Chaotic nonlinear transformations on CNN features yield consistent accuracy gains of up to 9% on limited-data image classification without adding parameters.
IEEE transactions on neural networks and learning systems30(9), 2866–2875 (2019)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Chaotic CNN for Limited Data Image Classification
Chaotic nonlinear transformations on CNN features yield consistent accuracy gains of up to 9% on limited-data image classification without adding parameters.