AHR combines an autoencoder with a repulsive-force class centroid layout to replay compressed latent exemplars, reporting higher accuracy than selected CIL baselines.
Latent replay for real-time continual learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Autoencoder-Based Hybrid Replay for Class-Incremental Learning
AHR combines an autoencoder with a repulsive-force class centroid layout to replay compressed latent exemplars, reporting higher accuracy than selected CIL baselines.