Accuracy: 93.5
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>
논문
Accuracy: 85.63
Accuracy: 93.50
Accuracy: 85.64
Accuracy: 90.85
Accuracy: 98.7
Accuracy: 94.02
Accuracy: 83.03
Accuracy: 92.14
Accuracy: 80.07
Accuracy: 92.48
Accuracy: 88.68
Accuracy: 93.99
Accuracy: 83.42
Accuracy: 89.40
Accuracy: 91.11
Accuracy: 81.9
Accuracy: 89.18
Accuracy: 96.28
Accuracy: 96.43
Accuracy: 93.37
Accuracy: 97.12
Accuracy: 97.12
Accuracy: 90.8
Accuracy: 94.09
Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
Accuracy: 88.65
Accuracy: 91.48