho, Shauhrat S Chopra, Varut Vardhanabhut, Lee Wei Lim
2020 bioRxiv   pre-print
We further showed that transfer learning of neural networks with dropout had increased accuracy and rate of learning.  ...  We used a convolutional neural network to classify handwritten digits and letters, applying dropout at different stages to simulate DBS effects on engrams.  ...  Acknowledgements & Disclosures The scientific work was funded by grants from the Hong Kong Research Grant Council (RGC-ECS 27104616) and The University of Hong Kong URC Supplementary Funding (102009728  ... 
doi:10.1101/2020.05.01.073486 fatcat:pskcr2ceoveebiqlkjcofwlzza

Towards adversarial robustness with 01 loss neural networks [article]

Yunzhe Xue, Meiyan Xie, Usman Roshan
2020 arXiv   pre-print
One measure of a model's robustness is the minimum distortion required to make the input adversarial.  ...  We compare the minimum distortion of the 01 loss network to the binarized neural network and the standard sigmoid activation network with cross-entropy loss all trained with and without Gaussian noise  ...  Index Terms-adversarial attacks, transferability of adversarial examples, 01 loss, stochastic coordinate descent, convolutional neural networks, deep learning I.  ... 
arXiv:2008.09148v1 fatcat:lkvy5tztazco7djd7r2rnwcdgq

MVIP 2020 Table of Contents

2020 2020 International Conference on Machine Vision and Image Processing (MVIP)  
Fast Prediction of Cortical Dementia Based on Original Brain MRI images Using Convolutional Neural Network 14.  ...  Image Colorization using Generative Adversarial Networks and Transfer Learning 10. Brain MR Image Classification for ADHD Diagnosis Using Deep Neural Networks 11.  ... 
doi:10.1109/mvip49855.2020.9116904 fatcat:6v7rolxpkfh6jb2fg2bhd4ssuq

Facial Expression Recognition Using Transfer Learning on Deep Convolutional Network

Ramchand Hablani
2020 Bioscience Biotechnology Research Communications  
First, we applied transfer learning to AlexNet, and VGG19 for classification. Second, we used AlexNet and Vgg19 for feature extraction and cascaded it with an SVM for classification.  ...  We achieved 86.11% accuracy with AlexNet and 94.44% with AlexNet-SVM cascade. We also achieved 94.44% accuracy with VGG19 and 86.11 with VGG19-SVM cascade.  ...  Convolution operation: convolutional neural network is based on convolution operation. the convolution operation in one dimension is define as y(n)=x(n)*h(n) (1) y(n) = ∑ k x(k)h(n-k) (2) Where x(n) is  ... 
doi:10.21786/bbrc/13.14/44 fatcat:tkdmapv2u5gmhbgsg3yeoj5tta

Age Invariant Face Recognition Using Convolutional Neural Networks and Set Distances

Hachim El Khiyari, Harry Wechsler
2017 Journal of Information Security  
Facial features are extracted using a convolutional neural network characteristic of deep learning.  ...  and aging.  ...  We use a robust feature extraction method based on deep convolutional neural networks (CNN) [4] [5] and transfer learning [6] .  ... 
doi:10.4236/jis.2017.83012 fatcat:ypafmfsnlreqpfdz2l7xuafqmu

Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks [article]

Hermann Baumgartl, Ricardo Buettner
2021 arXiv   pre-print
We achieved state-of-the-art results using various baseline convolutional neural networks and showed the robustness against lighting and viewpoint changes in challenging mobile robot place recognition.  ...  By training three mobile-ready (EfficientNetB0, MobileNetV2, MobileNetV3) and two large-scale baseline (VGG16, ResNet50) convolutional neural network architectures on the widely available Event8, Scene15  ...  ACKNOWLEDGMENT This research is partly funded by the German Federal Ministry of Education and Research (no. 13FH176PX8, no. 13FH4I05IA, no. 13FH566KX9).  ... 
arXiv:2107.11187v1 fatcat:m543iw3vzfb7panf3q24azwsdm

Implicit Priors for Knowledge Sharing in Bayesian Neural Networks [article]

Jack K Fitzsimons, Sebastian M Schmon, Stephen J Roberts
2019 arXiv   pre-print
, model robustness and regularisation.  ...  Bayesian interpretations of neural network have a long history, dating back to early work in the 1990's and have recently regained attention because of their desirable properties like uncertainty estimation  ...  Schmon's research is supported by the Engineering and Physical Sciences Research Council (EPSRC) grant EP/K503113/1.  ... 
arXiv:1912.00874v1 fatcat:2jehspgl3bf4ziknlzomyxkyvi

Dropout in Neural Networks Simulates the Paradoxical Effects of Deep Brain Stimulation on Memory

Shawn Zheng Kai Tan, Richard Du, Jose Angelo Udal Perucho, Shauhrat S. Chopra, Varut Vardhanabhuti, Lee Wei Lim
2020 Frontiers in Aging Neuroscience  
Dropout during training provided a more robust "skeleton" network and, together with transfer learning, mimicked the effects of chronic DBS on memory.  ...  We used a convolutional neural network (CNN) to classify handwritten digits and letters and applied dropout at different stages to simulate DBS effects on engrams.  ...  Dropout during training provided a more robust "skeleton" network and, together with transfer learning, mimicked the effects of chronic DBS on memory.  ... 
doi:10.3389/fnagi.2020.00273 pmid:33093830 pmcid:PMC7521073 fatcat:iumyssczzndxdozr64gs566liy
« Previous Showing results 1 — 15 out of 47,991 results