A two-stage optimization pipeline that alternates label loss with a KL divergence between feature maps of masked and unmasked inputs improves accuracy and robustness in small-data classification.
Do input gradients highlight discriminative features?Advances in Neural Information Processing Systems, 34:2046–2059,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning from Explanations
A two-stage optimization pipeline that alternates label loss with a KL divergence between feature maps of masked and unmasked inputs improves accuracy and robustness in small-data classification.