{"total":119,"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":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"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":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","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":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71,"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":"2206.07835","title":"Disentangling visual and written concepts in CLIP","created":"2022-06-15","cited_by_count":58,"area":null},{"id":"2106.12723","title":"Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations","created":"2021-06-24","cited_by_count":53,"area":null},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52,"area":null},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"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":"2303.13664","title":"Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data","created":"2023-03-23","cited_by_count":44,"area":null},{"id":"2309.16928","title":"Learning to Receive Help: Intervention-Aware Concept Embedding Models","created":"2023-09-29","cited_by_count":41,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2207.09679","title":"Explaining Deepfake Detection by Analysing Image Matching","created":"2022-07-20","cited_by_count":34,"area":null},{"id":"2307.10504","title":"Identifying Interpretable Subspaces in Image Representations","created":"2023-07-20","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":"2204.02735","title":"Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck","created":"2022-04-06","cited_by_count":30,"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":"2309.07742","title":"Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning","created":"2023-09-14","cited_by_count":22,"area":null},{"id":"2203.13909","title":"Concept Embedding Analysis: A Review","created":"2022-03-25","cited_by_count":20,"area":null},{"id":"2405.06855","title":"Linear Explanations for Individual Neurons","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","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":"2401.17975","title":"Understanding polysemanticity in neural networks through coding theory","created":"2024-01-31","cited_by_count":17,"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":"2107.04474","title":"Interpretable Compositional Convolutional Neural Networks","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2110.02802","title":"Self-conditioning pre-trained language models","created":"2021-09-30","cited_by_count":16,"area":null},{"id":"2307.14517","title":"The Co-12 Recipe for Evaluating Interpretable Part-Prototype Image Classifiers","created":"2023-07-26","cited_by_count":15,"area":null},{"id":"2402.18956","title":"WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts","created":"2024-02-29","cited_by_count":14,"area":null},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","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":"2108.05312","title":"Towards Interpretable Deep Networks for Monocular Depth Estimation","created":"2021-08-11","cited_by_count":12,"area":null},{"id":"2108.12931","title":"NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks","created":"2021-08-29","cited_by_count":12,"area":null},{"id":"2112.10161","title":"RELAX: Representation Learning Explainability","created":"2021-12-19","cited_by_count":12,"area":null},{"id":"2105.07371","title":"Expressive Explanations of DNNs by Combining Concept Analysis with ILP","created":"2021-05-16","cited_by_count":11,"area":null},{"id":"2304.14864","title":"Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2206.07690","title":"ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2105.06727","title":"Verification of Size Invariance in DNN Activations using Concept Embeddings","created":"2021-05-14","cited_by_count":9,"area":null},{"id":"2104.06118","title":"Automatic Correction of Internal Units in Generative Neural Networks","created":"2021-04-13","cited_by_count":8,"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":"2204.05899","title":"VisCUIT: Visual Auditor for Bias in CNN Image Classifier","created":"2022-04-12","cited_by_count":8,"area":null},{"id":"2206.08500","title":"What do navigation agents learn about their environment?","created":"2022-06-17","cited_by_count":8,"area":null},{"id":"2209.03268","title":"Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing","created":"2022-09-07","cited_by_count":8,"area":null},{"id":"2305.08950","title":"Causal Analysis for Robust Interpretability of Neural Networks","created":"2023-05-15","cited_by_count":8,"area":null},{"id":"2403.14566","title":"A survey on Concept-based Approaches For Model Improvement","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2201.00572","title":"Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings","created":"2022-01-03","cited_by_count":7,"area":null},{"id":"2203.04109","title":"Explaining Classifiers by Constructing Familiar Concepts","created":"2022-03-07","cited_by_count":7,"area":null},{"id":"2206.10611","title":"Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts","created":"2022-06-20","cited_by_count":7,"area":null},{"id":"2311.14435","title":"Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces","created":"2023-11-24","cited_by_count":7,"area":null},{"id":"2109.14170","title":"Semantic Communications With AI Tasks","created":"2021-09-29","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":"2202.09374","title":"Explaining, Evaluating and Enhancing Neural Networks' Learned Representations","created":"2022-02-18","cited_by_count":6,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2403.01231","title":"Benchmarking Segmentation Models with Mask-Preserved Attribute Editing","created":"2024-03-02","cited_by_count":6,"area":null},{"id":"2103.08820","title":"EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry","created":"2021-03-16","cited_by_count":5,"area":null},{"id":"2303.10523","title":"Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations","created":"2023-03-19","cited_by_count":5,"area":null},{"id":"2203.06043","title":"Sparse Subspace Clustering for Concept Discovery (SSCCD)","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2206.01627","title":"Pruning for Feature-Preserving Circuits in CNNs","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2211.12173","title":"Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models","created":"2022-11-22","cited_by_count":4,"area":null},{"id":"2305.07663","title":"Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces","created":"2023-04-30","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":"2108.06384","title":"Finding Representative Interpretations on Convolutional Neural Networks","created":"2021-08-13","cited_by_count":3,"area":null},{"id":"2203.16475","title":"Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries","created":"2022-03-30","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":"2602.23947","title":"Hierarchical Concept-based Interpretable Models","created":"2026-02-27","cited_by_count":3,"area":null},{"id":"2104.02922","title":"Sparse Oblique Decision Trees: A Tool to Understand and Manipulate Neural Net Features","created":"2021-04-07","cited_by_count":2,"area":null},{"id":"2312.12068","title":"PICNN: A Pathway towards Interpretable Convolutional Neural Networks","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2312.17285","title":"Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2405.17523","title":"Locally Testing Model Detections for Semantic Global Concepts","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2411.19700","title":"Multi-Depth Concept Extraction for Post-Hoc Vision Encoder Explanation","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2603.01535","title":"Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2102.05917","title":"PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2204.10529","title":"Exploring Hidden Semantics in Neural Networks with Symbolic Regression","created":"2022-04-22","cited_by_count":1,"area":null},{"id":"2209.13517","title":"Conceptual Views of Neural Networks: A Framework for Neuro-Symbolic Analysis","created":"2022-09-27","cited_by_count":1,"area":null},{"id":"2303.15632","title":"UFO: A unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations for CNNs","created":"2023-03-27","cited_by_count":1,"area":null},{"id":"2405.01661","title":"When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2407.14792","title":"FedPartWhole: Federated domain generalization via consistent part-whole hierarchies","created":"2024-07-20","cited_by_count":1,"area":null},{"id":"2409.03805","title":"Exploratory Visual Analysis for Increasing Data Readiness in Artificial Intelligence Projects","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2409.17109","title":"Unveiling Ontological Commitment in Multi-Modal Foundation Models","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.08455","title":"Why pre-training is beneficial for downstream classification tasks?","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2504.08602","title":"On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2509.23849","title":"CE-FAM: Concept-Based Explanation via Fusion of Activation Maps","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2106.04693","title":"On the Evolution of Neuron Communities in a Deep Learning Architecture","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2109.09389","title":"Explaining Convolutional Neural Networks by Tagging Filters","created":"2021-09-20","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":"2208.09717","title":"Learning Primitive-aware Discriminative Representations for Few-shot Learning","created":"2022-08-20","cited_by_count":0,"area":null},{"id":"2212.06576","title":"AI Model Utilization Measurements For Finding Class Encoding Patterns","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2305.10121","title":"FICNN: A Framework for the Interpretation of Deep Convolutional Neural Networks","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2308.10019","title":"Dissecting RGB-D Learning for Improved Multi-modal Fusion","created":"2023-08-19","cited_by_count":0,"area":null},{"id":"2309.14715","title":"Explaining Deep Face Algorithms through Visualization: A Survey","created":"2023-09-26","cited_by_count":0,"area":null},{"id":"2312.05864","title":"Finding Concept Representations in Neural Networks with Self-Organizing Maps","created":"2023-12-10","cited_by_count":0,"area":null},{"id":"2403.16782","title":"The Anatomy of Adversarial Attacks: Concept-based XAI Dissection","created":"2024-03-25","cited_by_count":0,"area":null}],"next_cursor":"100"}