{"total":246,"rows":[{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320,"area":null},{"id":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127,"area":null},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"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":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105,"area":null},{"id":"2205.07424","title":"Trustworthy Graph Neural Networks: Aspects, Methods and Trends","created":"2022-05-16","cited_by_count":89,"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":"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":"2104.10482","title":"GraphSVX: Shapley Value Explanations for Graph Neural Networks","created":"2021-04-18","cited_by_count":64,"area":null},{"id":"2103.01890","title":"Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations","created":"2021-03-02","cited_by_count":59,"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":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2201.12380","title":"GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games","created":"2022-01-28","cited_by_count":42,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"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":"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":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","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":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"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":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36,"area":null},{"id":"2106.06468","title":"Locally Sparse Neural Networks for Tabular Biomedical Data","created":"2021-06-11","cited_by_count":34,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"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":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","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":"2206.05075","title":"Diffeomorphic Counterfactuals with Generative Models","created":"2022-06-10","cited_by_count":29,"area":null},{"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":"2302.13080","title":"Does a Neural Network Really Encode Symbolic Concepts?","created":"2023-02-25","cited_by_count":27,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"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":"2302.13091","title":"Explaining Generalization Power of a DNN Using Interactive Concepts","created":"2023-02-25","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":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2110.05304","title":"You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction","created":"2021-10-11","cited_by_count":23,"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":"2212.03840","title":"Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations","created":"2022-12-07","cited_by_count":22,"area":null},{"id":"2206.12987","title":"FlowX: Towards Explainable Graph Neural Networks via Message Flows","created":"2022-06-26","cited_by_count":21,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2110.14297","title":"Revisiting Sanity Checks for Saliency Maps","created":"2021-10-27","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":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18,"area":null},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2211.14736","title":"Attribution-based XAI Methods in Computer Vision: A Review","created":"2022-11-27","cited_by_count":16,"area":null},{"id":"2303.11932","title":"Studying How to Efficiently and Effectively Guide Models with Explanations","created":"2023-03-21","cited_by_count":16,"area":null},{"id":"2303.14242","title":"IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients","created":"2023-03-24","cited_by_count":16,"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":"2503.13891","title":"Where do Large Vision-Language Models Look at when Answering Questions?","created":"2025-03-18","cited_by_count":15,"area":"mllm"},{"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":"2302.03225","title":"Efficient XAI Techniques: A Taxonomic Survey","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2211.13735","title":"Explainable Model-Agnostic Similarity and Confidence in Face Verification","created":"2022-11-24","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":"2111.09624","title":"IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration","created":"2021-11-18","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":"2206.05275","title":"Spatial-temporal Concept based Explanation of 3D ConvNets","created":"2022-06-09","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":"2304.13312","title":"Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs","created":"2023-04-26","cited_by_count":12,"area":null},{"id":"2308.05362","title":"FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis","created":"2023-08-10","cited_by_count":12,"area":null},{"id":"2310.08837","title":"Static Code Analysis in the AI Era: An In-depth Exploration of the Concept, Function, and Potential of Intelligent Code Analysis Agents","created":"2023-10-13","cited_by_count":12,"area":"agents"},{"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":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11,"area":null},{"id":"2305.08546","title":"Towards Visual Saliency Explanations of Face Verification","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2402.00281","title":"Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues","created":"2024-02-01","cited_by_count":11,"area":null},{"id":"2103.00752","title":"Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2105.10719","title":"Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?","created":"2021-05-22","cited_by_count":10,"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":"2205.13282","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","created":"2022-05-26","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":"2307.15007","title":"Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2310.15368","title":"Deep Integrated Explanations","created":"2023-10-23","cited_by_count":10,"area":null},{"id":"2312.02364","title":"Class-Discriminative Attention Maps for Vision Transformers","created":"2023-12-04","cited_by_count":10,"area":null},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2108.02646","title":"A Hypothesis for the Aesthetic Appreciation in Neural Networks","created":"2021-07-31","cited_by_count":9,"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":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2303.01538","title":"Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2105.07033","title":"Cause and Effect: Hierarchical Concept-based Explanation of Neural Networks","created":"2021-05-14","cited_by_count":8,"area":null},{"id":"2201.05077","title":"Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering","created":"2022-01-13","cited_by_count":8,"area":null},{"id":"2205.09901","title":"Cardinality-Minimal Explanations for Monotonic Neural Networks","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2304.04824","title":"Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning","created":"2023-04-10","cited_by_count":8,"area":null},{"id":"2305.15734","title":"On the Impact of Knowledge Distillation for Model Interpretability","created":"2023-05-25","cited_by_count":8,"area":"distill"},{"id":"2101.01032","title":"Local Black-box Adversarial Attacks: A Query Efficient Approach","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2101.10977","title":"Evaluating Input Perturbation Methods for Interpreting CNNs and Saliency Map Comparison","created":"2021-01-26","cited_by_count":7,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2203.02928","title":"Fidelity of Interpretability Methods and Perturbation Artifacts in Neural Networks","created":"2022-03-06","cited_by_count":7,"area":null}],"next_cursor":"100"}