Papers › Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

14 Apr 2023ICCV 2023 1arXiv:2304.07221archive 2025-07-28

Yaohua Zha, Jinpeng Wang, Tao Dai, Bin Chen, Zhi Wang, Shu-Tao Xia

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at https://github.com/zyh16143998882/ICCV23-IDPT.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 14 code samples harvested from 2 repositories linked to this paper: 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. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zyh16143998882/IDPT officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 7 ran (1 instrument-failed) · 3 unverified report
zyh16143998882/iccv23-idpt officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
zyh16143998882/aaai24-pointfemae mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
8ran
5unverified

Licence: 14 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

zyh16143998882/IDPT official repository 10 samples, 7 ran (1 instrument-failed) · 3 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32
models/Point_MAE.py ran · metamorphic tier: invariant no licence file found · pointer only · e50a82843946d9b4 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DGCNNView models/Point_MAE.py ran no licence file found · pointer only · 50a5714aab590a59 · report fixture: signature x:Tensor/3/float, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-24
DGCNNViewLight2 models/Point_MAE.py ran no licence file found · pointer only · f9673b64dec8e89c · report fixture: signature x:Tensor/3/float, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-24
DGCNNViewMLP models/Point_MAE.py ran no licence file found · pointer only · c7b64faa053f3761 · report fixture: signature x:Tensor/3/float, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Mlp in 102 papers models/Point_MAE.py ran · metamorphic tier: invariant no licence file found · pointer only · cc1832f8e8b3aa69 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
TransformerEncoder in 96 papers models/Point_MAE.py ran no licence file found · pointer only · bb22f81886c8963d · report fixture: signature x:Tensor/3/float, pos:Tensor/3/float · returned Tensor · level recorded 2026-09-24
act_layer in 20 papers models/Point_MAE.py ran · our draft was wrong no licence file found · pointer only · ed4cd8f3b2b83784 · report fixture: signature act:str/0/str, inplace:bool/0/bool, neg_slope:float/0/float, n_prelu:int/0/int · returned ReLU · level recorded 2026-09-22
DGCNNViewLight models/Point_MAE.py unverified no licence file found · pointer only · c87e47714f68fa7d · report
TransFormerLayerView models/Point_MAE.py unverified no licence file found · pointer only · 2ede111e17f38a68 · report
TransformerPromptEncoderLayerI models/Point_MAE.py unverified no licence file found · pointer only · b653db8db6d0a32f · report
zyh16143998882/aaai24-pointfemae community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
BlockH models/Point_MAE.py ran no licence file found · pointer only · 3310d0089f97cac4 · report fixture: signature x:Tensor/3/float, center_block:Tensor/3/float · returned Tensor · level recorded 2026-09-24
LEM models/Point_MAE.py ran no licence file found · pointer only · 892fce57c8dde09f · report fixture: returned LEM · level recorded 2026-09-22
MaskTransformerH models/Point_MAE.py unverified no licence file found · pointer only · 804ab252335f0df6 · report
TransformerEncoderH models/Point_MAE.py unverified no licence file found · pointer only · 05089574e956e053 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Instance-aware Dynamic Prompt Tuning (IDPT) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Instance-aware Dynamic Prompt Tuning (IDPT) (graph method: Instance-aware Dynamic Prompt Tuning (IDPT)). 9 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MaskTransformerH entry · level 0 · unverified · 804ab252335f0df6
  2. Encoder helper · level 1 · ran · 2b00cd3626cdb9f2
  3. TransformerEncoderH helper · level 0 · unverified · 05089574e956e053
  4. BlockH model · level 1 · ran · 3310d0089f97cac4
  5. Attention model · level 1 · ran · 9af3eb132594e510
  6. LEM model · level 1 · ran · 892fce57c8dde09f
  7. Mlp model · level 1 · ran · a1715055832f71fd
  8. get_graph_feature helper · level 1 · ran; the contract check could not run · 9a8756778dd8234a
  9. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb

harvested Assembly for Instance-aware Dynamic Prompt Tuning (IDPT) (graph method: Instance-aware Dynamic Prompt Tuning (IDPT)). 13 bricks; individually on a fixture: 10 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. TransformerPromptEncoderLayerI entry · level 0 · unverified · b653db8db6d0a32f
  2. Block model · level 1 · ran · e50a82843946d9b4
  3. DGCNNView helper · level 1 · ran · 50a5714aab590a59
  4. DGCNNViewLight helper · level 0 · unverified · c87e47714f68fa7d
  5. DGCNNViewLight2 helper · level 1 · ran · f9673b64dec8e89c
  6. DGCNNViewMLP helper · level 1 · ran · c7b64faa053f3761
  7. TransFormerLayerView helper · level 0 · unverified · 2ede111e17f38a68
  8. Attention model · level 1 · ran · 9af3eb132594e510
  9. Mlp model · level 1 · ran · cc1832f8e8b3aa69
  10. act_layer helper · level 1 · ran · our draft was wrong · ed4cd8f3b2b83784
  11. get_graph_feature helper · level 1 · ran; the contract check could not run · 9a8756778dd8234a
  12. TransformerEncoder model · level 1 · ran · bb22f81886c8963d
  13. knn helper · level 1 · ran; the contract check could not run · cdd0141594039dcb

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2304.07221") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Parameter-Efficient Fine-Tuning for Classification3D Point Cloud ClassificationFew-Shot 3D Point Cloud ClassificationVisual Prompt Tuning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 IDPT Overall Accuracy 94.4 #15 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN IDPT OBJ-BG (OA) 93.12 #35 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN IDPT Overall Accuracy 88.51 #35 of 77 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) IDPT Overall Accuracy 92.8 #12 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) IDPT Overall Accuracy 95.4 #13 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) IDPT Overall Accuracy 97.3 #9 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) IDPT Overall Accuracy 97.9 #14 of 30 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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