English

Unsupervised Class-Incremental Learning Through Confusion

Machine Learning 2021-12-09 v2 Computer Vision and Pattern Recognition

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.

Keywords

Cite

@article{arxiv.2104.04450,
  title  = {Unsupervised Class-Incremental Learning Through Confusion},
  author = {Shivam Khare and Kun Cao and James Rehg},
  journal= {arXiv preprint arXiv:2104.04450},
  year   = {2021}
}
R2 v1 2026-06-24T01:00:41.261Z