SPair-71k

Overview edit

Variants: SPair-71k

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Graph Matching - Metrics: matching accuracy
• Semantic correspondence - Metrics: PCK

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• Semantic Correspondence: Unified Benchmarking and a Strong Baseline (2025) -
• CleanDIFT: Diffusion Features without Noise (2024) -
• Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence (2023) -
• GMTR: Graph Matching Transformers (2023) -
• Unsupervised Semantic Correspondence Using Stable Diffusion (2023) -
• A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence (2023) -
• Graph Matching with Bi-level Noisy Correspondence (2022) -
• Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence (2022) -
• Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation (2022) -
• TransforMatcher: Match-to-Match Attention for Semantic Correspondence (2022) -
• CATs++: Boosting Cost Aggregation with Convolutions and Transformers (2022) -
• Cost Aggregation Is All You Need for Few-Shot Segmentation (2021) -
• Multi-scale Matching Networks for Semantic Correspondence (2021) -
• CATs: Cost Aggregation Transformers for Visual Correspondence (2021) -
• Convolutional Hough Matching Networks (2021) -
• Learning to Compose Hypercolumns for Visual Correspondence (2020) -
• Correspondence Networks with Adaptive Neighbourhood Consensus (2020) -
• Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers (2020) -
• Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching (2019) -
• Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features (2019) -