XRAI: Better Attributions Through Regions
arXiv:1906.02825
Abstract
Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution method, XRAI, that builds upon integrated gradients (Sundararajan et al. 2017), 2) introduce evaluation methods for empirically assessing the quality of image-based saliency maps (Performance Information Curves (PICs)), and 3) contribute an axiom-based sanity check for attribution methods. Through empirical experiments and example results, we show that XRAI produces better results than other saliency methods for common models and the ImageNet dataset.
References in corpus (14)
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Going Deeper with Convolutions
- SmoothGrad: removing noise by adding noise
- How to Explain Individual Classification Decisions
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- Review of Visual Saliency Detection with Comprehensive Information
- Visualizing and Understanding Convolutional Networks
- Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
- "Why Should I Trust You?": Explaining the Predictions of Any Classifier
- Learning how to explain neural networks: PatternNet and PatternAttribution
- Interpretation of Neural Networks is Fragile
- A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values