Papers › Persistent Test-time Adaptation in Recurring Testing Scenarios

Persistent Test-time Adaptation in Recurring Testing Scenarios

30 Nov 2023arXiv:2311.18193archive 2025-07-28

Trung-Hieu Hoang, Duc Minh Vo, Minh N. Do

Current test-time adaptation (TTA) approaches aim to adapt a machine learning model to environments that change continuously. Yet, it is unclear whether TTA methods can maintain their adaptability over prolonged periods. To answer this question, we introduce a diagnostic setting - recurring TTA where environments not only change but also recur over time, creating an extensive data stream. This setting allows us to examine the error accumulation of TTA models, in the most basic scenario, when they are regularly exposed to previous testing environments. Furthermore, we simulate a TTA process on a simple yet representative ϵ-perturbed Gaussian Mixture Model Classifier, deriving theoretical insights into the dataset- and algorithm-dependent factors contributing to gradual performance degradation. Our investigation leads us to propose persistent TTA (PeTTA), which senses when the model is diverging towards collapse and adjusts the adaptation strategy, striking a balance between the dual objectives of adaptation and model collapse prevention. The supreme stability of PeTTA over existing approaches, in the face of lifelong TTA scenarios, has been demonstrated over comprehensive experiments on various benchmarks. Our project page is available at https://hthieu166.github.io/petta.

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.

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

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 12 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 12 ran (6 with no instrument failure; 6 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hthieu166/petta officialmentioned on GitHubpytorchSyntology: 17 samples, 12 ran (6 instrument-failed) · 5 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

17 samples harvested: 12 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 6 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.

4ran · our draft was wrong
2ran; the contract check could not run
6ran
5unverified

Licence: 17 of the 17 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 hthieu166/petta. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

hthieu166/petta official repository 17 samples, 12 ran (6 instrument-failed) · 5 unverified
ColorJitterPro in 6 papers src/adapter/petta.py ran no licence file found · pointer only · 96a5a462737f2b96 · report fixture: returned ColorJitterPro · level recorded 2026-09-22
ImageList src/adapter/petta.py ran no licence file found · pointer only · 3fa65932f3503ca1 · report fixture: returned ImageList · level recorded 2026-09-22
ImageNormalizer src/adapter/petta.py ran fingerprinted no licence file found · pointer only · 396338a54ba1eba6 · report fixture: returned ImageNormalizer · level recorded 2026-09-22
MomentumBN src/adapter/petta.py ran no licence file found · pointer only · 5e69882c492dedf9 · report fixture: returned MomentumBN · level recorded 2026-09-22
RobustBN1d src/adapter/petta.py ran fingerprinted no licence file found · pointer only · 82eb95a8d9d858cf · report fixture: returned RobustBN1d · level recorded 2026-09-22
RobustBN2d src/adapter/petta.py ran fingerprinted no licence file found · pointer only · 3290e5fe60d2293f · report fixture: returned RobustBN2d · level recorded 2026-09-22
complete_data_dir_path in 9 papers src/adapter/petta.py ran · our draft was wrong no licence file found · pointer only · 9ffa7a7ccd232586 · report fixture: signature root:str/0/str, dataset_name:str/0/str · returned str · level recorded 2026-09-22
get_transform in 75 papers src/adapter/petta.py ran · our draft was wrong no licence file found · pointer only · b0c4eab726f2ba98 · report fixture: signature dataset_name:str/0/str, adaptation:str/0/str · returned Compose · level recorded 2026-09-22
get_tta_transforms in 10 papers src/adapter/petta.py ran · our draft was wrong no licence file found · pointer only · 36688c7857b983fd · report fixture: signature cfg:MockConfig/0/?, gaussian_std:float/0/float, soft:bool/0/bool · returned Compose · level recorded 2026-09-22
self_training src/adapter/petta.py ran; the contract check could not run (RAISES) no licence file found · pointer only · b1c468877aaa60d4 · report fixture: returned Tensor · level recorded 2026-09-22
softmax_entropy in 54 papers
census: 18 implementations from 29 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
src/adapter/petta.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 8cc4004512e3fa2f · report fixture: returned Tensor · level recorded 2026-09-22
split_up_model src/adapter/petta.py ran · our draft was wrong no licence file found · pointer only · 34146179c8a52772 · report fixture: signature model:callable/0/?, arch_name:str/0/str, dataset_name:str/0/str · returned tuple · level recorded 2026-09-22
BaseAdapter src/adapter/petta.py unverified no licence file found · pointer only · 688c1c2a9a37f39e · report
PeTTA src/adapter/petta.py unverified no licence file found · pointer only · 2ff8432b1e1c68ee · report
ResNetDomainNet126 src/adapter/petta.py unverified no licence file found · pointer only · 91692a77659382c6 · report
get_augmentation in 19 papers src/adapter/petta.py unverified no licence file found · pointer only · 8c308dba19373e9c · report
get_source_loader src/adapter/petta.py unverified no licence file found · pointer only · 31ed6a79ea94f774 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for PeTTA (graph method: PeTTA). 21 bricks; individually on a fixture: 16 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. PeTTA entry · level 0 · unverified · 2ff8432b1e1c68ee
  2. BaseAdapter model · level 0 · unverified · 688c1c2a9a37f39e
  3. RobustBN1d helper · level 1 · ran · 82eb95a8d9d858cf
  4. RobustBN2d helper · level 1 · ran · 3290e5fe60d2293f
  5. get_source_loader helper · level 0 · unverified · 31ed6a79ea94f774
  6. get_tta_transforms helper · level 1 · ran · our draft was wrong · 36688c7857b983fd
  7. self_training helper · level 1 · ran; the contract check could not run (RAISES) · b1c468877aaa60d4
  8. softmax_entropy helper · level 1 · ran; the contract check could not run (RAISES) · 8cc4004512e3fa2f
  9. split_up_model helper · level 1 · ran · our draft was wrong · 34146179c8a52772
  10. ResNetDomainNet126 helper · level 0 · unverified · 91692a77659382c6
  11. MomentumBN helper · level 1 · ran · 5e69882c492dedf9
  12. ImageList helper · level 1 · ran · 3fa65932f3503ca1
  13. complete_data_dir_path helper · level 1 · ran · our draft was wrong · 9ffa7a7ccd232586
  14. get_transform helper · level 1 · ran · our draft was wrong · b0c4eab726f2ba98
  15. Clip helper · level 1 · ran · f611b91f6dc1d3c0
  16. ColorJitterPro helper · level 1 · ran · 96a5a462737f2b96
  17. GaussianNoise helper · level 1 · ran · 8d0788e9468dc56a
  18. ImageNetXMaskingLayer helper · level 1 · ran · 9032562b014e775f
  19. ImageNormalizer helper · level 1 · ran · 396338a54ba1eba6
  20. TransformerWrapper helper · level 1 · ran · 701b69ab32deabd2
  21. get_augmentation helper · level 0 · unverified · 8c308dba19373e9c

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="2311.18193") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiagnosticTest-time Adaptation

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