{"list":"other","total":60,"rows":[{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"id":"1610.08452","title":"Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment","created":"2016-10-26","cited_by_count":369},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1812.03372","title":"What is the Effect of Importance Weighting in Deep Learning?","created":"2018-12-08","cited_by_count":251},{"id":"1905.00397","title":"Fast AutoAugment","created":"2019-05-01","cited_by_count":243},{"id":"1802.08626","title":"Empirical Risk Minimization under Fairness Constraints","created":"2018-02-23","cited_by_count":226},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"1902.04674","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","created":"2019-02-12","cited_by_count":176},{"id":"1508.03422","title":"Cost Sensitive Learning of Deep Feature Representations from Imbalanced Data","created":"2015-08-14","cited_by_count":167},{"id":"1905.05393","title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","created":"2019-05-14","cited_by_count":154},{"id":"1705.06270","title":"A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications","created":"2017-05-17","cited_by_count":129},{"id":"1909.12292","title":"Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks","created":"2019-09-26","cited_by_count":121},{"id":"1512.05830","title":"Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks","created":"2015-12-18","cited_by_count":115},{"id":"1803.06084","title":"A Kernel Theory of Modern Data Augmentation","created":"2018-03-16","cited_by_count":106},{"id":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"id":"1911.06987","title":"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation","created":"2019-11-16","cited_by_count":96},{"id":"1901.08665","title":"Fairness risk measures","created":"2019-01-24","cited_by_count":85},{"id":"1901.07590","title":"Striking the Right Balance with Uncertainty","created":"2019-01-22","cited_by_count":79},{"id":"2001.01385","title":"Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning","created":"2020-01-06","cited_by_count":76},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74},{"id":"1511.06727","title":"Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters","created":"2015-11-20","cited_by_count":71},{"id":"1803.06396","title":"Reviving and Improving Recurrent Back-Propagation","created":"2018-03-16","cited_by_count":69},{"id":"1804.10851","title":"Imbalanced Deep Learning by Minority Class Incremental Rectification","created":"2018-04-28","cited_by_count":65},{"id":"1704.07515","title":"Deep Over-sampling Framework for Classifying Imbalanced Data","created":"2017-04-25","cited_by_count":59},{"id":"1703.08383","title":"Smart Augmentation - Learning an Optimal Data Augmentation Strategy","created":"2017-03-24","cited_by_count":54},{"id":"1912.01857","title":"Adjusting Decision Boundary for Class Imbalanced Learning","created":"2019-12-04","cited_by_count":52},{"id":"1809.01465","title":"Deep Bilevel Learning","created":"2018-09-05","cited_by_count":49},{"id":"1808.05584","title":"BlockQNN: Efficient Block-wise Neural Network Architecture Generation","created":"2018-08-16","cited_by_count":31},{"id":"2010.05843","title":"How Important is the Train-Validation Split in Meta-Learning?","created":"2020-10-12","cited_by_count":30},{"id":"1909.09712","title":"Learning an Adaptive Learning Rate Schedule","created":"2019-09-20","cited_by_count":29},{"id":"2006.16537","title":"Theory-Inspired Path-Regularized Differential Network Architecture Search","created":"2020-06-30","cited_by_count":25},{"id":"2006.07965","title":"Meta Approach to Data Augmentation Optimization","created":"2020-06-14","cited_by_count":22},{"id":"1912.04486","title":"To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions","created":"2019-12-10","cited_by_count":20},{"id":"2104.14132","title":"Generalization Guarantees for Neural Architecture Search with Train-Validation Split","created":"2021-04-29","cited_by_count":14},{"id":"2002.09831","title":"On the Role of Dataset Quality and Heterogeneity in Model Confidence","created":"2020-02-23","cited_by_count":7}],"next_cursor":null}