Few-shot Classification via Adaptive Attention
This work addresses the challenge of quickly adapting neural networks to new tasks with limited data, which is incremental as it builds on existing meta-learning approaches.
The paper tackles the problem of few-shot learning by proposing a meta-reweighting strategy that adapts query sample representations using reference samples, achieving state-of-the-art classification results on benchmark datasets.
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from two aspects, namely optimizing an initial model or learning a distance metric. In this work, we propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples. To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and generate soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few-shot classification. Such an adaptive attention model is also able to explain what the classification model is looking for as the evidence for classification to some extent. As demonstrated experimentally, the proposed model achieves state-of-the-art classification results on various benchmark few-shot classification and fine-grained recognition datasets.