The DOI matches its Crossref record; 50 of the 52 references it cites were found in a registry or an index.
Transformer Interpretability Beyond Attention Visualization
Open accessAbstract
Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a certain classification, existing methods either rely on the obtained attention maps or employ heuristic propagation along the attention graph. In this work, we propose a novel way to compute relevancy for Transformer networks. The method assigns local relevance based on the Deep Taylor Decomposition principle and then propagates these relevancy scores through the layers. This propagation involves attention layers and skip connections, which challenge existing methods. Our solution is based on a specific formulation that is shown to maintain the total relevancy across layers. We benchmark our method on very recent visual Transformer networks, as well as on a text classification problem, and demonstrate a clear advantage over the existing explainability methods. Our code is available at: https://github.com/hila-chefer/Transformer-Explainability.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
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
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
End-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515
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
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623
Learning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
Deep 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
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
Axiomatic attribution for deep networks
Sundararajan, M., Taly, A., & Yan, Q. (2017) · arXiv · doi:10.48550/arxiv.1703.01365 · Cited by 4,087
Gaussian Error Linear Units (GELUs)
Hendrycks, D., & Gimpel, K. (2016) · arXiv · doi:10.48550/arxiv.1606.08415 · Cited by 3,537
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
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, H., & Bansal, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1514 · Cited by 2,319
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
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
Long Short-Term Memory-Networks for Machine Reading
Cheng, J., Dong, L., & Lapata, M. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1053 · Cited by 1,393
Explaining 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
A Decomposable Attention Model for Natural Language Inference
Parikh, A. P., Täckström, O., Das, D., & Uszkoreit, J. (2016) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d16-1244 · Cited by 1,351
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
Voita, E., Talbot, D., Moiseev, F., Sennrich, R., & Titov, I. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1580 · Cited by 1,146
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
(2020) · International Conference on Machine Learning · Cited by 1,012
Quantifying Attention Flow in Transformers
Abnar, S., & Zuidema, W. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.385 · Cited by 995
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., & Dai, J. (2019) · arXiv · doi:10.48550/arxiv.1908.08530 · Cited by 950
Not Just a Black Box: Learning Important Features Through Propagating Activation DifferencesPreprint
Shrikumar, A., Greenside, P., Shcherbina, A., & Kundaje, A. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.01713 · Cited by 853
Top-Down Neural Attention by Excitation Backprop
Zhang, J., Bargal, S. A., Lin, Z., Brandt, J., Shen, X., & Sclaroff, S. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-017-1059-x · Cited by 815
Mittelstadt, B., Russell, C., & Wachter, S. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287574 · Cited by 794
Tell Me Where to Look: Guided Attention Inference Network
Li, K., Wu, Z., Peng, K., Ernst, J., & Fu, Y. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00960 · Cited by 564
ERASER: A Benchmark to Evaluate Rationalized NLP Models
DeYoung, J., Jain, S., Rajani, N. F., Lehman, E., Xiong, C., Socher, R., & Wallace, B. C. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.408 · Cited by 561
A Benchmark for Interpretability Methods in Deep Neural NetworksPreprint
Hooker, S., Erhan, D., Kindermans, P.-J., & Kim, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.10758 · Cited by 531
Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers
Binder, A., Montavon, G., Lapuschkin, S., Müller, K., & Samek, W. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-44781-0_8 · Cited by 512
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images
Mahendran, A., & Vedaldi, A. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0911-8 · Cited by 500
Real Time Image Saliency for Black Box ClassifiersPreprint
Dabkowski, P., & Gal, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07857 · Cited by 421
Interpreting Deep Visual Representations via Network Dissection
Zhou, B., Bau, D., Oliva, A., & Torralba, A. B. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858759 · Cited by 347
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., & Dai, J. (2020) · International Conference on Learning Representations · Cited by 276
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured DataPreprint
Chen, J., Song, L., Wainwright, M. J., & Jordan, M. I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.02610 · Cited by 141
ImageNet Auto-Annotation with Segmentation Propagation
Guillaumin, M., Kuettel, D., & Ferrari, V. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-014-0713-9 · Cited by 138
Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
Iwana, B. K., Kuroki, R., & Uchida, S. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00513 · Cited by 121
Understanding Individual Decisions of CNNs via Contrastive Backpropagation
Gu, J., Yang, Y., & Volker Tresp, C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20893-6_8 · Cited by 106
Zaidan, O. F., & Eisner, J. M. (2008) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/1613715.1613721 · Cited by 100
Nam, W.-J., Gur, S., Choi, J., Wolf, L., & Lee, S.-W. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i03.5632 · Cited by 98
Self-citationFull-Gradient Representation for Neural Network VisualizationPreprint
Srinivas, S., & Fleuret, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.00780 · Cited by 72
Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization
Gur, S., Ali, A., & Wolf, L. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i13.17374 · Cited by 34
Self-citationVisualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization
Gur, S., Ali, A., & Wolf, L. (2020) · arXiv · doi:10.48550/arxiv.2012.02166 · Cited by 34
Self-citationExplaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance PropagationPreprint
Iwana, B. K., Kuroki, R., & Uchida, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04351 · Cited by 20
Flagged first, then by citations
2 of the 52 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- radford, 2019, Language Models are Unsupervised Multitask Learners
- erhan, 2009, Visualizing higher-layer features of a deep network, University of Montreal, 1341, 1
- 10.1109/ICCV.2019.00304 · DOI
Cited by
Sorted by citations
Han (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595
Transformers in medical imaging: A survey
Shamshad, F., Khan, S., Zamir, S. W., Khan, M. H., Hayat, M., Khan, F. S., & Fu, H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102802 · Cited by 1,523
A foundation model for generalizable disease detection from retinal images
Zhou, Y., Chia, M. A., Wagner, S. K., Ayhan, M. S., Williamson, D. J., Struyven, R. R., Liu, T., Xu, M., Lozano, M. G., Woodward-Court, P., et al. (2023) · Nature · doi:10.1038/s41586-023-06555-x · Cited by 1,014
Explainability for Large Language Models: A Survey
Zhao, H., Chen, H., Yang, F., Liu, N., Deng, H., Cai, H., Wang, S., Yin, D., & Du, M. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3639372 · Cited by 681
Metadata
- Authors
- Chefer, H., Gur, S., & Wolf, L.
- Affiliations
- Tel Aviv University (IL)
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 782-791
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3112516115
- Cited by
- 903
- References
- 52
- Citations by year
- 2026: 185 · 2025: 226 · 2024: 193 · 2023: 178 · 2022: 90 · 2021: 31
- FWCI
- 56.82
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- European Research Council
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- transformer interpretability, vision transformer, attention visualization, local relevance, relevance propagation, attention layers, skip connections, explainable AI, text classification, image classification
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
