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.
A Forward-Backward Approach for Visualizing Information Flow in Deep Networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We introduce a new, systematic framework for visualizing information flow in deep networks. Specifically, given any trained deep convolutional network model and a given test image, our method produces a compact support in the image domain that corresponds to a (high-resolution) feature that contributes to the given explanation. Our method is both computationally efficient as well as numerically robust. We present several preliminary numerical results that support the benefits of our framework over existing methods.
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.