Papers with Code · CC BY-SA 4.0
Few-Shot Image Classification
Few-Shot Image Classification is a computer vision task that involves training machine learning models to classify images into predefined categories using only a few labeled examples of each category (typically < 6 examples). The goal is to enable models to recognize and classify new images with minimal supervision and limited data, without having to train on large datasets. (typically < 6 examples)
<span style="color:grey; opacity: 0.6">( Image credit: Learning Embedding Adaptation for Few-Shot Learning )</span>
데이터셋
117개CIFAR-FS - 5-Shot LearningCUB 200 5-wayCUB-200-2011 5-way (1-shot)CUB-200-2011 5-way (5-shot)Caltech-256 5-way (5-shot)Caltech101CelebA-5FC100 5-way (10-shot)Fewshot-CIFAR100 - 1-Shot LearningFewshot-CIFAR100 - 5-Shot LearningFlowers-102 - 0-ShotLot-instsOMNIGLOT - 1-Shot, 1000 wayOMNIGLOT - 1-Shot, 423 wayOMNIGLOT - 5-Shot, 1000 wayOMNIGLOT - 5-Shot, 423 wayOxford 102 FlowerUT Zappos50KaPY - 0-ShotiNaturalist (227-way multi-shot)iNaturalist 2018 - 1-shotiNaturalist 2018 - 10-shotiNaturalist 2018 - 5-shotmini-ImageNet - 100-Waymini-ImageNet-LTminiImagenet → CUB (5-way 1-shot)miniImagenet → CUB (5-way 5-shot)