Papers › FOSTER: Feature Boosting and Compression for Class-Incremental Learning

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

10 Apr 2022arXiv:2204.04662archive 2025-07-28

Fu-Yun Wang, Da-Wei Zhou, Han-Jia Ye, De-Chuan Zhan

The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this phenomenon, whereas most of them either fall into the stability-plasticity dilemma or take too much computation or storage overhead. Inspired by the gradient boosting algorithm to gradually fit the residuals between the target model and the previous ensemble model, we propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively. Specifically, we first dynamically expand new modules to fit the residuals between the target and the output of the original model. Next, we remove redundant parameters and feature dimensions through an effective distillation strategy to maintain the single backbone model. We validate our method FOSTER on CIFAR-100 and ImageNet-100/1000 under different settings. Experimental results show that our method achieves state-of-the-art performance. Code is available at: https://github.com/G-U-N/ECCV22-FOSTER.

PaperPDFCodeCode 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 8 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 2 ran (2 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.

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

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

G-U-N/ECCV22-FOSTER officialmentioned in papermentioned on GitHubpytorchSyntology: 8 samples, 2 ran (0 instrument-failed) · 6 unverified report
g-u-n/pycil mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RMM: Reinforced Memory Management for Class-Incremental Learning (arXiv:2301.05792; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 2 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

8 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 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 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.

2ran
6unverified

Licence: 0 of the 8 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 G-U-N/ECCV22-FOSTER. “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.

G-U-N/ECCV22-FOSTER official repository 8 samples, 2 ran (0 instrument-failed) · 6 unverified
CifarResNet in 5 papers models/foster.py ran · metamorphic tier: deterministic MIT (permissive) · a2989710a793436e · report fixture: signature x:Tensor/4/float · returned dict · level recorded 2026-09-22
resnet32 in 47 papers models/foster.py ran MIT (permissive) · dff6861d5062f441 · report fixture: returned CifarResNet · level recorded 2026-09-22
BaseLearner in 15 papers models/foster.py unverified MIT (permissive) · 1afda64d8a5c5708 · report
FOSTER models/foster.py unverified MIT (permissive) · 96a31524768b2656 · report
FOSTERNet models/foster.py unverified MIT (permissive) · b0894f0cc1dd3e52 · report
ResNet in 139 papers models/foster.py unverified MIT (permissive) · 8af98f7f67a0fdda · report
_resnet in 27 papers models/foster.py unverified MIT (permissive) · 67c778a4fecccfd5 · report
get_convnet in 6 papers models/foster.py unverified MIT (permissive) · 4cad458166ad5417 · 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 FOSTER (graph method: FOSTER). 19 bricks; individually on a fixture: 13 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. FOSTER entry · level 0 · unverified · 96a31524768b2656
  2. BaseLearner helper · level 0 · unverified · 1afda64d8a5c5708
  3. FOSTERNet model · level 0 · unverified · b0894f0cc1dd3e52
  4. _KD_loss loss · level 1 · ran · our draft was wrong · 49b067de98344fbc
  5. count_parameters helper · level 1 · ran · honoured contract · 6bdbe3d6368c4cde
  6. tensor2numpy helper · level 1 · ran · honoured contract · 929c76a2fa2e8c42
  7. accuracy helper · level 1 · ran · our draft was wrong · fa5bbac75c929c9f
  8. SimpleLinear helper · level 1 · ran · 912a99c7a4b1f235
  9. get_convnet helper · level 0 · unverified · 4cad458166ad5417
  10. resnet32 helper · level 1 · ran · dff6861d5062f441
  11. CifarResNet helper · level 1 · ran · a2989710a793436e
  12. ResNetBasicblock helper · level 1 · ran · f68244225a96dc8d
  13. DownsampleA helper · level 1 · ran · de5434be7eacc33a
  14. BasicBlock helper · level 1 · ran · b120f2c9d259b10d
  15. Bottleneck helper · level 1 · ran · 51093a8658ab4353
  16. ResNet helper · level 0 · unverified · 8af98f7f67a0fdda
  17. _resnet helper · level 0 · unverified · 67c778a4fecccfd5
  18. conv1x1 helper · level 1 · ran · our draft was wrong · 09115aafa689d3d8
  19. conv3x3 helper · level 1 · ran · our draft was wrong · e0295c5753083aba

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="2204.04662") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Class Incremental LearningIncremental Learningclass-incremental learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Incremental Learning CIFAR-100 - 50 classes + 10 steps of 5 classes FOSTER Average Incremental Accuracy 67.95 #5 of 13 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 25 steps of 2 classes FOSTER Average Incremental Accuracy 63.83 #3 of 5 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 5 steps of 10 classes FOSTER Average Incremental Accuracy 69.46 #5 of 15 Archive leaderboard report
Incremental Learning CIFAR100-B0(10steps of 10 classes) FOSTER Average Incremental Accuracy 72.9 #5 of 6 Archive leaderboard report
Incremental Learning CIFAR100B020Step(5ClassesPerStep) FOSTER Average Incremental Accuracy 70.65 #5 of 5 Archive leaderboard report
Incremental Learning ImageNet - 10 steps FOSTER Average Incremental Accuracy 68.34 #4 of 10 Archive leaderboard report
Incremental Learning ImageNet-100 - 50 classes + 10 steps of 5 classes FOSTER Average Incremental Accuracy 77.54 #3 of 5 Archive leaderboard report
Incremental Learning ImageNet-100 - 50 classes + 25 steps of 2 classes FOSTER Average Incremental Accuracy 69.34 #2 of 3 Archive leaderboard report
Incremental Learning ImageNet-100 - 50 classes + 5 steps of 10 classes FOSTER Average Incremental Accuracy 80.22 #1 of 5 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps FOSTER Average Incremental Accuracy 77.75 #3 of 13 Archive leaderboard report
Incremental Learning ImageNet100 - 20 steps FOSTER Average Incremental Accuracy 74.49 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Knowledge Distillation

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