Wiggling Weights to Improve the Robustness of Classifiers
arXiv:2111.09779
Abstract
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.
arXiv commentarXiv admin note: text overlap with arXiv:2103.11372, arXiv:2107.09391
References in corpus (12)
- Intriguing properties of neural networks
- Exploring the Landscape of Spatial Robustness
- Why do deep convolutional networks generalize so poorly to small image transformations?
- Comparing deep neural networks against humans: object recognition when the signal gets weaker
- Do CIFAR-10 Classifiers Generalize to CIFAR-10?
- Locally Scale-Invariant Convolutional Neural Networks
- The Limitations of Adversarial Training and the Blind-Spot Attack
- Deep Scale-spaces: Equivariance Over Scale
- Learning perturbation sets for robust machine learning
- Quality Resilient Deep Neural Networks
- A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions
- Natural Perturbed Training for General Robustness of Neural Network Classifiers