Browse State-of-the-Art › Visual Prompt Tuning
Visual Prompt Tuning
37 papers with code · 4 benchmarks · 1 dataset archive 2025-07-28
Visual Prompt Tuning(VPT) only introduces a small amount of task-specific learnable parameters into the input space while freezing the entire pre-trained Transformer backbone during downstream training. In practice, these additional parameters are simply prepended into the input sequence of each Transformer layer and learned together with a linear head during fine-tuning. VPT is especially effective in the low-data regime, and maintains its advantage across data scales. Finally, VPT is competitive for a range of Transformer scales and designs (ViTBase/Large/Huge, Swin). Put together, the results suggest that VPT is one of the most effective ways of adapting ever-growing vision backbones.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| FGVC (10 rows) | SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | Revisiting the Power of Prompt for Visual Tuning | — | — | Compare |
| VTAB-1k(Natural<7>) (10 rows) | SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | Revisiting the Power of Prompt for Visual Tuning | — | — | Compare |
| VTAB-1k(Specialized<4>) (10 rows) | SPT-Deep(ViT-B/16_MoCo_v3_pretrained_ImageNet-1K) | Revisiting the Power of Prompt for Visual Tuning | — | — | Compare |
| VTAB-1k(Structured<8>) (10 rows) | SPT-Deep(ViT-B/16_MAE_pretrained_ImageNet-1K) | Revisiting the Power of Prompt for Visual Tuning | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 70 · with a code link: 37 · where Syntology ran a sample: 23 (22 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (23 of 70 tagged: 22 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 70 of 70, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
23 Mar 2022 6 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 18 ran (of which 12 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified (of 27 harvested samples) · 15 pointer-only (licence)The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.
-
28 Oct 2024 3 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 8 harvested samples) · 3 pointer-only (licence)To address this issue, we propose a novel method called Random SAM prompt tuning (RSAM-PT) to improve the model generalization, requiring only one-step gradient computation at each step.
-
14 Apr 2023 3 repositories listed Syntology official (archive's flag): 7 ran · 9 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 14 harvested samples) · 14 pointer-only (licence)To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
-
14 Dec 2022 2 repositories listedWe apply this training loss to two adaption methods, model finetuning and visual prompt tuning.
-
28 Jun 2025 1 repository listedVisual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts.
-
29 May 2025 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 5 harvested samples)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…
-
2 Apr 2025 1 repository listedTo mitigate this, we propose a new paradigm for perception-oriented instruction tuning, i. e., Q-Adapt, which aims to eliminate the conflicts and achieve the synergy between these two EIQA tasks when adapting LMM…
-
10 Mar 2025 1 repository listedSpecifically, we develop a prompt relocation strategy for ADO derived from this formulation, comprising two optimization steps: identifying and pruning idle prompts, followed by determining the optimal blocks for their…
-
16 Jan 2025 1 repository listed Syntology 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)We present a simple usage of pre-trained Vision Transformers (ViTs) for fine-grained analysis, aiming to identify and localize the traits that distinguish visually similar categories, such as different bird species or…
-
1 Jan 2025 1 repository listedWe present a simple approach to make pre-trained Vision Transformers (ViTs) interpretable for fine-grained analysis, aiming to identify and localize the traits that distinguish visually similar categories, such as bird…
-
22 Dec 2024 1 repository listedWe adaptively construct semantic hierarchies and use semantic-independent and semantic-shared prompts to learn hierarchical representations.
-
25 Nov 2024 1 repository listedTo address these challenges, we introduce Med-PerSAM, a novel and straightforward one-shot framework designed for the medical domain.
-
2 Nov 2024 1 repository listed Syntology official (archive's flag): 17 ran · 17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 2 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 17 harvested samples) · 17 pointer-only (licence)To address this challenge, we draw inspiration from human visual cognition, and propose the Visual Fourier Prompt Tuning (VFPT) method as a general and effective solution for adapting large-scale transformer-based…
-
7 Oct 2024 1 repository listedThis work presents an open-source benchmarking framework, TuneVLSeg, to integrate various unimodal and multimodal prompt tuning techniques into VLSMs, making prompt tuning usable for downstream segmentation datasets…
-
27 Aug 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 6 pointer-only (licence)These methods optimize large-scale pre-trained models for specific tasks by fine-tuning a select group of parameters.
-
24 Aug 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 10 pointer-only (licence)Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces.
-
9 Jun 2024 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified (of 19 harvested samples) · 2 pointer-only (licence)Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models.
-
11 May 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 10 pointer-only (licence)Then, a co-learning strategy with a dual-adapter module is designed to transfer visual knowledge from pseudo-visual prompt to text prompt, enhancing their visual representation abilities.
-
29 Mar 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task.
-
26 Mar 2024 1 repository listedSAVPT features a novel metric Severity that divides all adverse scene images into low-severity and high-severity images.
-
17 Feb 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)Our findings reveal that the image understanding capabilities of current VLMs are strongly correlated with their zero-shot performance on vision language (VL) tasks.
-
23 Jan 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning (VPT) as a parameter-efficient transfer learning technique has gained attention due to its superior performance compared to…
-
16 Dec 2023 1 repository listed Syntology official (archive's flag): 10 ran · 14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 2 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 14 harvested samples) · 10 pointer-only (licence)Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an input image as a flattened sequence of token embeddings and then learns a set of unordered…
-
6 Nov 2023 1 repository listedHolistic scene understanding includes semantic segmentation, surface normal estimation, object boundary detection, depth estimation, etc.
-
Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning27 Oct 2023 1 repository listed Syntology 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (of 14 harvested samples) · 3 pointer-only (licence)Existing Generalized FL (GFL) and Personalized FL (PFL) methods have limitations in balancing performance across both global and local data distributions.
-
9 Oct 2023 1 repository listedSecond, although the teacher-student scheme does enhance the training stability for segmentation TTA in the presence of noisy pseudo-labels and temporal correlation, it cannot directly result in performance improvement…
-
18 Aug 2023 1 repository listedIn addition, to alleviate the class imbalance problem, we introduce a new gradient similarity-based focal loss and adaptive feature scaling to ease overfitting to the major classes and underfitting to the minor classes.
-
25 Jul 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)Specifically, we introduce a set of learnable key-value prompts and visual prompts into self-attention and input layers, respectively, to improve the effectiveness of model fine-tuning.
-
19 Jul 2023 1 repository listedFirstly, the frozen features are transformed by an lightweight bottleneck layer to learn the domain-specific distribution of downstream medical tasks, and then a few learnable visual prompts are used as dynamic queries…
-
17 Jul 2023 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 13 harvested samples)In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view.
-
8 Jun 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
8 Jun 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (of 8 harvested samples)
-
1 Jun 2023 1 repository listed
-
21 Nov 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 3 pointer-only (licence)
-
13 Oct 2022 1 repository listed
-
3 Oct 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
17 Aug 2022 1 repository listed
-
Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization3 Jul 2025 0 repositories listed
-
Visual Variational Autoencoder Prompt Tuning22 Mar 2025 0 repositories listed
-
8 Mar 2025 0 repositories listed Syntology 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
31 Jan 2025 0 repositories listed Syntology 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection9 Jan 2025 0 repositories listed
-
MedFocusCLIP : Improving few shot classification in medical datasets using pixel wise attention7 Jan 2025 0 repositories listed
-
AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments1 Jan 2025 0 repositories listed
-
Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning1 Jan 2025 0 repositories listed
-
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning29 Dec 2024 0 repositories listed
-
Adaptive Prompt Tuning: Vision Guided Prompt Tuning with Cross-Attention for Fine-Grained Few-Shot Learning19 Dec 2024 0 repositories listed
-
End-to-end Multi-source Visual Prompt Tuning for Survival Analysis in Whole Slide Images5 Sep 2024 0 repositories listed
-
Probing the Efficacy of Federated Parameter-Efficient Fine-Tuning of Vision Transformers for Medical Image Classification16 Jul 2024 0 repositories listed
-
iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection8 Apr 2024 0 repositories listed
-
LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning27 Feb 2024 0 repositories listed
-
4 Feb 2024 0 repositories listed
-
Plug-and-Play Transformer Modules for Test-Time Adaptation6 Jan 2024 0 repositories listed
-
Disentangled Prompt Representation for Domain Generalization1 Jan 2024 0 repositories listed
-
Fair-VPT: Fair Visual Prompt Tuning for Image Classification1 Jan 2024 0 repositories listed
-
Open Vocabulary Semantic Scene Sketch Understanding18 Dec 2023 0 repositories listed
-
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression23 Nov 2023 0 repositories listed
-
Towards Few-shot Out-of-Distribution Detection20 Nov 2023 0 repositories listed
-
Task-driven Prompt Evolution for Foundation Models26 Oct 2023 0 repositories listed
-
VPA: Fully Test-Time Visual Prompt Adaptation26 Sep 2023 0 repositories listed
-
MVP: Meta Visual Prompt Tuning for Few-Shot Remote Sensing Image Scene Classification17 Sep 2023 0 repositories listed
-
Dynamic Visual Prompt Tuning for Parameter Efficient Transfer Learning12 Sep 2023 0 repositories listed
-
LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models3 Sep 2023 0 repositories listed
-
SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation9 Aug 2023 0 repositories listed
-
Do We Really Need a Large Number of Visual Prompts?26 May 2023 0 repositories listed
-
26 Apr 2023 0 repositories listed
-
Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models12 Mar 2023 0 repositories listed
-
10 Oct 2022 0 repositories listed
-
Visual Prompt Tuning for Few-Shot Text Classification1 Oct 2022 0 repositories listed
-
Prompt-Matched Semantic Segmentation22 Aug 2022 0 repositories listed
Syntology lines on 23 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections