{"total":24,"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":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117,"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":"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":"2104.05514","title":"Self-Training with Weak Supervision","created":"2021-04-12","cited_by_count":49,"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":"2205.06130","title":"Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models","created":"2022-05-12","cited_by_count":20,"area":null},{"id":"2110.13740","title":"DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples","created":"2021-10-26","cited_by_count":18,"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":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13,"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":"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":"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":"2111.11053","title":"DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing","created":"2021-11-22","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":"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":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2310.10495","title":"Metric Ensembles For Hallucination Detection","created":"2023-10-16","cited_by_count":2,"area":null},{"id":"2109.01381","title":"Segmentation of turbulent computational fluid dynamics simulations with unsupervised ensemble learning","created":"2021-09-03","cited_by_count":1,"area":null},{"id":"2204.06436","title":"Label Augmentation with Reinforced Labeling for Weak Supervision","created":"2022-04-13","cited_by_count":1,"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}],"next_cursor":null}