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 distinct regularization terms: the Align term, which reduces the feature distribution discrepancy between source and target data, ensuring the transferability of the pre-trained representation; the Minimize term, which encourages the model to make assertive predictions, pushing the outputs towards one-hot-like distributions in order to minimize prediction uncertainty, and finally, the Diversify term, which safeguards against the degeneracy in predictions by promoting varied and distinctive sequences throughout the target data, preventing informational collapse. Experimental results from several benchmarks demonstrated the effectiveness and robustness of AMD, showing it to be competitive and often outperforming DA methods in HTR.

该论文介绍了一种用于手写文本识别的Align, Minimize和Diversify（AMD）方法，它是一种无源无监督域自适应方法。通过解耦适应过程和源数据，这种方法不仅避免了资源密集型的重新训练过程，还能够利用现代深度学习架构中编码的丰富预训练知识。通过引入三个独立的正则化项，即对齐项、最小化项和多样化项，我们的方法明确消除了在适应过程中需要重新访问源数据的需求，保证了预训练表示的可迁移性，最小化预测的不确定性，同时通过促进目标数据中的多样性和独特序列，防止信息崩溃。多个基准实验结果证明了AMD的有效性和鲁棒性，在手写文本识别中竞争力强，常常胜过之前的域自适应方法。

对齐、最小化和多样化：一种基于源自由的无监督领域自适应方法用于手写文字识别