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.
Learning to unlearn: Instance-wise unlearning for pre-trained classifiers, 2024
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 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.