Synthetic image contamination degrades online continual learning, and ESRM's entropy-based buffer selection plus contrastive feature alignment significantly mitigates the degradation.
Dark experience for general continual learning: a strong, simple baseline
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Dealing with Synthetic Data Contamination in Online Continual Learning
Synthetic image contamination degrades online continual learning, and ESRM's entropy-based buffer selection plus contrastive feature alignment significantly mitigates the degradation.