{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"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":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"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":"1710.06924","title":"VisDA: The Visual Domain Adaptation Challenge","created":"2017-10-18","cited_by_count":435},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1511.05547","title":"Return of Frustratingly Easy Domain Adaptation","created":"2015-11-17","cited_by_count":391},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"1802.06509","title":"On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization","created":"2018-02-19","cited_by_count":284},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"1902.04742","title":"Uniform convergence may be unable to explain generalization in deep learning","created":"2019-02-13","cited_by_count":224},{"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":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"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":"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":"2007.02915","title":"Are Labels Always Necessary for Classifier Accuracy Evaluation?","created":"2020-07-06","cited_by_count":104},{"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},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"id":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69},{"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":"1905.12600","title":"Generalization bounds for deep convolutional neural networks","created":"2019-05-29","cited_by_count":59},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57},{"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":"2009.08092","title":"Distributional Generalization: A New Kind of Generalization","created":"2020-09-17","cited_by_count":42},{"id":"2102.13128","title":"An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization","created":"2021-02-25","cited_by_count":30},{"id":"2106.09913","title":"Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments","created":"2021-06-18","cited_by_count":30},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30},{"id":"1705.07086","title":"Estimating Accuracy from Unlabeled Data: A Probabilistic Logic Approach","created":"2017-05-19","cited_by_count":27},{"id":"1806.09755","title":"Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation","created":"2018-06-26","cited_by_count":27},{"id":"2105.00303","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","created":"2021-05-01","cited_by_count":20},{"id":"2212.02742","title":"A Learning Based Hypothesis Test for Harmful Covariate Shift","created":"2022-12-06","cited_by_count":19},{"id":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13}],"next_cursor":null}