Cited by 903Explainable Artificial Intelligence (XAI)Advanced Neural Network ApplicationsVisual Attention and Saliency Detection

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 access

Chefer, Hila, Gur, Shir, Wolf, Lior·2021·2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

DOI 10.1109/cvpr46437.2021.00084

Open this paper in CoChat — free account Open PDF

Abstract

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.

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

Crossref · 10.1109/cvpr46437.2021.00084

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

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.

Attention Is All You Need
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

Show all 52 references

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

Sorted by citations

Items 601–700 of 903

Artificial Intelligence in Ocular Surface Tumors: Current Advances, Challenges, and Future Directions
Ghanbari, H., Bayan, N., Rahimi, S., Salari, F., DolatAbadi, M. T., & Soleimani, M. (2026) · Diagnostics · doi:10.3390/diagnostics16071103 · Cited by 1
AI-Driven Malware Defense: Transformer Model for Real-Time Detection and Threat Analysis
Meskova, V., Valencia, N., Chaparro-Baquero, G. A., & Perez-Pons, A. (2026) · International Symposium on Digital Forensics and Security (ISDFS) · doi:10.1109/isdfs69419.2026.11459044 · Cited by 1
Emotions Are Not Random: Machine Learning Reveals Predictable Patterns in a 21-Day Second Language Learning Trajectory
Wang, P., Ganushchak, L. Y., Welie, C., & van Steensel, R. (2026) · Educational Psychology Review · doi:10.1007/s10648-026-10141-8 · Cited by 3
Interpretable convolutional neural networks for sequence-based classification and discovery of plastic-degrading enzymes
Lee, W.-H., Dumontet, L., Jung, K., Lee, H. J., Thapa, G., Oh, T., & Kang, M. (2026) · Applied and Environmental Microbiology · doi:10.1128/aem.01586-25 · Cited by 2
NEuRT: A Transformer-Based Model for Explainable Neuronal Activity Analysis
Raev, G., Baev, D., Gerasimov, E., Chukanov, V. V., & Pchitskaya, E. I. (2026) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2026.3689342 · Cited by 1
Robotic Tactile Sensing for Early Detection of Frost-Damaged Citrus Fruits with Pressure–Vibration Multimodal Fusion
Yu, Y., Wu, Z., An, C., Lv, X., Zhao, Y., & Xu, H. (2026) · Foods · doi:10.3390/foods15091597 · Cited by 1
ITSELF: Attention Guided Fine-Grained Alignment for Vision–Language Retrieval
Nguyen, T.-H., Tran, H.-L., & Ngo, T. D. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00147 · Cited by 1
Retinal vessel imaging in inflammatory disease: From endothelial dysfunction to clinical evidence and translation
Wallraven, T., Günthner, R., Ribeiro, A., Alnemer, M. S., Kotliar, K. E., Lech, M., Bleidißel, N., Wicklein, R., Hauser, C., Streese, L., et al. (2026) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2026.101472 · Cited by 1
Localization-aware chest X-ray classification via segmentation and gradient-based attention
Wu, Y., Japkowicz, N., Gilbert, S., & Corizzo, R. (2026) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-026-01214-x · Cited by 1
Clara: A Cross-Modal Learning Framework for Enhanced Vulnerability Detection
Peng, X., Wang, S., Lin, B., Qin, Y., Chen, L., & Mao, X. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3691741 · Cited by 1
A Quantitative Evaluation of Gradient-Based Visual Explainability Methods Across Convolutional and Transformer-Based Vision Models
Tzirtis, A., Troussas, C., Krouska, A., Phivos Mylonas, B., & Sgouropoulou, C. (2026) · Electronics · doi:10.3390/electronics15112241 · Cited by 1
Empowering healthcare 5.0 with deep learning: techniques, trends, and future directions
Maji, P. K., Chakraborty, S., Sadiq, A., Basu, S., & Ghosh, K. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11593-8 · Cited by 1
BehaVERT: A Transformer-Based Motion Language Model for Decoding Behavioral Semantics in Mice
Shin, S. J., Lee, J., Ko, C., & Kim, D. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02834-y · Cited by 1
SAHs: Unraveling Safety Attention Heads in Large Vision-Language Models
Zheng, Z., He, L., Zhao, J. Z., Yang, L., & Li, F. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3710895 · Cited by 1
Token-Based Affordance Grounding with Large Vision-Language Models
Lee, S. I., Lei, Q., Xu, D., Yang, D., Tan, R. T., Chen, Y., & Wang, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36846-1_24 · Cited by 1
Explainable AI for Early Detection of Neurological Disorders Using Multimodal Biomedical Data
Gautum, R., Tanwar, S., & Singh, R. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.574 · Cited by 1
From Principles to Practice: Engineering Responsible AI for Geospatial Intelligence
Hassan, M., Sardar, B., Islam, S., Imani, M., & Hakiri, A. (2026) · SN Computer Science · doi:10.1007/s42979-026-05258-0 · Cited by 1
Relevance Propagation through Deep Conditional Random Fields
Yang, X., Joukovsky, B., & Deligiannis, N. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095075 · Cited by 1
Small, Multilingual, Explainable Transformers for Online Handwriting Decoding
Ramo, M., Silvestre, G. C. M., & Balado, F. (2023) · Irish Signals and Systems Conference · doi:10.1109/issc59246.2023.10162050 · Cited by 1
Dense Multitask Learning to Reconfigure Comics
Bhattacharjee, D., Susstrunk, S. E., & Salzmann, M. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00598 · Cited by 1
DynaSlim: Dynamic Slimming for Vision Transformers
Shi, D., Gao, J., Liu, T., & Fu, Y. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00251 · Cited by 1
Strain-Level Identification and Analysis of Avian Coronavirus Using Raman Spectroscopy and Interpretable Machine Learning
Jin, P., Yeh, Y., Ye, J., Wang, Z., Xue, Y., Zhang, N., Huang, S., Ghedin, E., Lu, H., Schmitt, A. P., et al. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230416 · Cited by 1
Fine-tuning is not (always) overfitting artifacts
Bogaert, J., Jean, E., de Bodt, C., & Standaert, F. (2023) · European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) · doi:10.14428/esann/2023.es2023-152 · Cited by 1
A Case-based Channel Selection Method for EEG Emotion Recognition Using Interpretable Transformer Networks
Du, Y., Guan, Z., Huang, W., Zhang, X., & Huang, Q. (2023) · International Conference on Computer, Vision and Intelligent Technology (ICCVIT) · doi:10.1145/3627341.3630372 · Cited by 1
Deep Multi-task Image Clustering with Attention-Guided Patch Filtering and Correlation Mining
Tian, Z., Li, K., & Peng, J. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8462-6_11 · Cited by 1
Kidney Cancer Detection from CT Images by Transformer-Based Classifiers
Tanaka, T., Fukazawa, T., Kameya, Y., Yamada, K., Hotta, K., Takahashi, T., Sassa, N., Matsukawa, Y., Iwano, S., & Yamamoto, T. (2023) · IIAI International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiai-aai59060.2023.00094 · Cited by 1
DeciX: Explain Deep Learning Based Code Generation Applications
Chen, S. H., Li, Z., Yang, W. M., & Liu, C. (2024) · Proceedings of the ACM on software engineering. · doi:10.1145/3660814 · Cited by 1
Automated quantification of SARS-CoV-2 pneumonia with large vision model knowledge adaptation
Liang, Z., Xue, Z., Rajaraman, S., & Antani, S. (2024) · New Microbes and New Infections · doi:10.1016/j.nmni.2024.101457 · Cited by 1
GANet - Learning Tabular Data Using Global Attention
Bui, H., & Le, B. H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70816-9_8 · Cited by 1
Exploring the neural landscape: Visual analytics of neuron activation in large language models with NeuronautLLM
Woodman, O., Wen, Z., Lu, H., Ren, Y., Zhu, M., & Chen, W. (2024) · Graphical Models · doi:10.1016/j.gmod.2024.101238 · Cited by 1
Probabilistic Path Integration with Mixture of Baseline Distributions
Elisha, Y., Barkan, O., & Koenigstein, N. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679641 · Cited by 1
Masked Contrastive Representation Learning for Self-Supervised Visual Pre-Training
Yao, Y., Desai, N., & Palaniswami, M. S. (2024) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa61799.2024.10722789 · Cited by 2
Triplet Bridge for Zero-Shot Sketch-Based Image Retrieval
Zheng, J., Tang, Y., & Wu, D. O. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3502430 · Cited by 1
Machine Learning Explainability as a Service: Service Description and Economics
Fantozzi, P., Luigi Laura, A., & Naldi, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-81226-2_21 · Cited by 1
Facial expression recognition in the wild: A new Adaptive Attention-Modulated Contextual Spatial Information network
Li, X., Zhu, C., & Yang, S. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110258 · Cited by 2
More video-relevant paragraph captioning via Perturbed Attention Self-Distillation
Gao, Y., Suo, W., Sun, M., Liu, L., & Wang, P. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111871 · Cited by 1
Joint Item Response Models for Manual and Automatic Scores on Open-Ended Test Items
Bengs, D., Brefeld, U., Kroehne, U., & Zehner, F. (2025) · Psychometrika · doi:10.1017/psy.2025.10018
Improving risk assessment of local failure in brain metastases patients using vision transformers − A multicentric development and validation study
Erdur, A. C., Scholz, D., Nguyen, Q. M., Buchner, J. A., Mayinger, M. C., Christ, S. M., Brunner, T. B., Wittig, A., Zimmer, C., Meyer, B., et al. (2025) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2025.111031 · Cited by 2
Empowering Image Restoration: A Multi-Attention Approach
Wen, J., Li, Y., Zhang, C., Hou, W., Gool, L. V., & Timofte, R. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129065 · Cited by 1
Evidential Interpretation Approach for Deep Neural Networks in High-Frequency Electromagnetic Wave Processing
Li, X., Su, M., Zhu, Y., Ma, S., Liu, S., & Zheng, T. (2025) · Electronics · doi:10.3390/electronics14163277 · Cited by 1
Linearly-interpretable concept embedding models for text analysis
Santis, F. D., Bich, P., Ciravegna, G., Barbiero, P., Giordano, D., & Cerquitelli, T. (2025) · Machine Learning · doi:10.1007/s10994-025-06839-5 · Cited by 1
MHSI-Net: an interpretable multi-modal deep learning network for street identification in historical maps
Liu, Q., Gong, Z., Li, B., & Yin, J. (2025) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2025.2528098 · Cited by 2
MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualization
Zang, Z., Wang, Y., Wu, J., Liu, H., Shen, Y., Lei, Z., & Li, S. Z. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3705888 · Cited by 1
Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild
Brandl, S., Hershcovich, D., & Søgaard, A. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19389 · Cited by 1
GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation LearningPreprint
Kwak, B., Park, J., Kang, T., Lee, B., Yoon, S., & Jo, J. (2023) · Research Square · doi:10.21203/rs.3.rs-2990926/v1 · Cited by 1
Facial Expression Recognition with Enhanced Relation-Aware Attention and Cross-Feature Fusion transformerPreprint
Dong, Y., Wang, T., Pu, Y., & Gao, J. (2024) · Research Square · doi:10.21203/rs.3.rs-3948258/v1 · Cited by 1
Deep-Learning-Based Customer Complaints Monitoring System Using Online ReviewPreprint
Seok, J.-S., Kim, C.-Y., Kim, S.-Y., & Kim, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4795530 · Cited by 1
Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution PatchesPreprint
Heng, Y., Wu, Y., Dasmahapatra, S., & Kim, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4860829 · Cited by 1
Explainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetesPreprint
Klein, L., Ziegler, S., Gerst, F., Morgenroth, Y., Gotkowski, K., Schöniger, E., Heni, M., Kipke, N., Friedland, D., Seiler, A., et al. (2024) · medRxiv · doi:10.1101/2024.10.23.24315937 · Cited by 1
Pipvit: Patch-Based Visual Interpretable Prototypes for Retinal Image AnalysisPreprint
Oghbaie, M., Araújo, T., & Bogunović, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5336537 · Cited by 1
An Explainable Hybrid CNN–Transformer Framework with Aquila Optimization for MRI-Based Brain Tumor ClassificationPreprint
Thottempudi, P., Acharya, B., Aouthu, S., Dhanalakshmi, N., Bai, B. M., Madhavi, K. R., Swaraja, K., & Mallik, S. (2025) · medRxiv · doi:10.1101/2025.10.14.25338038 · Cited by 1
Video-Based Cattle Behavior Detection for Digital Twin Development in Precision Dairy SystemsPreprint
Rao, S., Garcia, E., & Neethirajan, S. R. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.11.13.688203 · Cited by 1
Towards a Cytometry Foundation Model: Interpretable Sample-level Predictive Modelling via Pretrained TransformersPreprint
Zhuang, Z., Mashford, B. S., Zheng, L., & Andrews, T. D. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.31.712806 · Cited by 1
Audiovisual speech representation learning applied to emotion recognition
Sadok, S. (2024) · theses.fr (ABES) · doi:10.70675/0f15a36fzecf8z4cffz94e7z120e7d8fd39d · Cited by 1
CrabNet for explainable deep learning in materials science: bridging the gap between academia and industryPreprint
Wang, A., Mahmoud, M. S., Czasny, M., & Gurlo, A. (2021) · doi:10.33774/chemrxiv-2021-b8ncl
Application Research of YOLOv3 Incorporating Self-attention Mechanism
Zhang, J., Jia, Y., & Yu, H. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-3927-3_45
Review of Human Violence Recognition Algorithms
Zhang, Y., Guo, S., & Li, Y. (2022) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc55077.2022.9886081
Augmenting Magnetic Resonance Imaging with Tabular Features for Enhanced and Interpretable Medial Temporal Lobe Atrophy Prediction
Lee, D., Suh, C. H., Kim, J., Jung, W., Park, C., Jung, K.-H., Kong, S. T., Shim, W. H., Heo, H., & Kim, S. J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17899-3_13
A Dataset Generation Framework for Evaluating Megapixel Image Classifiers and Their Explanations
Machiraju, G., Plevritis, S. K., & Mallick, P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19775-8_25 · Cited by 1
Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Nitta, T., Hirakawa, T., Fujiyoshi, H., & Tamaki, T. (2023) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2022edp7138
Near-Earth aircraft wake vortex recognition based on multiple LIDAR and transformer
Pan, W., & Wang, A. (2023) · International Conference on Artificial Intelligence, Virtual Reality and Visualization (AIVRV) · doi:10.1117/12.2667212
Evaluating Quality of Visual Explanations of Deep Learning Models for Vision Tasks
Yang, Y., Mahmoudpour, S., Schelkens, P., & Deligiannis, N. (2023) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex58391.2023.10178510
Visualization Enhancement of Saliency Methods Based on the Sliding Window Mechanism
Xiang, X., Zhang, F., Deng, X., & Ding, X. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230582
What Does Pre-Train Bring to Vision Transformer
Wu, Y., Ren, W., & Yang, Z. (2023) · International Conference on Big Data and Internet of Things (BDIOT) · doi:10.1145/3617695.3617708
Towards Explainable Computer Vision Methods via Uncertainty Activation Map
Shin, S., Bae, W., Noh, J., & Choi, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47634-1_1
Dual-Polarity ViT for Fine-Grained Visual Categorization
Guo, T., Cheng, L., Wang, C., Chen, R., Zhang, H., & Lan, L. (2023) · International Conference on Multimedia Communication Technologies (ICMCT) · doi:10.1109/icmct60483.2023.00016
Multi-depth Fusion Transformer and Batch Piecewise Loss for Visual Sentiment Analysis
Ou, H., Qing, C., Cen, J., & Xu, X. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8549-4_33
Attention-based estimation of topic model quality
Kataeva, V., & Khodorchenko, M. (2023) · Computational Linguistics and Intellectual Technologies · doi:10.28995/2075-7182-2023-22-215-224
Tractable Executable Binary Provenance Signalling through Vision Transformers
Nauman, M. (2024) · Learning and Technology Conference (L&T) · doi:10.1109/lt60077.2024.10469044
WordDiffuser: Helping Beginners Cognize and Memorize Glyph-Semantic Pairs Using Diffusion
Xu, Y., Xia, W., Chen, Y., Liu, J., & You, W. (2023) · International Symposium on Computational Intelligence and Design · doi:10.1109/iscid59865.2023.00028
Pharmacy Infusion Bottle Detection Based on Improved YOLOv8
Yu, N. H., & Li, L. (2023) · International Conference on Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR) · doi:10.1109/aihcir61661.2023.00047
From Attention to Assurance: Enhancing Transformer Encoder Reliability Through Advanced Testing and Online Error PredictionPreprint
Golshanrad, P., & Faghih, F. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4856933
Evaluating Harmony: Neural Network Explanation Metrics and Human Perception
Vukadin, D., Šilić, M., Delač, G., & Vladimir, K. (2024) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro60963.2024.10569295
Estimating Socioeconomic Proxy Variables Using Multimodal Deep Learning Models
Bai, Y., Zhu, Z., Su, H. C., Liu, X., & Li, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5618-6_35
Understanding Training Behaviour during Transfer Learning by drawing parallels to Grokking
Rath, K., & Gnanasigamani, L. J. (2024) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit61985.2024.10626430
Representing Outcome-Driven Higher-Order Dependencies in Graphs of Disease Trajectories
Krieg, S. J., Chawla, N. V., & Feldman, K. (2024) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi61247.2024.00010
Identifying Important Group of Pixels using Interactions
Sumiyasu, K., Kawamoto, K., & Kera, H. (2024) · 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/cvpr52733.2024.00575 · Cited by 2
SkipPLUS: Skip the First Few Layers to Better Explain Vision Transformers
Mehri, F., Fayyaz, M., Baghshah, M. S., & Pilehvar, M. T. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00025 · Cited by 1
Effective Optimization of Root Selection Towards Improved Explanation of Deep Classifiers
Zhang, X., Zhong, S.-H., & Jiang, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680866
Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities
Wu, J., Pan, K., Chen, Y., Deng, J., Pang, S., & Xu, W. (2024) · IEEE International Conference on Metaverse Computing, Networking and Applications (MetaCom) · doi:10.1109/metacom62920.2024.00029 · Cited by 1
Behavior Capture Based Explainable Engagement Recognition
Bei, Y., Guo, S., Gao, K., Feng, Z., Tong, Y., Cai, W., Cheng, L., & Liang, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8792-0_17
Enhancing Explainable Herbal Recognition with Vision Transformer Features and SVM
Huynh, P.-H. (2024) · Communications in computer and information science · doi:10.1007/978-981-96-0434-0_4
Assessing Aggressive Driving Behaviour Using Attention Based Models
Aechtner, J., Wilbik, A., & Popa, M. C. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-74650-5_4
Interpretable Visual Semantic Alignment via Spectral Attribution
Ambati, S., Padmanabhan, V., Bhukya, W. N., & Lal, R. P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78395-1_9
Interpreting DETR with Respect to Object QueriesPreprint
Farahani, M. S., Haghighi, M. J. M., & Mohammadi, M. R. (2024) · Research Square · doi:10.21203/rs.3.rs-5659752/v1
RSGM: a multi-modal image matching scheme guided by regional semantics
Jin, F., Liao, Y., Liu, J., Hu, Z., Qian, X., Li, Y., Teng, R., & Duan, Q. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02274-8
Research and Design of an Information Interaction Platform Based on Transformer Models and Data Visualization
Zhang, H., Dong, H., & Cui, J. (2024) · IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) · doi:10.1109/icaica63239.2024.10823065
On the Adaptability of Attention-Based Interpretability in Different Transformer Architectures for Multi-class Classification Tasks
Katsaki, S., Aivazidis, C., Mylonas, N., Mollas, I., & Tsoumakas, G. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-74630-7_4
The Impact of Decorrelation on Transformer Interpretation Methods: Applications to Clinical Speech AI
Xu, L., Mueller, K. D., Liss, J., & Berisha, V. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889946
Prototypical Part Transformer for Interpretable Image Recognition
Yu, A., & Yang, Y.-B. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10890753
Biophysically interpretable basal cell carcinoma classification using Raman spectroscopy transformer model
Khan, F. S., Xu, F., Fox, M. C., Reichenberg, J. S., Lopes, F. C. P. S., Sebastian, K., Markey, M. K., & Tunnell, J. W. (2025) · Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems · doi:10.1117/12.3041543
Holistic Visualization of Contextual Knowledge in Hotel Customer Reviews Using Self-Attention
Masuda, S., & Yamasaki, T. (2024) · International Symposium on Multimedia · doi:10.1109/ism63611.2024.00021
Apprentissage profond de variétés pour une meilleure caractérisation de l'hypertension artérielle en imagerie échocardiographique
Painchaud, N. (2024) · theses.fr (ABES) · doi:10.70675/637db7eazf47fz4d2czb112zaf2cafad29d8
A decision transformer approach to grain boundary network optimization
Adair, C. W., & Johnson, O. K. (2025) · Computational Materials Science · doi:10.1016/j.commatsci.2025.113852
Visual Latent Captioning - Towards Verbalizing Vision Transformer Encoders
Haghighat, S., Metzler, T. D., Thoduka, S., & Houben, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88711-6_25
Low-Compute Trash Segmentation Using Pretrained Vision Transformers Without Fine-Tuning
Keller, P., Möck, M., Heppner, G., & Dillmann, R. (2025) · International Conference on Automation, Robotics and Applications · doi:10.1109/icara64554.2025.10977695
VIS4SL: A visual analytic approach for interpreting and diagnosing shortcut learning
Meng, X., Tang, T., Zhou, Y., Yan, Z., Deng, D., Wang, Y., Wu, Y., & Wu, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113598
AdvancedScoreCAM: Enhancing visual explainability through hierarchical upsampling
Zhao, H., & Noor, M. H. M. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113265
How to Squeeze An Explanation Out of Your Model
Roxo, T., Costa, J. C., Inácio, P. R. M., & Proença, H. P. M. C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92089-9_16
Genetic Information Analysis of Age-Related Macular Degeneration Fellow Eye Using Multi-modal Selective ViT
Furukawa, Y., Kamiya, S., Sakurada, Y., Kashiwagi, K., & Hotta, K. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91721-9_7

Authors: Chefer, H., Gur, S., & Wolf, L.
Affiliations: Tel Aviv University (IL)
ORCID: Chefer, Hila
Wolf, Lior
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)
DOI: 10.1109/cvpr46437.2021.00084
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: cc-by
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)
doi.org/10.15223/policy-029 (stm-asf)
doi.org/10.15223/policy-037 (stm-asf)
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

Transformer Interpretability Beyond Attention Visualization

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks