Training a classifier with an auxiliary loss that matches its own non-ground-truth class probabilities to a learned per-class residual label improves accuracy on several benchmarks, though gains are small and top-5 ImageNet accuracy sometimes drops.
Ranking a stream of news
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Regularization of Labels
Training a classifier with an auxiliary loss that matches its own non-ground-truth class probabilities to a learned per-class residual label improves accuracy on several benchmarks, though gains are small and top-5 ImageNet accuracy sometimes drops.