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 ( Image credit: Learning Embedding Adaptation for Few-Shot Learning )
Papers
Showing 1–10 of 353 papers
All datasetsMini-Imagenet 5-way (1-shot)Mini-Imagenet 5-way (5-shot)Tiered ImageNet 5-way (5-shot)Tiered ImageNet 5-way (1-shot)CIFAR-FS 5-way (5-shot)CIFAR-FS 5-way (1-shot)CUB 200 5-way 1-shotCUB 200 5-way 5-shotFC100 5-way (1-shot)FC100 5-way (5-shot)Meta-DatasetOMNIGLOT - 1-Shot, 20-way
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SMAT (DINO-VIT-Base-16-224) | Accuracy | 85.27 | — | Unverified |
| 2 | P>M>F (P=DINO-ViT-base, M=ProtoNet) | Accuracy | 84.75 | — | Unverified |
| 3 | TSP (ResNet18; applied on TA^2-Net) | Accuracy | 81.4 | — | Unverified |
| 4 | TSA (ResNet18, URL, residual adapters, 84x84 image, shuffled data, scratch, MDL) | Accuracy | 78.07 | — | Unverified |
| 5 | UpperCaSE-EfficientNetB0 | Accuracy | 76.1 | — | Unverified |
| 6 | URL (ResNet18, 84x84 image, shuffled data, scratch, MDL) | Accuracy | 75.75 | — | Unverified |
| 7 | UpperCaSE-ResNet50 | Accuracy | 74.9 | — | Unverified |
| 8 | URT+MQDA | Accuracy | 74.3 | — | Unverified |
| 9 | URT | Accuracy | 72.15 | — | Unverified |
| 10 | SUR | Accuracy | 70.72 | — | Unverified |