Unsupervised Class-Incremental Learning through Confusion

Shivam Khare, Kun Cao, James Matthew Rehg

Keywords: Incremental Learning, Unsupervised Learning, Continual Learning, Novelty Detection, Out-of-Distribution Detection

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 common image classification benchmarks: MNIST, SVHN, CIFAR-10, and CIFAR-100.

One-sentence Summary: This paper introduces a novel OOD detection method that leverages network confusion to learn in an unsupervised incremental setting.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2104.04450/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ym46ql01PO