mlsanityData to 7 Oct 2026

Black-box Explanation of Object Detectors via Saliency Maps

arXiv 2006.03204 ↗First posted 5 Jun 2020cs.CV cs.AI cs.LGcited by 74

Not on the map. Why?

Abstract (arXiv)

We propose D-RISE, a method for generating visual explanations for the predictions of object detectors. Utilizing the proposed similarity metric that accounts for both localization and categorization aspects of object detection allows our method to produce saliency maps that show image areas that most affect the prediction. D-RISE can be considered "black-box" in the software testing sense, as it only needs access to the inputs and outputs of an object detector. Compared to gradient-based methods, D-RISE is more general and agnostic to the particular type of object detector being tested, and does not need knowledge of the inner workings of the model. We show that D-RISE can be easily applied to different object detectors including one-stage detectors such as YOLOv3 and two-stage detectors such as Faster-RCNN. We present a detailed analysis of the generated visual explanations to highlight the utilization of context and possible biases learned by object detectors.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 15; 2023: 18; 2024: 17; 2025: 9; 2026: 11.

74 papers.

Sort:

By area:

  1. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  2. 2022Diffusion Models for Counterfactual Explanationscited by 79
  3. 2022Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measurecited by 33
  4. 2025Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checkingcited by 29
  5. 2021Explainable Person Re-Identification with Attribute-guided Metric Distillationcited by 23
  6. 2024Interpreting Object-level Foundation Models via Visual Precision Searchcited by 20
  7. 2022Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanationscited by 17
  8. 2024Explaining generative diffusion models via visual analysis for interpretable decision-making processcited by 15
  9. 2023Towards Better Explanations for Object Detectioncited by 14
  10. 2022OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Datacited by 13
  11. 2022What You See is What You Classify: Black Box Attributionscited by 12
  12. 2023ODAM: Gradient-based instance-specific visual explanations for object detectioncited by 12
38 more
  1. 2024LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Taskscited by 12
  2. 2023Towards Visual Saliency Explanations of Face Verificationcited by 11
  3. 2023Bridging the Transparency Gap: What Can Explainable AI Learn From the AI Act?cited by 10
  4. 2023Towards Trust of Explainable AI in Thyroid Nodule Diagnosiscited by 10
  5. 2022"Is your explanation stable?": A Robustness Evaluation Framework for Feature Attributioncited by 7
  6. 2023G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectorscited by 7
  7. 2024XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approachcited by 7
  8. 2025Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIPcited by 7
  9. 2021Estimating and Maximizing Mutual Information for Knowledge Distillationcited by 6
  10. 2022Explaining YOLO: Leveraging Grad-CAM to Explain Object Detectionscited by 6
  11. 2023Model-agnostic explainable artificial intelligence for object detection in image datacited by 6
  12. 2023Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Modelscited by 6
  13. 2024CrisisKAN: Knowledge-infused and Explainable Multimodal Attention Network for Crisis Event Classificationcited by 6
  14. 2024Explainable Face Verification via Feature-Guided Gradient Backpropagationcited by 6
  15. 2024Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainercited by 6
  16. 2024Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detectorcited by 5
  17. 2023ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformercited by 4
  18. 2025Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitorscited by 4
  19. 2022Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Imagescited by 3
  20. 2022Recipro-CAM: Fast gradient-free visual explanations for convolutional neural networkscited by 3
  21. 2023Explanation of Face Recognition via Saliency Mapscited by 3
  22. 2023Improve Video Representation with Temporal Adversarial Augmentationcited by 3
  23. 2023Discriminative Deep Feature Visualization for Explainable Face Recognitioncited by 3
  24. 2023BSED: Baseline Shapley-Based Explainable Detectorcited by 3
  25. 2024Explaining Object Detectors via Collective Contribution of Pixelscited by 3
  26. 2025ODExAI: A Comprehensive Object Detection Explainable AI Evaluationcited by 3
  27. 2022DExT: Detector Explanation Toolkitcited by 2
  28. 2023Sanity Checks for Saliency Methods Explaining Object Detectorscited by 2
  29. 2024FFAM: Feature Factorization Activation Map for Explanation of 3D Detectorscited by 2
  30. 2021Co-segmentation Inspired Attention Module for Video-based Computer Vision Taskscited by 1
  31. 2022Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Toolscited by 1
  32. 2022Illuminating Salient Contributions in Neuron Activation with Attribution Equilibriumcited by 1
  33. 2023Defining Quality Requirements for a Trustworthy AI Wildflower Monitoring Platformcited by 1
  34. 2023ODSmoothGrad: Generating Saliency Maps for Object Detectorscited by 1
  35. 2023Assessing Trustworthiness of Autonomous Systemscited by 1
  36. 2023FM-G-CAM: A Holistic Approach for Explainable AI in Computer Visioncited by 1
  37. 2024Enhancing the Fairness and Performance of Edge Cameras with Explainable AIcited by 1
  38. 2024XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspectioncited by 1

50 most cited of 74 All 74 (JSON)