Towards Global Explanations of Convolutional Neural Networks With Concept Attribution
The DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
With the growing prevalence of convolutional neural networks (CNNs), there is an urgent demand to explain their behaviors. Global explanations contribute to understanding model predictions on a whole category of samples, and thus have attracted increasing interest recently. However, existing methods overwhelmingly conduct separate input attribution or rely on local approximations of models, making them fail to offer faithful global explanations of CNNs. To overcome such drawbacks, we propose a novel two-stage framework, Attacking for Interpretability (AfI), which explains model decisions in terms of the importance of user-defined concepts. AfI first conducts a feature occlusion analysis, which resembles a process of attacking models to derive the category-wide importance of different features. We then map the feature importance to concept importance through ad-hoc semantic tasks. Experimental results confirm the effectiveness of AfI and its superiority in providing more accurate estimations of concept importance than existing proposals.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
On 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 1×
“There is a vast body of work under this track, such as the gradient-based [36, 39, 35, 41, 38, 34, 28], structure-based [1, 24, 46, 51], proxy model-based [30, 23], and decision-based approach [8, 5, 53, 31, 6, 48, 46].”
Background(2012) · MPG.PuRe (Max Planck Society) · doi:10.5555/2188385.2188410 · Cited by 3,603
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503 · cited 1×
“These models cover representative sorts of models for image classification and have wide application in practice [29].”
BackgroundLearning Important Features Through Propagating Activation Differences
Shrikumar, A., Greenside, P., & Kundaje, A. (2017) · arXiv · doi:10.48550/arxiv.1704.02685 · Cited by 2,761
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Anchors: High-Precision Model-Agnostic Explanations
Ribeiro, M. T., Singh, S., & Guestrin, C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11491 · Cited by 2,162 · cited 1×
“There is a vast body of work under this track, such as the gradient-based [36, 39, 35, 41, 38, 34, 28], structure-based [1, 24, 46, 51], proxy model-based [30, 23], and decision-based approach [8, 5, 53, 31, 6, 48, 46].”
BackgroundEuropean Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131 · cited 1×
“It can not only justify decisions of CNNs to promote model trustworthiness, but also spot their latent defects to inspire the development of better models [12, 16, 9, 45].”
Background
Cited by
Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., Schlötterer, J., van Keulen, M., & Seifert, C. (2023) · ACM Computing Surveys · doi:10.1145/3583558 · Cited by 590
Rosenbacke, R., Melhus, Å., McKee, M., & Stuckler, D. (2024) · JMIR AI · doi:10.2196/53207 · Cited by 305
Naiseh, M., Al-Thani, D., Jiang, N., & Ali, R. (2023) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102941 · Cited by 170
Explainable recommendation: when design meets trust calibration
Naiseh, M., Al-Thani, D., Jiang, N., & Ali, R. (2021) · World Wide Web · doi:10.1007/s11280-021-00916-0 · Cited by 68
“Global explanation: explanations of this type provide the general logic and rules of AI reasoning [90].”
BackgroundValidating Automatic Concept-Based Explanations for AI-Based Digital Histopathology
Sauter, D., Lodde, G., Nensa, F., Schadendorf, D., Livingstone, E., & Kukuk, M. (2022) · Sensors · doi:10.3390/s22145346 · Cited by 26
Metadata
- Authors
- Wu, W., Su, Y., Chen, X., Zhao, S., King, I., Lyu, M. R., & Tai, Y.-W.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 8649-8658
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3035520720
- Cited by
- 40
- References
- 21
- FWCI
- 2.62
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Global Explanations of Convolutional Neural Networks With Concept Attribution. https://app.cochat.ai/papers/10.1109/cvpr42600.2020.00868
- The paper
- Wu, W., Su, Y., Chen, X., Zhao, S., King, I., Lyu, M. R., & Tai, Y.-W. (2020). Towards Global Explanations of Convolutional Neural Networks With Concept Attribution. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr42600.2020.00868
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.