Optimized Generic Feature Learning for Few-shot Classification across Domains

Abstract

To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all previous few-shot and meta-learning approaches.

References in corpus (3)

• Improved Regularization of Convolutional Neural Networks with Cutout
• Shake-Shake regularization
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

Cited by in corpus (4)

• A Universal Representation Transformer Layer for Few-Shot Image Classification
• Learning a Universal Template for Few-shot Dataset Generalization
• Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
• High-order structure preserving graph neural network for few-shot learning