Papers › CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast...

CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation

14 Aug 2023arXiv:2308.07146archive 2025-07-28

Hongguang Zhu, Yunchao Wei, Xiaodan Liang, Chunjie Zhang, Yao Zhao

Vision-Language Pretraining (VLP) has shown impressive results on diverse downstream tasks by offline training on large-scale datasets. Regarding the growing nature of real-world data, such an offline training paradigm on ever-expanding data is unsustainable, because models lack the continual learning ability to accumulate knowledge constantly. However, most continual learning studies are limited to uni-modal classification and existing multi-modal datasets cannot simulate continual non-stationary data stream scenarios. To support the study of Vision-Language Continual Pretraining (VLCP), we first contribute a comprehensive and unified benchmark dataset P9D which contains over one million product image-text pairs from 9 industries. The data from each industry as an independent task supports continual learning and conforms to the real-world long-tail nature to simulate pretraining on web data. We comprehensively study the characteristics and challenges of VLCP, and propose a new algorithm: Compatible momentum contrast with Topology Preservation, dubbed CTP. The compatible momentum model absorbs the knowledge of the current and previous-task models to flexibly update the modal feature. Moreover, Topology Preservation transfers the knowledge of embedding across tasks while preserving the flexibility of feature adjustment. The experimental results demonstrate our method not only achieves superior performance compared with other baselines but also does not bring an expensive training burden. Dataset and codes are available at https://github.com/KevinLight831/CTP.

PaperPDFCodeCode Syntology ran

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 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 10 ran (8 with no instrument failure; 2 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. 1 of the 10 samples that ran has no recorded date.

kevinlight831/ctp officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 10 ran (2 instrument-failed) · 4 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: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 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 · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
7ran
4unverified

Licence: 1 of the 14 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 kevinlight831/ctp. “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.

kevinlight831/ctp official repository 14 samples, 10 ran (2 instrument-failed) · 4 unverified
compute_acc in 61 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · aa81d03f07735ab8 · report fixture: signature logits:Tensor/2/float, label:Tensor/1/int, reduction:str/0/str · returned float · level recorded 2026-09-22
compute_ewc train/train_EWC.py ran MIT (permissive) · e0aecd946799c666 · report fixture: signature args:Args/0/?, model:callable/0/?, fisher:dict/0/?, older_params:dict/0/? · returned Tensor · level recorded 2026-09-24
compute_features in 10 papers models/exemplar.py ran MIT (permissive) · 34cd28d00f703058 · report fixture: signature model:callable/0/?, data_loader:list/1/tuple, device:str/0/str · returned tuple · level recorded 2026-09-24
cosine_scheduler in 74 papers utils.py ran MIT (permissive) · f7ce70abc24e5b7a · report fixture: signature init_lr:float/0/float, min_lr:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int, warmup_lr:float/0/float, warmup_epochs:int/0/int, warmup_iters:int/0/int, start_warmup_value:int/0/int · returned ndarray · level recorded 2026-09-24
interpolate_pos_embed in 59 papers models/vit.py ran · our draft was wrong MIT (permissive) · c6ec173f19f5c34d · report fixture: signature pos_embed_checkpoint:Tensor/3/float, visual_encoder:callable/0/? · returned Tensor · level recorded, date not recorded
is_url in 30 papers models/model_utils.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 4d1d9c47619920ba · report fixture: signature url_or_filename:str/0/str · returned bool · level recorded 2026-09-22
itm_eval in 27 papers product_evaluation.py ran MIT (permissive) · 7ceaadad301f8eb8 · report fixture: signature scores_i2t:ndarray/2/float, scores_t2i:ndarray/2/float, txt2img:dict/0/?, img2txt:dict/0/? · returned dict · level recorded 2026-09-24
merge_data in 6 papers utils.py ran MIT (permissive) · 610c6d50aa14ce9c · report fixture: signature data_1:dict/0/?, data_2:dict/0/? · returned dict · level recorded 2026-09-24
read_json in 250 papers product_evaluation.py ran MIT (permissive) · a9cfe36eb8375795 · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-24
update_memory models/exemplar.py ran MIT (permissive) · d32c3a0e4ff678d7 · report fixture: signature item_id_list_np:ndarray/1/int, mapped_prototypes:ndarray/2/float, memory_size_each_task:int/0/int · returned list · level recorded 2026-09-24
all_gather_with_grad in 93 papers models/clip_pretrain.py unverified MIT (permissive) · 0ec9fc2025c16f65 · report
compute_image_caption_features models/exemplar.py unverified MIT (permissive) · d03c46a963c94da7 · report
load_tf_weights_in_bert in 135 papers models/xbert.py unverified MIT (permissive) · e4471ca16a2e77e8 · report

Tasks

Continual LearningContinual Pretraining

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