XRAI: Better Attributions Through Regions
The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 2×
“Some examples include Guided Backprop [24], DeConvNet [29], Integrated Gradients [26], Layer-wise Relevance Propagation [3], SmoothGrad [23], Deep-Lift [20], GradCAM [19], Gradients*Input [21], and others [15, 16].”
MethodDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 2×
“Therefore, it is easy to show that Gradient [22] and Gradient*Input [21] do not pass, and attribute zero to all features.”
BackgroundMethodOn Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 2×
“, [24, 29, 14, 26, 3, 6]).”
MethodStriving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Learning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
SmoothGrad: removing noise by adding noise
Smilkov, D., Thorat, N., Kim, B., Viégas, F., & Wattenberg, M. (2017) · arXiv · doi:10.48550/arxiv.1706.03825 · Cited by 1,467 · cited 1×
“Some examples include Guided Backprop [24], DeConvNet [29], Integrated Gradients [26], Layer-wise Relevance Propagation [3], SmoothGrad [23], Deep-Lift [20], GradCAM [19], Gradients*Input [21], and others [15, 16].”
MethodSelf-citationExplaining nonlinear classification decisions with deep taylor decomposition
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., & Müller, K.-R. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.11.008 · Cited by 1,357 · cited 1×
“Some examples include Guided Backprop [24], DeConvNet [29], Integrated Gradients [26], Layer-wise Relevance Propagation [3], SmoothGrad [23], Deep-Lift [20], GradCAM [19], Gradients*Input [21], and others [15, 16].”
MethodSanity Checks for Saliency Maps
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2018) · arXiv · doi:10.48550/arxiv.1810.03292 · Cited by 1,294
Interpretable Explanations of Black Boxes by Meaningful Perturbation
Fong, R. C., & Vedaldi, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.371 · Cited by 1,097 · cited 1×
“One set of methods modify the inputs and measure the effect this perturbation has on the output by performing a forward pass through the network with these modified inputs [10, 5].”
MethodInterpretation of Neural Networks Is Fragile
Ghorbani, A., Abid, A., & Zou, J. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013681 · Cited by 765
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
Zintgraf, L. M., Cohen, T. S., Adel, T., & Welling, M. (2017) · arXiv · doi:10.48550/arxiv.1702.04595 · Cited by 487 · cited 1×
“While perturbation based-methods allow one to directly estimate the impact of a feature subset on the output, they require multiple queries to the model, making them slow [30].”
How to Explain Individual Classification Decisions
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1859912 · Cited by 54
Cited by
Towards Total Recall in Industrial Anomaly Detection
Roth, K., Pemula, L., Zepeda, J., Scholkopf, B., Brox, T., & Gehler, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01392 · Cited by 1,810
“For the majority of these approaches, anomaly localization comes naturally based on pixel-wise reconstruction errors, saliency-based approaches such as GradCAM [47] or XRAI [28] can be used for anomaly segmentation [42,45,52] as well.”
BackgroundAlgorithms to estimate Shapley value feature attributions
Chen, H., Covert, I. C., Lundberg, S. M., & Lee, S.-I. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00657-x · Cited by 472
Assessing the trustworthiness of saliency maps for localizing abnormalities in medical imaging
Arun, N., Gaw, N., Singh, P., Chang, K., Aggarwal, M., Chen, B., Hoebel, K., Gupta, S., Patel, J., Gidwani, M., et al. (2021) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2021200267 · Cited by 342
Benchmarking and survey of explanation methods for black box models
Bodria, F., Giannotti, F., Guidotti, R., Naretto, F., Pedreschi, D., & Rinzivillo, S. (2023) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-023-00933-9 · Cited by 264
Trustworthy AI in the Age of Pervasive Computing and Big Data
Kumar, A., Braud, T., Tarkoma, S., & Hui, P. (2020) · 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops48775.2020.9156127 · Cited by 68
Metadata
- Authors
- Kapishnikov, A., Bolukbasi, T., Viegas, F., & Terry, M.
- Venue
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 4947-4956
- OpenAlex
- W2969880113
- Cited by
- 198
- References
- 14
- FWCI
- 6.91
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.