{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1911.11132","title":"Scaling Out-of-Distribution Detection for Real-World Settings","created":"2019-11-25","cited_by_count":465},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"1802.03916","title":"Detecting and Correcting for Label Shift with Black Box Predictors","created":"2018-02-12","cited_by_count":366},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1810.11953","title":"Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift","created":"2018-10-29","cited_by_count":243},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"id":"1806.00451","title":"Do CIFAR-10 Classifiers Generalize to CIFAR-10?","created":"2018-06-01","cited_by_count":200},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"2010.15775","title":"Understanding the Failure Modes of Out-of-Distribution Generalization","created":"2020-10-29","cited_by_count":146},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"2003.04475","title":"Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift","created":"2020-03-10","cited_by_count":125},{"id":"1903.09734","title":"Regularized Learning for Domain Adaptation under Label Shifts","created":"2019-03-22","cited_by_count":120},{"id":"2003.07554","title":"A Unified View of Label Shift Estimation","created":"2020-03-17","cited_by_count":119},{"id":"2106.13799","title":"Assessing Generalization of SGD via Disagreement","created":"2021-06-25","cited_by_count":117},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116},{"id":"2003.12506","title":"Hybrid Models for Open Set Recognition","created":"2020-03-27","cited_by_count":109},{"id":"2007.02915","title":"Are Labels Always Necessary for Classifier Accuracy Evaluation?","created":"2020-07-06","cited_by_count":104},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"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},{"id":"1905.10498","title":"Cold Case: The Lost MNIST Digits","created":"2019-05-25","cited_by_count":62},{"id":"1905.12600","title":"Generalization bounds for deep convolutional neural networks","created":"2019-05-29","cited_by_count":59},{"id":"2007.03511","title":"Estimating Generalization under Distribution Shifts via Domain-Invariant Representations","created":"2020-07-06","cited_by_count":56},{"id":"2107.00643","title":"Mandoline: Model Evaluation under Distribution Shift","created":"2021-07-01","cited_by_count":55},{"id":"2106.15728","title":"Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles","created":"2021-06-29","cited_by_count":54},{"id":"1905.13344","title":"Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience","created":"2019-05-30","cited_by_count":51},{"id":"1705.07086","title":"Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach","created":"2017-05-19","cited_by_count":27},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20}],"next_cursor":null}