General Transform learns scalar weights to combine multiple discrete transforms, improving image and text classification accuracy by 0.1 to 1.6 percentage points over fixed-transform baselines.
, year 2010
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
-
General Transform: A Unified Framework for Adaptive Transform to Enhance Representations
General Transform learns scalar weights to combine multiple discrete transforms, improving image and text classification accuracy by 0.1 to 1.6 percentage points over fixed-transform baselines.