Meta-Learning with Differentiable Convex Optimization

CVPR 2019 Kwonjoon LeeSubhransu MajiAvinash RavichandranStefano Soatto

Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization... (read more)

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 72.8 # 10
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 85 # 9
Few-Shot Image Classification FC100 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 47.2 # 3
Few-Shot Image Classification FC100 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 62.5 # 5
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 64.09 # 19
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 80 # 18
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 65.81 # 16
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 81.75 # 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