Papers › Large Scale Incremental Learning

Large Scale Incremental Learning

30 May 2019CVPR 2019 6arXiv:1905.13260archive 2025-07-28

Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, Yun Fu

Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes. Incremental learning methods have been proposed to retain the knowledge acquired from the old classes, by using knowledge distilling and keeping a few exemplars from the old classes. However, these methods struggle to scale up to a large number of classes. We believe this is because of the combination of two factors: (a) the data imbalance between the old and new classes, and (b) the increasing number of visually similar classes. Distinguishing between an increasing number of visually similar classes is particularly challenging, when the training data is unbalanced. We propose a simple and effective method to address this data imbalance issue. We found that the last fully connected layer has a strong bias towards the new classes, and this bias can be corrected by a linear model. With two bias parameters, our method performs remarkably well on two large datasets: ImageNet (1000 classes) and MS-Celeb-1M (10000 classes), outperforming the state-of-the-art algorithms by 11.1% and 13.2% respectively.

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="1905.13260")

Code

Syntology Ran 1 of 1 code samples harvested from 0 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: 1 identical to code first harvested elsewhere. 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
sairin1202/BIC 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

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 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 · our draft was wrong

Licence: 1 of the 1 sample 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.

Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

conv3x3 identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · fac5364e2f53c6db · report

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 BiC Average Incremental Accuracy 53.21 #12 of 13 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 25 steps of 2 classes BiC Average Incremental Accuracy 48.96 #5 of 5 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 5 steps of 10 classes BiC Average Incremental Accuracy 56.86 #13 of 15 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 50 steps of 1 class BiC Average Incremental Accuracy 47.09 #2 of 2 Archive leaderboard report
Incremental Learning CIFAR-100-B0(5steps of 20 classes) BiC Average Incremental Accuracy 73.10 #5 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps BiC # M Params 11.68 #9 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps BiC Average Incremental Accuracy Top-5 84.00 #9 of 10 Archive leaderboard report
Incremental Learning ImageNet - 10 steps BiC Final Accuracy Top-5 73.20 #9 of 10 Archive leaderboard report
Incremental Learning ImageNet-100 - 50 classes + 50 steps of 1 class BiC Average Incremental Accuracy 46.49 #2 of 2 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps BiC # M Params 11.22 #10 of 13 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps BiC Average Incremental Accuracy Top-5 90.60 #10 of 13 Archive leaderboard report
Incremental Learning ImageNet100 - 10 steps BiC Final Accuracy Top-5 84.40 #10 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