{"total":25,"rows":[{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2212.06727","title":"What do Vision Transformers Learn? A Visual Exploration","created":"2022-12-13","cited_by_count":76,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2310.04420","title":"BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity","created":"2023-10-06","cited_by_count":19,"area":null},{"id":"2309.09901","title":"The role of causality in explainable artificial intelligence","created":"2023-09-18","cited_by_count":17,"area":null},{"id":"2212.06872","title":"Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods","created":"2022-12-13","cited_by_count":12,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2305.17023","title":"Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2312.04712","title":"Error Discovery by Clustering Influence Embeddings","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2402.10039","title":"Feature Accentuation: Revealing 'What' Features Respond to in Natural Images","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2403.11219","title":"Causality from Bottom to Top: A Survey","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2411.03993","title":"Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations","created":"2024-11-06","cited_by_count":5,"area":null},{"id":"2506.00698","title":"Concept-Centric Token Interpretation for Vector-Quantized Generative Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2503.22399","title":"VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2309.10989","title":"COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2512.12307","title":"MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2406.01365","title":"From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2406.05598","title":"Understanding Inhibition Through Maximally Tense Images","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2502.01490","title":"MoireDB: Formula-generated Interference-fringe Image Dataset","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2507.22832","title":"Pulling Back the Curtain on Deep Networks","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2511.04312","title":"Probing the Probes: Methods and Metrics for Concept Alignment","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}