We present an approach for unsupervised domain adaptation---with a strong
focus on practical considerations of within-domain class imbalance and
between-domain class distribution shift---from a class-conditioned domain
alignment perspective. Current methods for class-conditioned domain alignment
aim to explicitly minimize a loss function based on pseudo-label estimations of
the target domain. However, these methods suffer from pseudo-label bias in the
form of error accumulation. We propose a method that removes the need for
explicit optimization of model parameters from pseudo-labels directly. Instead,
we present a sampling-based implicit alignment approach, where the sample
selection procedure is implicitly guided by the pseudo-labels. Theoretical
analysis reveals the existence of a domain-discriminator shortcut in misaligned
classes, which is addressed by the proposed implicit alignment approach to
facilitate domain-adversarial learning. Empirical results and ablation studies
confirm the effectiveness of the proposed approach, especially in the presence
of within-domain class imbalance and between-domain class distribution shift.

我们提出了一种无监督领域适应方法，采用类条件域对齐的方法来解决领域内类别不平衡和领域间类别分布偏移的实际问题。我们提出了一种采样 - based 的隐式对齐方法，旨在减轻类别伪标签偏差问题。该方法通过移除对模型参数的伪标签显式优化，并使用伪标签隐式指导样本选择过程，以缓解领域对抗性学习中偏差的问题。理论分析表明在错误类别中存在一个域鉴别器快捷方式，该方法能够修复，并通过实验结果验证了其有效性，特别是在领域内类别不平衡和领域间类别分布偏移的情况下。