Align, Minimize and Diversify: A Source-Free Unsupervised Domain Adaptation Method for Handwritten Text Recognition

arXiv:2404.18260v1 Announce Type: new
Abstract: This paper serves to introduce the Align, Minimize and Diversify (AMD) method, a Source-Free Unsupervised Domain Adaptation approach for Handwritten Text Recognition (HTR). This framework decouples the adaptation process from the source data, thus not only sidestepping the resource-intensive retraining process but also making it possible to leverage the wealth of pre-trained knowledge encoded in modern Deep Learning architectures. Our method explicitly eliminates the need to revisit the source data during adaptation by incorporating three …

abstract amd arxiv cs.cv data domain domain adaptation framework free paper process recognition retraining source data text type unsupervised