Flatness Improves Backbone Generalisation in Few-shot Classification
This addresses the need for efficient adaptation of deep neural networks to new tasks with limited data, though it is incremental as it builds on existing few-shot classification methods.
The paper tackles the problem of improving backbone generalization in few-shot classification by introducing a flatness-aware training and fine-tuning strategy, achieving performance on par or better than state-of-the-art methods with a simpler approach.
Deployment of deep neural networks in real-world settings typically requires adaptation to new tasks with few examples. Few-shot classification (FSC) provides a solution to this problem by leveraging pre-trained backbones for fast adaptation to new classes. However, approaches for multi-domain FSC typically result in complex pipelines aimed at information fusion and task-specific adaptation without consideration of the importance of backbone training. In this work, we introduce an effective strategy for backbone training and selection in multi-domain FSC by utilizing flatness-aware training and fine-tuning. Our work is theoretically grounded and empirically performs on par or better than state-of-the-art methods despite being simpler. Further, our results indicate that backbone training is crucial for good generalisation in FSC across different adaptation methods.