Unlearning benchmark classes from CLIP creates a fairer few-shot test, on which most existing CLIP methods lose over half their accuracy, but the new method SEPRES remains strong.
Learning gen- erative visual models from few training examples: An in- cremental bayesian approach tested on 101 object cate- gories
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
-
Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting
Unlearning benchmark classes from CLIP creates a fairer few-shot test, on which most existing CLIP methods lose over half their accuracy, but the new method SEPRES remains strong.