{"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/correlation-congruence-for-knowledge","title":"Correlation Congruence for Knowledge Distillation","arxiv_id":"1904.01802","date":"2019-04-03","proceeding":"ICCV 2019 10","authors":["Baoyun Peng","Xiao Jin","Jiaheng Liu","Shunfeng Zhou","Yi-Chao Wu","Yu Liu","Dongsheng Li","Zhaoning Zhang"],"abstract":"Most teacher-student frameworks based on knowledge distillation (KD) depend\non a strong congruent constraint on instance level. However, they usually\nignore the correlation between multiple instances, which is also valuable for\nknowledge transfer. In this work, we propose a new framework named correlation\ncongruence for knowledge distillation (CCKD), which transfers not only the\ninstance-level information, but also the correlation between instances.\nFurthermore, a generalized kernel method based on Taylor series expansion is\nproposed to better capture the correlation between instances. Empirical\nexperiments and ablation studies on image classification tasks (including\nCIFAR-100, ImageNet-1K) and metric learning tasks (including ReID and Face\nRecognition) show that the proposed CCKD substantially outperforms the original\nKD and achieves state-of-the-art accuracy compared with other SOTA KD-based\nmethods. The CCKD can be easily deployed in the majority of the teacher-student\nframework such as KD and hint-based learning methods.","url_abs":"http://arxiv.org/abs/1904.01802v1","url_pdf":"http://arxiv.org/pdf/1904.01802v1.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":"correlation-congruence-for-knowledge","repo_url":"https://github.com/SimonZsx/nasproj","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"correlation-congruence-for-knowledge","repo_url":"https://github.com/yoshitomo-matsubara/torchdistill","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.01802","atlas_url":"https://app.syntology.ai/?focus=1904.01802","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":"1904.01802"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.01802\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.01802"},"call":"get_concepts_for_paper(arxiv_id=\"1904.01802\")"}],"by_repo":[{"repo":"SimonZsx/nasproj","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yoshitomo-matsubara/torchdistill","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":6,"harvested_for":["1503.02531","1512.03385","1605.07146","2011.12913","2104.09044","2205.10536"],"harvested_for_calls":[{"arxiv_id":"1503.02531","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1503.02531"},"call":"get_harvested_code_for_paper(arxiv_id=\"1503.02531\")"},{"arxiv_id":"1512.03385","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1512.03385"},"call":"get_harvested_code_for_paper(arxiv_id=\"1512.03385\")"},{"arxiv_id":"1605.07146","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1605.07146"},"call":"get_harvested_code_for_paper(arxiv_id=\"1605.07146\")"},{"arxiv_id":"2011.12913","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2011.12913"},"call":"get_harvested_code_for_paper(arxiv_id=\"2011.12913\")"},{"arxiv_id":"2104.09044","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.09044"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.09044\")"},{"arxiv_id":"2205.10536","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.10536"},"call":"get_harvested_code_for_paper(arxiv_id=\"2205.10536\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"6a3953e6ba62c8069245d99aed71b6da397ca1c2371296ea706fefcc26b83b45","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}