Most existing domain adaptation methods focus on adaptation from only one source domain, however, in practice there are a number of relevant sources that could be leveraged to help improve performance on target domain. We propose a novel approach named T-SVDNet to address the task of Multi-source Domain Adaptation (MDA), which is featured by incorporating Tensor Singular Value Decomposition (T-SVD) into a neural network's training pipeline. Overall, high-order correlations among multiple domains and categories are fully explored so as to better bridge the domain gap. Specifically, we impose Tensor-Low-Rank (TLR) constraint on a tensor obtained by stacking up a group of prototypical similarity matrices, aiming at capturing consistent data structure across different domains. Furthermore, to avoid negative transfer brought by noisy source data, we propose a novel uncertainty-aware weighting strategy to adaptively assign weights to different source domains and samples based on the result of uncertainty estimation. Extensive experiments conducted on public benchmarks demonstrate the superiority of our model in addressing the task of MDA compared to state-of-the-art methods.

该研究提出了一种名为T-SVDNet的新方法，通过将Tensor奇异值分解（T-SVD）结合到神经网络的训练管道中，全面探索多个域和类别之间的高阶相关性，旨在更好地弥合域差距，实现多源域自适应。与其他方法相比，在公共基准测试上，该模型在解决MDA任务时表现卓越。

T-SVDNet：探索多源域自适应的高阶样板相关性