A fuzzy-logic loss over unlabeled images improves object-type classification on PASCAL-Part, and reweighting Modus Ponens versus Modus Tollens gradients gives the best gain.
Regularizing relation representa- tions by first-order implications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Semi-Supervised Learning using Differentiable Reasoning
A fuzzy-logic loss over unlabeled images improves object-type classification on PASCAL-Part, and reweighting Modus Ponens versus Modus Tollens gradients gives the best gain.