SPair-71k: A Large-scale Benchmark for Semantic Correspondence

TL;DR

SPair-71k is a large-scale, richly annotated dataset designed to advance research in semantic correspondence by providing diverse, challenging image pairs for benchmarking computer vision algorithms.

Contribution

The paper introduces SPair-71k, a significantly larger and more diverse dataset for semantic correspondence, with accurate annotations to facilitate research and evaluation.

Findings

Recent methods evaluated as baselines

Dataset covers large viewpoint and scale variations

Provides a reliable testbed for semantic matching research

Abstract

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/.