Papers › iCaRL: Incremental Classifier and Representation Learning

iCaRL: Incremental Classifier and Representation Learning

23 Nov 2016CVPR 2017 7arXiv:1611.07725archive 2025-07-28

Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, Christoph H. Lampert

A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail.

PaperPDFConference PDFCodeCode 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="1611.07725")

Code

Syntology Ran 3 of 14 code samples harvested from 3 repositories linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 0 ran; community (archive-listed): 7 samples from 2 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

srebuffi/iCaRL officialmentioned in papermentioned on GitHubtfMIT report
DRSAD/iCaRL mentioned on GitHubpytorch report
donlee90/icarl mentioned on GitHubpytorch report
g-u-n/pycil 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

14 samples harvested; 3 ran; 0 honoured the contract we drafted; 11 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.

2ran · our draft was wrong
1ran
11unverified

Licence: 3 of the 14 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. “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.

get_variable srebuffi/iCaRL/iCaRL-Tensorflow/utils_resnet.py official repository unverified MIT (permissive) · 573afeddc57bd6d5 · report
load_class_in_feature_space srebuffi/iCaRL/iCaRL-Tensorflow/utils_icarl.py official repository unverified MIT (permissive) · 52298d4288456271 · report
parse_devkit_meta srebuffi/iCaRL/iCaRL-Tensorflow/utils_data.py official repository unverified MIT (permissive) · 2e54a5d9c05be1fc · report
read_data srebuffi/iCaRL/iCaRL-Tensorflow/utils_data.py official repository unverified MIT (permissive) · b1a4e999428538e9 · report
read_data_test srebuffi/iCaRL/iCaRL-Tensorflow/utils_data.py official repository unverified MIT (permissive) · a1952a1bd60c5594 · report
relu srebuffi/iCaRL/iCaRL-Tensorflow/utils_resnet.py official repository unverified MIT (permissive) · 4c8201151d6e4d18 · report
unpickle srebuffi/iCaRL/iCaRL-TheanoLasagne/utils_cifar100.py official repository unverified MIT (permissive) · 86aadd9c26d05f6c · report
dataset_transforms mmasana/FACIL/src/approach/icarl.py community (archive-listed) ran MIT (permissive) · 85bc3649f83b49eb · report
get_one_hot DRSAD/iCaRL/iCaRL.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 71a66063541d1b3b · report
override_dataset_transform mmasana/FACIL/src/approach/icarl.py community (archive-listed) ran · our draft was wrong MIT (permissive) · c60e16f66d93fb54 · report
Appr mmasana/FACIL/src/approach/icarl.py community (archive-listed) unverified MIT (permissive) · c9d0a1630e27cbbb · report
Inc_Learning_Appr mmasana/FACIL/src/approach/icarl.py community (archive-listed) unverified MIT (permissive) · 56204fa814f880a3 · report
iCIFAR100 DRSAD/iCaRL/iCaRL.py community (archive-listed) unverified no licence file found · pointer only · 3ce5508891ff92a2 · report
iCaRLmodel DRSAD/iCaRL/iCaRL.py community (archive-listed) unverified no licence file found · pointer only · 8b2070f8a9c2aa15 · report

Tasks

Class Incremental LearningIncremental LearningRepresentation Learningclass-incremental learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Class Incremental Learning cifar100 iCaRL 10-stage average accuracy 63.24 #3 of 7 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 10 steps of 5 classes iCaRL* Average Incremental Accuracy 52.57 #13 of 13 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 2 steps of 25 classes iCaRL Average Incremental Accuracy 71.33 #4 of 4 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 5 steps of 10 classes iCaRL* Average Incremental Accuracy 57.17 #12 of 15 Archive leaderboard report
Incremental Learning CIFAR-100-B0(5steps of 20 classes) iCaRL Average Incremental Accuracy 71.14 #7 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps iCaRL # M Params 11.68 #8 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps iCaRL Average Incremental Accuracy 38.40 #8 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps iCaRL Average Incremental Accuracy Top-5 63.70 #8 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps iCaRL Final Accuracy 22.70 #8 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps iCaRL Final Accuracy Top-5 44.00 #8 of 10 Archive leaderboard report
Incremental Learning ImageNet-100 - 50 classes + 5 steps of 10 classes iCaRL* Average Incremental Accuracy 65.56 #5 of 5 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps iCaRL # M Params 11.22 #13 of 13 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps iCaRL Average Incremental Accuracy Top-5 83.60 #13 of 13 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps iCaRL Final Accuracy Top-5 63.80 #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