The Caltech101 dataset contains images from 101 object categories (e.g., “helicopter”, “elephant” and “chair” etc.) and a background category that contains the images not from the 101 object categories. For each object category, there are about 40 to 800 images, while most classes have about 50 images. The resolution of the image is roughly about 300×200 pixels.
320 PAPERS • 6 BENCHMARKS
SPair-71k contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations.
27 PAPERS • 1 BENCHMARK