mlsanityData to 7 Oct 2026

Real Time Image Saliency for Black Box Classifiers

arXiv 1705.07857 ↗First posted 22 May 2017stat.MLcited by 246

Not on the map. Why?

Abstract (arXiv)

In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model generalises well to unseen images and requires a single forward pass to perform saliency detection, therefore suitable for use in real-time systems. We test our approach on CIFAR-10 and ImageNet datasets and show that the produced saliency maps are easily interpretable, sharp, and free of artifacts. We suggest a new metric for saliency and test our method on the ImageNet object localisation task. We achieve results outperforming other weakly supervised methods.

Key facts. Cited by 246 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 60; 2022: 59; 2023: 59; 2024: 38; 2025: 19; 2026: 11.

246 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2021Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformerscited by 316
  3. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 241
  4. 2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
  5. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
  6. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  7. 2022PlanT: Explainable Planning Transformers via Object-Level Representationscited by 105
  8. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  9. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  10. 2022Distilling Model Failures as Directions in Latent Spacecited by 82
  11. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  12. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63
38 more
  1. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  2. 2021Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanationscited by 56
  3. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  4. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  5. 2022Optimizing Relevance Maps of Vision Transformers Improves Robustnesscited by 41
  6. 2022Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanationscited by 40
  7. 2021Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learningcited by 38
  8. 2022Model Zoos: A Dataset of Diverse Populations of Neural Network Modelscited by 38
  9. 2022On the Explainability of Natural Language Processing Deep Modelscited by 37
  10. 2021Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networkscited by 36
  11. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  12. 2022Missingness Bias in Model Debuggingcited by 36
  13. 2021Locally Sparse Neural Networks for Tabular Biomedical Datacited by 34
  14. 20213DB: A Framework for Debugging Computer Vision Modelscited by 31
  15. 2022Making Heads or Tails: Towards Semantically Consistent Visual Counterfactualscited by 30
  16. 2022ModelDiff: A Framework for Comparing Learning Algorithmscited by 30
  17. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  18. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  19. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  20. 2022Towards Better Understanding Attribution Methodscited by 28
  21. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  22. 2023Circuit Breaking: Removing Model Behaviors with Targeted Ablationcited by 27
  23. 2021Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysiscited by 25
  24. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  25. 2023Explaining Generalization Power of a DNN Using Interactive Conceptscited by 25
  26. 2024The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysiscited by 24
  27. 2021You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Predictioncited by 23
  28. 2021UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Modelscited by 23
  29. 2022Human-Centered Concept Explanations for Neural Networkscited by 23
  30. 2022Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Valuecited by 23
  31. 2022Fairness and Explainability: Bridging the Gap Towards Fair Model Explanationscited by 22
  32. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  33. 2024Optimal ablation for interpretabilitycited by 21
  34. 2021Revisiting Sanity Checks for Saliency Mapscited by 20
  35. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 20
  36. 2022Concept Gradient: Concept-based Interpretation Without Linear Assumptioncited by 20
  37. 2023Distilling Cognitive Backdoor Patterns within an Imagecited by 20
  38. 2023CoRTX: Contrastive Framework for Real-time Explanationcited by 20

50 most cited of 246 All 246 (JSON)