Papers › FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

25 Sep 2023NeurIPS 2023 11arXiv:2309.14062archive 2025-07-28

Dipam Goswami, Yuyang Liu, Bartłomiej Twardowski, Joost Van de Weijer

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://github.com/dipamgoswami/FeCAM.

PaperPDFConference PDFCodeCode 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 21 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 11 ran (5 with no instrument failure; 6 where Syntology's instrument failed); community (archive-listed): 6 samples from 2 repositories, 4 ran (4 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 15 samples that ran have no recorded date.

dipamgoswami/fecam officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 11 ran (6 instrument-failed) · 4 unverified report
gmum/hint mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
gmum/hyperinterval mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 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

21 samples harvested: 15 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 6 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.

2ran · honoured contract
6ran · our draft was wrong
7ran
6unverified

Licence: 5 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 3 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.

dipamgoswami/fecam official repository 15 samples, 11 ran (6 instrument-failed) · 4 unverified
compute_common_cov utils/maha_utils.py ran · honoured contract MIT (permissive) · c9427cae68d6444f · report fixture: signature train_loader:list/1/tuple, model:callable/0/? · returned Tensor · level recorded, date not recorded
compute_new_common_cov utils/maha_utils.py ran · honoured contract MIT (permissive) · 1de4ff97b038199a · report fixture: signature train_loader:list/1/tuple, model:callable/0/? · returned Tensor · level recorded, date not recorded
conv1x1 in 691 papers convs/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
conv1x1 in 691 papers convs/modified_represnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · d5cd7ffe2dc51b21 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers convs/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
conv3x3 in 1,376 papers convs/resnet_cbam.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · 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 convs/modified_represnet.py ran · our draft was wrong MIT (permissive) · 1907f2ae25449f39 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
normalize_cov FeCAM_vit_core50.py ran MIT (permissive) · dbac5df5f6dc9433 · report fixture: signature cov_mat:list/1/ndarray · returned list · level recorded 2026-09-24
resnet18_rep in 9 papers convs/modified_represnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · ecaa7ca05d715804 · report fixture: signature pretrained:bool/0/bool, num_classes:int/0/int, args:dict/0/? · returned ResNet · level recorded 2026-09-25
shrink_cov FeCAM_vit_core50.py ran fingerprinted MIT (permissive) · 17ed71f058d7674a · report fixture: signature cov:ndarray/2/float · returned ndarray · level recorded 2026-09-24
shrink_cov FeCAM_vit_imagenet-r.py ran fingerprinted MIT (permissive) · 0365639e81fbf382 · report fixture: signature cov:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_dataset in 285 papers FeCAM_vit_imagenet-r.py unverified MIT (permissive) · f5c8f70797dc3539 · report
resnet18 in 432 papers convs/resnet.py unverified MIT (permissive) · 966d18702829b1c0 · report
resnet18_cbam in 13 papers convs/resnet_cbam.py unverified MIT (permissive) here; the stored copy is pointer only · 9d7277889d69cf2d · report
resnet34_cbam in 12 papers convs/resnet_cbam.py unverified MIT (permissive) here; the stored copy is pointer only · 9eb3d43ee2e8ae7d · report
gmum/hint community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
IntervalModuleWithWeights IntervalNets/interval_modules.py ran MIT (permissive) · 4d1ed8dab640e691 · report fixture: returned IntervalModuleWithWeights · level recorded 2026-09-22
IntervalLinear IntervalNets/interval_modules.py unverified MIT (permissive) · 5ac470f50d929fcf · report
gmum/hyperinterval community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
get_current_targets Utils/hnet_interval_regularizer.py ran MIT (permissive) · e488b43331809f71 · report fixture: signature task_id:int/0/int, hnet:callable/0/?, eps:float/0/float · returned tuple · level recorded 2026-09-24
get_current_targets Utils/hnet_middle_regularizer.py ran MIT (permissive) · d8e7aca624e3e8de · report fixture: signature task_id:int/0/int, hnet:callable/0/?, eps:float/0/float · returned list · level recorded 2026-09-24
parse_logits IntervalNets/interval_modules.py ran MIT (permissive) · a14c0ad5907d1cd5 · report fixture: signature x:Tensor/3/float · returned map · level recorded 2026-09-24
prepare_subset_imagenet_tasks DatasetHandlers/subset_image_net.py unverified MIT (permissive) · a740ad44865dbc9b · 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 FeCAM (graph method: FeCAM). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. IntervalLinear entry · level 0 · unverified · 5ac470f50d929fcf
  2. IntervalModuleWithWeights helper · level 1 · ran · 4d1ed8dab640e691

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="2309.14062") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Class Incremental LearningContinual LearningExemplar-FreeIncremental 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