Towards Robust Neural Networks with Lipschitz Continuity

11/22/2018
by   Muhammad Usama, et al.
0

Deep neural networks have shown remarkable performance across a wide range of vision-based tasks, particularly due to the availability of large-scale datasets for training and better architectures. However, data seen in the real world are often affected by distortions that not accounted for by the training datasets. In this paper, we address the challenge of robustness and stability of neural networks and propose a general training method that can be used to make the existing neural network architectures more robust and stable to input visual perturbations while using only available datasets for training. Proposed training method is convenient to use as it does not require data augmentation or changes in the network architecture. We provide theoretical proof as well as empirical evidence for the efficiency of the proposed training method by performing experiments with existing neural network architectures and demonstrate that same architecture when trained with the proposed training method perform better than when trained with conventional training approach in the presence of noisy datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/15/2016

Improving the Robustness of Deep Neural Networks via Stability Training

In this paper we address the issue of output instability of deep neural ...
research
05/07/2021

Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs

Although neural networks are capable of reaching astonishing performance...
research
09/08/2023

Towards Mitigating Architecture Overfitting in Dataset Distillation

Dataset distillation methods have demonstrated remarkable performance fo...
research
01/17/2022

Growing Neural Network with Shared Parameter

We propose a general method for growing neural network with shared param...
research
01/14/2019

Bayesian Learning of Neural Network Architectures

In this paper we propose a Bayesian method for estimating architectural ...
research
03/04/2023

Hierarchical Training of Deep Neural Networks Using Early Exiting

Deep neural networks provide state-of-the-art accuracy for vision tasks ...
research
05/16/2023

Noise robust neural network architecture

In which we propose neural network architecture (dune neural network) fo...

Please sign up or login with your details

Forgot password? Click here to reset