Multi-label Few-shot Learning with Semantic Inference (Student Abstract)

Few-shot learning can adapt the classification model to new labels with only a few labeled examples. Previous studies mainly focus on scenario of single category label per example but have not solved more challenging multi-label exponential-sized output space and low-data effectively. In this paper, we propose semantic-aware meta-learning for few-shot learning. Our approach learn infer semantic correlation between unseen historical quickly tasks from Specifically, features be mapped into embedding via word vectors explore exploit correlation, thus cope challenge overwhelming size space. Then novel inference mechanism is designed leveraging prior knowledge learned labels, which will produce good generalization performance alleviate problem. Finally, extensive empirical results show that proposed method significantly outperforms existing state-of-the-art methods tasks.