Unsupervised domain adaptation with structural attribute learning networks

Domain adaptation aims at improving the performance on an unknown target domain by transferring the knowledge learned from a related source domain. In this paper, we propose a structural attribute learning network (SAL Net) which can learn transferable domain-invariance features based on the attribute learning. Our proposed SAL Net can learn both the deep visual features which describe the appearance of objects and the semantic attribute features which are robust to the domain shift. To promote the adaptation performance, we construct a structural graph of the visual and semantic attributes by a graph convolutional network(GCN). Our structural attribute learning framework not only learns the domain-invariant attribute features but also extracts the relationship of the features. We perform a set of comparative experiments on the standard domain adaptation benchmarks. The results demonstrate that our proposed method outperforms the previous adaptation methods.