Studying Invariances of Trained Convolutional Neural Networks
Convolutional Neural Networks (CNNs) define an exceptionally powerful class of models for image classification, but the theoretical background and the understanding of how invariances to certain transformations are learned is limited. In a large scale screening with images modified by different affine and nonaffine transformations of varying magnitude, we analyzed the behavior of the CNN architectures AlexNet and ResNet. If the magnitude of different transformations does not exceed a class- and transformation dependent threshold, both architectures show invariant behavior. In this work we furthermore introduce a new learnable module, the Invariant Transformer Net, which enables us to learn differentiable parameters for a set of affine transformations. This allows us to extract the space of transformations to which the CNN is invariant and its class prediction robust.
Code (0)
등록된 구현이 없습니다.
Tasks
General Classificationimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Parametrizing filters of a CNN with a GAN
It is commonly agreed that the use of relevant invariances as a good statistical bias is important in machine-learning. However, most approaches that explicitly incorporate invariances into a model architecture only make…
Generative Adversarial NetworkMeasuring Representational Robustness of Neural Networks Through Shared Invariances
A major challenge in studying robustness in deep learning is defining the set of ``meaningless'' perturbations to which a given Neural Network (NN) should be invariant. Most work on robustness implicitly uses a human as …
Learning Invariances in Neural Networks
Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present in the data, or to what extent a model sh…
image-classificationImage ClassificationMolecular Property PredictionProperty Prediction+1Learning Invariances in Neural Networks from Training Data
Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present in the data, or to what extent a model sh…
image-classificationImage ClassificationMolecular Property PredictionProperty PredictionUnderstanding Cross-Model Perceptual Invariances Through Ensemble Metamers
Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are physically distinct yet produce identica…