{"total":161,"rows":[{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73,"area":"mllm"},{"id":"2112.09164","title":"High Fidelity Visualization of What Your Self-Supervised Representation Knows About","created":"2021-12-16","cited_by_count":66,"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":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2212.11261","title":"Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias","created":"2022-12-21","cited_by_count":43,"area":null},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2309.17230","title":"Spurious Feature Diversification Improves Out-of-distribution Generalization","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25,"area":null},{"id":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2406.19568","title":"How Far are AI-generated Videos from Simulating the 3D Visual World: A Learned 3D Evaluation Approach","created":"2024-06-27","cited_by_count":16,"area":"diffusion"},{"id":"2212.06925","title":"On the Relationship Between Explanation and Prediction: A Causal View","created":"2022-12-13","cited_by_count":14,"area":null},{"id":"2109.01359","title":"CAM-loss: Towards Learning Spatially Discriminative Feature Representations","created":"2021-09-03","cited_by_count":13,"area":null},{"id":"2208.14426","title":"Correct-by-Construction Runtime Enforcement in AI -- A Survey","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2311.06786","title":"Explainability of Vision Transformers: A Comprehensive Review and New Perspectives","created":"2023-11-12","cited_by_count":12,"area":null},{"id":"2305.08546","title":"Towards Visual Saliency Explanations of Face Verification","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2405.19796","title":"Explainable Attribute-Based Speaker Verification","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2406.04930","title":"MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers","created":"2024-06-07","cited_by_count":11,"area":null},{"id":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","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":"2305.18011","title":"Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2110.14787","title":"SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata","created":"2021-10-27","cited_by_count":9,"area":null},{"id":"2204.05427","title":"Generalizing Adversarial Explanations with Grad-CAM","created":"2022-04-11","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":"2112.02841","title":"GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation","created":"2021-12-06","cited_by_count":8,"area":null},{"id":"2311.16120","title":"Sanity checks for patch visualisation in prototype-based image classification","created":"2023-10-25","cited_by_count":8,"area":null},{"id":"2404.14956","title":"DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactions","created":"2024-04-23","cited_by_count":8,"area":null},{"id":"2408.07040","title":"KAN You See It? KANs and Sentinel for Effective and Explainable Crop Field Segmentation","created":"2024-08-13","cited_by_count":8,"area":null},{"id":"2508.13223","title":"MIRAGE: Towards AI-Generated Image Detection in the Wild","created":"2025-08-17","cited_by_count":8,"area":null},{"id":"2207.04394","title":"Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays","created":"2022-07-10","cited_by_count":7,"area":null},{"id":"2209.06357","title":"DASH: Visual Analytics for Debiasing Image Classification via User-Driven Synthetic Data Augmentation","created":"2022-09-14","cited_by_count":7,"area":null},{"id":"2209.08803","title":"Zero-shot Active Visual Search (ZAVIS): Intelligent Object Search for Robotic Assistants","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2310.14670","title":"Dataset Bias Mitigation in Multiple-Choice Visual Question Answering and Beyond","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2607.03647","title":"Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs","created":"2026-07-04","cited_by_count":7,"area":"mllm"},{"id":"2104.04968","title":"Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop","created":"2021-04-11","cited_by_count":6,"area":null},{"id":"2106.14292","title":"Knee Osteoarthritis Severity Prediction using an Attentive Multi-Scale Deep Convolutional Neural Network","created":"2021-06-27","cited_by_count":6,"area":null},{"id":"2112.09726","title":"Soundify: Matching Sound Effects to Video","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2306.12610","title":"Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2402.12790","title":"From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition","created":"2024-02-20","cited_by_count":6,"area":null},{"id":"2404.13567","title":"On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2409.19608","title":"Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model","created":"2024-09-29","cited_by_count":6,"area":"diffusion"},{"id":"2104.09073","title":"Improving Attribution Methods by Learning Submodular Functions","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2111.03995","title":"Explainable Deep Reinforcement Learning for Portfolio Management: An Empirical Approach","created":"2021-11-07","cited_by_count":5,"area":null},{"id":"2305.01888","title":"Fairness in AI Systems: Mitigating gender bias from language-vision models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2309.07159","title":"A Strong and Simple Deep Learning Baseline for BCI MI Decoding","created":"2023-09-11","cited_by_count":5,"area":null},{"id":"2510.26186","title":"ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2202.07118","title":"Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2206.08883","title":"CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2209.05690","title":"Concept-Based Explanations for Tabular Data","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2405.14002","title":"Animal Behavior Analysis Methods Using Deep Learning: A Survey","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2504.09202","title":"From Visual Explanations to Counterfactual Explanations with Latent Diffusion","created":"2025-04-12","cited_by_count":4,"area":"diffusion"},{"id":"2105.02410","title":"Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning","created":"2021-05-06","cited_by_count":3,"area":null},{"id":"2111.14260","title":"A Practical guide on Explainable AI Techniques applied on Biomedical use case applications","created":"2021-11-13","cited_by_count":3,"area":null},{"id":"2302.08508","title":"Sanity checks and improvements for patch visualisation in prototype-based image classification","created":"2023-01-20","cited_by_count":3,"area":null},{"id":"2304.14483","title":"Adversary Aware Continual Learning","created":"2023-04-27","cited_by_count":3,"area":"safety"},{"id":"2306.00402","title":"Discriminative Deep Feature Visualization for Explainable Face Recognition","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2308.04321","title":"All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2311.17466","title":"Slot-Mixup with Subsampling: A Simple Regularization for WSI Classification","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2402.13796","title":"Scalable Methods for Brick Kiln Detection and Compliance Monitoring from Satellite Imagery: A Deployment Case Study in India","created":"2024-02-21","cited_by_count":3,"area":null},{"id":"2410.17832","title":"Exploiting Text-Image Latent Spaces for the Description of Visual Concepts","created":"2024-10-23","cited_by_count":3,"area":null},{"id":"2501.18887","title":"Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability","created":"2025-01-31","cited_by_count":3,"area":"mechinterp"},{"id":"2604.23354","title":"Explainable AI in Speaker Recognition -- Making Latent Representations Understandable","created":"2026-04-25","cited_by_count":3,"area":null},{"id":"2110.15956","title":"A deep convolutional neural network for classification of Aedes albopictus mosquitoes","created":"2021-10-29","cited_by_count":2,"area":null},{"id":"2111.04862","title":"Explaining Face Presentation Attack Detection Using Natural Language","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2301.07266","title":"ACQ: Improving Generative Data-free Quantization Via Attention Correction","created":"2023-01-18","cited_by_count":2,"area":null},{"id":"2303.13850","title":"Towards Learning and Explaining Indirect Causal Effects in Neural Networks","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2305.06862","title":"A General Framework for Visualizing Embedding Spaces of Neural Survival Analysis Models Based on Angular Information","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2305.14882","title":"Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering","created":"2023-05-24","cited_by_count":2,"area":"mllm"},{"id":"2308.03999","title":"Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning","created":"2023-08-08","cited_by_count":2,"area":"lr"},{"id":"2309.02670","title":"Progressive Attention Guidance for Whole Slide Vulvovaginal Candidiasis Screening","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2404.14952","title":"Leveraging Speech for Gesture Detection in Multimodal Communication","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2406.15104","title":"Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors","created":"2024-06-21","cited_by_count":2,"area":null},{"id":"2406.18562","title":"Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2407.05112","title":"Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning","created":"2024-07-06","cited_by_count":2,"area":"safety"},{"id":"2407.08689","title":"Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2407.12331","title":"I2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps","created":"2024-07-17","cited_by_count":2,"area":"diffusion"},{"id":"2408.00792","title":"A Scalable and Generalized Deep Learning Framework for Anomaly Detection in Surveillance Videos","created":"2024-07-17","cited_by_count":2,"area":null},{"id":"2412.19979","title":"Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2501.06762","title":"Improving the adaptive and continuous learning capabilities of artificial neural networks: Lessons from multi-neuromodulatory dynamics","created":"2025-01-12","cited_by_count":2,"area":null},{"id":"2506.11035","title":"Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.14775","title":"See What I Mean? CUE: A Cognitive Model of Understanding Explanations","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2606.22901","title":"Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2209.13939","title":"Racial Bias in the Beautyverse","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2301.01223","title":"ExploreADV: Towards exploratory attack for Neural Networks","created":"2023-01-01","cited_by_count":1,"area":null},{"id":"2303.09858","title":"Preventing Unauthorized AI Over-Analysis by Medical Image Adversarial Watermarking","created":"2023-03-17","cited_by_count":1,"area":"safety"},{"id":"2304.07609","title":"ODSmoothGrad: Generating Saliency Maps for Object Detectors","created":"2023-04-15","cited_by_count":1,"area":null},{"id":"2307.16543","title":"On Transferability of Driver Observation Models from Simulated to Real Environments in Autonomous Cars","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2308.04753","title":"SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2309.12632","title":"Are Deep Learning Classification Results Obtained on CT Scans Fair and Interpretable?","created":"2023-09-22","cited_by_count":1,"area":null},{"id":"2401.06331","title":"Application Of Vision-Language Models For Assessing Osteoarthritis Disease Severity","created":"2024-01-12","cited_by_count":1,"area":"mllm"},{"id":"2403.01546","title":"Hyperspectral Image Analysis in Single-Modal and Multimodal setting using Deep Learning Techniques","created":"2024-03-03","cited_by_count":1,"area":null},{"id":"2404.16174","title":"MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification Models","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2405.09580","title":"Error-margin Analysis for Hidden Neuron Activation Labels","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2407.05983","title":"Towards A Comprehensive Visual Saliency Explanation Framework for AI-based Face Recognition Systems","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2410.13989","title":"Reproducibility study of \"LICO: Explainable Models with Language-Image Consistency\"","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2411.13053","title":"MEGL: Multimodal Explanation-Guided Learning","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2501.11901","title":"Enhancing Adversarial Transferability via Component-Wise Transformation","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2504.09956","title":"Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2505.17666","title":"Proto-FG3D: Prototype-based Interpretable Fine-Grained 3D Shape Classification","created":"2025-05-23","cited_by_count":1,"area":null}],"next_cursor":"100"}