mlsanityData to 7 Oct 2026

Top-down Neural Attention by Excitation Backprop

arXiv 1608.00507 ↗First posted 1 Aug 2016cs.CVcited by 318

Not on the map. Why?

Abstract (arXiv)

We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process. Furthermore, we introduce the concept of contrastive attention to make the top-down attention maps more discriminative. In experiments, we demonstrate the accuracy and generalizability of our method in weakly supervised localization tasks on the MS COCO, PASCAL VOC07 and ImageNet datasets. The usefulness of our method is further validated in the text-to-region association task. On the Flickr30k Entities dataset, we achieve promising performance in phrase localization by leveraging the top-down attention of a CNN model that has been trained on weakly labeled web images.

Key facts. Cited by 318 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 63; 2022: 64; 2023: 64; 2024: 59; 2025: 35; 2026: 33.

318 papers.

Sort:

By area:

  1. 2024SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agentscited by 553
  2. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  3. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  4. 2023Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Imagescited by 128
  5. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  6. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  7. 2021HIVE: Evaluating the Human Interpretability of Visual Explanationscited by 105
  8. 2021What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methodscited by 98
  9. 2021The effectiveness of feature attribution methods and its correlation with automatic evaluation scorescited by 87
  10. 2022Multi-Modal Knowledge Graph Construction and Application: A Surveycited by 74
  11. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  12. 2021Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysiscited by 65
38 more
  1. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63
  2. 2021Convolutional Dynamic Alignment Networks for Interpretable Classificationscited by 54
  3. 2021Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAycited by 53
  4. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  5. 2023FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methodscited by 49
  6. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  7. 2021Towards Better Explanations of Class Activation Mappingcited by 47
  8. 2021Describing and Localizing Multiple Changes with Transformerscited by 47
  9. 2022Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capabilitycited by 46
  10. 2024CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classificationcited by 40
  11. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 38
  12. 2021TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentationcited by 38
  13. 2022Large Loss Matters in Weakly Supervised Multi-Label Classificationcited by 38
  14. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  15. 2021Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networkscited by 36
  16. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  17. 2024Gradient based Feature Attribution in Explainable AI: A Technical Reviewcited by 34
  18. 2021Neural Response Interpretation through the Lens of Critical Pathwayscited by 32
  19. 2023FIND: A Function Description Benchmark for Evaluating Interpretability Methodscited by 32
  20. 2024LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivitycited by 32
  21. 2021Toward Explainable AI for Regression Modelscited by 30
  22. 2022On Guiding Visual Attention with Language Specificationcited by 30
  23. 2021NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weightscited by 28
  24. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  25. 2022Towards Better Understanding Attribution Methodscited by 28
  26. 2022ViT-CX: Causal Explanation of Vision Transformerscited by 27
  27. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  28. 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 25
  29. 2023Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directionscited by 25
  30. 2022Improving Visual Grounding by Encouraging Consistent Gradient-based Explanationscited by 24
  31. 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernelscited by 24
  32. 2021Explainable Person Re-Identification with Attribute-guided Metric Distillationcited by 23
  33. 2022Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanationscited by 22
  34. 2021Self-Interpretable Model with TransformationEquivariant Interpretationcited by 21
  35. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  36. 2021Focus! Rating XAI Methods and Finding Biasescited by 20
  37. 2022Do Explanations Explain? Model Knows Bestcited by 20
  38. 2024Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Conceptscited by 20

50 most cited of 318 All 318 (JSON)