MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning

MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning

Yi Xu, Lichen Wang, Yizhou Wang, Can Qin, Yulun Zhang, Yun Fu

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 3636-3642. https://doi.org/10.24963/ijcai.2022/505

Few-shot learning aims to enable models generalize to new categories (query instances) with only limited labeled samples (support instances) from each category. Metric-based mechanism is a promising direction which compares feature embeddings via different metrics. However, it always fail to generalize to unseen domains due to the considerable domain gap challenge. In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning. Specifically, an instance normalization algorithm is explored to alleviate feature dissimilarity, which provides the initial model generalization ability. However, naively normalizing the feature would lose fine-grained discriminative knowledge between different classes. To this end, a memorized module is further proposed to separate the most refined knowledge and remember it. Then, a restitution module is utilized to restitute the discrimination ability from the learned knowledge. A novel reverse contrastive learning strategy is proposed to stabilize the distillation process. Extensive experiments on five popular benchmark datasets demonstrate that MemREIN well addresses the domain shift challenge, and significantly improves the performance up to 16.43% compared with state-of-the-art baselines.
Keywords:
Machine Learning: Few-shot learning
Computer Vision: Transfer, low-shot, semi- and un- supervised learning   
Knowledge Representation and Reasoning: Applications
Knowledge Representation and Reasoning: Other
Machine Learning: Multi-task and Transfer Learning