SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

Code

• github.com/mileyan/simple_shot
  OfficialIn paperpytorch★ 0
• github.com/sicara/easy-few-shot-learning
  pytorch★ 1,301
• github.com/yhu01/PT-MAP
  pytorch★ 215
• github.com/yhu01/bms
  pytorch★ 39
• github.com/mbonto/fewshot_neuroimaging_classification
  pytorch★ 10
• github.com/mbonto/fewshot_generalization
  pytorch★ 2

Abstract

Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization outperforms prior results in three out of five settings on the miniImageNet dataset.

Tasks

Benchmark Results

Reproductions