Saliency Map Evaluation

Also known as MAP

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

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

Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations
Mar 5, 2026Hajar Dekdegue, Moncef Garouani, Josiane Mothe +1Explainable Image Classification Feature Attribution
IRIT, UMR5505 CNRS Universit´e de Toulouse · IRIT, UMR5505 CNRS Universit´e Toulouse Capitole · INRAE, Centre Occitanie-Toulouse Unit´e Exp´erimentale APC
DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging
Feb 22, 2026Krishna Khadka, Yu Lei, Raghu N. Kacker +1Explainable Image Classification Feature Attribution
Department of Computer Science & Engineering The University of Texas at Arlington Arlington, Texas, USA · Information Technology Laboratory National Institute of Standards and Technology (NIST) Gaithersburg, Maryland, USA
Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability
Sep 25, 2025Ali Yavari, Alireza Mohamadi, Elham Beydaghi +2Feature Attribution Perturbation-Based Feature Attribution
Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria · Independent · Dept. of Computer Engineering, Sharif University of Technology, Tehran, Iran +1
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

Mar 5, 2026J/K move · Enter open · S save

Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations

Hajar Dekdegue, Moncef Garouani, Josiane Mothe, Jordan Bernigaud

IRIT, UMR5505 CNRS Universit´e de Toulouse · IRIT, UMR5505 CNRS Universit´e Toulouse Capitole · INRAE, Centre Occitanie-Toulouse Unit´e Exp´erimentale APC

Explainable Image Classification Feature Attribution Gradient-Based Attribution Saliency Map Evaluation Explainability Evaluation

Open paper AskPDF arXiv

Interpreting the decision-making process of deep convolutional neural networks remains a central challenge in achieving trustworthy and transparent artificial intelligence. Explainable AI (XAI) techniques, particularly Class Activation Map (CAM) methods, are widely adopted to visualize the input regions influencing model predictions. Gradient-based approaches (e.g. Grad-CAM) provide highly discriminative, fine-grained details by computing gradients of class activations but often yield noisy and incomplete maps that emphasize only the most salient regions rather than the complete objects. Region-based approaches (e.g. Score-CAM) aggregate information over larger areas, capturing broader object coverage at the cost of over-smoothing and reduced sensitivity to subtle features. We introduce Fusion-CAM, a novel framework that bridges this explanatory gap by unifying both paradigms through a dedicated fusion mechanism to produce robust and highly discriminative visual explanations. Our method first denoises gradient-based maps, yielding cleaner and more focused activations. It then combines the refined gradient map with region-based maps using contribution weights to enhance class coverage. Finally, we propose an adaptive similarity-based pixel-level fusion that evaluates the agreement between both paradigms and dynamically adjusts the fusion strength. This adaptive mechanism reinforces consistent activations while softly blending conflicting regions, resulting in richer, context-aware, and input-adaptive visual explanations. Extensive experiments on standard benchmarks show that Fusion-CAM consistently outperforms existing CAM variants in both qualitative visualization and quantitative evaluation, providing a robust and flexible tool for interpreting deep neural networks.

Latest papers

Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations

DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability

Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps