A new dual-timescale FCL framework with layer-selective rehearsal and knowledge recovery improves mIoU by up to 8.3% in federated settings for autonomous systems.
EVCL: Elastic Variational Continual Learning with Weight Consolidation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AIFIND stabilizes incremental face forgery detection by aligning volatile features to invariant semantic anchors from low-level artifacts using attention and harmonization modules.
citing papers explorer
-
Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems
A new dual-timescale FCL framework with layer-selective rehearsal and knowledge recovery improves mIoU by up to 8.3% in federated settings for autonomous systems.
-
AIFIND: Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection
AIFIND stabilizes incremental face forgery detection by aligning volatile features to invariant semantic anchors from low-level artifacts using attention and harmonization modules.