Feature Importance in the Inception (v1) Network

This page shows visualizations of feature importance generated by applying the technique of integrated gradients to the Inception (v1) object recognition network.

In a nutshell, we examine the gradients of certain counterfactual images obtained by uniformly scaling the pixel intesities in the image at hand, and aggregate these gradients together. The scaled down images are essentially points along the straight line path from the actual image to the black image.

A different summarization of the gradients of scaled down images is to directly visualize them as an animation (GIF), which shows how the gradient of the image changes as the pixel intensities are scaled up.

The integrated gradients method can be implemented in a few lines of code, is applicable to a variety of deep networks and has some nice mathematical properties. We recommend reading our paper, presently under submission to ICML 2017, for more details.

Running the code

The code for generating and visualizing integrated gradients is in a single Jupyter notebook --- attributions.ipynb.

To run the notebook, please follow the following instructions.

• Clone this repository

  git clone https://github.com/ankurtaly/Attributions
  

• In the same directory, run the Jupyter notebook server.

  jupyter notebook
  

  Instructions for installing Jupyter are available here. Please make sure that you have TensorFlow, NumPy, and PIL.Image installed for Python 2.7.

• Open attributions.ipynb and run all cells.

Visualizations

Below are some visualizations of interior gradients (as a GIF) and integrated gradients for some images from the ImageNet object recognition dataset. For comparison, we also show a visualization of the gradients at the actual image.

Image: 6864d7789068273e

Image: e60dfdf262c5c74f

Image: 35655d94a4557fbb

Image: bda7f59b986d42c0

Image: 96bb6e948866e5b5

Image: 80c64f2e27f8784a

:gImage: b19f875f181025d3

Image: 2f401b18be02d7fe

Image: 92445d6529368418

Image: ba1011c8f9633a49

Image: 3721d654514bc885

Image: 12ec21fa7003eae5

Image: 82262660db12ad85

Image: b2ab69fbb052b435

Image: 9a7e268c95022a1c

Image: 023d8b91c64faf4b

Image: 7f12674c6943381d

Image: 7bcfe0265ad6a2b5

Image: 518a1c0660c5e32e

Image: e9c7c07cb5730dac