Diffusion-based Target Sampler for Unsupervised Domain Adaptation
This addresses the issue of limited transferability in deep learning models for new application scenarios, but it is incremental as it builds on existing UDA methods.
The paper tackles the problem of large domain shifts and sample scarcity in unsupervised domain adaptation (UDA) by proposing a plug-and-play Diffusion-based Target Sampler (DTS) that generates high-fidelity pseudo target samples, which improves transfer performance as demonstrated in extensive experiments on various benchmarks.
Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, unsupervised domain adaptation (UDA) has achieved significant progress in addressing this issue via learning domain-invariant features. However, large domain shifts and the sample scarcity in the target domain make existing UDA methods achieve suboptimal performance. To alleviate these issues, we propose a plug-and-play Diffusion-based Target Sampler (DTS) to generate high fidelity and diversity pseudo target samples. By introducing class-conditional information, the labels of the generated target samples can be controlled. The generated samples can well simulate the data distribution of the target domain and help existing UDA methods transfer from the source domain to the target domain more easily, thus improving the transfer performance. Extensive experiments on various benchmarks demonstrate that the performance of existing UDA methods can be greatly improved through the proposed DTS method.