Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution for cross-domain few-shot learning where there exist large domain shifts between the base task and the target task. ADAPTER is built upon the idea of bidirectional cross-attention to learn transferable features between the two domains. The proposed architecture is trained with DINO to produce diverse, and less biased features to avoid the supervision collapse problem. Furthermore, the label smoothing approach is proposed to improve the consistency and reliability of the predictions by also considering the predicted labels of the close samples in the embedding space. The performance of ADAPTER is rigorously evaluated in the BSCD-FSL benchmarks in which it outperforms prior arts with significant margins.

翻译：大多数小样本学习方法依赖于基任务与目标任务之间的同域假设，这限制了它们的实际应用。本文提出了一种自适应Transformer网络（ADAPTER），这是一种简单但有效的跨域小样本学习解决方案，适用于基任务与目标任务之间存在较大域偏移的场景。ADAPTER基于双向交叉注意力机制，旨在学习两个域之间的可迁移特征。该架构采用DINO训练策略，以生成多样化、偏差较小的特征，从而避免监督崩溃问题。此外，本文提出了标签平滑方法，通过考虑嵌入空间中邻近样本的预测标签，提高了预测的一致性和可靠性。在BSCD-FSL基准测试上对ADAPTER的性能进行了严格评估，结果表明其显著优于现有方法。