NOVO is a vision transformer that forgets classes at inference time by removing learned class keys, trained with simulated unlearning to generalize to any forget set.
https://oag.ca.gov/privacy/ccpa, 2018
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
-
NOVO: Unlearning-Compliant Vision Transformers
NOVO is a vision transformer that forgets classes at inference time by removing learned class keys, trained with simulated unlearning to generalize to any forget set.