tSF: Transformer-based Semantic Filter for Few-Shot Learning
This work addresses the problem of data scarcity in machine learning for researchers and practitioners by providing a more versatile and efficient module for few-shot learning, though it is incremental as it builds on existing transformer architectures.
The paper tackles the limited utility of task-specific feature embedding modules in few-shot learning by proposing a lightweight, universal transformer-based semantic filter (tSF) that embeds knowledge from base to novel sets and filters semantic features for target categories, achieving about 2% improvement across tasks and outperforming state-of-the-art methods on benchmark datasets.
Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples. Most feature embedding modules in recent FSL methods are specially designed for corresponding learning tasks (e.g., classification, segmentation, and object detection), which limits the utility of embedding features. To this end, we propose a light and universal module named transformer-based Semantic Filter (tSF), which can be applied for different FSL tasks. The proposed tSF redesigns the inputs of a transformer-based structure by a semantic filter, which not only embeds the knowledge from whole base set to novel set but also filters semantic features for target category. Furthermore, the parameters of tSF is equal to half of a standard transformer block (less than 1M). In the experiments, our tSF is able to boost the performances in different classic few-shot learning tasks (about 2% improvement), especially outperforms the state-of-the-arts on multiple benchmark datasets in few-shot classification task.