{"total":81,"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":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2111.02398","title":"Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods","created":"2021-11-01","cited_by_count":83,"area":null},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73,"area":null},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68,"area":null},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61,"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":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"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":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2104.11914","title":"EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case","created":"2021-04-24","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":"2202.03407","title":"Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2202.03482","title":"Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","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},{"id":"2108.10346","title":"Explaining Bayesian Neural Networks","created":"2021-08-23","cited_by_count":18,"area":null},{"id":"2111.07473","title":"Scrutinizing XAI using linear ground-truth data with suppressor variables","created":"2021-11-14","cited_by_count":18,"area":null},{"id":"2106.10938","title":"A Game-Theoretic Taxonomy of Visual Concepts in DNNs","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2108.05312","title":"Towards Interpretable Deep Networks for Monocular Depth Estimation","created":"2021-08-11","cited_by_count":12,"area":null},{"id":"2111.03549","title":"Interpreting Representation Quality of DNNs for 3D Point Cloud Processing","created":"2021-11-05","cited_by_count":12,"area":null},{"id":"2306.01464","title":"Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables","created":"2023-06-02","cited_by_count":12,"area":null},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2212.13261","title":"Explainable AI for Bioinformatics: Methods, Tools, and Applications","created":"2022-12-25","cited_by_count":11,"area":null},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","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":"2302.02162","title":"AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models","created":"2023-02-04","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":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2210.17376","title":"SoK: Modeling Explainability in Security Analytics for Interpretability, Trustworthiness, and Usability","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2306.12816","title":"XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance","created":"2023-06-22","cited_by_count":7,"area":null},{"id":"2103.10229","title":"Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profiles","created":"2021-03-18","cited_by_count":6,"area":null},{"id":"2111.13208","title":"Evaluation of Interpretability for Deep Learning algorithms in EEG Emotion Recognition: A case study in Autism","created":"2021-11-25","cited_by_count":6,"area":null},{"id":"2201.09205","title":"Deeply Explain CNN via Hierarchical Decomposition","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2311.06996","title":"AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2409.14590","title":"Explainable AI needs formalization","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2101.07312","title":"Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2107.02661","title":"Does Dataset Complexity Matters for Model Explainers?","created":"2021-07-06","cited_by_count":4,"area":null},{"id":"2108.04126","title":"Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf","created":"2021-08-09","cited_by_count":4,"area":null},{"id":"2301.08525","title":"Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research","created":"2023-01-20","cited_by_count":4,"area":null},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2103.11526","title":"ExAD: An Ensemble Approach for Explanation-based Adversarial Detection","created":"2021-03-22","cited_by_count":3,"area":null},{"id":"2104.06629","title":"Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2108.06896","title":"Challenges for cognitive decoding using deep learning methods","created":"2021-08-16","cited_by_count":3,"area":null},{"id":"2112.04882","title":"Evaluating saliency methods on artificial data with different background types","created":"2021-12-09","cited_by_count":3,"area":null},{"id":"2204.03528","title":"Visualizing Deep Neural Networks with Topographic Activation Maps","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2211.08425","title":"A Rigorous Study Of The Deep Taylor Decomposition","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2311.11491","title":"On the Relationship Between Interpretability and Explainability in Machine Learning","created":"2023-11-20","cited_by_count":3,"area":null},{"id":"2101.11889","title":"Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling","created":"2021-01-28","cited_by_count":2,"area":null},{"id":"2109.13412","title":"Discriminative Attribution from Counterfactuals","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2205.01940","title":"Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs","created":"2022-05-04","cited_by_count":2,"area":null},{"id":"2302.03318","title":"PAMI: partition input and aggregate outputs for model interpretation","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2307.09615","title":"Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2402.09197","title":"Implementing local-explainability in Gradient Boosting Trees: Feature Contribution","created":"2024-02-14","cited_by_count":2,"area":null},{"id":"2408.04600","title":"Improving Network Interpretability via Explanation Consistency Evaluation","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2101.06773","title":"Generating Attribution Maps with Disentangled Masked Backpropagation","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2411.10692","title":"DEBUG-HD: Debugging TinyML models on-device using Hyper-Dimensional computing","created":"2024-11-16","cited_by_count":1,"area":null},{"id":"2501.07801","title":"A Comparative Analysis of DNN-based White-Box Explainable AI Methods in Network Security","created":"2025-01-14","cited_by_count":1,"area":null},{"id":"2505.07005","title":"Explainable AI the Latest Advancements and New Trends","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2505.11210","title":"Minimizing False-Positive Attributions in Explanations of Non-Linear Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2602.08715","title":"Exploring SAIG Methods for an Objective Evaluation of XAI","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2602.09278","title":"The effect of whitening on explanation performance","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2102.07332","title":"Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2108.11054","title":"Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images","created":"2021-08-25","cited_by_count":0,"area":null},{"id":"2112.15571","title":"PCACE: A Statistical Approach to Ranking Neurons for CNN Interpretability","created":"2021-12-31","cited_by_count":0,"area":null},{"id":"2203.13120","title":"Feature visualization for convolutional neural network models trained on neuroimaging data","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2204.00617","title":"Visual explanations for polyp detection: How medical doctors assess intrinsic versus extrinsic explanations","created":"2022-03-23","cited_by_count":0,"area":null},{"id":"2206.01343","title":"HEX: Human-in-the-loop Explainability via Deep Reinforcement Learning","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2207.07769","title":"Anomalous behaviour in loss-gradient based interpretability methods","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2210.10849","title":"Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction","created":"2022-10-19","cited_by_count":0,"area":null},{"id":"2210.17360","title":"Explainable Deep Learning to Profile Mitochondrial Disease Using High Dimensional Protein Expression Data","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2211.04693","title":"Deep Explainable Learning with Graph Based Data Assessing and Rule Reasoning","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2211.10061","title":"Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation","created":"2022-11-18","cited_by_count":0,"area":null},{"id":"2312.08157","title":"CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2506.03664","title":"Assessing Intersectional Bias in Representations of Pre-Trained Image Recognition Models","created":"2025-06-04","cited_by_count":0,"area":null}],"next_cursor":null}