Unsupervised Transformation Learning via Convex Relaxations

11/06/2017
by   Tatsunori B. Hashimoto, et al.
0

Our goal is to extract meaningful transformations from raw images, such as varying the thickness of lines in handwriting or the lighting in a portrait. We propose an unsupervised approach to learn such transformations by attempting to reconstruct an image from a linear combination of transformations of its nearest neighbors. On handwritten digits and celebrity portraits, we show that even with linear transformations, our method generates visually high-quality modified images. Moreover, since our method is semiparametric and does not model the data distribution, the learned transformations extrapolate off the training data and can be applied to new types of images.

READ FULL TEXT

page 8

page 11

research
06/19/2019

Learning Generalized Transformation Equivariant Representations via Autoencoding Transformations

Learning Transformation Equivariant Representations (TERs) seeks to capt...
research
03/15/2018

Studying Invariances of Trained Convolutional Neural Networks

Convolutional Neural Networks (CNNs) define an exceptionally powerful cl...
research
02/21/2020

Face Phylogeny Tree Using Basis Functions

Photometric transformations, such as brightness and contrast adjustment,...
research
03/17/2023

Image comparison and scaling via nonlinear elasticity

A nonlinear elasticity model for comparing images is formulated and anal...
research
03/27/2018

Image Semantic Transformation: Faster, Lighter and Stronger

We propose Image-Semantic-Transformation-Reconstruction-Circle(ISTRC) mo...
research
11/09/2022

ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation

Over the past few years, AI methods of generating images have been incre...
research
12/03/2019

Learning Spatially Structured Image Transformations Using Planar Neural Networks

Learning image transformations is essential to the idea of mental simula...

Please sign up or login with your details

Forgot password? Click here to reset