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
117개CUB-200-2011 - 0-ShotCUB-LTImageNet - 0-ShotImageNet-LT-dMini-Imagenet 5-way (10-shot)SUN-LTCUB 200 50-way (0-shot)CUB-200 - 0-Shot LearningCaltech-256 5-way (1-shot)EGTEAImageNet-FS (5-shot, novel)ORBIT Clutter Video EvaluationStanford Dogs 5-way (1-shot)CIFAR-10-LT (ρ=200)CIFAR-100-LT (ρ=200)CIFAR100 5-way (1-shot)ImageNet (1-shot)ImageNet-FS (1-shot, all)ImageNet-FS (10-shot, all)ImageNet-FS (10-shot, novel)ImageNet-FS (2-shot, all)Mini-ImageNet to CUB - 5 shot learningOMNIGLOT-EMNIST 5-way (1-shot)OMNIGLOT-EMNIST 5-way (5-shot)ORBIT Clean Video EvaluationSUN - 0-ShotAWA - 0-ShotAWA1 - 0-ShotAWA2 - 0-ShotCIFAR-FS - 1-Shot Learning