XAI/XAI-papers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Anh M. Nguyen 2019-07-31 16:08:39 -05:00 committed by GitHub
parent d2479d7ae9
commit 51cf669c49
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 20 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@ -81,28 +81,40 @@ This is an on-going attempt to consolidate interesting efforts in the area of un
# B. Decision explanations
## B1. Heatmaps
#### White-box / Gradient-based
### B1.1 White-box / Gradient-based
* A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations. _Nie et al. 2018_ [pdf](https://arxiv.org/abs/1805.07039)
* A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks [pdf](https://arxiv.org/pdf/1606.07757.pdf)
#### Activation map
* CAM: Learning Deep Features for Discriminative Localization. _Zhou et al. 2016_ [code](https://github.com/metalbubble/CAM) | [web](http://cnnlocalization.csail.mit.edu/)
* Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. _Selvaraju et al. 2017_ [pdf](https://arxiv.org/abs/1610.02391)
* Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks. _Chattopadhyay et al. 2017_ [pdf](https://arxiv.org/abs/1710.11063) | [code](https://github.com/adityac94/Grad_CAM_plus_plus)
#### Learning the heatmap
* Interpretable Explanations of Black Boxes by Meaningful Perturbation. _Fong et al. 2017_ [pdf](http://openaccess.thecvf.com/content_ICCV_2017/papers/Fong_Interpretable_Explanations_of_ICCV_2017_paper.pdf)
* FIDO: Explaining image classifiers by counterfactual generation. _Chang et al. 2019_ [pdf](https://arxiv.org/pdf/1807.08024.pdf)
* FG-Vis: Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks. _Wagner et al. 2019_ [pdf](http://openaccess.thecvf.com/content_CVPR_2019/papers/Wagner_Interpretable_and_Fine-Grained_Visual_Explanations_for_Convolutional_Neural_Networks_CVPR_2019_paper.pdf)
#### Input x Gradient
* Integrated Gradients: Axiomatic Attribution for Deep Networks. _Sundararajan et al. 2018_ [pdf](http://proceedings.mlr.press/v70/sundararajan17a/sundararajan17a.pdf) | [code](https://github.com/ankurtaly/Integrated-Gradients)
* I-GOR: Visualizing Deep Networks by Optimizing with Integrated Gradients. _Qi et al. 2019_ [pdf](https://arxiv.org/pdf/1905.00954.pdf)
* LRP: Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation [pdf](https://arxiv.org/abs/1712.08268)
* DTD: Explaining NonLinear Classification Decisions With Deep Tayor Decomposition [pdf](https://arxiv.org/abs/1512.02479)
* Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks. _Seo et al. 2018_ [pdf](https://arxiv.org/pdf/1807.11720.pdf)
* Interpretable Explanations of Black Boxes by Meaningful Perturbation. _Fong et al. 2017_ [pdf](http://openaccess.thecvf.com/content_ICCV_2017/papers/Fong_Interpretable_Explanations_of_ICCV_2017_paper.pdf)
* Integrated Gradients: Axiomatic Attribution for Deep Networks. _Sundararajan et al. 2018_ [pdf](http://proceedings.mlr.press/v70/sundararajan17a/sundararajan17a.pdf) | [code](https://github.com/ankurtaly/Integrated-Gradients)
* I-GOR: Visualizing Deep Networks by Optimizing with Integrated Gradients. _Qi et al. 2019_ [pdf](https://arxiv.org/pdf/1905.00954.pdf)
#### Others
* Visual explanation by interpretation: Improving visual feedback capabilities of deep neural networks. _Oramas et al. 2019_ [pdf](https://arxiv.org/pdf/1712.06302.pdf)
* Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks. _Seo et al. 2018_ [pdf](https://arxiv.org/pdf/1807.11720.pdf)b
#### Black-box / Perturbation-based
### B1.2 Black-box / Perturbation-based
* RISE: Randomized Input Sampling for Explanation of Black-box Models. _Petsiuk et al. 2018_ [pdf](https://arxiv.org/pdf/1806.07421.pdf)
* LIME: Why should i trust you?: Explaining the predictions of any classifier. _Ribeiro et al. 2016_ [pdf](https://arxiv.org/pdf/1602.04938.pdf) | [blog](https://homes.cs.washington.edu/~marcotcr/blog/lime/)
* OSFT: Interpreting Black Box Models via Hypothesis Testing. _Burns et al. 2019_ [pdf](https://arxiv.org/pdf/1904.00045.pdf)
#### Evaluating heatmaps
### B1.3 Evaluating heatmaps
* The (Un)reliability of saliency methods. _Kindermans et al. 2018_ [pdf](https://openreview.net/forum?id=r1Oen--RW)
* Sanity Checks for Saliency Maps. _Adebayo et al. 2018_ [pdf](http://papers.nips.cc/paper/8160-sanity-checks-for-saliency-maps.pdf)
* A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations. _Nie et al. 2018_ [pdf](https://arxiv.org/abs/1805.07039)
* BIM: Towards Quantitative Evaluation of Interpretability Methods with Ground Truth. _Yang et al. 2019_ [pdf](https://arxiv.org/abs/1907.09701)
## B2. Learning to explain
* Learning how to explain neural networks: PatternNet and PatternAttribution [pdf](https://arxiv.org/abs/1705.05598)