FSS-1000 is a 1000 class dataset for few-shot segmentation. The dataset contains significant number of objects that have never been seen or annotated in previous datasets, such as tiny daily objects, merchandise, cartoon characters, logos, etc.
Source: https://github.com/HKUSTCV/FSS-1000
Image Source: https://github.com/HKUSTCV/FSS-1000
Variants: FSS-1000
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Few-Shot Semantic Segmentation | LSeg | Language-driven Semantic Segmentation | 2022-01-10 |
| Few-Shot Semantic Segmentation | DoG-BConvLSTM | On the Texture Bias for … | 2020-03-09 |
| Few-Shot Semantic Segmentation | EfficientLab | Meta-Learning Initializations for Image Segmentation | 2019-12-13 |
Recent papers with results on this dataset: