paper-with-me

홈 › Papers

Invariance and Stability of Deep Convolutional Representations

2017-12-01 · NeurIPS 2017 12 · Alberto Bietti, Julien Mairal

In this paper, we study deep signal representations that are near-invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information. This is achieved by generalizing the multilayer kernel introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable, and that models from this functional space, such as a large class of convolutional neural networks, may enjoy the same stability.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations

2017-06-09 · Alberto Bietti, Julien Mairal

The success of deep convolutional architectures is often attributed in part to their ability to learn multiscale and invariant representations of natural signals. However, a precise study of these properties and how they…

Generalization Bounds

Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs

2018-04-12 · ICLR 2019 5 · Avraham Ruderman, Neil C. Rabinowitz, Ari S. Morcos, Daniel Zoran

Many of our core assumptions about how neural networks operate remain empirically untested. One common assumption is that convolutional neural networks need to be stable to small translations and deformations to solve im…

General Classificationimage-classificationImage ClassificationInductive Bias

Unitary convolutions for learning on graphs and groups

2024-10-07 · Bobak T. Kiani, Lukas Fesser, Melanie Weber

Data with geometric structure is ubiquitous in machine learning often arising from fundamental symmetries in a domain, such as permutation-invariance in graphs and translation-invariance in images. Group-convolutional ar…

Inductive Bias

Deep Convolutional Neural Networks on Cartoon Functions

2016-04-29 · Philipp Grohs, Thomas Wiatowski, Helmut Bölcskei

Wiatowski and B\"olcskei, 2015, proved that deformation stability and vertical translation invariance of deep convolutional neural network-based feature extractors are guaranteed by the network structure per se rather th…

Translation

Quantifying Translation-Invariance in Convolutional Neural Networks

2017-12-10 · Eric Kauderer-Abrams

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 re…

Data AugmentationObject RecognitionTranslation