Saliency Map Evaluation

Also known as MAP

Ask about this topic

Overview

Saliency map evaluation asks whether highlighted image regions reflect the evidence a model actually uses, correctly localize relevant objects, and help people understand or use its predictions. Common approaches include insertion and deletion tests, masking and sufficiency measures, comparisons with boxes or segmentation masks, and checks of stability under input changes; human studies and eye-tracking provide complementary judgments. Results depend on choices such as masking operators, perturbations, metrics, and model architecture, so rankings can change across benchmarks and settings. A central challenge is establishing standardized evaluations whose scores reliably predict both faithful explanations and human usefulness.

Latest papers

CardsList

34 papers10 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

  1. Explaining Basketball Shot Classifications with Grad-CAM: An Investigation of Shortcut Reliance with Spatiotemporal Correlations

    Oct 23, 2026Hongyi Tian, Robin CohenSports Video AnalysisShortcut Learning

    Computer Science, University of Waterloo 200 University Ave W, Waterloo, ON, N2L 3G1, Canada

  2. AVAtt: A Free-Viewing Eye-Tracking Dataset and Benchmark for Visual Attention on Paintings

    Oct 21, 2026Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani +1Visual AttentionVisual Saliency

    F-Initiatives, France · University of Orléans, PRISME Laboratory, France · IULM University, Milan, Italy

  3. What Not to Erase: Saliency-Constrained Augmentation for Low-Resource Handwritten Character Recognition

    Oct 19, 2026Paraskevi Platanou, John PavlopoulosData AugmentationOptical Character Recognition

    Athens University of Economics and Business Archimedes, Athena Research Center, Greece

  4. Can We Use Saliency Maps for the Evaluation of Generative Image Models?

    Oct 16, 2026Eleonora Ristori, Luca Bindini, Marco Lippi +1Image Generation EvaluationSaliency Map Evaluation

    AI Lab, DINFO, University of Florence, Florence, Italy

  5. [Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning

    Oct 10, 2026Anton Nuzhdin, Andrei Gruzitski, Balázs Egyed +1VLM InterpretabilitySaliency Map Evaluation

    University of Amsterdam

  6. Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation

    Oct 8, 2026Marco Stefani, Edoardo Parpaiola, Matteo Bino +5Neural Network InterpretabilitySaliency Map Evaluation

    Department of Information Engineering (DEI), University of Padova, Padova, Italy

  7. For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature Importance

    Oct 7, 2026Bjørn Leth Møller, Bulat Ibragimov, Christian IgelFeature AttributionNeural Network Interpretability

    Department of Computer Science, University of Copenhagen, Denmark

  8. Spatial Supervision Without Attribution Optimization: Improving Post-Hoc Class Activation Maps via Box-Guided Evidence Routing

    Oct 5, 2026Wenhao Liang, Liangwei Nathan Zheng, Lin Yue +3Gradient-Based AttributionFeature Attribution

    Adelaide University, Adelaide, Australia

  9. ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution

    Oct 3, 2026Yehonatan Elisha, Oren Barkan, Ziv Weiss Haddad +1Concept-Based ExplanationsExplainable Image Classification

    Tel Aviv University · The Open University

  10. Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters

    Oct 2, 2026Susmit Agrawal, Rebecca Wanner, Juliane Verwiebe +3Video Saliency PredictionVisual Saliency

    Tübingen AI Center, University of Tübingen · IMPRS-IS · Optocycle +2

  11. Faithful Faithfulness Evaluations: Challenges & Pitfalls Learned from a Breast MRI Case Study

    Sep 22, 2026Peachapong Poolpol, Henrik H. J. Detjen, Eike PetersenPerturbation-Based Feature AttributionSaliency Map Evaluation

    Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany · Deggendorf Institute of Technology, Deggendorf, Germany

  12. Pathology Transport: Optimal-Transport Explanations for Clinical Data, and When Their Heatmaps (Fail to) Localize Disease

    Aug 18, 2026Lalit KumarExplainable Medical Image AnalysisSaliency Map Evaluation

    Department of Computer Science The University of Texas at Austin

  13. Human versus Computer Vision

    Aug 10, 2026Elena SirotkinaVisual AttentionAlgorithmic Fairness

    Center for Data Science, New York University

  14. VGER: Voxel-Guided Global Event Ranking for Event Cloud Attribution

    Aug 2, 2026Youxin Jiang, Baoheng Fu, Hongwei Ren +1Event-Based VisionFeature Attribution

    Harbin Institute of Technology

  15. Explaining AI-Image Detection: What the Heatmap Actually Shows

    Jul 31, 2026Leonid Kuturin, Ilya Sotnikov, Mark Khusnutdinov +4Image Forgery DetectionDigital Image Forensics

    Sirius Educational Centre, Big Challenges programme · HSE University, Faculty of Computer Science

  16. What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks

    Jul 10, 2026Magdalena Trędowicz, Łukasz Struski, Arkadiusz Lewicki +4Transformer InterpretabilitySaliency Map Evaluation

    Jagiellonian University · University of Information Technology and Management in Rzeszów · Jagiellonian University Medical College

  17. Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation

    Jun 22, 2026Yanze Xu, Mark D. Plumbley, Wenwu WangGradient-Based AttributionFeature Attribution

    Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, UK · Department of Informatics, King’s College London, London, WC2R 2LS, UK

  18. SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches

    Jun 16, 2026Wencan Zhang, Mario Michelessa, Xuejun Zhao +1Explainable Artificial IntelligenceSaliency Map Evaluation

    National University of Singapore

  19. What's Old is New Again: Classical Dimensionality Reduction for Efficient Saliency-Guided Biometric Attack Detection

    Jun 11, 2026Samuel Webster, Walter ScheirerSaliency Map Evaluation

    Department of Computer Science and Engineering University of Notre Dame, IN, USA

  20. AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps

    May 16, 2026Chia-Ying Hsieh, Hsin-Yuan Fang, Chun-Shu WeiGradient-Based AttributionSaliency Map Evaluation

    National Yang Ming Chiao Tung University

  21. Raising the Ceiling: Better Empirical Fixation Densities for Saliency Benchmarking

    May 5, 2026Susmit Agrawal, Jannis Hollman, Matthias KümmererBenchmark DesignEye Tracking

    Tübingen AI Center, University of Tübingen, Germany

  22. How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?

    May 3, 2026Daniel da Silva Costa, Pedro Nuno de Souza Moura, Adriana C. F. AlvimFeature AttributionSaliency Map Evaluation

    Postgraduate Program in Informatics, Federal University of the State of Rio de Janeiro (UNIRIO), Rio de Janeiro, RJ, 22290-240, Brazil

  23. From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models

    May 1, 2026Yearim Kim, Sangyu Han, Nojun KwakSaliency Map EvaluationMechanistic Interpretability

    Seoul National University, Seoul 08826, South Korea

  24. Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification

    Apr 9, 2026Kabilan Elangovan, Daniel TingExplainability EvaluationSaliency Map Evaluation

    Singapore Health Services, Singapore · Singapore Eye Research Institute, Singapore

  25. Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?

    Apr 2, 2026Kamalasankari Subramaniakuppusamy, Jugal GajjarExplainability EvaluationPerturbation-Based Feature Attribution

    The George Washington University Washington D.C.

  26. Structural Compactness as a Complementary Criterion for Explanation Quality

    Mar 31, 2026Mohammad Mahdi Mesgari, Jackie Ma, Wojciech Samek +2Explainability EvaluationExplanation Evaluation

    Fraunhofer Heinrich Hertz Institute, Berlin, Germany · Technische Universität Berlin, Berlin, Germany · BIFOLD – Berlin Institute for the Foundations of Learning and Data, Berlin, Germany +1

  27. End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution

    Mar 26, 2026Parniyan Farvardin, David ChapmanNeural Network InterpretabilityExplainable Image Classification

    University of Miami

  28. Attribution Upsampling should Redistribute, Not Interpolate

    Mar 17, 2026Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat +2Feature AttributionSaliency Map Evaluation

    Halmstad University, Halmstad, Sweden

  29. Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology

    Mar 9, 2026Mina Jamshidi Idaji, Julius Hense, Tom Neuhäuser +12Saliency Map EvaluationMultiple Instance Learning

    Berlin Institute for the Foundations of Learning and Data, Berlin, Germany · Machine Learning Group, Technische Universität Berlin, Berlin, Germany · Department of Chemistry, Chemical Physics Theory Group, University of Toronto, Canada +9

  30. Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing

    Mar 7, 2026Dipkamal Bhusal, Md Tanvirul Alam, Nidhi RastogiGradient-Based AttributionExplanation Stability

    Rochester Institute of Technology