Representation Learning Through Latent Canonicalizations

02/26/2020
by   Or Litany, et al.
21

We seek to learn a representation on a large annotated data source that generalizes to a target domain using limited new supervision. Many prior approaches to this problem have focused on learning "disentangled" representations so that as individual factors vary in a new domain, only a portion of the representation need be updated. In this work, we seek the generalization power of disentangled representations, but relax the requirement of explicit latent disentanglement and instead encourage linearity of individual factors of variation by requiring them to be manipulable by learned linear transformations. We dub these transformations latent canonicalizers, as they aim to modify the value of a factor to a pre-determined (but arbitrary) canonical value (e.g., recoloring the image foreground to black). Assuming a source domain with access to meta-labels specifying the factors of variation within an image, we demonstrate experimentally that our method helps reduce the number of observations needed to generalize to a similar target domain when compared to a number of supervised baselines.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 7

page 9

page 10

page 12

research
04/17/2023

Leveraging sparse and shared feature activations for disentangled representation learning

Recovering the latent factors of variation of high dimensional data has ...
research
07/25/2020

Learning Disentangled Representations with Latent Variation Predictability

Latent traversal is a popular approach to visualize the disentangled lat...
research
04/28/2019

Domain Agnostic Learning with Disentangled Representations

Unsupervised model transfer has the potential to greatly improve the gen...
research
10/01/2022

DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability

In representation learning, a common approach is to seek representations...
research
02/07/2020

Weakly-Supervised Disentanglement Without Compromises

Intelligent agents should be able to learn useful representations by obs...
research
11/15/2017

DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images

Disentangling factors of variation has always been a challenging problem...
research
11/11/2020

Quantifying and Learning Disentangled Representations with Limited Supervision

Learning low-dimensional representations that disentangle the underlying...

Please sign up or login with your details

Forgot password? Click here to reset