{"total":99,"rows":[{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116,"area":null},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77,"area":null},{"id":"2106.05961","title":"What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?","created":"2021-06-10","cited_by_count":63,"area":null},{"id":"2106.15728","title":"Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles","created":"2021-06-29","cited_by_count":54,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2506.07673","title":"How Benchmark Prediction from Fewer Data Misses the Mark","created":"2025-06-09","cited_by_count":28,"area":null},{"id":"2202.06881","title":"Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation","created":"2022-02-14","cited_by_count":26,"area":null},{"id":"2106.00184","title":"Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation","created":"2021-06-01","cited_by_count":23,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2502.07551","title":"Early Stopping Against Label Noise Without Validation Data","created":"2025-02-11","cited_by_count":21,"area":null},{"id":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2209.08436","title":"Estimating and Explaining Model Performance When Both Covariates and Labels Shift","created":"2022-09-18","cited_by_count":19,"area":null},{"id":"2310.14586","title":"GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2408.03573","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","created":"2024-08-07","cited_by_count":17,"area":null},{"id":"2109.11126","title":"A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels","created":"2021-09-23","cited_by_count":16,"area":null},{"id":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2303.15488","title":"On the Importance of Feature Separability in Predicting Out-Of-Distribution Error","created":"2023-03-27","cited_by_count":15,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2310.04414","title":"CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2403.09953","title":"Online GNN Evaluation Under Test-time Graph Distribution Shifts","created":"2024-03-15","cited_by_count":12,"area":null},{"id":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2112.00694","title":"Label-Free Model Evaluation with Semi-Structured Dataset Representations","created":"2021-12-01","cited_by_count":10,"area":null},{"id":"2207.09957","title":"Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2412.12910","title":"Sequential Harmful Shift Detection Without Labels","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2202.14034","title":"Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2207.10942","title":"Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation","created":"2022-07-22","cited_by_count":9,"area":null},{"id":"2401.08348","title":"Estimating Model Performance Under Covariate Shift Without Labels","created":"2024-01-16","cited_by_count":9,"area":null},{"id":"2108.10310","title":"Ranking Models in Unlabeled New Environments","created":"2021-08-23","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2404.01542","title":"Predicting the Performance of Foundation Models via Agreement-on-the-Line","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2308.11111","title":"CAME: Contrastive Automated Model Evaluation","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2403.13803","title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2406.09908","title":"What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2207.05161","title":"What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization","created":"2022-07-11","cited_by_count":5,"area":null},{"id":"2312.00656","title":"Simple Transferability Estimation for Regression Tasks","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2510.07959","title":"DISCO: Diversifying Sample Condensation for Efficient Model Evaluation","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2302.08287","title":"Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2304.08288","title":"Toward Auto-evaluation with Confidence-based Category Relation-aware Regression","created":"2023-04-17","cited_by_count":4,"area":null},{"id":"2304.09758","title":"K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation","created":"2023-04-17","cited_by_count":4,"area":null},{"id":"2310.12793","title":"OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2412.17284","title":"Towards Unsupervised Model Selection for Domain Adaptive Object Detection","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2501.19032","title":"Error Slice Discovery via Manifold Compactness","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2110.11567","title":"Logical Assessment Formula and Its Principles for Evaluations with Inaccurate Ground-Truth Labels","created":"2021-10-22","cited_by_count":3,"area":null},{"id":"2206.10697","title":"Performance Prediction Under Dataset Shift","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2208.01358","title":"What can we Learn by Predicting Accuracy?","created":"2022-08-02","cited_by_count":3,"area":null},{"id":"2210.04166","title":"Test-time Recalibration of Conformal Predictors Under Distribution Shift Based on Unlabeled Examples","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2307.10062","title":"Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2503.17717","title":"BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors","created":"2025-03-22","cited_by_count":3,"area":null},{"id":"2308.07223","title":"Distance Matters For Improving Performance Estimation Under Covariate Shift","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2404.04969","title":"Temporal Generalization Estimation in Evolving Graphs","created":"2024-04-07","cited_by_count":2,"area":null},{"id":"2507.12894","title":"LanePerf: a Performance Estimation Framework for Lane Detection","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2601.09001","title":"Entropy Sentinel: Probing Entropy Traces for LLM Monitoring","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2310.10490","title":"On the Transferability of Learning Models for Semantic Segmentation for Remote Sensing Data","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2402.09204","title":"Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2407.14306","title":"Label-Free Model Failure Detection for Lidar-based Point Cloud Segmentation","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2408.02209","title":"Source-Free Domain-Invariant Performance Prediction","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2506.14978","title":"ODD: Overlap-aware Estimation of Model Performance under Distribution Shift","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2510.02956","title":"Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.27263","title":"ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2605.08870","title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2111.12386","title":"One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data","created":"2021-11-24","cited_by_count":0,"area":null},{"id":"2206.01251","title":"Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2207.00827","title":"Firenze: Model Evaluation Using Weak Signals","created":"2022-07-02","cited_by_count":0,"area":null},{"id":"2303.13589","title":"On the Efficacy of Generalization Error Prediction Scoring Functions","created":"2023-03-23","cited_by_count":0,"area":null},{"id":"2304.08855","title":"A Domain-Region Based Evaluation of ML Performance Robustness to Covariate Shift","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2306.10160","title":"On Orderings of Probability Vectors and Unsupervised Performance Estimation","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2307.02709","title":"Validation of the Practicability of Logical Assessment Formula for Evaluations with Inaccurate Ground-Truth Labels: An Application Study on Tumour Segmentation for Breast Cancer","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2309.10977","title":"PAGER: A Framework for Failure Analysis of Deep Regression Models","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2311.15906","title":"MetaDefa: Meta-learning based on Domain Enhancement and Feature Alignment for Single Domain Generalization","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2406.09257","title":"Assessing Model Generalization in Vicinity","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2409.04241","title":"Calibration of Network Confidence for Unsupervised Domain Adaptation Using Estimated Accuracy","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2505.11006","title":"Is Supervised Learning Really That Different from Unsupervised?","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2508.12082","title":"Automated Model Evaluation for Object Detection via Prediction Consistency and Reliability","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2508.19613","title":"ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2511.11834","title":"Volatility in Certainty (VC): A Metric for Detecting Adversarial Perturbations During Inference in Neural Network Classifiers","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2601.01254","title":"Entity-Aware and Secure Query Optimization in Database Using Named Entity Recognition","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2604.20944","title":"LAF-Based Evaluation and UTTL-Based Learning Strategies with MIATTs","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.23289","title":"MetaErr: Towards Predicting Error Patterns in Deep Neural Networks","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.21590","title":"Radial Basis Function Networks as Projection Heads in Self-Supervised Learning","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.22054","title":"Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2609.04388","title":"Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}