Learning to Compare: Relation Network for Few-Shot Learning

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) Relation Networks* Accuracy 69.3 # 20
Few-Shot Image Classification CUB 200 5-way 1-shot Relation Net Accuracy 50.44 # 17
Few-Shot Image Classification CUB 200 5-way 5-shot Relation Net Accuracy 65.32 # 16
Few-Shot Image Classification Meta-Dataset Relation Networks Accuracy 53.315 # 14
Few-Shot Image Classification Meta-Dataset Rank Relation Networks Mean Rank 11.8 # 13
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) Relation Networks Accuracy 34.9 # 8
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) Relation Networks Accuracy 47.9 # 11
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Relation Net (Sung et al., 2018) Accuracy 50.4 # 55
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Relation Net Accuracy 97.6% # 6
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Relation Net Accuracy 99.6 # 4
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Relation Net Accuracy 99.1% # 8
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Relation Net Accuracy 99.8 # 7
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) Relation Networks Accuracy 36.3 # 9
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) Relation Networks Accuracy 58.0 # 7

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) RelationNet (Sung et al., 2018) Accuracy 42.91 # 5
Image Classification Tiered ImageNet 5-way (5-shot) Relation Net Accuracy 71.31 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet