Papers › OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free...

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning

6 Feb 2024arXiv:2402.04129archive 2025-07-28

Wei-Cheng Huang, Chun-Fu Chen, Hsiang Hsu

Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superior performance to prominent rehearsal-based ones. Rehearsal-free CIL methods struggle with distinguishing classes from different tasks, as those are not trained together. In this work we propose a regularization method based on virtual outliers to tighten decision boundaries of the classifier, such that confusion of classes among different tasks is mitigated. Recent prompt-based methods often require a pool of task-specific prompts, in order to prevent overwriting knowledge of previous tasks with that of the new task, leading to extra computation in querying and composing an appropriate prompt from the pool. This additional cost can be eliminated, without sacrificing accuracy, as we reveal in the paper. We illustrate that a simplified prompt-based method can achieve results comparable to previous state-of-the-art (SOTA) methods equipped with a prompt pool, using much less learnable parameters and lower inference cost. Our regularization method has demonstrated its compatibility with different prompt-based methods, boosting those previous SOTA rehearsal-free CIL methods' accuracy on the ImageNet-R and CIFAR-100 benchmarks. Our source code is available at https://github.com/jpmorganchase/ovor.

PaperPDFCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.04129")

Code

Syntology Ran 19 of 27 code samples harvested from 3 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 15 ran with no contract checked.

By repository: found in paper text by Syntology: 25 samples from 3 repositories, 17 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jpmorganchase/ovor found in paper text by Syntology report
GT-RIPL/CODA-Prompt found in paper text by Syntology report
pprp/timm found in paper text by SyntologyApache-2.0 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

27 samples harvested; 19 ran; 1 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
15ran
8unverified

Licence: 2 of the 27 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 3 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

CodaPrompt GT-RIPL/CODA-Prompt/models/zoo.py found in paper text by Syntology ran · metamorphic tier: deterministic MIT (permissive) · e1716fdcd4486b32 · report
CosineSchedule jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology ran Apache-2.0 (permissive) · fb5af0c577ee3e37 · report
NPOS jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology ran Apache-2.0 (permissive) · cd90daeda39e4548 · report
accuracy jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology ran · our draft was wrong Apache-2.0 (permissive) · 14e1f6edf047e2fe · report
adaptive_avgmax_pool2d pprp/timm/timm/layers/adaptive_avgmax_pool.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · bbb0ade8018ebd05 · report
adaptive_catavgmax_pool2d pprp/timm/timm/layers/adaptive_avgmax_pool.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · c98e5e298f086636 · report
adaptive_pool_feat_mult pprp/timm/timm/layers/adaptive_avgmax_pool.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · 01c6892d9a801397 · report
get_condconv_initializer pprp/timm/timm/layers/cond_conv2d.py found in paper text by Syntology ran · our draft was wrong Apache-2.0 (permissive) · 816ebe82b6b6275f · report
hard_sigmoid_jit pprp/timm/timm/layers/activations_jit.py found in paper text by Syntology ran Apache-2.0 (permissive) · 91c27523dde7eb4a · report
mish pprp/timm/timm/layers/activations.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · 801c85b8903bfff5 · report
mish_jit pprp/timm/timm/layers/activations_jit.py found in paper text by Syntology ran Apache-2.0 (permissive) · 14eddd8cc4c65fe0 · report
sigmoid pprp/timm/timm/layers/activations.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · d83b6ecf3cdc1d6a · report
swish pprp/timm/timm/layers/activations.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · 717e4d22b6d103e6 · report
swish_jit pprp/timm/timm/layers/activations_jit.py found in paper text by Syntology ran Apache-2.0 (permissive) · 8e341f8585b3fe94 · report
swish_jit_bwd pprp/timm/timm/layers/activations_me.py found in paper text by Syntology ran Apache-2.0 (permissive) · ccf59d4aa2ccacdb · report
swish_jit_fwd pprp/timm/timm/layers/activations_me.py found in paper text by Syntology ran Apache-2.0 (permissive) · 2d53e47b891cd927 · report
swish_me pprp/timm/timm/layers/activations_me.py found in paper text by Syntology ran Apache-2.0 (permissive) · 51a2f9920a170144 · report
NormalNN jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 3e51324f77696213 · report
OnePrompt jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 10a3cf3944acb574 · report
Prompt jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 94d1744c930d27d6 · report
_LRScheduler jpmorganchase/ovor/learners/prompt.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 0da189d1706732b7 · report
conv2d_same pprp/timm/timm/layers/conv2d_same.py found in paper text by Syntology unverified Apache-2.0 (permissive) · 8cf70ff8a63b107f · report
create_classifier pprp/timm/timm/layers/classifier.py found in paper text by Syntology unverified Apache-2.0 (permissive) · f3958c754a8750d7 · report
create_conv2d_pad pprp/timm/timm/layers/conv2d_same.py found in paper text by Syntology unverified Apache-2.0 (permissive) · c7ec3481c1905e5b · report
rel_logits_1d pprp/timm/timm/layers/bottleneck_attn.py found in paper text by Syntology unverified Apache-2.0 (permissive) · f0b44651e598ca66 · report
ortho_penalty identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · a763dc6f8d5d1498 · report
tensor_prompt identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · 3f33843b601c8d4d · report

Tasks

Class Incremental LearningIncremental Learningclass-incremental learning

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