A Baseline for Few-Shot Image Classification
arXiv:1909.02729
Abstract
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approach as the solution for few-shot learning, but simply use the results to highlight limitations of current benchmarks and few-shot protocols. We perform extensive studies on benchmark datasets to propose a metric that quantifies the "hardness" of a few-shot episode. This metric can be used to report the performance of few-shot algorithms in a more systematic way.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- mixup: Beyond Empirical Risk Minimization
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Meta-Learning for Semi-Supervised Few-Shot Classification
- Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
- Few-Shot Learning with Graph Neural Networks
- Distributional Smoothing with Virtual Adversarial Training
- Meta-Learning with Latent Embedding Optimization
- A Closer Look at Few-shot Classification
- Meta-learning with differentiable closed-form solvers
- Bag of Tricks for Image Classification with Convolutional Neural Networks