Current methods of blended targets domain adaptation (BTDA) usually infer or consider domain label information but underemphasize hybrid categorical feature structures of targets, which yields limited performance, especially under the label distribution shift. We demonstrate that domain labels are not directly necessary for BTDA if categorical distributions of various domains are sufficiently aligned even facing the imbalance of domains and the label distribution shift of classes. However, we observe that the cluster assumption in BTDA does not comprehensively hold. The hybrid categorical feature space hinders the modeling of categorical distributions and the generation of reliable pseudo labels for categorical alignment. To address these, we propose a categorical domain discriminator guided by uncertainty to explicitly model and directly align categorical distributions $P(Z|Y)$. Simultaneously, we utilize the low-level features to augment the single source features with diverse target styles to rectify the biased classifier $P(Y|Z)$ among diverse targets. Such a mutual conditional alignment of $P(Z|Y)$ and $P(Y|Z)$ forms a mutual reinforced mechanism. Our approach outperforms the state-of-the-art in BTDA even compared with methods utilizing domain labels, especially under the label distribution shift, and in single target DA on DomainNet.

翻译：当前混合目标域自适应（BTDA）方法通常推断或考虑域标签信息，但忽略了对目标域混合类别特征结构的关注，导致性能受限，尤其在标签分布偏移的情况下。我们证明，若各类域充分对齐类别分布，即使面对域不平衡和类别标签分布偏移，域标签对BTDA并非直接必要。然而，我们观察到BTDA中的聚类假设并不完全成立。混合类别特征空间阻碍了类别分布的建模以及用于类别对齐的可靠伪标签生成。为此，我们提出一种由不确定性引导的类别域判别器，用于显式建模并直接对齐类别分布$P(Z|Y)$。同时，利用低层特征以多样目标风格增强单一源特征，从而修正不同目标域中偏差的分类器$P(Y|Z)$。这种对$P(Z|Y)$和$P(Y|Z)$的互条件对齐形成了相互增强机制。我们的方法在BTDA中超越当前最优水平，甚至优于使用域标签的方法，尤其在标签分布偏移和DomainNet单目标域自适应场景中表现突出。