A Data Centric Approach for Unsupervised Domain Generalization via Retrieval from Web Scale Multimodal Data
CoRR(2024)
摘要
Domain generalization (DG) is an important problem that learns a model that
can generalize to unseen test domains leveraging one or more source domains,
under the assumption of shared label spaces. However, most DG methods assume
access to abundant source data in the target label space, a requirement that
proves overly stringent for numerous real-world applications, where acquiring
the same label space as the target task is prohibitively expensive. For this
setting, we tackle the multimodal version of the unsupervised domain
generalization (UDG) problem, which uses a large task-agnostic unlabeled source
dataset, such as LAION-2B during finetuning. Our framework does not explicitly
assume any relationship between the source dataset and target task. Instead, it
relies only on the premise that the source dataset can be efficiently searched
in a joint vision-language space. For this multimodal UDG setting, we propose a
novel method to build a small (<100K) subset of the source data in three
simple steps: (1) diversified retrieval using label names as queries, (2) rank
pseudo-labeling, and (3) clustering to find representative samples. To
demonstrate the value of studying the multimodal UDG problem, we compare our
results against state-of-the-art source-free DG and zero-shot (ZS) methods on
their respective benchmarks and show up to 10
diverse target datasets. Additionally, our multi-stage dataset construction
method achieves 3
Code is available: https://github.com/Chris210634/mudg
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要