ASR uses label-flip fluctuations to trigger a shrink-restore reinitialization of continual test-time adaptation models, improving long-run accuracy on CIN-C, CIN-3DCC, and CCC to 40.0 versus RDumb's 37.9.
Loss of plasticity in deep continual 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
support 1representative citing papers
citing papers explorer
-
Maintain Plasticity in Long-timescale Continual Test-time Adaptation
ASR uses label-flip fluctuations to trigger a shrink-restore reinitialization of continual test-time adaptation models, improving long-run accuracy on CIN-C, CIN-3DCC, and CCC to 40.0 versus RDumb's 37.9.