ACMap achieves exemplar-free class-incremental learning with constant inference time by averaging task-specific adapters and shifting previous prototypes with the current task's centroid drift.
PODNet: Pooled Outputs Dis- tillation for Small-Tasks Incremental Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
ACMap achieves exemplar-free class-incremental learning with constant inference time by averaging task-specific adapters and shifting previous prototypes with the current task's centroid drift.