A hooking layer (LinearScope) freezes the nonlinear decisions of a CNN to expose the network as a single linear map, revealing bias-dominated classifier scores, wavelet-like super-resolution bases, and copy-move/template strategies in CycleGAN.
Tenenbaum, William T
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Tour of Convolutional Networks Guided by Linear Interpreters
A hooking layer (LinearScope) freezes the nonlinear decisions of a CNN to expose the network as a single linear map, revealing bias-dominated classifier scores, wavelet-like super-resolution bases, and copy-move/template strategies in CycleGAN.