Structured Discriminative Tensor Dictionary Learning for Unsupervised Domain Adaptation
This addresses the problem of domain adaptation in computer vision for scenarios with limited labeled data, representing an incremental improvement over existing methods.
The paper tackles performance degradation in unsupervised domain adaptation due to domain shift and limited labeled source samples by learning a structured discriminative tensor dictionary to separate domain-specific and class-specific information, and it demonstrates that the proposed method outperforms state-of-the-art approaches on various datasets.
Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on vector-form data although the typical format of data or features in visual applications is multi-dimensional tensor. Besides, current methods, including the deep network approaches, assume that abundant labeled source samples are provided for training. However, the number of labeled source samples are always limited due to expensive annotation cost in practice, making sub-optimal performance been observed. In this paper, we propose to seek discriminative representation for multi-dimensional data by learning a structured dictionary in tensor space. The dictionary separates domain-specific information and class-specific information to guarantee the representation robust to domains. In addition, a pseudo-label estimation scheme is developed to combine with discriminant analysis in the algorithm iteration for avoiding the external classifier design. We perform extensive results on different datasets with limited source samples. Experimental results demonstrates that the proposed method outperforms the state-of-the-art approaches.