Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of the datasets for semantic correspondence are limited to a small amount of image pairs with similar viewpoints and scales. In this paper, we present a new large-scale benchmark dataset of semantically paired images, SPair-71k, which 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. We believe this dataset will provide a reliable testbed to study the problem of semantic correspondence and will help to advance research in this area. We provide the results of recent methods on our new dataset as baselines for further research. Our benchmark is available online at http://cvlab.postech.ac.kr/research/SPair-71k/.
@article{arxiv.1908.10543,
title = {SPair-71k: A Large-scale Benchmark for Semantic Correspondence},
author = {Juhong Min and Jongmin Lee and Jean Ponce and Minsu Cho},
journal= {arXiv preprint arXiv:1908.10543},
year = {2019}
}
Comments
Extension of ICCV 2019 paper, Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features. arXiv admin note: text overlap with arXiv:1908.06537