A Baseline for Few-Shot Image Classification

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.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification Dirichlet CUB-200 (5-way, 1-shot) Entropy Minimization 1:1 Accuracy 67.5 # 7
Few-Shot Image Classification Dirichlet CUB-200 (5-way, 5-shot) Entropy Minimization 1:1 Accuracy 82.9 # 7
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 1-shot) Entropy Minimization 1:1 Accuracy 58.5 # 9
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 5-shot) Entropy Minimization 1:1 Accuracy 74.8 # 7
Few-Shot Image Classification Dirichlet Tiered-Imagenet (5-way, 1-shot) Entropy Minimization 1:1 Accuracy 61.2 # 9
Few-Shot Image Classification Dirichlet Tiered-Imagenet (5-way, 5-shot) Entropy Minimization 1:1 Accuracy 75.5 # 8

Methods


No methods listed for this paper. Add relevant methods here