Papers › iCaRL: Incremental Classifier and Representation Learning
iCaRL: Incremental Classifier and Representation Learning
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.
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.
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.
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.
573afeddc57bd6d5 · report
52298d4288456271 · report
2e54a5d9c05be1fc · report
b1a4e999428538e9 · report
a1952a1bd60c5594 · report
4c8201151d6e4d18 · report
86aadd9c26d05f6c · report
85bc3649f83b49eb · report
71a66063541d1b3b · report
c60e16f66d93fb54 · report
c9d0a1630e27cbbb · report
56204fa814f880a3 · report
3ce5508891ff92a2 · report
8b2070f8a9c2aa15 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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