Test-Time Adaptation for Visual Document Understanding. (arXiv:2206.07240v1 [cs.CV])

Self-supervised pretraining has been able to produce transferable
representations for various visual document understanding (VDU) tasks. However,
the ability of such representations to adapt to new distribution shifts at
test-time has not been studied yet. We propose DocTTA, a novel test-time
adaptation approach for documents that leverages cross-modality self-supervised
learning via masked visual language modeling as well as pseudo labeling to
adapt models learned on a \textit{source} domain to an unlabeled
\textit{target} domain at test time. We also introduce new …

arxiv cv document understanding test time understanding