{"list":"other","total":70,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"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":"1911.08251","title":"General $E(2)$-Equivariant Steerable CNNs","created":"2019-11-19","cited_by_count":446},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1411.4357","title":"Sketching as a Tool for Numerical Linear Algebra","created":"2014-11-17","cited_by_count":288},{"id":"1711.04340","title":"Data Augmentation Generative Adversarial Networks","created":"2017-11-12","cited_by_count":278},{"id":"1805.10917","title":"Deep Anomaly Detection Using Geometric Transformations","created":"2018-05-28","cited_by_count":269},{"id":"1902.04615","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","created":"2019-02-11","cited_by_count":267},{"id":"1711.06721","title":"Learning SO(3) Equivariant Representations with Spherical CNNs","created":"2017-11-17","cited_by_count":248},{"id":"2002.12880","title":"Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data","created":"2020-02-25","cited_by_count":248},{"id":"1905.00397","title":"Fast AutoAugment","created":"2019-05-01","cited_by_count":243},{"id":"2103.10158","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","created":"2021-03-18","cited_by_count":227},{"id":"2005.02359","title":"Classification-Based Anomaly Detection for General Data","created":"2020-05-05","cited_by_count":211},{"id":"1711.07289","title":"Learning Steerable Filters for Rotation Equivariant CNNs","created":"2017-11-20","cited_by_count":194},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1602.04474","title":"Generalization Properties of Learning with Random Features","created":"2016-02-14","cited_by_count":164},{"id":"1506.04091","title":"On the properties of variational approximations of Gibbs posteriors","created":"2015-06-12","cited_by_count":121},{"id":"1906.02611","title":"Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation","created":"2019-06-06","cited_by_count":105},{"id":"1905.13177","title":"Graph Normalizing Flows","created":"2019-05-30","cited_by_count":104},{"id":"1911.06987","title":"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation","created":"2019-11-16","cited_by_count":96},{"id":"1709.01643","title":"Learning to Compose Domain-Specific Transformations for Data Augmentation","created":"2017-09-06","cited_by_count":91},{"id":"1605.08636","title":"PAC-Bayesian Theory Meets Bayesian Inference","created":"2016-05-27","cited_by_count":88},{"id":"2106.04015","title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","created":"2021-06-07","cited_by_count":82},{"id":"1712.09376","title":"Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors","created":"2017-12-26","cited_by_count":81},{"id":"2007.02933","title":"Meta-Learning Symmetries by Reparameterization","created":"2020-07-06","cited_by_count":76},{"id":"1505.02250","title":"Newton Sketch: A Linear-time Optimization Algorithm with Linear-Quadratic Convergence","created":"2015-05-09","cited_by_count":72},{"id":"2003.03780","title":"DADA: Differentiable Automatic Data Augmentation","created":"2020-03-08","cited_by_count":57},{"id":"1808.05563","title":"Learning Invariances using the Marginal Likelihood","created":"2018-08-16","cited_by_count":51},{"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":"2106.09848","title":"PAC Prediction Sets Under Covariate Shift","created":"2021-06-17","cited_by_count":45},{"id":"1307.2118","title":"A PAC-Bayesian Tutorial with A Dropout Bound","created":"2013-07-08","cited_by_count":43},{"id":"1905.07373","title":"Online Hyper-parameter Learning for Auto-Augmentation Strategy","created":"2019-05-17","cited_by_count":38},{"id":"1411.0347","title":"Iterative Hessian sketch: Fast and accurate solution approximation for constrained least-squares","created":"2014-11-03","cited_by_count":34},{"id":"2002.12287","title":"Deep Randomized Neural Networks","created":"2020-02-27","cited_by_count":33},{"id":"1504.04595","title":"Random-projection ensemble classification","created":"2015-04-17","cited_by_count":29},{"id":"1804.01552","title":"Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection","created":"2018-04-04","cited_by_count":27},{"id":"2005.10247","title":"Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data","created":"2020-05-20","cited_by_count":27},{"id":"1404.7203","title":"Randomized Sketches of Convex Programs with Sharp Guarantees","created":"2014-04-29","cited_by_count":25},{"id":"2006.07965","title":"Meta Approach to Data Augmentation Optimization","created":"2020-06-14","cited_by_count":22},{"id":"1406.5986","title":"A Statistical Perspective on Randomized Sketching for Ordinary Least-Squares","created":"2014-06-23","cited_by_count":21},{"id":"2106.07512","title":"Last Layer Marginal Likelihood for Invariance Learning","created":"2021-06-14","cited_by_count":21},{"id":"1910.02373","title":"Ridge Regression: Structure, Cross-Validation, and Sketching","created":"2019-10-06","cited_by_count":15},{"id":"1702.04837","title":"Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging","created":"2017-02-16","cited_by_count":13},{"id":"2006.10016","title":"The Nystr\\\"om method for convex loss functions","created":"2020-06-17","cited_by_count":8},{"id":"1911.10800","title":"Random projections: data perturbation for classification problems","created":"2019-11-25","cited_by_count":7},{"id":"1610.03045","title":"Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data","created":"2016-10-10","cited_by_count":6},{"id":"1405.1792","title":"RAPTT: An Exact Two-Sample Test in High Dimensions Using Random Projections","created":"2014-05-08","cited_by_count":4},{"id":"1811.04351","title":"Generalization Bounds for Vicinal Risk Minimization Principle","created":"2018-11-11","cited_by_count":4}],"next_cursor":null}