# Defying Imbalanced Forgetting in Class Incremental Learning

Source: [Defying Imbalanced Forgetting in Class Incremental Learning](<https://www.sota2.com/research/paper/68fa72a01e209131cea57a46>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:05.190Z

Authors: Shixiong Xu, Gaofeng Meng, Xing Nie, Bolin Ni, Bin Fan, Shiming Xiang

Published: 2024-03-22T02:06:44.000Z

## Abstract

We observe a high level of imbalance in the accuracy of different classes in the same old task for the first time. This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting. This discovery remains previously unidentified due to the reliance on average incremental accuracy as the measurement for CIL, which assumes that the accuracy of classes within the same task is similar. However, this assumption is invalid in the face of catastrophic forgetting. Further empirical studies indicate that this imbalanced forgetting is caused by conflicts in representation between semantically similar old and new classes. These conflicts are rooted in the data imbalance present in replay-based CIL methods. Building on these insights, we propose CLass-Aware Disentanglement (CLAD) to predict the old classes that are more likely to be forgotten and enhance their accuracy. Importantly, CLAD can be seamlessly integrated into existing CIL methods. Extensive experiments demonstrate that CLAD consistently improves current replay-based methods, resulting in performance gains of up to 2.56%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Ranking past classes by forgetting on CIFAR-100 (incremental)](<https://www.sota2.com/research/sota/ranking-past-classes-by-forgetting-on-cifar-100-incremental.md>): Ranking past classes by forgetting; CIFAR-100 (incremental); Spearman's Rho: 0.67.

- [Class-Incremental Learning on Tiny-ImageNet (incremental)](<https://www.sota2.com/research/sota/class-incremental-learning-on-tiny-imagenet-incremental.md>): Ranking past classes by forgetting; Tiny-ImageNet (incremental); Spearman's Rho: 0.49.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2403.14910>)

[PDF](<https://arxiv.org/pdf/2403.14910.pdf>)