Papers › Learning a Unified Classifier Incrementally via Rebalancing

Learning a Unified Classifier Incrementally via Rebalancing

1 Jun 2019CVPR 2019 6archive 2025-07-28

Saihui Hou, Xinyu Pan, Chen Change Loy, Zilei Wang, Dahua Lin

Conventionally, deep neural networks are trained offline, relying on a large dataset prepared in advance. This paradigm is often challenged in real-world applications, e.g. online services that involve continuous streams of incoming data. Recently, incremental learning receives increasing attention, and is considered as a promising solution to the practical challenges mentioned above. However, it has been observed that incremental learning is subject to a fundamental difficulty -- catastrophic forgetting, namely adapting a model to new data often results in severe performance degradation on previous tasks or classes. Our study reveals that the imbalance between previous and new data is a crucial cause to this problem. In this work, we develop a new framework for incrementally learning a unified classifier, e.g. a classifier that treats both old and new classes uniformly. Specifically, we incorporate three components, cosine normalization, less-forget constraint, and inter-class separation, to mitigate the adverse effects of the imbalance. Experiments show that the proposed method can effectively rebalance the training process, thus obtaining superior performance compared to the existing methods. On CIFAR-100 and ImageNet, our method can reduce the classification errors by more than 6% and 13% respectively, under the incremental setting of 10 phases.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

aimagelab/mammoth pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning (arXiv:2407.15793; that paper's own run record: 8 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; 7 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hshustc/CVPR19_Incremental_Learning pytorchSyntology: not harvested report
mmasana/FACIL pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning without Forgetting (arXiv:1606.09282; that paper's own run record: 9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified), iCaRL: Incremental Classifier and Representation Learning (arXiv:1611.07725; that paper's own run record: 5 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; 3 where Syntology's instrument failed) · 9 unverified) and Overcoming catastrophic forgetting in neural networks (arXiv:1612.00796; that paper's own run record: 16 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Class Incremental LearningIncremental Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Class Incremental Learning cifar100 LUCIR 10-stage average accuracy 56.53 #4 of 7 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 10 steps of 5 classes UCIR (CNN)* Average Incremental Accuracy 60.18 #10 of 13 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 10 steps of 5 classes UCIR (NME)* Average Incremental Accuracy 60.12 #11 of 13 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 5 steps of 10 classes UCIR (CNN)* Average Incremental Accuracy 63.42 #10 of 15 Archive leaderboard report
Incremental Learning CIFAR-100 - 50 classes + 5 steps of 10 classes UCIR (NME)* Average Incremental Accuracy 63.12 #11 of 15 Archive leaderboard report
Incremental Learning CIFAR-100-B0(5steps of 20 classes) UCIR Average Incremental Accuracy 62.77 #10 of 10 Archive leaderboard report
Incremental Learning ImageNet - 500 classes + 10 steps of 50 classes UCIR (NME)* Average Incremental Accuracy 59.92 #3 of 4 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