{"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/simple-semi-supervised-knowledge-distillation","title":"Simple Semi-supervised Knowledge Distillation from Vision-Language Models via $\\mathbf{\\texttt{D}}$ual-$\\mathbf{\\texttt{H}}$ead $\\mathbf{\\texttt{O}}$ptimization","arxiv_id":"2505.07675","date":"2025-05-12","proceeding":null,"authors":["Seongjae Kang","Dong Bok Lee","Hyungjoon Jang","Sung Ju Hwang"],"abstract":"Vision-language models (VLMs) have achieved remarkable success across diverse tasks by leveraging rich textual information with minimal labeled data. However, deploying such large models remains challenging, particularly in resource-constrained environments. Knowledge distillation (KD) offers a well-established solution to this problem; however, recent KD approaches from VLMs often involve multi-stage training or additional tuning, increasing computational overhead and optimization complexity. In this paper, we propose $\\mathbf{\\texttt{D}}$ual-$\\mathbf{\\texttt{H}}$ead $\\mathbf{\\texttt{O}}$ptimization ($\\mathbf{\\texttt{DHO}}$) -- a simple yet effective KD framework that transfers knowledge from VLMs to compact, task-specific models in semi-supervised settings. Specifically, we introduce dual prediction heads that independently learn from labeled data and teacher predictions, and propose to linearly combine their outputs during inference. We observe that $\\texttt{DHO}$ mitigates gradient conflicts between supervised and distillation signals, enabling more effective feature learning than single-head KD baselines. As a result, extensive experiments show that $\\texttt{DHO}$ consistently outperforms baselines across multiple domains and fine-grained datasets. Notably, on ImageNet, it achieves state-of-the-art performance, improving accuracy by 3% and 0.1% with 1% and 10% labeled data, respectively, while using fewer parameters.","url_abs":"https://arxiv.org/abs/2505.07675v1","url_pdf":"https://arxiv.org/pdf/2505.07675v1.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":"simple-semi-supervised-knowledge-distillation","repo_url":"https://github.com/erjui/DHO","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"},{"task_slug":null,"task_name":"Semi-Supervised Image Classification on ImageNet - 10% labeled data"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"DHO (ViT-Large)","rank_in_archive_order":1,"of":65,"metrics":{"Top 1 Accuracy":"84.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"DHO (ViT-Base)","rank_in_archive_order":3,"of":65,"metrics":{"Top 1 Accuracy":"81.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"DHO (ViT-Large)","rank_in_archive_order":1,"of":75,"metrics":{"Top 1 Accuracy":"85.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"DHO (ViT-Base)","rank_in_archive_order":8,"of":75,"metrics":{"Top 1 Accuracy":"82.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.07675","atlas_url":"https://app.syntology.ai/?focus=2505.07675","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":"2505.07675"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2505.07675\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2505.07675"},"call":"get_concepts_for_paper(arxiv_id=\"2505.07675\")"}],"by_repo":[{"repo":"erjui/DHO","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":"01da113c67d7f5e9929ddf955e11b0fff251099370b901fd46068abbb0af58ba","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}