Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting

Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting

Tiange Zhang, Qing Cai, Feng Gao, Lin Qi, Junyu Dong

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 5490-5498. https://doi.org/10.24963/ijcai.2024/607

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.
Keywords:
Machine Learning: ML: Classification
Machine Learning: ML: Few-shot learning
Machine Learning: ML: Meta-learning
Machine Learning: ML: Multi-task and transfer learning