Quantifying Translation-Invariance in Convolutional Neural Networks
A fundamental problem in object recognition is the development of image representations that are invariant to common transformations such as translation, rotation, and small deformations. There are multiple hypotheses regarding the source of translation invariance in CNNs. One idea is that translation invariance is due to the increasing receptive field size of neurons in successive convolution layers. Another possibility is that invariance is due to the pooling operation. We develop a simple a tool, the translation-sensitivity map, which we use to visualize and quantify the translation-invariance of various architectures. We obtain the surprising result that architectural choices such as the number of pooling layers and the convolution filter size have only a secondary effect on the translation-invariance of a network. Our analysis identifies training data augmentation as the most important factor in obtaining translation-invariant representations of images using convolutional neural networks.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationObject RecognitionTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Tracking translation invariance in CNNs
Although Convolutional Neural Networks (CNNs) are widely used, their translation invariance (ability to deal with translated inputs) is still subject to some controversy. We explore this question using translation-sensit…
SensitivityTranslationManitest: Are classifiers really invariant?
Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks. Nevertheless, it is unclear to which extent state-of-the-art classifiers are invariant to b…
Data AugmentationA quantifiable testing of global translational invariance in Convolutional and Capsule Networks
We design simple and quantifiable testing of global translation-invariance in deep learning models trained on the MNIST dataset. Experiments on convolutional and capsules neural networks show that both models have poor …
Data AugmentationTranslationLocality defeats the curse of dimensionality in convolutional teacher-student scenarios
Convolutional neural networks perform a local and translationally-invariant treatment of the data: quantifying which of these two aspects is central to their success remains a challenge. We study this problem within a te…
regressionDeep Learning for Target Classification from SAR Imagery: Data Augmentation and Translation Invariance
This report deals with translation invariance of convolutional neural networks (CNNs) for automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery. In particular, the translation invariance of CNNs …
Data AugmentationGeneral ClassificationTranslation