{"total":838,"rows":[{"id":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386,"area":"diffusion"},{"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":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2202.01602","title":"The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective","created":"2022-02-03","cited_by_count":159,"area":null},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126,"area":null},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105,"area":null},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2202.00449","title":"A Consistent and Efficient Evaluation Strategy for Attribution Methods","created":"2022-02-01","cited_by_count":102,"area":null},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"area":null},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2203.15636","title":"Diffusion Models for Counterfactual Explanations","created":"2022-03-29","cited_by_count":79,"area":"diffusion"},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78,"area":null},{"id":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73,"area":"lr"},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"area":null},{"id":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65,"area":null},{"id":"2310.16228","title":"On the Foundations of Shortcut Learning","created":"2023-10-24","cited_by_count":65,"area":null},{"id":"2202.11912","title":"A Rigorous Study of Integrated Gradients Method and Extensions to Internal Neuron Attributions","created":"2022-02-24","cited_by_count":64,"area":null},{"id":"2210.03735","title":"\"Help Me Help the AI\": Understanding How Explainability Can Support Human-AI Interaction","created":"2022-10-02","cited_by_count":63,"area":null},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55,"area":null},{"id":"2104.00032","title":"Convolutional Dynamic Alignment Networks for Interpretable Classifications","created":"2021-03-31","cited_by_count":54,"area":null},{"id":"2402.10086","title":"Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"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":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2102.05228","title":"Towards Better Explanations of Class Activation Mapping","created":"2021-02-10","cited_by_count":47,"area":null},{"id":"2106.02740","title":"ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes","created":"2021-06-04","cited_by_count":47,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46,"area":null},{"id":"2306.09346","title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","created":"2023-06-15","cited_by_count":46,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2212.08158","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","created":"2022-12-15","cited_by_count":43,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2201.13291","title":"Metrics for saliency map evaluation of deep learning explanation methods","created":"2022-01-31","cited_by_count":40,"area":null},{"id":"2205.07277","title":"Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations","created":"2022-05-15","cited_by_count":40,"area":null},{"id":"2202.07728","title":"Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis","created":"2022-02-15","cited_by_count":38,"area":null},{"id":"2206.03740","title":"Large Loss Matters in Weakly Supervised Multi-Label Classification","created":"2022-06-08","cited_by_count":38,"area":null},{"id":"2301.04011","title":"Learning Support and Trivial Prototypes for Interpretable Image Classification","created":"2023-01-08","cited_by_count":38,"area":null},{"id":"2305.10289","title":"Explain Any Concept: Segment Anything Meets Concept-Based Explanation","created":"2023-05-17","cited_by_count":37,"area":null},{"id":"2103.13859","title":"Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks","created":"2021-03-25","cited_by_count":36,"area":null},{"id":"2209.13429","title":"WeightedSHAP: analyzing and improving Shapley based feature attributions","created":"2022-09-27","cited_by_count":36,"area":null},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2312.17174","title":"Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution","created":"2023-12-28","cited_by_count":34,"area":"mllm"},{"id":"2403.10415","title":"Gradient based Feature Attribution in Explainable AI: A Technical Review","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2203.15064","title":"Cycle-Consistent Counterfactuals by Latent Transformations","created":"2022-03-28","cited_by_count":33,"area":null},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33,"area":null},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2205.04766","title":"Explainable Deep Learning Methods in Medical Image Classification: A Survey","created":"2022-05-10","cited_by_count":32,"area":null},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","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":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2106.10649","title":"CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency","created":"2021-06-20","cited_by_count":28,"area":null},{"id":"2205.10435","title":"Towards Better Understanding Attribution Methods","created":"2022-05-20","cited_by_count":28,"area":null},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","cited_by_count":28,"area":null},{"id":"2309.07944","title":"Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach","created":"2023-09-14","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":"2410.08417","title":"Bilinear MLPs enable weight-based mechanistic interpretability","created":"2024-10-10","cited_by_count":28,"area":"mechinterp"},{"id":"2510.12252","title":"PromptLocate: Localizing Prompt Injection Attacks","created":"2025-10-14","cited_by_count":28,"area":"safety"},{"id":"2107.14317","title":"Temporal Dependencies in Feature Importance for Time Series Predictions","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2303.00652","title":"Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science","created":"2023-03-01","cited_by_count":27,"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":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2108.01070","title":"Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution","created":"2021-08-02","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":"2207.06236","title":"Explainable Intrusion Detection Systems (X-IDS): A Survey of Current Methods, Challenges, and Opportunities","created":"2022-07-13","cited_by_count":25,"area":null},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","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":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","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":"2206.04394","title":"Xplique: A Deep Learning Explainability Toolbox","created":"2022-06-09","cited_by_count":24,"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":"2401.10831","title":"Understanding Video Transformers via Universal Concept Discovery","created":"2024-01-19","cited_by_count":23,"area":"mechinterp"},{"id":"2211.05667","title":"What Makes a Good Explanation?: A Harmonized View of Properties of Explanations","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21,"area":null},{"id":"2111.04927","title":"Self-Interpretable Model with TransformationEquivariant Interpretation","created":"2021-11-09","cited_by_count":21,"area":null},{"id":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21,"area":null},{"id":"2207.03648","title":"Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks","created":"2022-07-08","cited_by_count":20,"area":null},{"id":"2208.14966","title":"Concept Gradient: Concept-based Interpretation Without Linear Assumption","created":"2022-08-31","cited_by_count":20,"area":null},{"id":"2301.10908","title":"Distilling Cognitive Backdoor Patterns within an Image","created":"2023-01-26","cited_by_count":20,"area":null},{"id":"2303.02794","title":"CoRTX: Contrastive Framework for Real-time Explanation","created":"2023-03-05","cited_by_count":20,"area":null},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"area":null},{"id":"2202.12270","title":"Evaluating Feature Attribution Methods in the Image Domain","created":"2022-02-22","cited_by_count":19,"area":null},{"id":"2306.07462","title":"On the Robustness of Removal-Based Feature Attributions","created":"2023-06-12","cited_by_count":19,"area":null},{"id":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2510.25785","title":"HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series","created":"2025-10-28","cited_by_count":19,"area":null},{"id":"2103.10005","title":"Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset","created":"2021-03-18","cited_by_count":18,"area":null}],"next_cursor":"100"}