{"total":582,"rows":[{"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":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"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":"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":"2203.15636","title":"Diffusion Models for Counterfactual Explanations","created":"2022-03-29","cited_by_count":79,"area":"diffusion"},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2207.04978","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","created":"2022-07-11","cited_by_count":78,"area":null},{"id":"2203.00962","title":"Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation","created":"2022-03-02","cited_by_count":75,"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":"2304.12777","title":"Class Attention Transfer Based Knowledge Distillation","created":"2023-04-25","cited_by_count":61,"area":"distill"},{"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":"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":"2303.09962","title":"Adversarial Counterfactual Visual Explanations","created":"2023-03-17","cited_by_count":47,"area":"diffusion"},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44,"area":"distill"},{"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":"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":"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":"2210.08465","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","created":"2022-10-16","cited_by_count":33,"area":null},{"id":"2209.07046","title":"Exploring Visual Interpretability for Contrastive Language-Image Pre-training","created":"2022-09-15","cited_by_count":30,"area":null},{"id":"2308.02062","title":"Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images","created":"2023-08-03","cited_by_count":30,"area":"diffusion"},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29,"area":null},{"id":"2207.04976","title":"Dual Vision Transformer","created":"2022-07-11","cited_by_count":29,"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":"2103.14441","title":"Visual Explanations from Spiking Neural Networks using Interspike Intervals","created":"2021-03-26","cited_by_count":27,"area":null},{"id":"2305.01275","title":"Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation","created":"2023-05-02","cited_by_count":27,"area":null},{"id":"2109.07069","title":"F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling","created":"2021-09-15","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":"2301.07002","title":"Opti-CAM: Optimizing saliency maps for interpretability","created":"2023-01-17","cited_by_count":25,"area":null},{"id":"2502.06755","title":"Interpretable and Testable Vision Features via Sparse Autoencoders","created":"2025-02-10","cited_by_count":25,"area":"mechinterp"},{"id":"2208.11342","title":"Discovering Transferable Forensic Features for CNN-generated Images Detection","created":"2022-08-24","cited_by_count":24,"area":null},{"id":"2211.08129","title":"Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2502.14807","title":"FetalCLIP: A Visual-Language Foundation Model for Fetal Ultrasound Image Analysis","created":"2025-02-20","cited_by_count":24,"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":"2308.12462","title":"Overcoming Generic Knowledge Loss with Selective Parameter Update","created":"2023-08-23","cited_by_count":23,"area":null},{"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":"2302.03985","title":"Cross-Layer Retrospective Retrieving via Layer Attention","created":"2023-02-08","cited_by_count":22,"area":null},{"id":"2103.11257","title":"Robust Models Are More Interpretable Because Attributions Look Normal","created":"2021-03-20","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":"2103.01546","title":"Real Masks and Spoof Faces: On the Masked Face Presentation Attack Detection","created":"2021-03-02","cited_by_count":20,"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":"2305.10727","title":"Boost Vision Transformer with GPU-Friendly Sparsity and Quantization","created":"2023-05-18","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":"2201.01249","title":"ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesions","created":"2022-01-04","cited_by_count":19,"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":"2310.18585","title":"Visual Explanations via Iterated Integrated Attributions","created":"2023-10-28","cited_by_count":19,"area":null},{"id":"2107.03107","title":"Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition","created":"2021-07-07","cited_by_count":18,"area":null},{"id":"2109.09150","title":"A Study of the Generalizability of Self-Supervised Representations","created":"2021-09-19","cited_by_count":18,"area":null},{"id":"2402.18919","title":"Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2312.16151","title":"Large-scale Long-tailed Disease Diagnosis on Radiology Images","created":"2023-12-26","cited_by_count":17,"area":null},{"id":"2503.12068","title":"Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation","created":"2025-03-15","cited_by_count":17,"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":"2205.13769","title":"Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection","created":"2022-05-27","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":"2303.11932","title":"Studying How to Efficiently and Effectively Guide Models with Explanations","created":"2023-03-21","cited_by_count":16,"area":null},{"id":"2305.14691","title":"Label-Efficient Learning in Agriculture: A Comprehensive Review","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2404.17825","title":"ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing","created":"2024-04-27","cited_by_count":16,"area":null},{"id":"2409.16756","title":"Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics","created":"2024-09-25","cited_by_count":16,"area":null},{"id":"2105.06506","title":"Sanity Simulations for Saliency Methods","created":"2021-05-13","cited_by_count":15,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2106.14845","title":"Iris Presentation Attack Detection by Attention-based and Deep Pixel-wise Binary Supervision Network","created":"2021-06-28","cited_by_count":15,"area":null},{"id":"2209.07828","title":"Weakly Supervised Semantic Segmentation via Progressive Patch Learning","created":"2022-09-16","cited_by_count":15,"area":null},{"id":"2311.01961","title":"Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2501.11309","title":"Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation","created":"2025-01-20","cited_by_count":15,"area":null},{"id":"2303.09660","title":"Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detection","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2306.02744","title":"Towards Better Explanations for Object Detection","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2308.11568","title":"SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation","created":"2023-08-22","cited_by_count":14,"area":null},{"id":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2507.22264","title":"SmartCLIP: Modular Vision-language Alignment with Identification Guarantees","created":"2025-07-29","cited_by_count":14,"area":null},{"id":"2105.00937","title":"LFI-CAM: Learning Feature Importance for Better Visual Explanation","created":"2021-05-03","cited_by_count":13,"area":null},{"id":"2110.11111","title":"A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metrics","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2206.08477","title":"Backdoor Attacks on Vision Transformers","created":"2022-06-16","cited_by_count":13,"area":"safety"},{"id":"2209.09209","title":"Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2022-09-09","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":"2510.09741","title":"Constructive Distortion: Improving MLLMs with Attention-Guided Image Warping","created":"2025-10-10","cited_by_count":13,"area":"mllm"},{"id":"2108.13828","title":"PACE: Posthoc Architecture-Agnostic Concept Extractor for Explaining CNNs","created":"2021-08-31","cited_by_count":12,"area":null},{"id":"2111.12994","title":"NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition","created":"2021-11-25","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":"2208.14542","title":"TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2212.06872","title":"Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods","created":"2022-12-13","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":"2304.13409","title":"Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation","created":"2023-04-26","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":"2412.01829","title":"Explainable Artificial Intelligence for Medical Applications: A Review","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2501.09333","title":"Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2502.15176","title":"Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review","created":"2025-02-21","cited_by_count":12,"area":"diffusion"},{"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":"2503.14640","title":"Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer","created":"2025-03-18","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":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2208.01838","title":"Re-Attention Transformer for Weakly Supervised Object Localization","created":"2022-08-03","cited_by_count":11,"area":null},{"id":"2208.09756","title":"Artifact-Based Domain Generalization of Skin Lesion Models","created":"2022-08-20","cited_by_count":11,"area":null},{"id":"2210.07356","title":"Consistency and Accuracy of CelebA Attribute Values","created":"2022-10-13","cited_by_count":11,"area":null},{"id":"2304.14614","title":"Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection","created":"2023-04-28","cited_by_count":11,"area":null},{"id":"2409.01030","title":"Learning to Discover Forgery Cues for Face Forgery Detection","created":"2024-09-02","cited_by_count":11,"area":null},{"id":"2412.02542","title":"Unveiling Concept Attribution in Diffusion Models","created":"2024-12-03","cited_by_count":11,"area":"diffusion"},{"id":"2503.06873","title":"Interactive Medical Image Analysis with Concept-based Similarity Reasoning","created":"2025-03-10","cited_by_count":11,"area":null}],"next_cursor":"100"}