{"total":60,"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":"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":"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":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26,"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":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"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":"2401.12689","title":"Energy-based Automated Model Evaluation","created":"2024-01-23","cited_by_count":17,"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":"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":"2404.17202","title":"Self-supervised visual learning in the low-data regime: a comparative evaluation","created":"2024-04-26","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":"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":"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":"2211.07625","title":"What Images are More Memorable to Machines?","created":"2022-11-14","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":"2210.07239","title":"Composite Learning for Robust and Effective Dense Predictions","created":"2022-10-13","cited_by_count":4,"area":null},{"id":"2302.02628","title":"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness","created":"2023-02-06","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":"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":"2206.10697","title":"Performance Prediction Under Dataset Shift","created":"2022-06-21","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":"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":"2505.13584","title":"Self-Supervised Learning for Image Segmentation: A Comprehensive Survey","created":"2025-05-19","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":"2209.02881","title":"Improving Self-supervised Learning for Out-of-distribution Task via Auxiliary Classifier","created":"2022-09-07","cited_by_count":1,"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":"2408.02209","title":"Source-Free Domain-Invariant Performance Prediction","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","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":"2303.13589","title":"On the Efficacy of Generalization Error Prediction Scoring Functions","created":"2023-03-23","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":"2406.09257","title":"Assessing Model Generalization in Vicinity","created":"2024-06-13","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":"2604.23289","title":"MetaErr: Towards Predicting Error Patterns in Deep Neural Networks","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2609.32672","title":"STAMP: Predicting Out-of-Distribution Generalization without Target Data","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}