FSS-1000

FSS-1000 is a few-shot segmentation dataset where the number of annotated training examples are limited to 5 only. It consists of 1000 object classes with pixelwise annotation of ground-truth segmentation. Unique in FSS-1000, our 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. We first referred to the classes in ILSVRC in our choice of object categories for FSS1000. Consequently, FSS-1000 has 584 classes out of its 1,000 classes overlap with the classes in the ILSVRC dataset. We find ILSVRC dataset heavily biases toward animals, both in terms of the distribution of categories and number of images. Therefore, we fill in the other 486 by new classes unseen in any existing datasets. Specifically, we include more daily objects so that network models trained on FSS-1000 can learn from diverse artificial and manmade objects/features in addition to natural and organic objects/features where the latter was emphasized by existing large-scale datasets. To avoid bias, the raw images were retrieved by querying object keywords on three different Internet search engines, namely, Google, Bing and Yahoo. We downloaded the first 100 results returned (or less if less than 100 images were returned) from a given search engine. No special criteria or assumption was used to select the candidates, however, due to the bias of Internet search engines, a large number of the images returned contain a single object photographed with sharp focus. In the final step, we intentionally included some images with a relatively small object, multiple objects or other objects in the background to balance the easy and hard examples of the dataset. Images with aspect ratio larger than 2 or smaller than 0.5 were excluded. Since all images and their segmentation maps were to be resized to 224¡Á224, bad aspect ratio would destroy important geometric properties after the resize operation. For the same reason, images with height or width less than 224 pixels were discarded because they would trigger upsampling which would affect the image quality after resizing. We used Photoshop¡¯s ¡°quick selection" tool which allows users to loosely select an object automatically, and refined or corrected the selected area to produce the desired segmentation.