Saliency Map Evaluation

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 15

All topics

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 Attribution Neural Network Interpretability
Department of Computer Science, University of Copenhagen, Denmark
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 Attribution Feature Attribution
Adelaide University, Adelaide, Australia
Faithful Faithfulness Evaluations: Challenges & Pitfalls Learned from a Breast MRI Case Study
Sep 22, 2026Peachapong Poolpol, Henrik H. J. Detjen, Eike PetersenPerturbation-Based Feature Attribution Saliency Map Evaluation
Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany · Deggendorf Institute of Technology, Deggendorf, Germany
Human versus Computer Vision
Aug 10, 2026Elena SirotkinaVisual Attention Algorithmic Fairness
Center for Data Science New York University
VGER: Voxel-Guided Global Event Ranking for Event Cloud Attribution
Aug 2, 2026Youxin Jiang, Baoheng Fu, Hongwei Ren +1Event-Based Vision Feature Attribution
Harbin Institute of Technology
Explaining AI-Image Detection: What the Heatmap Actually Shows
Jul 31, 2026Leonid Kuturin, Ilya Sotnikov, Mark Khusnutdinov +4Image Forgery Detection Digital Image Forensics
Sirius Educational Centre, Big Challenges programme · HSE University, Faculty of Computer Science
What Pixels Are Enough? SEAMS: Sufficiency Saliency via MSE-Preservation Soft-Masks
Jul 10, 2026Magdalena Trędowicz, Łukasz Struski, Arkadiusz Lewicki +4Transformer Interpretability Saliency Map Evaluation
Jagiellonian University · University of Information Technology and Management in Rzeszów · Jagiellonian University Medical College
Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation
Jun 22, 2026Yanze Xu, Mark D. Plumbley, Wenwu WangGradient-Based Attribution Feature 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
SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches
Jun 16, 2026Wencan Zhang, Mario Michelessa, Xuejun Zhao +1Explainable Artificial Intelligence Saliency Map Evaluation
National University of Singapore
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
AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps
May 16, 2026Chia-Ying Hsieh, Hsin-Yuan Fang, Chun-Shu WeiGradient-Based Attribution Saliency Map Evaluation
National Yang Ming Chiao Tung University
Raising the Ceiling: Better Empirical Fixation Densities for Saliency Benchmarking
May 5, 2026Susmit Agrawal, Jannis Hollman, Matthias KümmererBenchmark Design Eye Tracking
Tübingen AI Center, University of Tübingen, Germany
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 Attribution Saliency Map Evaluation
Postgraduate Program in Informatics, Federal University of the State of Rio de Janeiro (UNIRIO), Rio de Janeiro, RJ, 22290-240, Brazil
From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
May 1, 2026Yearim Kim, Sangyu Han, Nojun KwakSaliency Map Evaluation Mechanistic Interpretability
Seoul National University, Seoul 08826, South Korea
Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps
Apr 23, 2025Felix Kares, Timo Speith, Hanwei Zhang +1Saliency Map Evaluation Explainability Evaluation
Saarland University, Germany · University of Bayreuth, Germany · University of Freiburg, Germany

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

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

Bjørn Leth Møller, Bulat Ibragimov, Christian Igel

Department of Computer Science, University of Copenhagen, Denmark

Feature Attribution Neural Network Interpretability Saliency Map Evaluation

Open paper AskPDF arXiv

The adoption of machine learning for socially relevant tasks requires effective explainable artificial intelligence (XAI) methods to better understand the behavior of machine learning models. Attribution methods are a popular XAI approach in which input-output relationships are characterized by heat maps that reflect the relative importance of input features for a particular prediction. The quality of such maps is often assessed by measuring faithfulness based on the area under insertion and deletion curves, which measures changes in the model output as features are added and removed. In this study, we derive an objective function from this notion of faithfulness and a way to approximate its gradient. We establish the connection between insertion curves and top-

k

feature selection, which leads to a loss function measuring the quality of attributions. Randomization of the loss allows us to efficiently approximate its gradient. To show the effectiveness of the general approach, we combine the loss function with the neural explanation mask framework. The resulting method, termed Ra-NEM, can be used with any differentiable model without affecting the model's performance. Experiments demonstrate that Ra-NEM provides accurate attributions robustly and efficiently. Compared to other algorithms, the attributions have not only higher faithfulness but also perform well in terms of other XAI metrics. The high inference speed of Ra-NEM makes the method suitable for online applications. The code is available online: https://github.com/baerminator/Ra_Nem

Momentum

Related topics

Latest papers 15