Domain Generalization for Domain-Linked Classes
- URL: http://arxiv.org/abs/2306.00879v1
- Date: Thu, 1 Jun 2023 16:39:50 GMT
- Title: Domain Generalization for Domain-Linked Classes
- Authors: Kimathi Kaai, Saad Hossain, Sirisha Rambhatla
- Abstract summary: In the real-world, classes may often be domain-linked, i.e. expressed only in a specific domain.
We propose a Fair and cONtrastive feature-space regularization algorithm for Domain-linked DG, FOND.
- Score: 8.738092015092207
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Domain generalization (DG) focuses on transferring domain-invariant knowledge
from multiple source domains (available at train time) to an, a priori, unseen
target domain(s). This requires a class to be expressed in multiple domains for
the learning algorithm to break the spurious correlations between domain and
class. However, in the real-world, classes may often be domain-linked, i.e.
expressed only in a specific domain, which leads to extremely poor
generalization performance for these classes. In this work, we aim to learn
generalizable representations for these domain-linked classes by transferring
domain-invariant knowledge from classes expressed in multiple source domains
(domain-shared classes). To this end, we introduce this task to the community
and propose a Fair and cONtrastive feature-space regularization algorithm for
Domain-linked DG, FOND. Rigorous and reproducible experiments with baselines
across popular DG tasks demonstrate our method and its variants' ability to
accomplish state-of-the-art DG results for domain-linked classes. We also
provide practical insights on data conditions that increase domain-linked class
generalizability to tackle real-world data scarcity.
Related papers
- Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions.
We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space.
Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
arXiv Detail & Related papers (2022-03-24T11:54:59Z) - Unsupervised Domain Generalization by Learning a Bridge Across Domains [78.855606355957]
Unsupervised Domain Generalization (UDG) setup has no training supervision in neither source nor target domains.
Our approach is based on self-supervised learning of a Bridge Across Domains (BrAD) - an auxiliary bridge domain accompanied by a set of semantics preserving visual (image-to-image) mappings to BrAD from each of the training domains.
We show how using an edge-regularized BrAD our approach achieves significant gains across multiple benchmarks and a range of tasks, including UDG, Few-shot UDA, and unsupervised generalization across multi-domain datasets.
arXiv Detail & Related papers (2021-12-04T10:25:45Z) - Exploiting Domain-Specific Features to Enhance Domain Generalization [10.774902700296249]
Domain Generalization (DG) aims to train a model, from multiple observed source domains, in order to perform well on unseen target domains.
Prior DG approaches have focused on extracting domain-invariant information across sources to generalize on target domains.
We propose meta-Domain Specific-Domain Invariant (mD) - a novel theoretically sound framework.
arXiv Detail & Related papers (2021-10-18T15:42:39Z) - Structured Latent Embeddings for Recognizing Unseen Classes in Unseen
Domains [108.11746235308046]
We propose a novel approach that learns domain-agnostic structured latent embeddings by projecting images from different domains.
Our experiments on the challenging DomainNet and DomainNet-LS benchmarks show the superiority of our approach over existing methods.
arXiv Detail & Related papers (2021-07-12T17:57:46Z) - Domain Consistency Regularization for Unsupervised Multi-source Domain
Adaptive Classification [57.92800886719651]
Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years.
domain shift in MUDA exists not only between the source and target domains but also among multiple source domains.
We propose an end-to-end trainable network that exploits domain Consistency Regularization for unsupervised Multi-source domain Adaptive classification.
arXiv Detail & Related papers (2021-06-16T07:29:27Z) - Open Domain Generalization with Domain-Augmented Meta-Learning [83.59952915761141]
We study a novel and practical problem of Open Domain Generalization (OpenDG)
We propose a Domain-Augmented Meta-Learning framework to learn open-domain generalizable representations.
Experiment results on various multi-domain datasets demonstrate that the proposed Domain-Augmented Meta-Learning (DAML) outperforms prior methods for unseen domain recognition.
arXiv Detail & Related papers (2021-04-08T09:12:24Z) - Robust Domain-Free Domain Generalization with Class-aware Alignment [4.442096198968069]
Domain-Free Domain Generalization (DFDG) is a model-agnostic method to achieve better generalization performance on the unseen test domain.
DFDG uses novel strategies to learn domain-invariant class-discriminative features.
It obtains competitive performance on both time series sensor and image classification public datasets.
arXiv Detail & Related papers (2021-02-17T17:46:06Z) - Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation [65.38975706997088]
Open set domain adaptation (OSDA) assumes the presence of unknown classes in the target domain.
We show that existing state-of-the-art methods suffer a considerable performance drop in the presence of larger domain gaps.
We propose a novel framework to specifically address the larger domain gaps.
arXiv Detail & Related papers (2020-03-08T14:20:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.