Berkeley Segmentation Dataset 500
Berkeley Segmentation Data Set 500 (BSDS500) is a standard benchmark for contour detection. This dataset is designed for evaluating natural edge detection that includes not only object contours but also object interior boundaries and background boundaries. It includes 500 natural images with carefully annotated boundaries collected from multiple users. The dataset is divided into three parts: 200 for training, 100 for validation and the rest 200 for test.
Source: Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
Image Source: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html
Variants: BSDS500 (Quality 30 Grayscale), BSDS500 (Quality 30 Color), BSDS500 (Quality 20 Grayscale), BSDS500 (Quality 20 Color), BSDS500 (Quality 10 Grayscale), BSDS500 (Quality 10 Color), BSDS500
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Edge Detection | RCN | Object Contour and Edge Detection … | 2019-04-30 |
Recent papers with results on this dataset: