{"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/it-s-all-in-the-head-representation-knowledge","title":"It's All in the Head: Representation Knowledge Distillation through Classifier Sharing","arxiv_id":"2201.06945","date":"2022-01-18","proceeding":null,"authors":["Emanuel Ben-Baruch","Matan Karklinsky","Yossi Biton","Avi Ben-Cohen","Hussam Lawen","Nadav Zamir"],"abstract":"Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models' embedding vectors. Such direct methods may be limited in transferring high-order dependencies embedded in the representation vectors, or in handling the capacity gap between the teacher and student models. Moreover, in standard knowledge distillation, the teacher is trained without awareness of the student's characteristics and capacity. In this paper, we explore two mechanisms for enhancing representation distillation using classifier sharing between the teacher and student. We first investigate a simple scheme where the teacher's classifier is connected to the student backbone, acting as an additional classification head. Then, we propose a student-aware mechanism that asks to tailor the teacher model to a student with limited capacity by training the teacher with a temporary student's head. We analyze and compare these two mechanisms and show their effectiveness on various datasets and tasks, including image classification, fine-grained classification, and face verification. In particular, we achieve state-of-the-art results for face verification on the IJB-C dataset for a MobileFaceNet model: TAR@(FAR=1e-5)=93.7\\%. Code is available at https://github.com/Alibaba-MIIL/HeadSharingKD.","url_abs":"https://arxiv.org/abs/2201.06945v2","url_pdf":"https://arxiv.org/pdf/2201.06945v2.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":"it-s-all-in-the-head-representation-knowledge","repo_url":"https://github.com/alibaba-miil/headsharingkd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"tar","task_name":"TAR"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-verification-on-ijb-c","task":"Face Verification","dataset":"IJB-C","model":"HeadSharing: SH-KD","rank_in_archive_order":1,"of":26,"metrics":{"TAR @ FAR=1e-4":"95.64%","TAR @ FAR=1e-5":"93.73%","TAR @ FAR=1e-6":"90.24%","model":"MobileFaceNet","training dataset":"MS1M V3"},"uses_additional_data":false},{"leaderboard":"/sota/face-verification-on-ijb-c","task":"Face Verification","dataset":"IJB-C","model":"HeadSharing: TH-KD","rank_in_archive_order":2,"of":26,"metrics":{"TAR @ FAR=1e-4":"95.48%","TAR @ FAR=1e-5":"93.50%","TAR @ FAR=1e-6":"89.82%","model":"MobileFaceNet","training dataset":"MS1M V3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.06945","atlas_url":"https://app.syntology.ai/?focus=2201.06945","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":"2201.06945"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2201.06945\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2201.06945"},"call":"get_concepts_for_paper(arxiv_id=\"2201.06945\")"}],"by_repo":[{"repo":"alibaba-miil/headsharingkd","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":"65eb41e366ebce5c93de4ccea5b28332d842138029d5b848a531cdde7a752f15","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}