Papers › RanPAC: Random Projections and Pre-trained Models for Continual Learning

RanPAC: Random Projections and Pre-trained Models for Continual Learning

5 Jul 2023NeurIPS 2023 11arXiv:2307.02251archive 2025-07-28

Mark D. McDonnell, Dong Gong, Amin Parveneh, Ehsan Abbasnejad, Anton Van Den Hengel

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch paradigm. However, with the increasing prominence of foundation models, pre-trained models equipped with informative representations have become available for various downstream requirements. Several CL methods based on pre-trained models have been explored, either utilizing pre-extracted features directly (which makes bridging distribution gaps challenging) or incorporating adaptors (which may be subject to forgetting). In this paper, we propose a concise and effective approach for CL with pre-trained models. Given that forgetting occurs during parameter updating, we contemplate an alternative approach that exploits training-free random projectors and class-prototype accumulation, which thus bypasses the issue. Specifically, we inject a frozen Random Projection layer with nonlinear activation between the pre-trained model's feature representations and output head, which captures interactions between features with expanded dimensionality, providing enhanced linear separability for class-prototype-based CL. We also demonstrate the importance of decorrelating the class-prototypes to reduce the distribution disparity when using pre-trained representations. These techniques prove to be effective and circumvent the problem of forgetting for both class- and domain-incremental continual learning. Compared to previous methods applied to pre-trained ViT-B/16 models, we reduce final error rates by between 20% and 62% on seven class-incremental benchmarks, despite not using any rehearsal memory. We conclude that the full potential of pre-trained models for simple, effective, and fast CL has not hitherto been fully tapped. Code is at github.com/RanPAC/RanPAC.

PaperPDFConference PDFCodeCode 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 15 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 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: 15 samples from 1 repository, 10 ran (5 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 10 samples that ran have no recorded date.

ranpac/ranpac officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 10 ran (5 instrument-failed) · 5 unverified report
aimagelab/mammoth pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning (arXiv:2407.15793; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 5 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
5ran · our draft was wrong
1ran
5unverified

Licence: 6 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 ranpac/ranpac. “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.

ranpac/ranpac official repository 15 samples, 10 ran (5 instrument-failed) · 5 unverified
build_transform in 170 papers utils/data.py ran MIT (permissive) · 8425222b4660e321 · report fixture: signature is_train:bool/0/bool, args:ArgsStandIn/0/?, isCifar:bool/0/bool · returned list · level recorded 2026-09-24
conv1x1 in 691 papers resnet.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers resnet.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
count_parameters in 278 papers utils/toolkit.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 6bdbe3d6368c4cde · report fixture: signature model:callable/0/?, trainable:bool/0/bool · returned int · level recorded 2026-09-22
get_init_weights_vit in 28 papers petl/vision_transformer_ssf.py ran · our draft was wrong MIT (permissive) · def23f7d7d042968 · report fixture: signature mode:str/0/str, head_bias:float/0/float · returned partial · level recorded 2026-09-24
init_ssf_scale_shift in 9 papers petl/vision_transformer_ssf.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 896b5eec245f1bab · report fixture: signature dim:int/0/int · returned tuple · level recorded, date not recorded
pil_loader in 144 papers utils/data_manager.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 66b63ed4f327a712 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-25
ssf_ada in 8 papers petl/vision_transformer_ssf.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 61e8364b7e9bcb70 · report fixture: signature x:Tensor/2/float, scale:Tensor/1/float, shift:Tensor/1/float · returned Tensor · level recorded, date not recorded
target2onehot in 8 papers utils/toolkit.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 284e2e0345abe291 · report fixture: signature targets:Tensor/1/int, n_classes:int/0/int · returned Tensor · level recorded 2026-09-22
tensor2numpy in 18 papers utils/toolkit.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 929c76a2fa2e8c42 · report fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22
build_promptmodel petl/vpt.py unverified MIT (permissive) · caf426ace8f9b740 · report
get_convnet in 6 papers inc_net.py unverified MIT (permissive) · 2edd6df79bc77668 · report
resnet18 in 432 papers resnet.py unverified MIT (permissive) · d48a8b0d2e61f5f7 · report
vit_base_patch16_224_adapter petl/vision_transformer_adapter.py unverified MIT (permissive) · f51aa4aca78dae1d · report
vit_base_patch16_224_in21k_adapter petl/vision_transformer_adapter.py unverified MIT (permissive) · 606a5e08f74e25f2 · report

Tasks

Continual Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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