{"url":"/dataset/spair-71k","name":"SPair-71k","full_name":null,"description_markdown":"SPair-71k 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. \r\n\r\nSource: [SPair-71k: A Large-scale Benchmark for Semantic Correspondence](/paper/spair-71k-a-large-scale-benchmark-for)\r\nImage Source: [http://cvlab.postech.ac.kr/research/SPair-71k/](http://cvlab.postech.ac.kr/research/SPair-71k/)","description_withheld":null,"homepage":"http://cvlab.postech.ac.kr/research/SPair-71k/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/spair-71k-a-large-scale-benchmark-for","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","first_author":"Juhong Min","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Semantic correspondence","url":"/task/semantic-correspondence","datasets_with_task":"/datasets/task/semantic-correspondence"},{"name":"Graph Matching","url":"/task/graph-matching","datasets_with_task":"/datasets/task/graph-matching"},{"name":"Colorization","url":"/task/colorization","datasets_with_task":"/datasets/task/colorization"}],"languages":[],"variants":["SPair-71k"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/0jl/SPair-71k","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":71,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset_variant":"SPair-71k","rows":22,"metrics":["PCK"],"first_row_in_archive_order":{"model":"GeoAware-SC (Supervised, AP-10K P.T.)","paper":"/paper/telling-left-from-right-identifying-geometry","metrics":{"PCK":"85.6"},"code_links":[{"title":"Junyi42/geoaware-sc","url":"https://github.com/Junyi42/geoaware-sc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/graph-matching-on-spair-71k","task":"Graph Matching","dataset_variant":"SPair-71k","rows":8,"metrics":["matching accuracy"],"first_row_in_archive_order":{"model":"CREAM","paper":"/paper/cross-modal-retrieval-with-noisy","metrics":{"matching accuracy":"0.851"},"code_links":[{"title":"XLearning-SCU/2024-TIP-CREAM","url":"https://github.com/XLearning-SCU/2024-TIP-CREAM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/semantic-correspondence-unified-benchmarking","title":"Semantic Correspondence: Unified Benchmarking and a Strong Baseline","date":"2025-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cleandift-diffusion-features-without-noise","title":"CleanDIFT: Diffusion Features without Noise","date":"2024-12-04","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-modal-retrieval-with-noisy","title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","date":"2024-03-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/telling-left-from-right-identifying-geometry","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","date":"2023-11-28","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":15,"samples_ran":11,"samples_unverified":4,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gmtr-graph-matching-transformers","title":"GMTR: Graph Matching Transformers","date":"2023-11-14","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-semantic-correspondence-using","title":"Unsupervised Semantic Correspondence Using Stable Diffusion","date":"2023-05-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-tale-of-two-features-stable-diffusion","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","date":"2023-05-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-matching-with-bi-level-noisy","title":"Graph Matching with Bi-level Noisy Correspondence","date":"2022-12-08","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":7,"samples_unverified":0,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/integrative-feature-and-cost-aggregation-with","title":"Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence","date":"2022-09-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cost-aggregation-with-4d-convolutional-swin","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","date":"2022-07-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":20,"samples_ran":12,"samples_unverified":8,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transformatcher-match-to-match-attention-for","title":"TransforMatcher: Match-to-Match Attention for Semantic Correspondence","date":"2022-05-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cats-boosting-cost-aggregation-with","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","date":"2022-02-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graph-context-attention-networks-for-size","title":"Graph-Context Attention Networks for Size-Varied Deep Graph Matching","date":"2022-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cost-aggregation-is-all-you-need-for-few-shot","title":"Cost Aggregation Is All You Need for Few-Shot Segmentation","date":"2021-12-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/multi-scale-matching-networks-for-semantic","title":"Multi-scale Matching Networks for Semantic Correspondence","date":"2021-07-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/semantic-correspondence-with-transformers","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","date":"2021-06-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/convolutional-hough-matching-networks","title":"Convolutional Hough Matching Networks","date":"2021-03-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-to-compose-hypercolumns-for-visual","title":"Learning to Compose Hypercolumns for Visual Correspondence","date":"2020-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/semantic-correspondence-as-an-optimal","title":"Semantic Correspondence as an Optimal Transport Problem","date":"2020-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/correspondence-networks-with-adaptive","title":"Correspondence Networks with Adaptive Neighbourhood Consensus","date":"2020-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-graph-matching-via-blackbox","title":"Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers","date":"2020-03-25","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-graph-matching-network-learning","title":"Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching","date":"2019-11-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hyperpixel-flow-semantic-correspondence-with","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","date":"2019-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":9,"samples_harvested":100,"samples_ran":49,"samples_unverified":51,"pointer_only_for_licence":32,"papers_with_no_sample_that_ran":3,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}