Tailoring Embedding Function to Heterogeneous Few-Shot Tasks by Global and Local Feature Adaptors
AbstractFew-Shot Learning (FSL) is essential for visual recognition. Many methods tackle this challenging problem via learning an embedding function from seen classes and transfer it to unseen classes with a few labeled instances. Researchers recently found it beneficial to incorporate task-specific feature adaptation into FSL models, which produces the most representative features for each task. However, these methods ignore the diversity of classes and apply a global transformation to the task. In this paper, we propose Global and Local Feature Adaptor (GLoFA), a unifying framework that tailors the instance representation to specific tasks by global and local feature adaptors. We claim that class-specific local transformation helps to improve the representation ability of feature adaptor. Global masks tend to capture sketchy patterns, while local masks focus on detailed characteristics. A strategy to measure the relationship between instances adaptively based on the characteristics of both tasks and classes endow GLoFA with the ability to handle mix-grained tasks. GLoFA outperforms other methods on a heterogeneous task distribution and achieves competitive results on benchmark datasets.
How to Cite
Lu, S., Ye, H.-J., & Zhan, D.-C. (2021). Tailoring Embedding Function to Heterogeneous Few-Shot Tasks by Global and Local Feature Adaptors. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 8776-8783. https://doi.org/10.1609/aaai.v35i10.17063
AAAI Technical Track on Machine Learning III