Unsupervised Class-Incremental Learning Through Confusion

By Shivam Khare, Kun Cao, James M. Rehg. 2021

8 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. C. Dovrolis
2. Cameron Taylor
3. James Smith
4. Seth Baer

In Radiology, Nuclear Medicine and Imaging

1. C. Dovrolis

Citations in the corpus

• Memory Replay with Data Compression for Continual Learning (2022, neutral): “, 2021a), and unsupervised continual learning (Khare et al., 2021).”
• Unsupervised Progressive Learning and the STAM Architecture (2019, methodology): “For these reasons, we choose not to compare STAM with CURL because such a comparison would not be fair for the latter. iLAP [ Khare et al. , 2021 ] learns classes incrementally by analyzing changes in performance as new data is introduced – it assumes however a single new class at each transition…”