A transformer with class and task prototype prompts, trained with three losses, reports state-of-the-art class-incremental accuracy on three image benchmarks.
How does a brain build a cogni- tive code?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DPFormer: Dynamic Prompt Transformer for Continual Learning
A transformer with class and task prototype prompts, trained with three losses, reports state-of-the-art class-incremental accuracy on three image benchmarks.