RelationNet2: Deep Comparison Columns for Few-Shot Learning

17 Nov 2018Xueting ZhangYuting QiangFlood SungYongxin YangTimothy M. Hospedales

Few-shot deep learning is a topical challenge area for scaling visual recognition to open ended growth of unseen new classes with limited labeled examples. A promising approach is based on metric learning, which trains a deep embedding to support image similarity matching... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Few-Shot Image Classification Mini-Imagenet 20-way (1-shot) Deep Comparison Network Accuracy 32.07 # 1
Few-Shot Image Classification Mini-Imagenet 20-way (5-shot) Deep Comparison Network Accuracy 47.31 # 1
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Deep Comparison Network Accuracy 62.88 # 18
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Deep Comparison Network Accuracy 75.84 # 23
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) Deep Comparison Network Accuracy 68.83 # 10
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) Deep Comparison Network Accuracy 79.62 # 15

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