Papers › Visual Prompt Tuning in Null Space for Continual Learning

Visual Prompt Tuning in Null Space for Continual Learning

9 Jun 2024arXiv:2406.05658archive 2025-07-28

Yue Lu, Shizhou Zhang, De Cheng, Yinghui Xing, Nannan Wang, Peng Wang, Yanning Zhang

Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL), by selecting and updating relevant prompts in the vision-transformer models. On the contrary, this paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features, so as to ensure no interference on tasks that have been learned to overcome catastrophic forgetting in CL. However, different from the orthogonal projection in the traditional CNN architecture, the prompt gradient orthogonal projection in the ViT architecture shows completely different and greater challenges, i.e., 1) the high-order and non-linear self-attention operation; 2) the drift of prompt distribution brought by the LayerNorm in the transformer block. Theoretically, we have finally deduced two consistency conditions to achieve the prompt gradient orthogonal projection, which provide a theoretical guarantee of eliminating interference on previously learned knowledge via the self-attention mechanism in visual prompt tuning. In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient orthogonal projection. Extensive experimental results demonstrate the effectiveness of anti-forgetting on four class-incremental benchmarks with diverse pre-trained baseline models, and our approach achieves superior performances to state-of-the-art methods. Our code is available at https://github.com/zugexiaodui/VPTinNSforCL.

PaperPDFCodeCode 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.

Syntology holds a reference implementation of Visual Prompt Tuning in Null Space, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Visual Prompt Tuning in Null Space') (how to connect); the free check have('2406.05658') needs no token.

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

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 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. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 12 ran (7 with no instrument failure; 5 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.

zugexiaodui/vptinnsforcl officialmentioned in paperpytorchMITSyntology: 19 samples, 12 ran (5 instrument-failed) · 7 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

19 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
5ran · our draft was wrong
6ran
7unverified

Licence: 2 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zugexiaodui/vptinnsforcl. “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.

zugexiaodui/vptinnsforcl official repository 19 samples, 12 ran (5 instrument-failed) · 7 unverified
ClassIncrementalManager train_eval.py ran MIT (permissive) · 3268683b13ffdab4 · report fixture: returned ClassIncrementalManager · level recorded 2026-09-22
ImagePathDataset train_eval.py ran MIT (permissive) · 078149a1266f4078 · report fixture: returned ImagePathDataset · level recorded 2026-09-22
ImagePathDatasetClassManager train_eval.py ran MIT (permissive) · 96c050fd4ac91bfd · report fixture: returned ImagePathDatasetClassManager · level recorded 2026-09-22
SDomainNetPath train_eval.py ran MIT (permissive) · 8cfe390097de1132 · report fixture: returned SDomainNetPath · level recorded 2026-09-22
basic_clean in 217 papers clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 98f385d847636a3e · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
calc_accuracy in 14 papers utils/misc.py ran MIT (permissive) · 971c46b0aa73eb28 · report fixture: signature preds:Tensor/2/int, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-24
format_duration in 11 papers utils/misc.py ran · our draft was wrong fingerprinted MIT (permissive) · d06fe57a613a4c54 · report fixture: signature delta_time:float/0/float · returned str · level recorded 2026-09-24
get_init_weights_vit in 28 papers utils/vit_builder.py ran · our draft was wrong MIT (permissive) · 398c127f958b7a62 · report fixture: signature mode:str/0/str, head_bias:float/0/float · returned partial · level recorded 2026-09-24
get_pairs in 260 papers clip/simple_tokenizer.py ran · our draft was wrong MIT (permissive) · d919ae32e5e4e616 · report fixture: signature word:tuple/1/str · returned set · level recorded 2026-09-22
resize_pos_embed in 102 papers utils/vit_builder.py ran MIT (permissive) · aba59faf86f45da9 · report fixture: signature posemb:Tensor/3/float, posemb_new:Tensor/3/float, num_prefix_tokens:int/0/int, gs_new:tuple/1/int, interpolation:str/0/str, antialias:bool/0/bool · returned Tensor · level recorded 2026-09-24
str2bool in 533 papers utils/misc.py ran · violated contract MIT (permissive) · 29848dd47d2443ef · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
whitespace_clean in 230 papers clip/simple_tokenizer.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9542161e9640b858 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
CIFAR100Path train_eval.py unverified MIT (permissive) · ff2fbb0ab73e96ea · report
GlobalVarsManager train_eval.py unverified MIT (permissive) · a8edf98dd5c2d59b · report
ImageNetRPath train_eval.py unverified MIT (permissive) · 474413fb5eedd59b · report
build_model in 469 papers clip/model.py unverified MIT (permissive) · 6a720146b65b3fd6 · report
define_dataset utils/dataset_builder.py unverified MIT (permissive) · 35a10325e8443f2e · report
get_update_projection_dict train_eval.py unverified MIT (permissive) · fc5d7b56e09282a5 · report
load in 392 papers clip/clip.py unverified MIT (permissive) · fb0f7e6d8dacdf56 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Visual Prompt Tuning in Null Space (graph method: Visual Prompt Tuning in Null Space), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. null_space_projection entry · level 3 · ran · honoured contract · 22cb8015f3c083aa4256d7bf40a6b1c3d62ff412d40edabeaac84ef89c3c837e

harvested Assembly for Visual Prompt Tuning in Null Space (graph method: Visual Prompt Tuning in Null Space). 8 bricks; individually on a fixture: 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) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. get_update_projection_dict entry · level 0 · unverified · fc5d7b56e09282a5
  2. GlobalVarsManager helper · level 0 · unverified · a8edf98dd5c2d59b
  3. ClassIncrementalManager helper · level 1 · ran · 3268683b13ffdab4
  4. ImagePathDataset helper · level 1 · ran · 078149a1266f4078
  5. ImagePathDatasetClassManager helper · level 1 · ran · 96c050fd4ac91bfd
  6. CIFAR100Path helper · level 0 · unverified · ff2fbb0ab73e96ea
  7. ImageNetRPath helper · level 0 · unverified · 474413fb5eedd59b
  8. SDomainNetPath helper · level 1 · ran · 8cfe390097de1132

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="2406.05658") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continual LearningVisual Prompt Tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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