{"total":144,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2103.08907","title":"BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation","created":"2021-03-16","cited_by_count":105,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"area":null},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2103.10226","title":"Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations","created":"2021-03-18","cited_by_count":56,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2111.09094","title":"STEEX: Steering Counterfactual Explanations with Semantics","created":"2021-11-17","cited_by_count":40,"area":null},{"id":"2101.12446","title":"Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning","created":"2021-01-29","cited_by_count":39,"area":null},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2106.01127","title":"Towards Robust Classification Model by Counterfactual and Invariant Data Generation","created":"2021-06-02","cited_by_count":30,"area":null},{"id":"2203.12892","title":"Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals","created":"2022-03-24","cited_by_count":30,"area":null},{"id":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","cited_by_count":29,"area":null},{"id":"2211.12380","title":"OCTET: Object-aware Counterfactual Explanations","created":"2022-11-22","cited_by_count":28,"area":null},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28,"area":null},{"id":"2107.14317","title":"Temporal Dependencies in Feature Importance for Time Series Predictions","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2103.13701","title":"ECINN: Efficient Counterfactuals from Invertible Neural Networks","created":"2021-03-25","cited_by_count":26,"area":null},{"id":"2104.10252","title":"Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis","created":"2021-04-20","cited_by_count":25,"area":null},{"id":"2301.07002","title":"Opti-CAM: Optimizing saliency maps for interpretability","created":"2023-01-17","cited_by_count":25,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2110.15499","title":"UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models","created":"2021-10-29","cited_by_count":23,"area":null},{"id":"2202.12451","title":"Human-Centered Concept Explanations for Neural Networks","created":"2022-02-25","cited_by_count":23,"area":null},{"id":"2208.03608","title":"Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value","created":"2022-08-07","cited_by_count":23,"area":null},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"area":null},{"id":"2112.05746","title":"On Causally Disentangled Representations","created":"2021-12-10","cited_by_count":22,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2207.02812","title":"Towards Counterfactual Image Manipulation via CLIP","created":"2022-07-06","cited_by_count":19,"area":null},{"id":"2109.11495","title":"DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications","created":"2021-09-23","cited_by_count":18,"area":null},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2305.12895","title":"DEGREE: Decomposition Based Explanation For Graph Neural Networks","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2307.07832","title":"MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation","created":"2023-07-15","cited_by_count":18,"area":null},{"id":"2206.07387","title":"The Manifold Hypothesis for Gradient-Based Explanations","created":"2022-06-15","cited_by_count":16,"area":null},{"id":"2109.14274","title":"Designing Counterfactual Generators using Deep Model Inversion","created":"2021-09-29","cited_by_count":15,"area":null},{"id":"2110.03485","title":"Cartoon Explanations of Image Classifiers","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2105.06677","title":"XAI Handbook: Towards a Unified Framework for Explainable AI","created":"2021-05-14","cited_by_count":14,"area":null},{"id":"2108.09451","title":"Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model","created":"2021-08-21","cited_by_count":14,"area":null},{"id":"2410.12591","title":"Rethinking Visual Counterfactual Explanations Through Region Constraint","created":"2024-10-16","cited_by_count":14,"area":null},{"id":"2204.11642","title":"Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset","created":"2022-04-25","cited_by_count":13,"area":null},{"id":"2403.13086","title":"Listenable Maps for Audio Classifiers","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2103.14332","title":"Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation","created":"2021-03-26","cited_by_count":12,"area":null},{"id":"2107.14000","title":"Resisting Out-of-Distribution Data Problem in Perturbation of XAI","created":"2021-07-27","cited_by_count":12,"area":null},{"id":"2205.11266","title":"What You See is What You Classify: Black Box Attributions","created":"2022-05-23","cited_by_count":12,"area":null},{"id":"2212.08733","title":"Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differ","created":"2022-12-16","cited_by_count":12,"area":null},{"id":"2304.06354","title":"ODAM: Gradient-based instance-specific visual explanations for object detection","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2110.08252","title":"A Rate-Distortion Framework for Explaining Black-box Model Decisions","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2408.03915","title":"Hard to Explain: On the Computational Hardness of In-Distribution Model Interpretation","created":"2024-08-07","cited_by_count":11,"area":null},{"id":"2412.15619","title":"Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning","created":"2024-12-20","cited_by_count":11,"area":null},{"id":"2201.08802","title":"Deconfounding to Explanation Evaluation in Graph Neural Networks","created":"2022-01-21","cited_by_count":10,"area":null},{"id":"2211.02912","title":"New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2306.01630","title":"A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2110.07120","title":"Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2204.00492","title":"Provable concept learning for interpretable predictions using variational autoencoders","created":"2022-04-01","cited_by_count":9,"area":null},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2210.13389","title":"A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems","created":"2022-10-24","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2207.11175","title":"Explaining Dynamic Graph Neural Networks via Relevance Back-propagation","created":"2022-07-22","cited_by_count":8,"area":null},{"id":"2211.14646","title":"Towards Improved Input Masking for Convolutional Neural Networks","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2403.07733","title":"Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2407.11910","title":"Benchmarking the Attribution Quality of Vision Models","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2106.14556","title":"Contrastive Counterfactual Visual Explanations With Overdetermination","created":"2021-06-28","cited_by_count":7,"area":null},{"id":"2111.00177","title":"On Quantitative Evaluations of Counterfactuals","created":"2021-10-30","cited_by_count":7,"area":null},{"id":"2211.12857","title":"Explaining Image Classifiers with Multiscale Directional Image Representation","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2407.15360","title":"Dissecting Multiplication in Transformers: Insights into LLMs","created":"2024-07-22","cited_by_count":7,"area":null},{"id":"2112.02747","title":"Making a Bird AI Expert Work for You and Me","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2305.03601","title":"Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2406.07961","title":"Accurate Explanation Model for Image Classifiers using Class Association Embedding","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2105.10238","title":"An Interpretable Approach to Automated Severity Scoring in Pelvic Trauma","created":"2021-05-21","cited_by_count":5,"area":null},{"id":"2108.06898","title":"Neural-to-Tree Policy Distillation with Policy Improvement Criterion","created":"2021-08-16","cited_by_count":5,"area":null},{"id":"2110.06863","title":"Improving Users' Mental Model with Attention-directed Counterfactual Edits","created":"2021-10-13","cited_by_count":5,"area":null},{"id":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2110.14927","title":"Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Network","created":"2021-10-28","cited_by_count":5,"area":null},{"id":"2201.11674","title":"Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities","created":"2022-01-27","cited_by_count":4,"area":null},{"id":"2207.01917","title":"GLANCE: Global to Local Architecture-Neutral Concept-based Explanations","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2302.01416","title":"Neural Insights for Digital Marketing Content Design","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2503.18629","title":"Towards Human-Understandable Multi-Dimensional Concept Discovery","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2207.01916","title":"Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models","created":"2022-07-05","cited_by_count":3,"area":"lr"},{"id":"2207.03324","title":"Calibrate to Interpret","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2211.09859","title":"Data-Centric Debugging: mitigating model failures via targeted data collection","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2307.09050","title":"R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2309.01458","title":"Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning","created":"2023-09-04","cited_by_count":3,"area":null},{"id":"2405.17615","title":"Listenable Maps for Zero-Shot Audio Classifiers","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2103.14712","title":"Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2106.10947","title":"Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2109.06181","title":"When Stability meets Sufficiency: Informative Explanations that do not Overwhelm","created":"2021-09-13","cited_by_count":2,"area":null},{"id":"2205.07774","title":"Gradient-based Counterfactual Explanations using Tractable Probabilistic Models","created":"2022-05-16","cited_by_count":2,"area":null},{"id":"2303.01965","title":"A Lifted Bregman Formulation for the Inversion of Deep Neural Networks","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2305.18143","title":"Reason to explain: Interactive contrastive explanations (REASONX)","created":"2023-05-29","cited_by_count":2,"area":null},{"id":"2307.14825","title":"Simplified Concrete Dropout -- Improving the Generation of Attribution Masks for Fine-grained Classification","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2404.14996","title":"CA-Stream: Attention-based pooling for interpretable image recognition","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2407.03108","title":"How Reliable and Stable are Explanations of XAI Methods?","created":"2024-07-03","cited_by_count":2,"area":null},{"id":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","cited_by_count":2,"area":null}],"next_cursor":"100"}