Few-Shot Learning by Integrating Spatial and Frequency Representation
This work addresses the challenge of few-shot learning for machine learning systems, offering a domain-specific improvement that is incremental in nature.
The paper tackles the problem of few-shot learning by integrating frequency information with spatial representations to improve classification accuracy, achieving significant boosts across various backbones, datasets, and algorithms.
Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algorithms in few-shot learning only utilize spatial information of the images. In this paper, we propose to integrate the frequency information into the learning model to boost the discrimination ability of the system. We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification. The proposed strategy and its effectiveness are validated with different backbones, datasets, and algorithms. Extensive experiments demonstrate that the frequency information is complementary to the spatial representations in few-shot classification. The classification accuracy is boosted significantly by integrating features from both the spatial and frequency domains in different few-shot learning tasks.