DeepAI
Log In Sign Up

Geodesics in fibered latent spaces: A geometric approach to learning correspondences between conditions

05/16/2020
by   Tariq Daouda, et al.
6

This work introduces a geometric framework and a novel network architecture for creating correspondences between samples of different conditions. Under this formalism, the latent space is a fiber bundle stratified into a base space encoding conditions, and a fiber space encoding the variations within conditions. The correspondences between conditions are obtained by minimizing an energy functional, resulting in diffeomorphism flows between fibers. We illustrate this approach using MNIST and Olivetti and benchmark its performances on the task of batch correction, which is the problem of integrating multiple biological datasets together.

READ FULL TEXT

page 8

page 11

page 12

page 13

page 30

page 31

page 32

09/21/2022

GNPM: Geometric-Aware Neural Parametric Models

We propose Geometric Neural Parametric Models (GNPM), a learned parametr...
10/29/2020

Latent Space Oddity: Exploring Latent Spaces to Design Guitar Timbres

We introduce a novel convolutional network architecture with an interpre...
02/01/2022

Deep Kernelized Dense Geometric Matching

Dense geometric matching is a challenging computer vision task, requirin...
04/20/2020

Learning Geometric Word Meta-Embeddings

We propose a geometric framework for learning meta-embeddings of words f...
08/06/2021

GLASS: Geometric Latent Augmentation for Shape Spaces

We investigate the problem of training generative models on a very spars...
12/27/2018

Eyes on the Prize: Improved Registration via Forward Propagation

We develop a robust method for improving pairwise correspondences for a ...
10/17/2011

Algorithms to automatically quantify the geometric similarity of anatomical surfaces

We describe new approaches for distances between pairs of 2-dimensional ...

Code Repositories

FiberedAE

Implementation of Fibered Auto-Encoders


view repo