A Closer Look at Few-shot Classification

ICLR 2019 ā€¢ Wei-Yu Chen ā€¢ Yen-Cheng Liu ā€¢ Zsolt Kira ā€¢ Yu-Chiang Frank Wang ā€¢ Jia-Bin Huang

Few-shot classiļ¬cation aims to learn a classiļ¬er to recognize unseen classes during training with limited labeled examples. While signiļ¬cant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difļ¬cult... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Few-Shot Image Classification Mini-ImageNet - 5-Shot Learning Baseline++ Accuracy 76.16% # 9