6 datasets found

The dataset used in the paper is a multi-view clustering dataset, which contains 6 views of 2000 samples each. The dataset is used to evaluate the performance of the proposed...

The SBCoseg dataset is a new challenging image dataset with simple background for evaluating co-segmentation algorithms.

The iCoseg dataset consists of 38 groups of total 643 images, each group contains 17 images on average.

The Internet dataset contains images of three object categories including airplane, car and horse.

Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the...

The dataset used in the paper is the Pascal VOC 2012 dataset, which is a benchmark for instance segmentation. The dataset consists of 1464 images with 20 class categories and...