English
Related papers

Related papers: Geodesics of learned representations

200 papers

Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three…

Computer Vision and Pattern Recognition · Computer Science 2015-06-23 Karel Lenc , Andrea Vedaldi

Learning maps between data samples is fundamental. Applications range from representation learning, image translation and generative modeling, to the estimation of spatial deformations. Such maps relate feature vectors, or map between…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Hastings Greer , Roland Kwitt , Francois-Xavier Vialard , Marc Niethammer

This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synthesis. Such interpretable directions correspond to…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 James Oldfield , Markos Georgopoulos , Yannis Panagakis , Mihalis A. Nicolaou , Ioannis Patras

When a three-dimensional object moves relative to an observer, a change occurs on the observer's image plane and in the visual representation computed by a learned model. Starting with the idea that a good visual representation is one that…

Machine Learning · Computer Science 2019-04-23 Taco S. Cohen , Max Welling

Most of the existing handcrafted and learning-based local descriptors are still at best approximately invariant to affine image transformations, often disregarding deformable surfaces. In this paper, we take one step further by proposing a…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Guilherme Potje , Renato Martins , Felipe Cadar , Erickson R. Nascimento

Deep learning models develop successive representations of their input in sequential layers, the last of which maps the final representation to the output. Here we investigate the informational content of these representations by observing…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Benjamin L. Badger

Dimensionality reduction techniques map data represented on higher dimensions onto lower dimensions with varying degrees of information loss. Graph dimensionality reduction techniques adopt the same principle of providing latent…

Machine Learning · Computer Science 2022-11-11 Akhil Pandey Akella

It is known that for a variety of choices of metrics, including the standard bottleneck distance, the space of persistence diagrams admits geodesics. Typically these existence results produce geodesics that have the form of a convex…

Metric Geometry · Mathematics 2019-05-28 Samir Chowdhury

Finding local correspondences between images with different viewpoints requires local descriptors that are robust against geometric transformations. An approach for transformation invariance is to integrate out the transformations by…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Yuan Liu , Zehong Shen , Zhixuan Lin , Sida Peng , Hujun Bao , Xiaowei Zhou

Self-supervised representation learning is heavily dependent on data augmentations to specify the invariances encoded in representations. Previous work has shown that applying diverse data augmentations is crucial to downstream performance,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Philip Andrew Mansfield , Arash Afkanpour , Warren Richard Morningstar , Karan Singhal

Recent work has established clear links between the generalization performance of trained neural networks and the geometry of their loss landscape near the local minima to which they converge. This suggests that qualitative and quantitative…

Machine Learning · Computer Science 2022-01-28 Stefan Horoi , Jessie Huang , Bastian Rieck , Guillaume Lajoie , Guy Wolf , Smita Krishnaswamy

Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the…

Neural and Evolutionary Computing · Computer Science 2015-04-01 Antti Rasmus , Tapani Raiko , Harri Valpola

Existing visual localization methods are typically either 2D image-based, which are easy to build and maintain but limited in effective geometric reasoning, or 3D structure-based, which achieve high accuracy but require a centralized…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Xudong Jiang , Fangjinhua Wang , Silvano Galliani , Christoph Vogel , Marc Pollefeys

Statistical modeling of spatiotemporal phenomena often requires selecting a covariance matrix from a covariance class. Yet standard parametric covariance families can be insufficiently flexible for practical applications, while…

Computation · Statistics 2020-12-24 Antoni Musolas , Steven T. Smith , Youssef Marzouk

Geodesic distance serves as a reliable means of measuring distance in nonlinear spaces, and such nonlinear manifolds are prevalent in the current multimodal learning. In these scenarios, some samples may exhibit high similarity, yet they…

Computer Vision and Pattern Recognition · Computer Science 2025-05-19 Shibin Mei , Hang Wang , Bingbing Ni

This communication describes a representation of images as a set of edges characterized by their position and orientation. This representation allows the comparison of two images and the computation of their similarity. The first step in…

Computer Vision and Pattern Recognition · Computer Science 2007-05-23 Joel Le Roux , Philippe Chaurand , Mickael Urrutia

Decomposing a deep neural network's learned representations into interpretable features could greatly enhance its safety and reliability. To better understand features, we adopt a geometric perspective, viewing them as a learned coordinate…

Machine Learning · Computer Science 2025-04-30 Aryeh Brill

Standard convolutions are prevalent in image processing and deep learning, but their fixed kernels limits adaptability. Several deformation strategies of the reference kernel grid have been proposed. Yet, they lack a unified theoretical…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Thomas Dagès , Michael Lindenbaum , Alfred M. Bruckstein

We introduce a general method for learning representations that are equivariant to symmetries of data. Our central idea is to decompose the latent space into an invariant factor and the symmetry group itself. The components semantically…

Machine Learning · Computer Science 2023-02-08 Giovanni Luca Marchetti , Gustaf Tegnér , Anastasiia Varava , Danica Kragic

Deep neural networks progressively transform their inputs across multiple processing layers. What are the geometrical properties of the representations learned by these networks? Here we study the intrinsic dimensionality (ID) of…

Machine Learning · Computer Science 2019-10-29 Alessio Ansuini , Alessandro Laio , Jakob H. Macke , Davide Zoccolan