Source-free domain adaptation has become popular because of its practical usefulness and no need to access source data. However, the adaptation process still takes a considerable amount of time and is predominantly based on optimization that relies on back-propagation. In this work we present a simple feed-forward approach that challenges the need for back-propagation based adaptation. Our approach is based on computing prototypes of classes under the domain shift using a pre-trained model. It achieves strong improvements in accuracy compared to the pre-trained model and requires only a small fraction of time of existing domain adaptation methods.

翻译：无源领域自适应因其实用性且无需访问源数据而逐渐流行。然而，自适应过程仍需消耗大量时间，且主要依赖基于反向传播的优化方法。本文提出一种简单的前馈方法，挑战了基于反向传播的自适应需求。该方法利用预训练模型计算域偏移下的类原型，相比预训练模型在准确率上取得了显著提升，且所需时间仅为现有领域自适应方法的极小部分。