Dynamically Decoding Source Domain Knowledge For Unseen Domain Generalization

Domain generalization is an important problem which has gain much attention recently. While most existing studies focus on learning domain-invariant feature representations, some researchers try ensemble learning of multi experts and demonstrate promising performance. However, in existing multi-expert learning frameworks, the source domain knowledge has not yet been much explored, resulting in sub-optimal performance. In this paper, we propose to adapt Transformers for the purpose of dynamically decoding source domain knowledge for domain generalization. Specifically, we build one domain-specific local expert per source domain, and one domain-agnostic feature branch as query. Then, all local-domain features will be encoded by Transformer encoders, as source domain knowledge in memory. While in the Transformer decoders, the domain-agnostic query will interact with the memory in the cross-attention module, where similar domains with the input will contribute more in the attention output. This way, the source domain knowledge will be dynamically decoded for the inference of the current input from unseen domain. Therefore, this mechanism makes the proposed method well generalizable to unseen domains. The proposed method is evaluated on three benchmarks in the domain generalization field. The comparison with the state-of-the-art methods shows that the proposed method achieves the best performance, outperforming the others with a clear gap.