GROTO is a source-free class-incremental domain adaptation method that uses multi-granularity class prototypes and prototype topology distillation, achieving state-of-the-art final accuracy on three benchmark variants.
A continual learning survey: Defying for- getting in classification tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
GROTO is a source-free class-incremental domain adaptation method that uses multi-granularity class prototypes and prototype topology distillation, achieving state-of-the-art final accuracy on three benchmark variants.