Papers › Learning without Forgetting

Learning without Forgetting

29 Jun 2016arXiv:1606.09282archive 2025-07-28

Zhizhong Li, Derek Hoiem

When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.

PaperPDFCodeCode 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="1606.09282")

Code

Syntology Ran 9 of 15 code samples harvested from 8 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 4 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: community (archive-listed): 15 samples from 8 repositories, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

g-u-n/pycil mentioned on GitHubpytorch report
geox-lab/cmn mentioned on GitHubpytorch report
ivclab/cvs mentioned on GitHubpytorch report
kibok90/iccv2019-inc mentioned on GitHubpytorchMIT report
ngailapdi/LWF mentioned on GitHubpytorch report
wannabeOG/ExpertNet-Pytorch mentioned on GitHubpytorch report
yaoyao-liu/mnemonics mentioned on GitHubpytorch 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

15 samples harvested; 9 ran; 1 honoured the contract we drafted; 6 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
1ran · our draft was wrong
4ran · fixture could not drive it
3ran
6unverified

Licence: 1 of the 15 samples is 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 8 repositories linked to this paper, official or community; each sample names its own and says which. “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.

Appr mmasana/FACIL/src/approach/lwf.py community (archive-listed) ran MIT (permissive) · a65368ea6628ffd0 · report
Inc_Learning_Appr mmasana/FACIL/src/approach/lwf.py community (archive-listed) ran MIT (permissive) · 686c76397b75be4d · report
KDLoss ivclab/cvs/kdloss.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 28946d6ab7de665b · report
LearningWithoutForgetting ContinualAI/avalanche/avalanche/training/regularization.py community (archive-listed) ran MIT (permissive) · 68bc5e317dccf467 · report
MultiClassCrossEntropy ngailapdi/LWF/model.py community (archive-listed) ran · fixture could not drive it Apache-2.0 (permissive) · b43737d7d32870ed · report
get_one_hot geox-lab/cmn/LwF-CIFAR100/LwF.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · dc209a0ea5b09a3f · report
incremental_train_and_eval yaoyao-liu/mnemonics/mnemonics-training/1_train/trainer/incremental.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · a99cc76d5a5b058b · report
loss_fn_kd GMvandeVen/continual-learning/models/utils/loss_functions.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · b76db52297524e52 · report
model_criterion wannabeOG/ExpertNet-Pytorch/utils/model_utils.py community (archive-listed) ran · fixture could not drive it BSD-2-Clause (permissive) · 25e295f6e060e434 · report
LwFmodel geox-lab/cmn/LwF-CIFAR100/LwF.py community (archive-listed) unverified MIT (permissive) · f08f055b7c6c13c0 · report
Model ngailapdi/LWF/model.py community (archive-listed) unverified Apache-2.0 (permissive) · 8bb63a717b07a3b8 · report
iCIFAR100 geox-lab/cmn/LwF-CIFAR100/LwF.py community (archive-listed) unverified MIT (permissive) · 97e769f51fb2d580 · report
kaiming_normal_init ngailapdi/LWF/model.py community (archive-listed) unverified Apache-2.0 (permissive) · a8174ba24a4f43da · report
network geox-lab/cmn/LwF-CIFAR100/LwF.py community (archive-listed) unverified MIT (permissive) · da1b0e40683dca7a · report
weighted_average GMvandeVen/continual-learning/models/utils/loss_functions.py community (archive-listed) unverified MIT (permissive) · 1179cbb68303ab65 · report

Tasks

Class Incremental LearningContinual LearningDisjoint 10-1Disjoint 15-1Disjoint 15-5Domain 1-1Domain 11-1Domain 11-5Incremental LearningOverlapped 10-1Overlapped 15-1Overlapped 15-5

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Continual Learning visual domain decathlon (10 tasks) LwF Avg. Accuracy 76.93 #11 of 14 Archive leaderboard report
Continual Learning visual domain decathlon (10 tasks) LwF decathlon discipline (Score) 2515 #11 of 14 Archive leaderboard report
Disjoint 10-1 PASCAL VOC 2012 LWF mIoU 4.3 #8 of 8 Archive leaderboard report
Disjoint 15-1 PASCAL VOC 2012 LWF mIoU 5.3 #9 of 9 Archive leaderboard report
Disjoint 15-5 PASCAL VOC 2012 LWF Mean IoU 54.9 #9 of 9 Archive leaderboard report
Overlapped 10-1 PASCAL VOC 2012 LWF mIoU 4.8 #13 of 13 Archive leaderboard report
Overlapped 15-1 PASCAL VOC 2012 LWF mIoU 5.5 #13 of 13 Archive leaderboard report
Overlapped 15-5 PASCAL VOC 2012 LWF Mean IoU (val) 55.0 #13 of 13 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.

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