Search Results for author:
Found 37 papers, 20 papers with code
CARL: A Framework for Equivariant Image Registration
Image registration estimates spatial correspondences between a pair of images.
Neural Persistence Dynamics
We consider the problem of learning the dynamics in the topology of time-evolving point clouds, the prevalent spatiotemporal model for systems exhibiting collective behavior, such as swarms of insects and birds or particles in physics.
uniGradICON: A Foundation Model for Medical Image Registration
We therefore propose uniGradICON, a first step toward a foundation model for registration providing 1) great performance \emph{across} multiple datasets which is not feasible for current learning-based registration methods, 2) zero-shot capabilities for new registration tasks suitable for different acquisitions, anatomical regions, and modalities compared to the training dataset, and 3) a strong initialization for finetuning on out-of-distribution registration tasks.
Position: Topological Deep Learning is the New Frontier for Relational Learning
At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.
Latent SDEs on Homogeneous Spaces
We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE).
Inverse Consistency by Construction for Multistep Deep Registration
Inverse consistency is a desirable property for image registration.
GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency
We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration.
$\texttt{GradICON}$: Approximate Diffeomorphisms via Gradient Inverse Consistency
We present an approach to learning regular spatial transformations between image pairs in the context of medical image registration.
On Measuring Excess Capacity in Neural Networks
We study the excess capacity of deep networks in the context of supervised classification.
Comparing object recognition in humans and deep convolutional neural networks -- An eye tracking study
Deep convolutional neural networks (DCNNs) and the ventral visual pathway share vast architectural and functional similarities in visual challenges such as object recognition.
Topological Attention for Time Series Forecasting
The problem of (point) forecasting $ \textit{univariate} $ time series is considered.
ICON: Learning Regular Maps Through Inverse Consistency
We explore if it is possible to obtain spatial regularity using an inverse consistency loss only and elucidate what explains map regularity in such a context.
Sparse Pose Trajectory Completion
In the absence of dense pose sampling in image space, these latent space trajectories provide cross-modal guidance for learning.
Dissecting Supervised Contrastive Learning
Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks.
A Shooting Formulation of Deep Learning
Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE).
Topologically Densified Distributions
We study regularization in the context of small sample-size learning with over-parameterized neural networks.
Deep Multi-View Learning via Task-Optimal CCA
Canonical Correlation Analysis (CCA) is widely used for multimodal data analysis and, more recently, for discriminative tasks such as multi-view learning; however, it makes no use of class labels.
Connectivity-Optimized Representation Learning via Persistent Homology
In particular, we control the connectivity of an autoencoder's latent space via a novel type of loss, operating on information from persistent homology.
Graph Filtration Learning
We propose an approach to learning with graph-structured data in the problem domain of graph classification.
Metric Learning for Image Registration
Our approach is a radical departure from existing deep learning approaches to image registration by embedding a deep learning model in an optimization-based registration algorithm to parameterize and data-adapt the registration model itself.
Ranked #1 on
Diffeomorphic Medical Image Registration
on CUMC12
Stochastic Block Models with Multiple Continuous Attributes
While there are recent examples in the literature that combine connectivity and attribute information to inform community detection, our model is the first augmented stochastic block model to handle multiple continuous attributes.
Feature Space Transfer for Data Augmentation
A new architecture, denoted the FeATure TransfEr Network (FATTEN), is proposed for the modeling of feature trajectories induced by variations of object pose.
Brain Extraction from Normal and Pathological Images: A Joint PCA/Image-Reconstruction Approach
Extracting the brain from images with strong pathologies, for example, the presence of a tumor or of a traumatic brain injury, is challenging.
Fast Predictive Simple Geodesic Regression
Deformable image registration and regression are important tasks in medical image analysis.
Deep Learning with Topological Signatures
Inferring topological and geometrical information from data can offer an alternative perspective on machine learning problems.
AGA: Attribute-Guided Augmentation
We implement our approach as a deep encoder-decoder architecture that learns the synthesis function in an end-to-end manner.
Compressing networks with super nodes
Community detection is a commonly used technique for identifying groups in a network based on similarities in connectivity patterns.
Social and Information Networks Physics and Society
Quicksilver: Fast Predictive Image Registration - a Deep Learning Approach
A deep encoder-decoder network is used as the prediction model.
Efficient Registration of Pathological Images: A Joint PCA/Image-Reconstruction Approach
Registration involving one or more images containing pathologies is challenging, as standard image similarity measures and spatial transforms cannot account for common changes due to pathologies.
Fast Predictive Multimodal Image Registration
We introduce a deep encoder-decoder architecture for image deformation prediction from multimodal images.
AGA: Attribute Guided Augmentation
We implement our approach as a deep encoder-decoder architecture that learns the synthesis function in an end-to-end manner.
Fast Predictive Image Registration
We present a method to predict image deformations based on patch-wise image appearance.
One-Shot Learning of Scene Locations via Feature Trajectory Transfer
In particular, we leverage a recently introduced dataset with fine-grain annotations to estimate feature trajectories for a collection of transient attributes and then show how these trajectories can be transferred to new image representations.
Statistical Topological Data Analysis - A Kernel Perspective
We consider the problem of statistical computations with persistence diagrams, a summary representation of topological features in data.
Parametric Regression on the Grassmannian
We then specialize this idea to the Grassmann manifold and demonstrate that it yields a simple, extensible and easy-to-implement solution to the parametric regression problem.
Proceedings of The 39th Annual Workshop of the Austrian Association for Pattern Recognition (OAGM), 2015
The 39th annual workshop of the Austrian Association for Pattern Recognition (OAGM/AAPR) provides a platform for presentation and discussion of research progress as well as research projects within the OAGM/AAPR community.
A Stable Multi-Scale Kernel for Topological Machine Learning
Topological data analysis offers a rich source of valuable information to study vision problems.
