Trainable Class Prototypes for Few-Shot Learning
Open paper
Benchmark
Model
Rank
Results
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-1-shot
TrainProto
–
Accuracy: 58.92
unsupervised-few-shot-image-classification-on-mini-imagenet-5-way-5-shot
TrainProto
–
Accuracy: 73.94
Rank counts only results with a code link.