Saved in:
Bibliographic Details
Main Authors: Thomas, Xavier, Ghadiyaram, Deepti
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.06698
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910921411002368
author Thomas, Xavier
Ghadiyaram, Deepti
author_facet Thomas, Xavier
Ghadiyaram, Deepti
contents Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. In this work, we study how model architectures and pre-training objectives impact feature richness and propose a method to effectively leverage them for domain generalization. Specifically, given a pre-trained feature space, we first discover latent domain structures, referred to as pseudo-domains, that capture domain-specific variations in an unsupervised manner. Next, we augment existing classifiers with these complementary pseudo-domain representations making them more amenable to diverse unseen test domains. We analyze how different pre-training feature spaces differ in the domain-specific variances they capture. Our empirical studies reveal that features from diffusion models excel at separating domains in the absence of explicit domain labels and capture nuanced domain-specific information. On 5 datasets, we show that our very simple framework improves generalization to unseen domains by a maximum test accuracy improvement of over 4% compared to the standard baseline Empirical Risk Minimization (ERM). Crucially, our method outperforms most algorithms that access domain labels during training.
format Preprint
id arxiv_https___arxiv_org_abs_2503_06698
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
Thomas, Xavier
Ghadiyaram, Deepti
Machine Learning
Computer Vision and Pattern Recognition
Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. In this work, we study how model architectures and pre-training objectives impact feature richness and propose a method to effectively leverage them for domain generalization. Specifically, given a pre-trained feature space, we first discover latent domain structures, referred to as pseudo-domains, that capture domain-specific variations in an unsupervised manner. Next, we augment existing classifiers with these complementary pseudo-domain representations making them more amenable to diverse unseen test domains. We analyze how different pre-training feature spaces differ in the domain-specific variances they capture. Our empirical studies reveal that features from diffusion models excel at separating domains in the absence of explicit domain labels and capture nuanced domain-specific information. On 5 datasets, we show that our very simple framework improves generalization to unseen domains by a maximum test accuracy improvement of over 4% compared to the standard baseline Empirical Risk Minimization (ERM). Crucially, our method outperforms most algorithms that access domain labels during training.
title What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.06698