{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/da-vpt-semantic-guided-visual-prompt-tuning","title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers","arxiv_id":"2505.23694","date":"2025-05-29","proceeding":"CVPR 2025 1","authors":["Li Ren","Chen Chen","Liqiang Wang","Kien Hua"],"abstract":"Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnable tokens while keeping most model parameters frozen. Recent research has explored modifying the connection structures of the prompts. However, the fundamental correlation and distribution between the prompts and image tokens remain unexplored. In this paper, we leverage metric learning techniques to investigate how the distribution of prompts affects fine-tuning performance. Specifically, we propose a novel framework, Distribution Aware Visual Prompt Tuning (DA-VPT), to guide the distributions of the prompts by learning the distance metric from their class-related semantic data. Our method demonstrates that the prompts can serve as an effective bridge to share semantic information between image patches and the class token. We extensively evaluated our approach on popular benchmarks in both recognition and segmentation tasks. The results demonstrate that our approach enables more effective and efficient fine-tuning of ViT models by leveraging semantic information to guide the learning of the prompts, leading to improved performance on various downstream vision tasks.","url_abs":"https://arxiv.org/abs/2505.23694v1","url_pdf":"https://arxiv.org/pdf/2505.23694v1.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":"da-vpt-semantic-guided-visual-prompt-tuning","repo_url":"https://github.com/noahsark/da-vpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"visual-prompt-tuning","task_name":"Visual Prompt Tuning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"aware","method_name":"AWARE"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.23694","atlas_url":"https://app.syntology.ai/?focus=2505.23694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23694"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/noahsark/da-vpt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Noahsark/DA-VPT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ebb75069e48400f8","entry":"L2NormalizationLayer","repo":"Noahsark/DA-VPT","repo_kind":"official","path":"models/vpt.py","file_url":"https://github.com/Noahsark/DA-VPT/blob/HEAD/models/vpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ebb75069e48400f8"}},{"code_sha256_prefix":"117b52636875a268","entry":"VPTAttention","repo":"Noahsark/DA-VPT","repo_kind":"official","path":"models/vpt.py","file_url":"https://github.com/Noahsark/DA-VPT/blob/HEAD/models/vpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"117b52636875a268"}},{"code_sha256_prefix":"b37499af922bdf28","entry":"VPTBlock","repo":"Noahsark/DA-VPT","repo_kind":"official","path":"models/vpt.py","file_url":"https://github.com/Noahsark/DA-VPT/blob/HEAD/models/vpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b37499af922bdf28"}},{"code_sha256_prefix":"628df582f1a0b815","entry":"VPTCriterion","repo":"Noahsark/DA-VPT","repo_kind":"official","path":"models/vpt.py","file_url":"https://github.com/Noahsark/DA-VPT/blob/HEAD/models/vpt.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"628df582f1a0b815"}},{"code_sha256_prefix":"da74658301fab142","entry":"PromptVisionTransformer","repo":"Noahsark/DA-VPT","repo_kind":"official","path":"models/vpt.py","file_url":"https://github.com/Noahsark/DA-VPT/blob/HEAD/models/vpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da74658301fab142"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}