Wiggling Weights to Improve the Robustness of Classifiers
Robustness against unwanted perturbations is an important aspect of deploying neural network classifiers in the real world. Common natural perturbations include noise, saturation, occlusion, viewpoint changes, and blur deformations. All of them can be modelled by the newly proposed transform-augmented convolutional networks. While many approaches for robustness train the network by providing augmented data to the network, we aim to integrate perturbations in the network architecture to achieve improved and more general robustness. To demonstrate that wiggling the weights consistently improves classification, we choose a standard network and modify it to a transform-augmented network. On perturbed CIFAR-10 images, the modified network delivers a better performance than the original network. For the much smaller STL-10 dataset, in addition to delivering better general robustness, wiggling even improves the classification of unperturbed, clean images substantially. We conclude that wiggled transform-augmented networks acquire good robustness even for perturbations not seen during training.
Code (1)
Similar Papers 제목 키워드 기반
Auxiliary Training: Towards Accurate and Robust Models
Training process is crucial for the deployment of the network in applications which have two strict requirements on both accuracy and robustness. However, most existing approaches are in a dilemma, i.e. model accuracy an…
The Marginal Stability of Proteins: How Jiggling and Wiggling of Atoms are Connected to Neutral Evolution
Here we propose that the upper bound marginal stability of proteins (7.4 kcal/mol) is a universal property that includes macro-molecular complexes and is not affected by molecular changes such as mutations and Post-Trans…
Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples
Most of the existing defense methods improve the adversarial robustness by making the models adapt to the training set augmented with some adversarial examples. However, the augmented adversarial examples may not be natu…
Adversarial RobustnessBuilt-in Elastic Transformations for Improved Robustness
We focus on building robustness in the convolutions of neural visual classifiers, especially against natural perturbations like elastic deformations, occlusions and Gaussian noise. Existing CNNs show outstanding performa…
Data AugmentationSparsity-driven weighted ensemble classifier
In this study, a novel sparsity-driven weighted ensemble classifier (SDWEC) that improves classification accuracy and minimizes the number of classifiers is proposed. Using pre-trained classifiers, an ensemble in which b…
General Classification