A Forward-Backward Approach for Visualizing Information Flow in Deep Networks
This work addresses interpretability for deep learning practitioners, but appears incremental as it builds on existing visualization techniques.
The paper tackles the problem of visualizing information flow in deep convolutional networks by introducing a systematic framework that identifies compact image regions contributing to specific features, with preliminary results showing benefits over existing methods.
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.