XRAI is a region-based saliency method extension.
XRAI converts feature-based saliency methods into region-based saliency. It over-segments the input into many regions, computes saliency using another saliency method (e.g., integrated gradients and guided integrated gradients), and sums the saliency within each region.
Developed by: Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viégas, Michael Terry at Google.
References:
- Original Paper: XRAI: Better Attributions Through Regions
- Blog Post: Google PAIR Blog on XRAI
Implementations and Tutorials:
Example: The XRAI saliency map (right) on an ImageNet image for the class samoyed
(left) using a Inception v3. This example is from the Google PAIR Blog on XRAI.
XRAI is deterministic unless using a non-deterministic saliency method or segmentation method.
XRAI relies on a choice of saliency method
and segmentation method
.
It inherits the hyperparameter dependence of its saliency method
(integrated gradients and guided integrated gradients are used in the original paper). The regions will depend on the segmentation method
and its parameters (the original paper uses Felzenszwalb image segmentation).
XRAI requires input features that can be meaningfully segmented. It inherits the model agnosticism of its underlying saliency method.
Computing XRAI takes on the order of
XRAI represents the importance of input regions. Its semantic directness depends on the semantic directness of its underlying saliency method.
Not tested for input sensitivity.
Not tested for label sensitivity.
🟥 Model Weight Randomization: XRAI did not reach randomization even on a fully randomized model. Evaluated on SIIM-ACR Pneumothorax and RSNA Pneumonia medical images.
🟢 Repeatability: XRAI has the highest repeatability across saliency methods (vanilla gradients, integrated gradients, SmoothGrad, Grad-CAM, guided backpropagation, and guided Grad-CAM) and outperformed the baseline. Evaluated using Inception v3 models on SIIM-ACR Pneumothorax and RSNA Pneumonia medical images.
🟢 Reproducibility: XRAI has the highest reproducibility across saliency methods (vanilla gradients, integrated gradients, SmoothGrad, Grad-CAM, guided backpropagation, and guided Grad-CAM). Evaluated using Inception V3 and DenseNet-121 on SIIM-ACR Pneumothorax and RSNA Pneumonia medical images.
Not tested for minimality.
🟢 Localization Utility: XRAI passes the localization utility test. It outperformed the other saliency methods (vanilla gradients, integrated gradients, SmoothGrad, Grad-CAM, guided backpropagation, and guided Grad-CAM) and the average saliency map. Evaluated using Inception V3 and DenseNet-121 on SIIM-ACR Pneumothorax and RSNA Pneumonia medical images.
BibTeX:
@inproceedings{xrai,
author = {Andrei Kapishnikov and
Tolga Bolukbasi and
Fernanda B. Vi{\'{e}}gas and
Michael Terry},
title = {{XRAI:} {B}etter Attributions Through Regions},
booktitle = {Proceedings of the International Conference on Computer Vision ({ICCV})},
pages = {4947--4956},
publisher = {{IEEE}},
year = {2019},
}