Papers › Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set...

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

28 May 2019arXiv:1905.12019archive 2025-07-28

Martin Mundt, Iuliia Pliushch, Sagnik Majumder, Yongwon Hong, Visvanathan Ramesh

Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating catastrophic interference with learned representations. In this work, we introduce a probabilistic approach that connects these perspectives based on variational inference in a single deep autoencoder model. Specifically, we propose to bound the approximate posterior by fitting regions of high density on the basis of correctly classified data points. These bounds are shown to serve a dual purpose: unseen unknown out-of-distribution data can be distinguished from already trained known tasks towards robust application. Simultaneously, to retain already acquired knowledge, a generative replay process can be narrowed to strictly in-distribution samples, in order to significantly alleviate catastrophic interference.

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 13 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

MrtnMndt/OCDVAE_ContinualLearning officialmentioned in papermentioned on GitHubpytorchMITSyntology: not harvested report
MrtnMndt/OCDVAEContinualLearning officialmentioned on GitHubpytorchMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 unverified report
TimmHess/OCDVAEContinualLearning mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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

13 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

12ran
1unverified

Licence: 0 of the 13 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

MrtnMndt/OCDVAEContinualLearning official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
KLD in 6 papers lib/Training/loss_functions.py ran fingerprinted MIT (permissive) · 35a868da9fed37c9 · report fixture: signature mu:Tensor/2/float, std:Tensor/2/float · returned Tensor · level recorded 2026-09-25
augment_data in 7 papers lib/Training/augmentation.py ran MIT (permissive) · acecd7a6217e354d · report fixture: signature batch:Tensor/4/float, args:Args/0/? · returned Tensor · level recorded 2026-09-25
augment_flip lib/Training/augmentation.py ran fingerprinted MIT (permissive) · 4333c3e5ee86bb81 · report fixture: signature img:Tensor/4/float, hflip_p:float/0/float, vflip_p:float/0/float · returned Tensor · level recorded 2026-09-25
augment_random_translate lib/Training/augmentation.py ran fingerprinted MIT (permissive) · 77b460b279b0da2d · report fixture: signature img:Tensor/3/float, random_factor:float/0/float · returned Tensor · level recorded 2026-09-25
calc_distances_to_means lib/OpenSet/meta_recognition.py ran MIT (permissive) · 4bf4bed0805b9389 · report fixture: signature means:list/1/Tensor, tensors:list/1/Tensor, distance_function:str/0/str · returned list · level recorded 2026-09-25
encoder_loss_with_fake lib/Training/loss_functions.py ran MIT (permissive) · b3576c10e8d51fce · report fixture: signature output_samples_classification:Tensor/2/float, target:Tensor/1/int, output_samples_recon:Tensor/2/float, inp:Tensor/2/float, real_mu:Tensor/2/float, real_std:Tensor/2/float, rec_mu:Tensor/2/float, rec_std:Tensor/2/float, fake_mu:Tensor/2/float, fake_std:Tensor/2/float, device:device/0/?, args:Args/0/? · returned tuple · level recorded 2026-09-25
eval_dataset lib/Training/evaluate.py ran MIT (permissive) · 5bb73bb78d01fb53 · report fixture: signature model:callable/0/?, data_loader:list/1/tuple, num_classes:int/0/int, device:str/0/str, samples:int/0/int, calc_reconstruction:bool/0/bool, autoregression:bool/0/bool · returned dict · level recorded 2026-09-25
eval_openset_dataset lib/Training/evaluate.py ran MIT (permissive) · ff4c1bd619f2a04b · report fixture: signature model:callable/0/?, data_loader:list/1/tuple, num_classes:int/0/int, device:str/0/str, samples:int/0/int, calc_reconstruction:bool/0/bool, autoregression:bool/0/bool · returned dict · level recorded 2026-09-25
get_feat_size lib/Models/architectures.py ran MIT (permissive) · 8b8425aa050b8c28 · report fixture: signature block:callable/0/?, spatial_size:int/0/int, ncolors:int/0/int · returned tuple · level recorded 2026-09-25
get_latent_embedding lib/Training/evaluate.py ran MIT (permissive) · f28bb4760db0af78 · report fixture: signature model:callable/0/?, data_loader:list/1/tuple, num_classes:int/0/int, device:str/0/str · returned list · level recorded 2026-09-25
get_means lib/OpenSet/meta_recognition.py ran MIT (permissive) · 9a2c9f801548b8b5 · report fixture: signature tensors_list:list/1/Tensor · returned list · level recorded 2026-09-25
joint_loss_function lib/Training/loss_functions.py unverified MIT (permissive) · 13389065de3e98b6 · report
TimmHess/OCDVAEContinualLearning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
surrogate_loss in 5 papers lib/Models/si.py ran MIT (permissive) · 41cc1bfa6d07666f · report fixture: signature model:callable/0/?, storage_unit:StorageUnit/0/? · returned Tensor · level recorded 2026-09-24

Tasks

Audio ClassificationBayesian InferenceContinual LearningOpen Set LearningVariational Inference

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