PASCAL-5i is a dataset used to evaluate few-shot segmentation. The dataset is sub-divided into 4 folds each containing 5 classes. A fold contains labelled samples from 5 classes that are used for evaluating the few-shot learning method. The rest 15 classes are used for training.
Source: AMP: Adaptive Masked Proxies for Few-Shot SegmentationBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
Pascal5i
|
A-MCG-Conv-LSTM
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
