{"total":180,"rows":[{"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":"2206.12654","title":"BackdoorBench: A Comprehensive Benchmark of Backdoor Learning","created":"2022-06-25","cited_by_count":128,"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":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"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":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96,"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":"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":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66,"area":null},{"id":"2106.12543","title":"Synthetic Benchmarks for Scientific Research in Explainable Machine Learning","created":"2021-06-23","cited_by_count":59,"area":null},{"id":"2104.00032","title":"Convolutional Dynamic Alignment Networks for Interpretable Classifications","created":"2021-03-31","cited_by_count":54,"area":null},{"id":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2104.02297","title":"Shapley Explanation Networks","created":"2021-04-06","cited_by_count":41,"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":"2409.06219","title":"Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learning","created":"2024-09-10","cited_by_count":35,"area":null},{"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":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","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":"2205.07972","title":"Sparse Visual Counterfactual Explanations in Image Space","created":"2022-05-16","cited_by_count":30,"area":null},{"id":"2205.10435","title":"Towards Better Understanding Attribution Methods","created":"2022-05-20","cited_by_count":28,"area":null},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26,"area":null},{"id":"2208.11342","title":"Discovering Transferable Forensic Features for CNN-generated Images Detection","created":"2022-08-24","cited_by_count":24,"area":null},{"id":"2104.07235","title":"Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification","created":"2021-04-15","cited_by_count":21,"area":null},{"id":"2203.02269","title":"Do Explanations Explain? Model Knows Best","created":"2022-03-04","cited_by_count":20,"area":null},{"id":"2205.02049","title":"Self-Supervised Learning for Invariant Representations from Multi-Spectral and SAR Images","created":"2022-05-04","cited_by_count":20,"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":"2207.11025","title":"Custom Structure Preservation in Face Aging","created":"2022-07-22","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":"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":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","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":"2102.07805","title":"Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring","created":"2021-02-15","cited_by_count":16,"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":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2109.04954","title":"Saliency Guided Experience Packing for Replay in Continual Learning","created":"2021-09-10","cited_by_count":15,"area":null},{"id":"2208.00781","title":"Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods","created":"2022-07-26","cited_by_count":15,"area":null},{"id":"2409.19660","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","created":"2024-09-29","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":"2108.13828","title":"PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs","created":"2021-08-31","cited_by_count":12,"area":null},{"id":"2411.00715","title":"B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2502.20134","title":"Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2102.07799","title":"Ada-SISE: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2304.11744","title":"SketchXAI: A First Look at Explainability for Human Sketches","created":"2023-04-23","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":"2407.04370","title":"Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2507.10846","title":"Winsor-CAM: Human-Tunable Visual Explanations from Deep Networks via Layer-Wise Winsorization","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2209.14881","title":"Sequential Attention for Feature Selection","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2301.08669","title":"Holistically Explainable Vision Transformers","created":"2023-01-20","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":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","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":"2301.06989","title":"Negative Flux Aggregation to Estimate Feature Attributions","created":"2023-01-17","cited_by_count":7,"area":null},{"id":"2312.13630","title":"MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2407.09115","title":"Layer-Wise Relevance Propagation with Conservation Property for ResNet","created":"2024-07-12","cited_by_count":7,"area":null},{"id":"2108.01335","title":"Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability","created":"2021-08-03","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":"2310.16316","title":"Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2402.03348","title":"Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition","created":"2024-01-25","cited_by_count":6,"area":null},{"id":"2404.11330","title":"Toward Understanding the Disagreement Problem in Neural Network Feature Attribution","created":"2024-04-17","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":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2106.12773","title":"Evaluation of Saliency-based Explainability Method","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2402.10039","title":"Feature Accentuation: Revealing 'What' Features Respond to in Natural Images","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2407.19308","title":"Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2506.03484","title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2301.04970","title":"Hierarchical Dynamic Masks for Visual Explanation of Neural Networks","created":"2023-01-12","cited_by_count":4,"area":null},{"id":"2301.13445","title":"A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2303.11884","title":"Better Understanding Differences in Attribution Methods via Systematic Evaluations","created":"2023-03-21","cited_by_count":4,"area":null},{"id":"2310.16584","title":"Learning to Explain: A Model-Agnostic Framework for Explaining Black Box Models","created":"2023-10-25","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":"2507.23497","title":"Sufficient, Necessary and Complete Causal Explanations in Image Classification","created":"2025-07-31","cited_by_count":4,"area":null},{"id":"2602.06613","title":"DAVE: Distribution-aware Attribution via ViT Gradient Decomposition","created":"2026-02-06","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":"2207.03324","title":"Calibrate to Interpret","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2305.14395","title":"Towards credible visual model interpretation with path attribution","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2307.11513","title":"Bone mineral density estimation from a plain X-ray image by learning decomposition into projections of bone-segmented computed tomography","created":"2023-07-21","cited_by_count":3,"area":null},{"id":"2311.13297","title":"Retargeting Visual Data with Deformation Fields","created":"2023-11-22","cited_by_count":3,"area":null},{"id":"2408.16395","title":"IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology","created":"2024-08-29","cited_by_count":3,"area":null},{"id":"2410.05085","title":"Explanation sensitivity to the randomness of large language models: the case of journalistic text classification","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2412.01202","title":"Neuron Abandoning Attention Flow: Visual Explanation of Dynamics inside CNN Models","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2502.17469","title":"PixleepFlow: A Pixel-Based Lifelog Framework for Predicting Sleep Quality and Stress Level","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2503.20685","title":"Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound","created":"2025-03-26","cited_by_count":3,"area":null},{"id":"2503.22881","title":"Pairwise Matching of Intermediate Representations for Fine-grained Explainability","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2504.06800","title":"A Meaningful Perturbation Metric for Evaluating Explainability Methods","created":"2025-04-09","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":"2106.15067","title":"Towards Understanding the Effectiveness of Attention Mechanism","created":"2021-06-29","cited_by_count":2,"area":null},{"id":"2110.05182","title":"TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2206.02761","title":"Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2209.04326","title":"Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System","created":"2022-09-09","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":"2303.14608","title":"Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability","created":"2023-03-26","cited_by_count":2,"area":null},{"id":"2303.17836","title":"Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers","created":"2023-03-31","cited_by_count":2,"area":null},{"id":"2305.12178","title":"Model Debiasing via Gradient-based Explanation on Representation","created":"2023-05-20","cited_by_count":2,"area":null},{"id":"2309.01955","title":"A Survey on Interpretable Cross-modal Reasoning","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2405.02344","title":"A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions","created":"2024-05-02","cited_by_count":2,"area":null}],"next_cursor":"100"}