Optimized Generic Feature Learning for Few-shot Classification across Domains
arXiv:2001.07926
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 (8)
- Prototypical Networks for Few-shot Learning
- Improved Regularization of Convolutional Neural Networks with Cutout
- Fine-Grained Visual Classification of Aircraft
- DropBlock: A regularization method for convolutional networks
- Revisiting Small Batch Training for Deep Neural Networks
- Shake-Shake regularization
- Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
- Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
Cited by in corpus (8)
- CrossTransformers: spatially-aware few-shot transfer
- A Universal Representation Transformer Layer for Few-Shot Image Classification
- Hyperparameter Ensembles for Robustness and Uncertainty Quantification
- Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
- Cross-domain Few-shot Learning with Task-specific Adapters
- 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