{"total":189,"rows":[{"id":"2206.08129","title":"Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline","created":"2022-06-16","cited_by_count":248,"area":"driving"},{"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":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2112.00686","title":"CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning","created":"2021-12-01","cited_by_count":33,"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":"2403.11650","title":"Prioritized Semantic Learning for Zero-shot Instance Navigation","created":"2024-03-18","cited_by_count":31,"area":null},{"id":"2301.01006","title":"Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling","created":"2023-01-03","cited_by_count":26,"area":"driving"},{"id":"2301.07002","title":"Opti-CAM: Optimizing saliency maps for interpretability","created":"2023-01-17","cited_by_count":25,"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":"2310.07473","title":"FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation","created":"2023-10-11","cited_by_count":22,"area":null},{"id":"2209.04851","title":"OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning","created":"2022-09-11","cited_by_count":21,"area":null},{"id":"2207.11025","title":"Custom Structure Preservation in Face Aging","created":"2022-07-22","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":"2206.03826","title":"Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks","created":"2022-06-08","cited_by_count":18,"area":null},{"id":"2203.07373","title":"SATr: Slice Attention with Transformer for Universal Lesion Detection","created":"2022-03-13","cited_by_count":17,"area":null},{"id":"2210.05189","title":"Neural Networks are Decision Trees","created":"2022-10-11","cited_by_count":17,"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":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15,"area":null},{"id":"2210.14985","title":"Learning Deep Sensorimotor Policies for Vision-based Autonomous Drone Racing","created":"2022-10-26","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":"2501.03775","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","created":"2025-01-07","cited_by_count":14,"area":null},{"id":"2503.15293","title":"Test-Time Backdoor Detection for Object Detection Models","created":"2025-03-19","cited_by_count":14,"area":null},{"id":"2402.12525","title":"LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2406.05704","title":"Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2211.17161","title":"Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification","created":"2022-11-30","cited_by_count":12,"area":null},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","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":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2312.06701","title":"Dynamic Adversarial Attacks on Autonomous Driving Systems","created":"2023-12-10","cited_by_count":11,"area":null},{"id":"2405.15495","title":"Towards Natural Machine Unlearning","created":"2024-05-24","cited_by_count":11,"area":"safety"},{"id":"2304.11744","title":"SketchXAI: A First Look at Explainability for Human Sketches","created":"2023-04-23","cited_by_count":10,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2403.09359","title":"D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2403.16020","title":"PaPr: Training-Free One-Step Patch Pruning with Lightweight ConvNets for Faster Inference","created":"2024-03-24","cited_by_count":9,"area":null},{"id":"2306.05527","title":"Teaching AI to Teach: Leveraging Limited Human Salience Data Into Unlimited Saliency-Based Training","created":"2023-06-08","cited_by_count":8,"area":"distill"},{"id":"2404.18326","title":"SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies","created":"2024-04-28","cited_by_count":8,"area":"deeprl"},{"id":"2407.11771","title":"XEdgeAI: A Human-centered Industrial Inspection Framework with Data-centric Explainable Edge AI Approach","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2407.13036","title":"ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2401.02044","title":"A multi-modal vision-language model for generalizable annotation-free pathology localization","created":"2024-01-04","cited_by_count":7,"area":"mllm"},{"id":"2507.14787","title":"FOCUS: Fused Observation of Channels for Unveiling Spectra","created":"2025-07-20","cited_by_count":7,"area":null},{"id":"2108.00273","title":"Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents","created":"2021-07-31","cited_by_count":6,"area":null},{"id":"2110.05074","title":"Rethinking Person Re-Identification via Semantic-Based Pretraining","created":"2021-10-11","cited_by_count":6,"area":null},{"id":"2305.01361","title":"Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature","created":"2023-05-02","cited_by_count":6,"area":null},{"id":"2305.03601","title":"Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models","created":"2023-05-05","cited_by_count":6,"area":null},{"id":"2311.15022","title":"Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space","created":"2023-11-25","cited_by_count":6,"area":null},{"id":"2406.05090","title":"Provably Better Explanations with Optimized Aggregation of Feature Attributions","created":"2024-06-07","cited_by_count":6,"area":null},{"id":"2410.00267","title":"KPCA-CAM: Visual Explainability of Deep Computer Vision Models using Kernel PCA","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2412.16619","title":"Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity","created":"2024-12-21","cited_by_count":6,"area":null},{"id":"2503.08420","title":"Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2602.02259","title":"Segment to Focus: Guiding Latent Action Models in the Presence of Distractors","created":"2026-02-02","cited_by_count":6,"area":null},{"id":"2204.06901","title":"RankNEAT: Outperforming Stochastic Gradient Search in Preference Learning Tasks","created":"2022-04-14","cited_by_count":5,"area":null},{"id":"2306.13813","title":"DualAttNet: Synergistic Fusion of Image-level and Fine-Grained Disease Attention for Multi-Label Lesion Detection in Chest X-rays","created":"2023-06-23","cited_by_count":5,"area":null},{"id":"2402.02574","title":"Spatio-temporal Prompting Network for Robust Video Feature Extraction","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2511.07827","title":"Deep Learning Analysis of Prenatal Ultrasound for Identification of Ventriculomegaly","created":"2025-11-11","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":"2305.02911","title":"UPDExplainer: an Interpretable Transformer-based Framework for Urban Physical Disorder Detection Using Street View Imagery","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2405.01705","title":"Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning","created":"2024-05-02","cited_by_count":4,"area":"diffusion"},{"id":"2406.06037","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","created":"2024-06-10","cited_by_count":4,"area":"deeprl"},{"id":"2411.08013","title":"Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech","created":"2024-11-12","cited_by_count":4,"area":null},{"id":"2506.20550","title":"Lightweight Multi-Frame Integration for Robust YOLO Object Detection in Videos","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2508.18898","title":"Interpretable Decision-Making for End-to-End Autonomous Driving","created":"2025-08-26","cited_by_count":4,"area":"driving"},{"id":"2509.18715","title":"What Makes You Unique? Attribute Prompt Composition for Object Re-Identification","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2205.14851","title":"Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2306.10265","title":"NBMOD: Find It and Grasp It in Noisy Background","created":"2023-06-17","cited_by_count":3,"area":null},{"id":"2307.04036","title":"Designing a Direct Feedback Loop between Humans and Convolutional Neural Networks through Local Explanations","created":"2023-07-08","cited_by_count":3,"area":null},{"id":"2307.09050","title":"R-Cut: Enhancing Explainability in Vision Transformers with Relationship Weighted Out and Cut","created":"2023-07-18","cited_by_count":3,"area":null},{"id":"2310.01837","title":"Extending CAM-based XAI methods for Remote Sensing Imagery Segmentation","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2311.05043","title":"Zero-shot Translation of Attention Patterns in VQA Models to Natural Language","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2403.16858","title":"XAIport: A Service Framework for the Early Adoption of XAI in AI Model Development","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2404.07685","title":"Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation Patterns","created":"2024-04-11","cited_by_count":3,"area":null},{"id":"2405.06340","title":"Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing","created":"2024-05-10","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":"2410.02384","title":"Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errors","created":"2024-10-03","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":"2506.12706","title":"NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models","created":"2025-06-15","cited_by_count":3,"area":"mllm"},{"id":"2506.13917","title":"Evaluating Explainability: A Framework for Systematic Assessment and Reporting of Explainable AI Features","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2207.02179","title":"Activation Template Matching Loss for Explainable Face Recognition","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2211.00933","title":"Deep Multimodal Fusion for Generalizable Person Re-identification","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2303.16407","title":"LMDA-Net:A lightweight multi-dimensional attention network for general EEG-based brain-computer interface paradigms and interpretability","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2304.08111","title":"Leveraging Multi-view Data for Improved Detection Performance: An Industrial Use Case","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2307.05017","title":"Feature Activation Map: Visual Explanation of Deep Learning Models for Image Classification","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2308.00710","title":"Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2308.08407","title":"Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2309.14304","title":"Overview of Class Activation Maps for Visualization Explainability","created":"2023-09-25","cited_by_count":2,"area":null},{"id":"2311.14081","title":"You Only Explain Once","created":"2023-11-23","cited_by_count":2,"area":null},{"id":"2402.11670","title":"Challenging the Black Box: A Comprehensive Evaluation of Attribution Maps of CNN Applications in Agriculture and Forestry","created":"2024-02-18","cited_by_count":2,"area":null},{"id":"2403.12988","title":"Enhancing Object Detection Robustness: Detecting and Restoring Confidence in the Presence of Adversarial Patch Attacks","created":"2024-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2404.16268","title":"Lacunarity Pooling Layers for Plant Image Classification using Texture Analysis","created":"2024-04-25","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},{"id":"2405.16016","title":"ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces","created":"2024-05-25","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":"2409.03192","title":"PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2409.14679","title":"Quantifying Context Bias in Domain Adaptation for Object Detection","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2409.20287","title":"Leveraging CAM Algorithms for Explaining Medical Semantic Segmentation","created":"2024-09-30","cited_by_count":2,"area":null},{"id":"2410.20109","title":"GiVE: Guiding Visual Encoder to Perceive Overlooked Information","created":"2024-10-26","cited_by_count":2,"area":"mllm"},{"id":"2411.03376","title":"An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2501.12216","title":"RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression","created":"2025-01-21","cited_by_count":2,"area":null}],"next_cursor":"100"}