litlas
Log inCreate account

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

Authors: Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho - arXiv 2019 cited by 122

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/.

SIFT Flow: DenseCorrespondence across…SIFT Flow: Dense Correspondence across Scenes and Its ApplicationsDeformable SpatialPyramid Matching for…Deformable Spatial Pyramid Matching for Fast Dense CorrespondencesThe Pascal Visual ObjectClasses Challenge: A…The Pascal Visual Object Classes Challenge: A RetrospectiveBeyond PASCAL: Abenchmark for 3D object…Beyond PASCAL: A benchmark for 3D object detection in the wildDetect What You Can:Detecting and…Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body PartsJoint Recovery of DenseCorrespondence and…Joint Recovery of Dense Correspondence and Cosegmentation in Two ImagesProposal FlowProposal FlowConvolutional NeuralNetwork Architecture fo…Convolutional Neural Network Architecture for Geometric MatchingProposal Flow: SemanticCorrespondences from…Proposal Flow: Semantic Correspondences from Object ProposalsAttentive SemanticAlignment with…Attentive Semantic Alignment with Offset-Aware Correlation KernelsSemantic Correspondencevia 2D-3D-2D CycleSemantic Correspondence via 2D-3D-2D CycleProbabilistic ModelDistillation for…Probabilistic Model Distillation for Semantic CorrespondenceWarp Consistency forUnsupervised Learning o…Warp Consistency for Unsupervised Learning of Dense CorrespondencesCATs: Cost AggregationTransformers for Visual…CATs: Cost Aggregation Transformers for Visual CorrespondenceConvolutional HoughMatching NetworksConvolutional Hough Matching NetworksDiscoBox: WeaklySupervised Instance…DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box SupervisionProbabilistic WarpConsistency for…Probabilistic Warp Consistency for Weakly-Supervised Semantic CorrespondencesConvolutional HoughMatching Networks for…Convolutional Hough Matching Networks for Robust and Efficient Visual CorrespondenceA Tale of Two Features:Stable Diffusion…A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic CorrespondenceASIC: Aligning Sparsein-the-wild Image…ASIC: Aligning Sparse in-the-wild Image CollectionsTelling Left from Right:Identifying…Telling Left from Right: Identifying Geometry-Aware Semantic CorrespondenceSemantic Correspondence:Unified Benchmarking an…Semantic Correspondence: Unified Benchmarking and a Strong BaselineSPair-71k: A Large-scaleBenchmark for Semantic…SPair-71k: A Large-scale Benchmark for Semantic CorrespondenceEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.