Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations

• URL: http://arxiv.org/abs/2511.13081v2
• Date: Tue, 18 Nov 2025 07:20:26 GMT
• Title: Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations
• Authors: Yehonatan Elisha, Seffi Cohen, Oren Barkan, Noam Koenigstein,
• Abstract summary: We introduce the Reference-Frame $times$ Granularity (RFxG) taxonomy.<n>RFxG organizes saliency explanations along two essential axes:Reference-Frame: Distinguishing between pointwise ("Why this prediction?") and contrastive ("Why this and not an alternative?") explanations.<n>Our comprehensive evaluation framework applies these metrics to ten state-of-the-art saliency methods, four model architectures, and three datasets.
• Score: 16.045822460720363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Saliency maps are widely used for visual explanations in deep learning, but a fundamental lack of consensus persists regarding their intended purpose and alignment with diverse user queries. This ambiguity hinders the effective evaluation and practical utility of explanation methods. We address this gap by introducing the Reference-Frame $\times$ Granularity (RFxG) taxonomy, a principled conceptual framework that organizes saliency explanations along two essential axes:Reference-Frame: Distinguishing between pointwise ("Why this prediction?") and contrastive ("Why this and not an alternative?") explanations. Granularity: Ranging from fine-grained class-level (e.g., "Why Husky?") to coarse-grained group-level (e.g., "Why Dog?") interpretations. Using the RFxG lens, we demonstrate critical limitations in existing evaluation metrics, which overwhelmingly prioritize pointwise faithfulness while neglecting contrastive reasoning and semantic granularity. To systematically assess explanation quality across both RFxG dimensions, we propose four novel faithfulness metrics. Our comprehensive evaluation framework applies these metrics to ten state-of-the-art saliency methods, four model architectures, and three datasets. By advocating a shift toward user-intent-driven evaluation, our work provides both the conceptual foundation and the practical tools necessary to develop visual explanations that are not only faithful to the underlying model behavior but are also meaningfully aligned with the complexity of human understanding and inquiry.

Related papers

• Insight: Interpretable Semantic Hierarchies in Vision-Language Encoders [52.94006363830628]
  Language-aligned vision foundation models perform strongly across diverse downstream tasks.<n>Recent works decompose these representations into human-interpretable concepts, but provide poor spatial grounding and are limited to image classification tasks.<n>We propose Insight, a language-aligned concept foundation model that provides fine-grained concepts, which are human-interpretable and spatially grounded in the input image.
  arXiv  Detail & Related papers  (2026-01-20T09:57:26Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Explain Before You Answer: A Survey on Compositional Visual Reasoning [74.27548620675748]
  Compositional visual reasoning has emerged as a key research frontier in multimodal AI.<n>This survey systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, etc.)<n>We then catalog 60+ benchmarks and corresponding metrics that probe compositional visual reasoning along dimensions such as grounding accuracy, chain-of-thought faithfulness, and high-resolution perception.
  arXiv  Detail & Related papers  (2025-08-24T11:01:51Z)
• Explainable Evidential Clustering [0.0]
  Real-world data often contain imperfections, characterized by uncertainty and imprecision, which are not well handled by traditional methods.<n>Evidential clustering, based on Dempster-Shafer theory, addresses these challenges.<n>We propose the Iterative Evidential Mistake Minimization (IEMM) algorithm, which provides interpretable and cautious decision tree explanations.
  arXiv  Detail & Related papers  (2025-07-16T12:44:25Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• Take A Step Back: Rethinking the Two Stages in Visual Reasoning [57.16394309170051]
  This paper revisits visual reasoning with a two-stage perspective. It is more efficient to implement symbolization via separated encoders for different data domains while using a shared reasoner. The proposed two-stage framework achieves impressive generalization ability on various visual reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-29T02:56:19Z)
• Evaluating Readability and Faithfulness of Concept-based Explanations [35.48852504832633]
  Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by Large Language Models. Current methods approach concepts from different perspectives, lacking a unified formalization. This makes evaluating the core measures of concepts, namely faithfulness or readability, challenging.
  arXiv  Detail & Related papers  (2024-04-29T09:20:25Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability [25.545486537295144]
  Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. Despite their popularity, they suffer from limitations that are not well-understood and articulated by the literature. We analyze three commonly overlooked factors in concept-based explanations.
  arXiv  Detail & Related papers  (2022-07-20T01:59:39Z)
• On the Objective Evaluation of Post Hoc Explainers [10.981508361941335]
  Modern trends in machine learning research have led to algorithms that are increasingly intricate to the degree that they are considered to be black boxes. In an effort to reduce the opacity of decisions, methods have been proposed to construe the inner workings of such models in a human-comprehensible manner. We propose a framework for the evaluation of post hoc explainers on ground truth that is directly derived from the additive structure of a model.
  arXiv  Detail & Related papers  (2021-06-15T19:06:51Z)
• CURI: A Benchmark for Productive Concept Learning Under Uncertainty [33.83721664338612]
  We introduce a new few-shot, meta-learning benchmark, Compositional Reasoning Under Uncertainty (CURI) CURI evaluates different aspects of productive and systematic generalization, including abstract understandings of disentangling, productive generalization, learning operations, variable binding, etc. It also defines a model-independent "compositionality gap" to evaluate the difficulty of generalizing out-of-distribution along each of these axes.
  arXiv  Detail & Related papers  (2020-10-06T16:23:17Z)
• Evaluations and Methods for Explanation through Robustness Analysis [117.7235152610957]
  We establish a novel set of evaluation criteria for such feature based explanations by analysis. We obtain new explanations that are loosely necessary and sufficient for a prediction. We extend the explanation to extract the set of features that would move the current prediction to a target class.
  arXiv  Detail & Related papers  (2020-05-31T05:52:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.