Domain Generalization via Inference-time Label-Preserving Target Projections

03/01/2021
by   Prashant Pandey, et al.
0

Generalization of machine learning models trained on a set of source domains on unseen target domains with different statistics, is a challenging problem. While many approaches have been proposed to solve this problem, they only utilize source data during training but do not take advantage of the fact that a single target example is available at the time of inference. Motivated by this, we propose a method that effectively uses the target sample during inference beyond mere classification. Our method has three components - (i) A label-preserving feature or metric transformation on source data such that the source samples are clustered in accordance with their class irrespective of their domain (ii) A generative model trained on the these features (iii) A label-preserving projection of the target point on the source-feature manifold during inference via solving an optimization problem on the input space of the generative model using the learned metric. Finally, the projected target is used in the classifier. Since the projected target feature comes from the source manifold and has the same label as the real target by design, the classifier is expected to perform better on it than the true target. We demonstrate that our method outperforms the state-of-the-art Domain Generalization methods on multiple datasets and tasks.

READ FULL TEXT

page 3

page 10

page 12

page 14

page 15

research
07/28/2020

Discrepancy Minimization in Domain Generalization with Generative Nearest Neighbors

Domain generalization (DG) deals with the problem of domain shift where ...
research
03/12/2020

Deep Domain-Adversarial Image Generation for Domain Generalisation

Machine learning models typically suffer from the domain shift problem w...
research
11/19/2015

Deep Manifold Traversal: Changing Labels with Convolutional Features

Many tasks in computer vision can be cast as a "label changing" problem,...
research
08/26/2021

Learning to Diversify for Single Domain Generalization

Domain generalization (DG) aims to generalize a model trained on multipl...
research
02/11/2021

Defuse: Harnessing Unrestricted Adversarial Examples for Debugging Models Beyond Test Accuracy

We typically compute aggregate statistics on held-out test data to asses...
research
08/19/2023

TDG: Text-guided Domain Generalization

Domain generalization (DG) attempts to generalize a model trained on sin...
research
08/19/2021

Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization

Domain generalization aims to enhance the model robustness against domai...

Please sign up or login with your details

Forgot password? Click here to reset