{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/a-tale-of-two-features-stable-diffusion","title":"A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence","arxiv_id":"2305.15347","date":"2023-05-24","proceeding":"NeurIPS 2023 11","authors":["Junyi Zhang","Charles Herrmann","Junhwa Hur","Luisa Polania Cabrera","Varun Jampani","Deqing Sun","Ming-Hsuan Yang"],"abstract":"Text-to-image diffusion models have made significant advances in generating and editing high-quality images. As a result, numerous approaches have explored the ability of diffusion model features to understand and process single images for downstream tasks, e.g., classification, semantic segmentation, and stylization. However, significantly less is known about what these features reveal across multiple, different images and objects. In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations. Interestingly, the qualitative analysis reveals that SD features have very different properties compared to existing representation learning features, such as the recently released DINOv2: while DINOv2 provides sparse but accurate matches, SD features provide high-quality spatial information but sometimes inaccurate semantic matches. We demonstrate that a simple fusion of these two features works surprisingly well, and a zero-shot evaluation using nearest neighbors on these fused features provides a significant performance gain over state-of-the-art methods on benchmark datasets, e.g., SPair-71k, PF-Pascal, and TSS. We also show that these correspondences can enable interesting applications such as instance swapping in two images.","url_abs":"https://arxiv.org/abs/2305.15347v2","url_pdf":"https://arxiv.org/pdf/2305.15347v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-tale-of-two-features-stable-diffusion","repo_url":"https://github.com/Junyi42/sd-dino","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dense-pixel-correspondence-estimation","task_name":"Dense Pixel Correspondence Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dense-pixel-correspondence-estimation-on-tss","task":"Dense Pixel Correspondence Estimation","dataset":"TSS","model":"SD+DINO (Zero-shot)","rank_in_archive_order":1,"of":1,"metrics":{"Average PCK@0.05":"79.7"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-pf-pascal","task":"Semantic correspondence","dataset":"PF-PASCAL","model":"SD+DINO (Supervised)","rank_in_archive_order":5,"of":15,"metrics":{"PCK":"93.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"SD+DINO (Supervised)","rank_in_archive_order":4,"of":22,"metrics":{"PCK":"74.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"SD+DINO (Zero-shot)","rank_in_archive_order":9,"of":22,"metrics":{"PCK":"64.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.15347","atlas_url":"https://app.syntology.ai/?focus=2305.15347","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2305.15347"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.15347\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.15347"},"call":"get_concepts_for_paper(arxiv_id=\"2305.15347\")"}],"by_repo":[{"repo":"Junyi42/sd-dino","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bc3b96e7d74bea6704b7c69b342543c925c3f15189d1389d7d6ad72b124f6cd0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}