论文标题
吸引和分散：一种简单的无源域适应方法
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
论文作者
论文摘要
我们提出了一种简单但有效的无源域适应性（SFDA）方法。将SFDA视为一个无监督的聚类问题，并遵循直觉，即特征空间中的本地邻居应该比其他特征具有更多相似的预测，我们建议优化预测一致性的目标。该目标鼓励特征空间中的本地邻域功能具有相似的预测，而在特征空间中更远的特征具有不同的预测，从而导致有效的特征聚类和聚类分配同时进行。为了进行有效的培训，我们试图优化目标的上限，从而有两个简单的术语。此外，我们通过可区分性和多样性的角度将流行的现有方法与域适应性，无源领域适应和对比度学习有关。实验结果证明了我们方法的优势，我们的方法可以作为SFDA未来研究的简单但强大的基线。我们的方法还可以适应无源的开放集和部分集合DA，这进一步显示了我们方法的概括能力。代码可在https://github.com/albert0147/aad_sfda中找到。
We propose a simple but effective source-free domain adaptation (SFDA) method. Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of prediction consistency. This objective encourages local neighborhood features in feature space to have similar predictions while features farther away in feature space have dissimilar predictions, leading to efficient feature clustering and cluster assignment simultaneously. For efficient training, we seek to optimize an upper-bound of the objective resulting in two simple terms. Furthermore, we relate popular existing methods in domain adaptation, source-free domain adaptation and contrastive learning via the perspective of discriminability and diversity. The experimental results prove the superiority of our method, and our method can be adopted as a simple but strong baseline for future research in SFDA. Our method can be also adapted to source-free open-set and partial-set DA which further shows the generalization ability of our method. Code is available in https://github.com/Albert0147/AaD_SFDA.
