Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation or task diversity improvement while neglecting the phenomenon that deep networks tend to rely more on high-frequency cues to make the classification decision, which thus degenerates the robustness of learned inductive bias since high-frequency information is vulnerable and easy to be disturbed by noisy information. Hence in this paper, we make one of the first attempts to propose a Frequency-Aware Prompting method with mutual attention for Cross-Domain Few-Shot classification, which can let networks simulate the human visual perception of selecting different frequency cues when facing new recognition tasks. Specifically, a frequency-aware prompting mechanism is first proposed, in which high-frequency components of the decomposed source image are switched either with normal distribution sampling or zeroing to get frequency-aware augment samples. Then, a mutual attention module is designed to learn generalizable inductive bias under CD-FSL settings. More importantly, the proposed method is a plug-and-play module that can be directly applied to most off-the-shelf CD-FLS methods. Experimental results on CD-FSL benchmarks demonstrate the effectiveness of our proposed method as well as robustly improve the performance of existing CD-FLS methods. Resources at https://github.com/tinkez/FAP_CDFSC.

翻译：随着元学习的发展，跨域少样本学习已取得显著进展。然而，现有方法大多侧重于通过特征层面的操作或任务多样性改进来学习领域自适应的归纳偏置（元知识），却忽视了深度网络倾向于依赖高频线索进行分类决策的现象。由于高频信息脆弱且易受噪声干扰，这一现象会降低所学归纳偏置的鲁棒性。为此，本文率先提出一种基于互注意力机制的频率感知提示方法用于跨域少样本分类，使网络能够模拟人类在面对新识别任务时选择不同频率线索的视觉感知机制。具体而言，我们首先提出频率感知提示机制：通过将分解后的源图像高频分量替换为正态分布采样或零值化，生成频率感知增强样本。随后，设计互注意力模块以在跨域少样本学习设定下学习可泛化的归纳偏置。更重要的是，该方法为即插即用模块，可直接应用于大多数现成的跨域少样本学习方法。在跨域少样本学习基准测试上的实验结果表明，所提方法不仅有效，还能稳健提升现有跨域少样本学习方法的性能。相关资源详见 https://github.com/tinkez/FAP_CDFSC。