{"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/promptkd-unsupervised-prompt-distillation-for","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","arxiv_id":"2403.02781","date":"2024-03-05","proceeding":"CVPR 2024 1","authors":["Zheng Li","Xiang Li","Xinyi Fu","Xin Zhang","Weiqiang Wang","Shuo Chen","Jian Yang"],"abstract":"Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting the potential of prompts as effective distillers for learning from larger teacher models. In this paper, we introduce an unsupervised domain prompt distillation framework, which aims to transfer the knowledge of a larger teacher model to a lightweight target model through prompt-driven imitation using unlabeled domain images. Specifically, our framework consists of two distinct stages. In the initial stage, we pre-train a large CLIP teacher model using domain (few-shot) labels. After pre-training, we leverage the unique decoupled-modality characteristics of CLIP by pre-computing and storing the text features as class vectors only once through the teacher text encoder. In the subsequent stage, the stored class vectors are shared across teacher and student image encoders for calculating the predicted logits. Further, we align the logits of both the teacher and student models via KL divergence, encouraging the student image encoder to generate similar probability distributions to the teacher through the learnable prompts. The proposed prompt distillation process eliminates the reliance on labeled data, enabling the algorithm to leverage a vast amount of unlabeled images within the domain. Finally, the well-trained student image encoders and pre-stored text features (class vectors) are utilized for inference. To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student. Extensive experiments on 11 datasets demonstrate the effectiveness of our method.","url_abs":"https://arxiv.org/abs/2403.02781v5","url_pdf":"https://arxiv.org/pdf/2403.02781v5.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":"promptkd-unsupervised-prompt-distillation-for","repo_url":"https://github.com/zhengli97/promptkd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/prompt-engineering-on-caltech-101","task":"Prompt Engineering","dataset":"Caltech-101","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"97.77"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-dtd","task":"Prompt Engineering","dataset":"DTD","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"77.94"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-eurosat","task":"Prompt Engineering","dataset":"EuroSAT","model":"PromptKD","rank_in_archive_order":2,"of":14,"metrics":{"Harmonic mean":"89.14"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-fgvc-aircraft","task":"Prompt Engineering","dataset":"FGVC-Aircraft","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"45.17"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-food-101","task":"Prompt Engineering","dataset":"Food-101","model":"PromptKD","rank_in_archive_order":1,"of":13,"metrics":{"Harmonic mean":"93.05"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet","task":"Prompt Engineering","dataset":"ImageNet","model":"PromptKD","rank_in_archive_order":1,"of":15,"metrics":{"Harmonic mean":"77.62"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","task":"Prompt Engineering","dataset":"Oxford 102 Flower","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"90.24"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-iiit-pet-dataset","task":"Prompt Engineering","dataset":"Oxford-IIIT Pet Dataset","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"97.15"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-sun397","task":"Prompt Engineering","dataset":"SUN397","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"82.60"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-stanford-cars-1","task":"Prompt Engineering","dataset":"Stanford Cars","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"83.13"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-ucf101","task":"Prompt Engineering","dataset":"UCF101","model":"PromptKD","rank_in_archive_order":1,"of":14,"metrics":{"Harmonic mean":"86.10"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.02781","atlas_url":"https://app.syntology.ai/?focus=2403.02781","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":"2403.02781"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2403.02781\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2403.02781"},"call":"get_concepts_for_paper(arxiv_id=\"2403.02781\")"}],"by_repo":[{"repo":"zhengli97/promptkd","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2412.09442"],"harvested_for_calls":[{"arxiv_id":"2412.09442","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.09442"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.09442\")"}]}],"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":"a7f710e087ecb89c41e13e89c4710e19203489b06662d924b5a21ac1d9ca7ba2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}