Built-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 performance on clean images, but fail to tackle naturally occurring perturbations. In this paper, we start from elastic perturbations, which approximate (local) view-point changes of the object. We present elastically-augmented convolutions (EAConv) by parameterizing filters as a combination of fixed elastically-perturbed bases functions and trainable weights for the purpose of integrating unseen viewpoints in the CNN. We show on CIFAR-10 and STL-10 datasets that the general robustness of our method on unseen occlusion, zoom, rotation, image cut and Gaussian perturbations improves, while significantly improving the performance on clean images without any data augmentation.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
Augmenting Model Robustness with Transformation-Invariant Attacks
The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensiti…
Image CroppingmodelTranslationSBDet: A Symmetry-Breaking Object Detector via Relaxed Rotation-Equivariance
Introducing Group Equivariant Convolution (GConv) empowers models to explore symmetries hidden in visual data, improving their performance. However, in real-world scenarios, objects or scenes often exhibit perturbations …
2D Object Detectionimage-classificationImage ClassificationObject+2Image comparison and scaling via nonlinear elasticity
A nonlinear elasticity model for comparing images is formulated and analyzed, in which optimal transformations between images are sought as minimizers of an integral functional. The existence of minimizers in a suitable …
DArFace: Deformation Aware Robustness for Low Quality Face Recognition
Facial recognition systems have achieved remarkable success by leveraging deep neural networks, advanced loss functions, and large-scale datasets. However, their performance often deteriorates in real-world scenarios inv…
Face RecognitionRobust Face RecognitionTowards Verifying the Geometric Robustness of Large-scale Neural Networks
Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation. This paper aims to verify the robustness of large-scale DNNs against the combination of multiple geometric transformations w…