用于无源混合目标域适应的证据图对比对齐
Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptation
- Sun Yat-Sen University（中山大学）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对无源混合目标域适应（SF-BTDA）问题，提出证据对比对齐方法（ECA），通过校准证据学习模块提升伪标签质量，并利用图对比学习缓解标签偏移，显著优于现有方法。
AI中文摘要：
在本文中，我们首先解决一个更现实的域适应（DA）设置：无源混合目标域适应（SF-BTDA），在该设置中我们无法访问源域数据，同时面临混合的多个目标域且没有任何域标签。与现有的DA场景相比，SF-BTDA通常面临不同目标中不同标签偏移的共存，以及由源模型生成的噪声目标伪标签。在本文中，我们提出了一种名为证据对比对齐（ECA）的新方法，以解耦混合目标域并减轻噪声目标伪标签的影响。首先，为了提高目标伪标签的质量，我们提出了一个校准的证据学习模块，以迭代地提高生成模型的准确性和确定性，并自适应地生成高质量的目标伪标签。其次，我们设计了一种图对比学习，结合域距离矩阵和置信度-不确定性准则，以最小化混合目标域中同一类别样本的分布差距，从而缓解混合目标中不同标签偏移的共存。我们基于三个标准DA数据集构建了一个新基准，ECA以可观的增益优于其他方法，并与那些预先具有域标签或源数据的方法取得了可比的结果。
英文摘要：
In this paper, we firstly tackle a more realistic Domain Adaptation (DA) setting: Source-Free Blending-Target Domain Adaptation (SF-BTDA), where we can not access to source domain data while facing mixed multiple target domains without any domain labels in prior. Compared to existing DA scenarios, SF-BTDA generally faces the co-existence of different label shifts in different targets, along with noisy target pseudo labels generated from the source model. In this paper, we propose a new method called Evidential Contrastive Alignment (ECA) to decouple the blending target domain and alleviate the effect from noisy target pseudo labels. First, to improve the quality of pseudo target labels, we propose a calibrated evidential learning module to iteratively improve both the accuracy and certainty of the resulting model and adaptively generate high-quality pseudo target labels. Second, we design a graph contrastive learning with the domain distance matrix and confidence-uncertainty criterion, to minimize the distribution gap of samples of a same class in the blended target domains, which alleviates the co-existence of different label shifts in blended targets. We conduct a new benchmark based on three standard DA datasets and ECA outperforms other methods with considerable gains and achieves comparable results compared with those that have domain labels or source data in prior.
