ICPL generates pseudo-labels by clustering embeddings with KMeans, keeps only confident ones, and uses them to train class-incremental models without human labels, losing about 10 points versus supervised CIL but beating class-iNCD baselines by more than 5.
Unsupervised Class-Incremental Learning Through Confusion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
ICPL generates pseudo-labels by clustering embeddings with KMeans, keeps only confident ones, and uses them to train class-incremental models without human labels, losing about 10 points versus supervised CIL but beating class-iNCD baselines by more than 5.