Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

6 Jun 2020 Yuqing Hu Vincent Gripon Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) PT+MAP Accuracy 87.69 # 2
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) PT+MAP Accuracy 90.68 # 2
Few-Shot Image Classification CUB 200 5-way 1-shot PT+MAP Accuracy 91.55% # 2
Few-Shot Image Classification CUB 200 5-way 5-shot PT+MAP Accuracy 93.99 # 2
Few-Shot Image Classification Mini-ImageNet - 1-Shot Learning PT+MAP Accuracy 82.92% # 1
Few-Shot Image Classification Mini-Imagenet 5-way (10-shot) PT+MAP Accuracy 90.03 # 1
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) PT+MAP Accuracy 82.92 # 1
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) PT+MAP Accuracy 88.82 # 2
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) PT+MAP Accuracy 62.49 # 1
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (5-shot) PT+MAP Accuracy 76.51 # 1
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) PT+MAP Accuracy 85.41 # 1
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) PT+MAP Accuracy 90.44 # 1

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