{"url":"/task/semantic-correspondence","name":"Semantic correspondence","slug":"semantic-correspondence","description_markdown":"The task of semantic correspondence aims to establish reliable visual correspondence between different instances of the same object category.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":175,"papers_with_code":88,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","slug":"semantic-correspondence-on-spair-71k","dataset":"SPair-71k","dataset_url":"/dataset/spair-71k","rows_in_archive":22,"metrics":["PCK"],"first_row_in_archive_order":{"model":"GeoAware-SC (Supervised, AP-10K P.T.)","paper_title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","paper_url":"/paper/telling-left-from-right-identifying-geometry","paper_date":"2023-11-28","arxiv_id":"2311.17034","code_links":[{"title":"Junyi42/geoaware-sc","url":"https://github.com/Junyi42/geoaware-sc"}],"syntology":{"n":15,"n_ran":11,"n_unverified":4,"n_pointer_only":15}}},{"leaderboard":"/sota/semantic-correspondence-on-pf-pascal","slug":"semantic-correspondence-on-pf-pascal","dataset":"PF-PASCAL","dataset_url":"/dataset/pf-pascal","rows_in_archive":15,"metrics":["PCK","PCK (weak)"],"first_row_in_archive_order":{"model":"DINOv2","paper_title":"Semantic Correspondence: Unified Benchmarking and a Strong Baseline","paper_url":"/paper/semantic-correspondence-unified-benchmarking","paper_date":"2025-05-23","arxiv_id":"2505.18060","code_links":[{"title":"Visual-AI/Semantic-Correspondence","url":"https://github.com/Visual-AI/Semantic-Correspondence"}],"syntology":null}},{"leaderboard":"/sota/semantic-correspondence-on-pf-willow","slug":"semantic-correspondence-on-pf-willow","dataset":"PF-WILLOW","dataset_url":"/dataset/pf-willow","rows_in_archive":8,"metrics":["PCK","PCK (weak)"],"first_row_in_archive_order":{"model":"LDMCorrespondences","paper_title":"Unsupervised Semantic Correspondence Using Stable Diffusion","paper_url":"/paper/unsupervised-semantic-correspondence-using","paper_date":"2023-05-24","arxiv_id":"2305.15581","code_links":[{"title":"ubc-vision/LDM_correspondences","url":"https://github.com/ubc-vision/LDM_correspondences"}],"syntology":{"n":12,"n_ran":4,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/semantic-correspondence-on-caltech-101","slug":"semantic-correspondence-on-caltech-101","dataset":"Caltech-101","dataset_url":"/dataset/caltech-101","rows_in_archive":2,"metrics":["IoU","LT-ACC","IoU (weak)","LT-ACC (weak)"],"first_row_in_archive_order":{"model":"HPF","paper_title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","paper_url":"/paper/hyperpixel-flow-semantic-correspondence-with","paper_date":"2019-08-18","arxiv_id":"1908.06537","code_links":[{"title":"juhongm999/hpf","url":"https://github.com/juhongm999/hpf"}],"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}}},{"leaderboard":"/sota/semantic-correspondence-on-ap-10k","slug":"semantic-correspondence-on-ap-10k","dataset":"AP-10K","dataset_url":"/dataset/ap-10k","rows_in_archive":1,"metrics":["PCK"],"first_row_in_archive_order":{"model":"DINOv2","paper_title":"Semantic Correspondence: Unified Benchmarking and a Strong Baseline","paper_url":"/paper/semantic-correspondence-unified-benchmarking","paper_date":"2025-05-23","arxiv_id":"2505.18060","code_links":[{"title":"Visual-AI/Semantic-Correspondence","url":"https://github.com/Visual-AI/Semantic-Correspondence"}],"syntology":null}},{"leaderboard":"/sota/semantic-correspondence-on-cub-200-2011","slug":"semantic-correspondence-on-cub-200-2011","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":1,"metrics":["Mean PCK@0.05","Mean PCK@0.1"],"first_row_in_archive_order":{"model":"LDM Correspondences","paper_title":"Unsupervised Semantic Correspondence Using Stable Diffusion","paper_url":"/paper/unsupervised-semantic-correspondence-using","paper_date":"2023-05-24","arxiv_id":"2305.15581","code_links":[{"title":"ubc-vision/LDM_correspondences","url":"https://github.com/ubc-vision/LDM_correspondences"}],"syntology":{"n":12,"n_ran":4,"n_unverified":8,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/caltech-101","name":"Caltech-101","full_name":"","num_papers_in_archive":709},{"url":"/dataset/spair-71k","name":"SPair-71k","full_name":"","num_papers_in_archive":71},{"url":"/dataset/pf-pascal","name":"PF-PASCAL","full_name":"","num_papers_in_archive":60},{"url":"/dataset/ap-10k","name":"AP-10K","full_name":"","num_papers_in_archive":39},{"url":"/dataset/pf-willow","name":"PF-WILLOW","full_name":"","num_papers_in_archive":37},{"url":"/dataset/avmit","name":"AVMIT","full_name":"Audiovisual Moments in Time","num_papers_in_archive":2},{"url":"/dataset/funkpoint","name":"FunKPoint","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/interspecies-facial-keypoint-transfer","name":"Interspecies Facial Keypoint Transfer"}],"parent_tasks":[{"url":"/task/image-matching","name":"Image Matching"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":88,"tagged_in_all":175,"items":[{"url":"/paper/color2style-real-time-exemplar-based-image","title":"Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings","date":"2021-06-15","arxiv_id":"2106.08017","repositories_listed":3,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/discobox-weakly-supervised-instance","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","date":"2021-05-13","arxiv_id":"2105.06464","repositories_listed":3,"syntology":null},{"url":"/paper/patentmatch-a-dataset-for-matching-patent","title":"PatentMatch: A Dataset for Matching Patent Claims & Prior Art","date":"2020-12-27","arxiv_id":"2012.13919","repositories_listed":3,"syntology":null},{"url":"/paper/neighbourhood-consensus-networks","title":"Neighbourhood Consensus Networks","date":"2018-10-24","arxiv_id":"1810.10510","repositories_listed":3,"syntology":{"n":21,"n_ran":5,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/hdc-hierarchical-semantic-decoding-with-1","title":"CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation","date":"2024-05-24","arxiv_id":"2405.15658","repositories_listed":2,"syntology":null},{"url":"/paper/emergent-correspondence-from-image-diffusion","title":"Emergent Correspondence from Image Diffusion","date":"2023-06-06","arxiv_id":"2306.03881","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/going-denser-with-open-vocabulary-part","title":"Going Denser with Open-Vocabulary Part Segmentation","date":"2023-05-18","arxiv_id":"2305.11173","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/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","arxiv_id":"2112.11685","repositories_listed":2,"syntology":null},{"url":"/paper/ssat-a-symmetric-semantic-aware-transformer","title":"SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal","date":"2021-12-07","arxiv_id":"2112.03631","repositories_listed":2,"syntology":null},{"url":"/paper/snapmix-semantically-proportional-mixing-for","title":"SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data","date":"2020-12-09","arxiv_id":"2012.04846","repositories_listed":2,"syntology":null},{"url":"/paper/ispa-net-iterative-semantic-pose-alignment","title":"iSPA-Net: Iterative Semantic Pose Alignment Network","date":"2018-08-03","arxiv_id":"1808.01134","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-weakly-supervised-semantic","title":"End-to-end weakly-supervised semantic alignment","date":"2017-12-19","arxiv_id":"1712.06861","repositories_listed":2,"syntology":null},{"url":"/paper/cora-correspondence-aware-image-editing-using","title":"Cora: Correspondence-aware image editing using few step diffusion","date":"2025-05-29","arxiv_id":"2505.23907","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-correspondence-unified-benchmarking","title":"Semantic Correspondence: Unified Benchmarking and a Strong Baseline","date":"2025-05-23","arxiv_id":"2505.18060","repositories_listed":1,"syntology":null},{"url":"/paper/tc-mgc-text-conditioned-multi-grained","title":"TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video Retrieval","date":"2025-04-07","arxiv_id":"2504.04707","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/evaluation-of-multilingual-image-captioning","title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","date":"2025-02-10","arxiv_id":"2502.06600","repositories_listed":1,"syntology":null},{"url":"/paper/common3d-self-supervised-learning-of-3d","title":"Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cleandift-diffusion-features-without-noise","title":"CleanDIFT: Diffusion Features without Noise","date":"2024-12-04","arxiv_id":"2412.03439","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":5}},{"url":"/paper/multi-level-correlation-network-for-few-shot","title":"Multi-Level Correlation Network For Few-Shot Image Classification","date":"2024-12-04","arxiv_id":"2412.03159","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-potential-of-the-diffusion","title":"Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation","date":"2024-10-03","arxiv_id":"2410.02369","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/sgor-outlier-removal-by-leveraging-semantic","title":"SGOR: Outlier Removal by Leveraging Semantic and Geometric Information for Robust Point Cloud Registration","date":"2024-07-08","arxiv_id":"2407.06297","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-image-editing-with-reference","title":"Zero-shot Image Editing with Reference Imitation","date":"2024-06-11","arxiv_id":"2406.07547","repositories_listed":1,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/zero-shot-video-semantic-segmentation-based","title":"Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models","date":"2024-05-27","arxiv_id":"2405.16947","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/semantic-gesticulator-semantics-aware-co","title":"Semantic Gesticulator: Semantics-Aware Co-Speech Gesture Synthesis","date":"2024-05-16","arxiv_id":"2405.09814","repositories_listed":1,"syntology":null},{"url":"/paper/factual-serialization-enhancement-a-key","title":"Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation","date":"2024-05-15","arxiv_id":"2405.09586","repositories_listed":1,"syntology":null},{"url":"/paper/pixel-level-semantic-correspondence-through","title":"Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/patch-wise-graph-contrastive-learning-for","title":"Patch-wise Graph Contrastive Learning for Image Translation","date":"2023-12-13","arxiv_id":"2312.08223","repositories_listed":1,"syntology":null},{"url":"/paper/stableviton-learning-semantic-correspondence","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","date":"2023-12-04","arxiv_id":"2312.01725","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}},{"url":"/paper/match-me-if-you-can-semantic-correspondence","title":"Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images","date":"2023-11-30","arxiv_id":"2311.18540","repositories_listed":1,"syntology":null},{"url":"/paper/telling-left-from-right-identifying-geometry","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","date":"2023-11-28","arxiv_id":"2311.17034","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_unverified":4,"n_pointer_only":15}}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}