Unsupervised Class-Incremental Learning Through Confusion
arXiv:2104.04450
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.
References in corpus (13)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- A continual learning survey: Defying forgetting in classification tasks
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
- Deep Anomaly Detection with Outlier Exposure
- Learning Confidence for Out-of-Distribution Detection in Neural Networks
- Continual Learning with Deep Generative Replay
- Lifelong Learning with Dynamically Expandable Networks
- Input complexity and out-of-distribution detection with likelihood-based generative models
- Deep Generative Dual Memory Network for Continual Learning
- A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
- Continual Unsupervised Representation Learning
- Uncertainty in the Variational Information Bottleneck
- Novelty Detection with GAN