# Unsupervised Class-Incremental Learning Through Confusion

Source: [Unsupervised Class-Incremental Learning Through Confusion](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc93>)

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

Data updated: 2025-10-28T13:56:50.882Z

Authors: Shivam Khare, Kun Cao, James Rehg

Published: 2021-04-09T15:58:43.000Z

## Abstract

While many works on Continual Learning have shown promising results for mitigating catastrophic forgetting, they have relied on supervised training. To successfully learn in a label-agnostic incremental setting, a model must distinguish between learned and novel classes to properly include samples for training. We introduce a novelty detection method that leverages network confusion caused by training incoming data as a new class. We found that incorporating a class-imbalance during this detection method substantially enhances performance. The effectiveness of our approach is demonstrated across a set of image classification benchmarks: MNIST, SVHN, CIFAR-10, CIFAR-100, and CRIB.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.04450>)

[PDF](<https://arxiv.org/pdf/2104.04450.pdf>)