Search Results for author:
Found 12 papers, 2 papers with code
Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold
Our method is based on the principle that if a model is dependent on a feature, then removal of that feature should significantly harm its performance.
Learning Spatially-Continuous Fiber Orientation Functions
Recent deep learning methods in super-resolving diffusion MRIs have focused on upsampling to a fixed spatial grid, but this does not satisfy tractography's need for a continuous field.
Quantifying Hippocampal Shape Asymmetry in Alzheimer's Disease Using Optimal Shape Correspondences
Hippocampal atrophy in Alzheimer's disease (AD) is asymmetric and spatially inhomogeneous.
Feature Gradient Flow for Interpreting Deep Neural Networks in Head and Neck Cancer Prediction
This paper introduces feature gradient flow, a new technique for interpreting deep learning models in terms of features that are understandable to humans.
NASDM: Nuclei-Aware Semantic Histopathology Image Generation Using Diffusion Models
In recent years, computational pathology has seen tremendous progress driven by deep learning methods in segmentation and classification tasks aiding prognostic and diagnostic settings.
Modeling the Shape of the Brain Connectome via Deep Neural Networks
The goal of diffusion-weighted magnetic resonance imaging (DWI) is to infer the structural connectivity of an individual subject's brain in vivo.
Integrated Construction of Multimodal Atlases with Structural Connectomes in the Space of Riemannian Metrics
In order to enable population-level statistical analysis of the structural connectome, we propose representing a connectome as a Riemannian metric, which is a point on an infinite-dimensional manifold.
Structural Connectome Atlas Construction in the Space of Riemannian Metrics
The structural connectome is often represented by fiber bundles generated from various types of tractography.
The Adversarial Attack and Detection under the Fisher Information Metric
By considering the data space as a non-linear space with the Fisher information metric induced from a neural network, we first propose an adversarial attack algorithm termed one-step spectral attack (OSSA).
The Riemannian Geometry of Deep Generative Models
Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space.
Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently.
Local Group Invariant Representations via Orbit Embeddings
We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations.
