Advocacy learning, with class-conditional attention maps from per-class advocates and a judge network, yields small classification accuracy improvements on some image benchmarks.
Kingma and Jimmy Ba
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
-
Advocacy Learning: Learning through Competition and Class-Conditional Representations
Advocacy learning, with class-conditional attention maps from per-class advocates and a judge network, yields small classification accuracy improvements on some image benchmarks.